From 1c86a28ca5d8c6f6941d7de60dde1bc9a8f77488 Mon Sep 17 00:00:00 2001 From: geoffreychen777 Date: Wed, 7 Aug 2024 18:26:14 +0000 Subject: [PATCH] update: cvpr24 --- metadata/conferences/cvpr/cvpr24.json | 69305 +++++++++++++++++++++++- 1 file changed, 66590 insertions(+), 2715 deletions(-) diff --git a/metadata/conferences/cvpr/cvpr24.json b/metadata/conferences/cvpr/cvpr24.json index 7c1b370..fd6cfa2 100644 --- a/metadata/conferences/cvpr/cvpr24.json +++ b/metadata/conferences/cvpr/cvpr24.json @@ -7,19005 +7,82880 @@ "collection": [ { "title": "Unmixing Diffusion for Self-Supervised Hyperspectral Image Denoising", - "authors": "Haijin Zeng, Jiezhang Cao, Kai Zhang, Yongyong Chen, Hiep Luong, Wilfried Philips", + "authors": [ + { + "first_name": "Haijin", + "last_name": "Zeng" + }, + { + "first_name": "Jiezhang", + "last_name": "Cao" + }, + { + "first_name": "Kai", + "last_name": "Zhang" + }, + { + "first_name": "Yongyong", + "last_name": "Chen" + }, + { + "first_name": "Hiep", + "last_name": "Luong" + }, + { + "first_name": "Wilfried", + "last_name": "Philips" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Seeing the World through Your Eyes", - "authors": "Hadi Alzayer, Kevin Zhang, Brandon Feng, Christopher A. Metzler, Jia-Bin Huang", + "authors": [ + { + "first_name": "Hadi", + "last_name": "Alzayer" + }, + { + "first_name": "Kevin", + "last_name": "Zhang" + }, + { + "first_name": "Brandon", + "last_name": "Feng" + }, + { + "first_name": "Christopher", + "last_name": "A. Metzler" + }, + { + "first_name": "Jia-Bin", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DPMesh: Exploiting Diffusion Prior for Occluded Human Mesh Recovery", - "authors": "Yixuan Zhu, Ao Li, Yansong Tang, Wenliang Zhao, Jie Zhou, Jiwen Lu", + "authors": [ + { + "first_name": "Yixuan", + "last_name": "Zhu" + }, + { + "first_name": "Ao", + "last_name": "Li" + }, + { + "first_name": "Yansong", + "last_name": "Tang" + }, + { + "first_name": "Wenliang", + "last_name": "Zhao" + }, + { + "first_name": "Jie", + "last_name": "Zhou" + }, + { + "first_name": "Jiwen", + "last_name": "Lu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Ungeneralizable Examples", - "authors": "Jingwen Ye, Xinchao Wang", + "authors": [ + { + "first_name": "Jingwen", + "last_name": "Ye" + }, + { + "first_name": "Xinchao", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LaneCPP: Continuous 3D Lane Detection using Physical Priors", - "authors": "Maximilian Pittner, Joel Janai, Alexandru P. Condurache", + "authors": [ + { + "first_name": "Maximilian", + "last_name": "Pittner" + }, + { + "first_name": "Joel", + "last_name": "Janai" + }, + { + "first_name": "Alexandru", + "last_name": "P. Condurache" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CityDreamer: Compositional Generative Model of Unbounded 3D Cities", - "authors": "Haozhe Xie, Zhaoxi Chen, Fangzhou Hong, Ziwei Liu", + "authors": [ + { + "first_name": "Haozhe", + "last_name": "Xie" + }, + { + "first_name": "Zhaoxi", + "last_name": "Chen" + }, + { + "first_name": "Fangzhou", + "last_name": "Hong" + }, + { + "first_name": "Ziwei", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HEAL-SWIN: A Vision Transformer On The Sphere", - "authors": "Oscar Carlsson, Jan E. Gerken, Hampus Linander, Heiner Spieß, Fredrik Ohlsson, Christoffer Petersson, Daniel Persson", + "authors": [ + { + "first_name": "Oscar", + "last_name": "Carlsson" + }, + { + "first_name": "Jan", + "last_name": "E. Gerken" + }, + { + "first_name": "Hampus", + "last_name": "Linander" + }, + { + "first_name": "Heiner", + "last_name": "Spieß" + }, + { + "first_name": "Fredrik", + "last_name": "Ohlsson" + }, + { + "first_name": "Christoffer", + "last_name": "Petersson" + }, + { + "first_name": "Daniel", + "last_name": "Persson" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "3D Paintbrush: Local Stylization of 3D Shapes with Cascaded Score Distillation", - "authors": "Dale Decatur, Itai Lang, Kfir Aberman, Rana Hanocka", + "authors": [ + { + "first_name": "Dale", + "last_name": "Decatur" + }, + { + "first_name": "Itai", + "last_name": "Lang" + }, + { + "first_name": "Kfir", + "last_name": "Aberman" + }, + { + "first_name": "Rana", + "last_name": "Hanocka" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Test-Time Linear Out-of-Distribution Detection", - "authors": "Ke Fan, Tong Liu, Xingyu Qiu, Yikai Wang, Lian Huai, Zeyu Shangguan, Shuang Gou, Fengjian Liu, Yuqian Fu, Yanwei Fu, Xingqun Jiang", + "authors": [ + { + "first_name": "Ke", + "last_name": "Fan" + }, + { + "first_name": "Tong", + "last_name": "Liu" + }, + { + "first_name": "Xingyu", + "last_name": "Qiu" + }, + { + "first_name": "Yikai", + "last_name": "Wang" + }, + { + "first_name": "Lian", + "last_name": "Huai" + }, + { + "first_name": "Zeyu", + "last_name": "Shangguan" + }, + { + "first_name": "Shuang", + "last_name": "Gou" + }, + { + "first_name": "Fengjian", + "last_name": "Liu" + }, + { + "first_name": "Yuqian", + "last_name": "Fu" + }, + { + "first_name": "Yanwei", + "last_name": "Fu" + }, + { + "first_name": "Xingqun", + "last_name": "Jiang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Guided Slot Attention for Unsupervised Video Object Segmentation", - "authors": "Minhyeok Lee, Suhwan Cho, Dogyoon Lee, Chaewon Park, Jungho Lee, Sangyoun Lee", + "authors": [ + { + "first_name": "Minhyeok", + "last_name": "Lee" + }, + { + "first_name": "Suhwan", + "last_name": "Cho" + }, + { + "first_name": "Dogyoon", + "last_name": "Lee" + }, + { + "first_name": "Chaewon", + "last_name": "Park" + }, + { + "first_name": "Jungho", + "last_name": "Lee" + }, + { + "first_name": "Sangyoun", + "last_name": "Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Unsupervised Blind Image Deblurring Based on Self-Enhancement", - "authors": "Lufei Chen, Xiangpeng Tian, Shuhua Xiong, Yinjie Lei, Chao Ren", + "authors": [ + { + "first_name": "Lufei", + "last_name": "Chen" + }, + { + "first_name": "Xiangpeng", + "last_name": "Tian" + }, + { + "first_name": "Shuhua", + "last_name": "Xiong" + }, + { + "first_name": "Yinjie", + "last_name": "Lei" + }, + { + "first_name": "Chao", + "last_name": "Ren" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Action Detection via an Image Diffusion Process", - "authors": "Lin Geng Foo, Tianjiao Li, Hossein Rahmani, Jun Liu", + "authors": [ + { + "first_name": "Lin", + "last_name": "Geng Foo" + }, + { + "first_name": "Tianjiao", + "last_name": "Li" + }, + { + "first_name": "Hossein", + "last_name": "Rahmani" + }, + { + "first_name": "Jun", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Programmable Motion Generation for Open-Set Motion Control Tasks", - "authors": "Hanchao Liu, Xiaohang Zhan, Shaoli Huang, Tai-Jiang Mu, Ying Shan", + "authors": [ + { + "first_name": "Hanchao", + "last_name": "Liu" + }, + { + "first_name": "Xiaohang", + "last_name": "Zhan" + }, + { + "first_name": "Shaoli", + "last_name": "Huang" + }, + { + "first_name": "Tai-Jiang", + "last_name": "Mu" + }, + { + "first_name": "Ying", + "last_name": "Shan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SCE-MAE: Selective Correspondence Enhancement with Masked Autoencoder for Self-Supervised Landmark Estimation", - "authors": "Kejia Yin, Varshanth Rao, Ruowei Jiang, Xudong Liu, Parham Aarabi, David B. Lindell", + "authors": [ + { + "first_name": "Kejia", + "last_name": "Yin" + }, + { + "first_name": "Varshanth", + "last_name": "Rao" + }, + { + "first_name": "Ruowei", + "last_name": "Jiang" + }, + { + "first_name": "Xudong", + "last_name": "Liu" + }, + { + "first_name": "Parham", + "last_name": "Aarabi" + }, + { + "first_name": "David", + "last_name": "B. Lindell" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LAKE-RED: Camouflaged Images Generation by Latent Background Knowledge Retrieval-Augmented Diffusion", - "authors": "Pancheng Zhao, Peng Xu, Pengda Qin, Deng-Ping Fan, Zhicheng Zhang, Guoli Jia, Bowen Zhou, Jufeng Yang", + "authors": [ + { + "first_name": "Pancheng", + "last_name": "Zhao" + }, + { + "first_name": "Peng", + "last_name": "Xu" + }, + { + "first_name": "Pengda", + "last_name": "Qin" + }, + { + "first_name": "Deng-Ping", + "last_name": "Fan" + }, + { + "first_name": "Zhicheng", + "last_name": "Zhang" + }, + { + "first_name": "Guoli", + "last_name": "Jia" + }, + { + "first_name": "Bowen", + "last_name": "Zhou" + }, + { + "first_name": "Jufeng", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "TIGER: Time-Varying Denoising Model for 3D Point Cloud Generation with Diffusion Process", - "authors": "Zhiyuan Ren, Minchul Kim, Feng Liu, Xiaoming Liu", + "authors": [ + { + "first_name": "Zhiyuan", + "last_name": "Ren" + }, + { + "first_name": "Minchul", + "last_name": "Kim" + }, + { + "first_name": "Feng", + "last_name": "Liu" + }, + { + "first_name": "Xiaoming", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ConTex-Human: Free-View Rendering of Human from a Single Image with Texture-Consistent Synthesis", - "authors": "Xiangjun Gao, Xiaoyu Li, Chaopeng Zhang, Qi Zhang, Yanpei Cao, Ying Shan, Long Quan", + "authors": [ + { + "first_name": "Xiangjun", + "last_name": "Gao" + }, + { + "first_name": "Xiaoyu", + "last_name": "Li" + }, + { + "first_name": "Chaopeng", + "last_name": "Zhang" + }, + { + "first_name": "Qi", + "last_name": "Zhang" + }, + { + "first_name": "Yanpei", + "last_name": "Cao" + }, + { + "first_name": "Ying", + "last_name": "Shan" + }, + { + "first_name": "Long", + "last_name": "Quan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "UFineBench: Towards Text-based Person Retrieval with Ultra-fine Granularity", - "authors": "Jialong Zuo, Hanyu Zhou, Ying Nie, Feng Zhang, Tianyu Guo, Nong Sang, Yunhe Wang, Changxin Gao", + "authors": [ + { + "first_name": "Jialong", + "last_name": "Zuo" + }, + { + "first_name": "Hanyu", + "last_name": "Zhou" + }, + { + "first_name": "Ying", + "last_name": "Nie" + }, + { + "first_name": "Feng", + "last_name": "Zhang" + }, + { + "first_name": "Tianyu", + "last_name": "Guo" + }, + { + "first_name": "Nong", + "last_name": "Sang" + }, + { + "first_name": "Yunhe", + "last_name": "Wang" + }, + { + "first_name": "Changxin", + "last_name": "Gao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Efficient Hyperparameter Optimization with Adaptive Fidelity Identification", - "authors": "Jiantong Jiang, Zeyi Wen, Atif Mansoor, Ajmal Mian", + "authors": [ + { + "first_name": "Jiantong", + "last_name": "Jiang" + }, + { + "first_name": "Zeyi", + "last_name": "Wen" + }, + { + "first_name": "Atif", + "last_name": "Mansoor" + }, + { + "first_name": "Ajmal", + "last_name": "Mian" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ASH: Animatable Gaussian Splats for Efficient and Photoreal Human Rendering", - "authors": "Haokai Pang, Heming Zhu, Adam Kortylewski, Christian Theobalt, Marc Habermann", + "authors": [ + { + "first_name": "Haokai", + "last_name": "Pang" + }, + { + "first_name": "Heming", + "last_name": "Zhu" + }, + { + "first_name": "Adam", + "last_name": "Kortylewski" + }, + { + "first_name": "Christian", + "last_name": "Theobalt" + }, + { + "first_name": "Marc", + "last_name": "Habermann" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Focus on Hiders: Exploring Hidden Threats for Enhancing Adversarial Training", - "authors": "Qian Li, Yuxiao Hu, Yinpeng Dong, Dongxiao Zhang, Yuntian Chen", + "authors": [ + { + "first_name": "Qian", + "last_name": "Li" + }, + { + "first_name": "Yuxiao", + "last_name": "Hu" + }, + { + "first_name": "Yinpeng", + "last_name": "Dong" + }, + { + "first_name": "Dongxiao", + "last_name": "Zhang" + }, + { + "first_name": "Yuntian", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ArtAdapter: Text-to-Image Style Transfer using Multi-Level Style Encoder and Explicit Adaptation", - "authors": "Dar-Yen Chen, Hamish Tennent, Ching-Wen Hsu", + "authors": [ + { + "first_name": "Dar-Yen", + "last_name": "Chen" + }, + { + "first_name": "Hamish", + "last_name": "Tennent" + }, + { + "first_name": "Ching-Wen", + "last_name": "Hsu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GoodSAM: Bridging Domain and Capacity Gaps via Segment Anything Model for Distortion-aware Panoramic Semantic Segmentation", - "authors": "Weiming Zhang, Yexin Liu, Xu Zheng, Lin Wang", + "authors": [ + { + "first_name": "Weiming", + "last_name": "Zhang" + }, + { + "first_name": "Yexin", + "last_name": "Liu" + }, + { + "first_name": "Xu", + "last_name": "Zheng" + }, + { + "first_name": "Lin", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DYSON: Dynamic Feature Space Self-Organization for Online Task-Free Class Incremental Learning", - "authors": "Yuhang He, Yingjie Chen, Yuhan Jin, Songlin Dong, Xing Wei, Yihong Gong", + "authors": [ + { + "first_name": "Yuhang", + "last_name": "He" + }, + { + "first_name": "Yingjie", + "last_name": "Chen" + }, + { + "first_name": "Yuhan", + "last_name": "Jin" + }, + { + "first_name": "Songlin", + "last_name": "Dong" + }, + { + "first_name": "Xing", + "last_name": "Wei" + }, + { + "first_name": "Yihong", + "last_name": "Gong" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Streaming Dense Video Captioning", - "authors": "Xingyi Zhou, Anurag Arnab, Shyamal Buch, Shen Yan, Austin Myers, Xuehan Xiong, Arsha Nagrani, Cordelia Schmid", + "authors": [ + { + "first_name": "Xingyi", + "last_name": "Zhou" + }, + { + "first_name": "Anurag", + "last_name": "Arnab" + }, + { + "first_name": "Shyamal", + "last_name": "Buch" + }, + { + "first_name": "Shen", + "last_name": "Yan" + }, + { + "first_name": "Austin", + "last_name": "Myers" + }, + { + "first_name": "Xuehan", + "last_name": "Xiong" + }, + { + "first_name": "Arsha", + "last_name": "Nagrani" + }, + { + "first_name": "Cordelia", + "last_name": "Schmid" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Rethinking Inductive Biases for Surface Normal Estimation", - "authors": "Gwangbin Bae, Andrew J. Davison", + "authors": [ + { + "first_name": "Gwangbin", + "last_name": "Bae" + }, + { + "first_name": "Andrew", + "last_name": "J. Davison" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Event-based Structure-from-Orbit", - "authors": "Ethan Elms, Yasir Latif, Tae Ha Park, Tat-Jun Chin", + "authors": [ + { + "first_name": "Ethan", + "last_name": "Elms" + }, + { + "first_name": "Yasir", + "last_name": "Latif" + }, + { + "first_name": "Tae", + "last_name": "Ha Park" + }, + { + "first_name": "Tat-Jun", + "last_name": "Chin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LED: A Large-scale Real-world Paired Dataset for Event Camera Denoising", - "authors": "Yuxing Duan", + "authors": [ + { + "first_name": "Yuxing", + "last_name": "Duan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Fair Federated Learning under Domain Skew with Local Consistency and Domain Diversity", - "authors": "Yuhang Chen, Wenke Huang, Mang Ye", + "authors": [ + { + "first_name": "Yuhang", + "last_name": "Chen" + }, + { + "first_name": "Wenke", + "last_name": "Huang" + }, + { + "first_name": "Mang", + "last_name": "Ye" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Activity-Biometrics: Person Identification from Daily Activities", - "authors": "Shehreen Azad, Yogesh Singh Rawat", + "authors": [ + { + "first_name": "Shehreen", + "last_name": "Azad" + }, + { + "first_name": "Yogesh", + "last_name": "Singh Rawat" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Z*: Zero-shot Style Transfer via Attention Reweighting", - "authors": "Yingying Deng, Xiangyu He, Fan Tang, Weiming Dong", + "authors": [ + { + "first_name": "Yingying", + "last_name": "Deng" + }, + { + "first_name": "Xiangyu", + "last_name": "He" + }, + { + "first_name": "Fan", + "last_name": "Tang" + }, + { + "first_name": "Weiming", + "last_name": "Dong" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HIG: Hierarchical Interlacement Graph Approach to Scene Graph Generation in Video Understanding", - "authors": "Trong-Thuan Nguyen, Pha Nguyen, Khoa Luu", + "authors": [ + { + "first_name": "Trong-Thuan", + "last_name": "Nguyen" + }, + { + "first_name": "Pha", + "last_name": "Nguyen" + }, + { + "first_name": "Khoa", + "last_name": "Luu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "OOSTraj: Out-of-Sight Trajectory Prediction With Vision-Positioning Denoising", - "authors": "Haichao Zhang, Yi Xu, Hongsheng Lu, Takayuki Shimizu, Yun Fu", + "authors": [ + { + "first_name": "Haichao", + "last_name": "Zhang" + }, + { + "first_name": "Yi", + "last_name": "Xu" + }, + { + "first_name": "Hongsheng", + "last_name": "Lu" + }, + { + "first_name": "Takayuki", + "last_name": "Shimizu" + }, + { + "first_name": "Yun", + "last_name": "Fu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FADES: Fair Disentanglement with Sensitive Relevance", - "authors": "Taeuk Jang, Xiaoqian Wang", + "authors": [ + { + "first_name": "Taeuk", + "last_name": "Jang" + }, + { + "first_name": "Xiaoqian", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning Continuous 3D Words for Text-to-Image Generation", - "authors": "Ta-Ying Cheng, Matheus Gadelha, Thibault Groueix, Matthew Fisher, Radomir Mech, Andrew Markham, Niki Trigoni", + "authors": [ + { + "first_name": "Ta-Ying", + "last_name": "Cheng" + }, + { + "first_name": "Matheus", + "last_name": "Gadelha" + }, + { + "first_name": "Thibault", + "last_name": "Groueix" + }, + { + "first_name": "Matthew", + "last_name": "Fisher" + }, + { + "first_name": "Radomir", + "last_name": "Mech" + }, + { + "first_name": "Andrew", + "last_name": "Markham" + }, + { + "first_name": "Niki", + "last_name": "Trigoni" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MarkovGen: Structured Prediction for Efficient Text-to-Image Generation", - "authors": "Sadeep Jayasumana, Daniel Glasner, Srikumar Ramalingam, Andreas Veit, Ayan Chakrabarti, Sanjiv Kumar", + "authors": [ + { + "first_name": "Sadeep", + "last_name": "Jayasumana" + }, + { + "first_name": "Daniel", + "last_name": "Glasner" + }, + { + "first_name": "Srikumar", + "last_name": "Ramalingam" + }, + { + "first_name": "Andreas", + "last_name": "Veit" + }, + { + "first_name": "Ayan", + "last_name": "Chakrabarti" + }, + { + "first_name": "Sanjiv", + "last_name": "Kumar" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Self-Supervised Class-Agnostic Motion Prediction with Spatial and Temporal Consistency Regularizations", - "authors": "Kewei Wang, Yizheng Wu, Jun Cen, Zhiyu Pan, Xingyi Li, Zhe Wang, Zhiguo Cao, Guosheng Lin", + "authors": [ + { + "first_name": "Kewei", + "last_name": "Wang" + }, + { + "first_name": "Yizheng", + "last_name": "Wu" + }, + { + "first_name": "Jun", + "last_name": "Cen" + }, + { + "first_name": "Zhiyu", + "last_name": "Pan" + }, + { + "first_name": "Xingyi", + "last_name": "Li" + }, + { + "first_name": "Zhe", + "last_name": "Wang" + }, + { + "first_name": "Zhiguo", + "last_name": "Cao" + }, + { + "first_name": "Guosheng", + "last_name": "Lin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HashPoint: Accelerated Point Searching and Sampling for Neural Rendering", - "authors": "Jiahao Ma, Miaomiao Liu, David Ahmedt-Aristizabal, Chuong Nguyen", + "authors": [ + { + "first_name": "Jiahao", + "last_name": "Ma" + }, + { + "first_name": "Miaomiao", + "last_name": "Liu" + }, + { + "first_name": "David", + "last_name": "Ahmedt-Aristizabal" + }, + { + "first_name": "Chuong", + "last_name": "Nguyen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MFP: Making Full Use of Probability Maps for Interactive Image Segmentation", - "authors": "Chaewon Lee, Seon-Ho Lee, Chang-Su Kim", + "authors": [ + { + "first_name": "Chaewon", + "last_name": "Lee" + }, + { + "first_name": "Seon-Ho", + "last_name": "Lee" + }, + { + "first_name": "Chang-Su", + "last_name": "Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CAT: Exploiting Inter-Class Dynamics for Domain Adaptive Object Detection", - "authors": "Mikhail Kennerley, Jian-Gang Wang, Bharadwaj Veeravalli, Robby T. Tan", + "authors": [ + { + "first_name": "Mikhail", + "last_name": "Kennerley" + }, + { + "first_name": "Jian-Gang", + "last_name": "Wang" + }, + { + "first_name": "Bharadwaj", + "last_name": "Veeravalli" + }, + { + "first_name": "Robby", + "last_name": "T. Tan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "StyLitGAN: Image-Based Relighting via Latent Control", - "authors": "Anand Bhattad, James Soole, D.A. Forsyth", + "authors": [ + { + "first_name": "Anand", + "last_name": "Bhattad" + }, + { + "first_name": "James", + "last_name": "Soole" + }, + { + "first_name": "D.A.", + "last_name": "Forsyth" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "An Empirical Study of Scaling Law for Scene Text Recognition", - "authors": "Miao Rang, Zhenni Bi, Chuanjian Liu, Yunhe Wang, Kai Han", + "authors": [ + { + "first_name": "Miao", + "last_name": "Rang" + }, + { + "first_name": "Zhenni", + "last_name": "Bi" + }, + { + "first_name": "Chuanjian", + "last_name": "Liu" + }, + { + "first_name": "Yunhe", + "last_name": "Wang" + }, + { + "first_name": "Kai", + "last_name": "Han" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Text2Loc: 3D Point Cloud Localization from Natural Language", - "authors": "Yan Xia, Letian Shi, Zifeng Ding, Joao F. Henriques, Daniel Cremers", + "authors": [ + { + "first_name": "Yan", + "last_name": "Xia" + }, + { + "first_name": "Letian", + "last_name": "Shi" + }, + { + "first_name": "Zifeng", + "last_name": "Ding" + }, + { + "first_name": "Joao", + "last_name": "F. Henriques" + }, + { + "first_name": "Daniel", + "last_name": "Cremers" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SVDinsTN: A Tensor Network Paradigm for Efficient Structure Search from Regularized Modeling Perspective", - "authors": "Yu-Bang Zheng, Xi-Le Zhao, Junhua Zeng, Chao Li, Qibin Zhao, Heng-Chao Li, Ting-Zhu Huang", + "authors": [ + { + "first_name": "Yu-Bang", + "last_name": "Zheng" + }, + { + "first_name": "Xi-Le", + "last_name": "Zhao" + }, + { + "first_name": "Junhua", + "last_name": "Zeng" + }, + { + "first_name": "Chao", + "last_name": "Li" + }, + { + "first_name": "Qibin", + "last_name": "Zhao" + }, + { + "first_name": "Heng-Chao", + "last_name": "Li" + }, + { + "first_name": "Ting-Zhu", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Decomposing Disease Descriptions for Enhanced Pathology Detection: A Multi-Aspect Vision-Language Pre-training Framework", - "authors": "Vu Minh Hieu Phan, Yutong Xie, Yuankai Qi, Lingqiao Liu, Liyang Liu, Bowen Zhang, Zhibin Liao, Qi Wu, Minh-Son To, Johan W. Verjans", + "authors": [ + { + "first_name": "Vu", + "last_name": "Minh Hieu Phan" + }, + { + "first_name": "Yutong", + "last_name": "Xie" + }, + { + "first_name": "Yuankai", + "last_name": "Qi" + }, + { + "first_name": "Lingqiao", + "last_name": "Liu" + }, + { + "first_name": "Liyang", + "last_name": "Liu" + }, + { + "first_name": "Bowen", + "last_name": "Zhang" + }, + { + "first_name": "Zhibin", + "last_name": "Liao" + }, + { + "first_name": "Qi", + "last_name": "Wu" + }, + { + "first_name": "Minh-Son", + "last_name": "To" + }, + { + "first_name": "Johan", + "last_name": "W. Verjans" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MoMask: Generative Masked Modeling of 3D Human Motions", - "authors": "Chuan Guo, Yuxuan Mu, Muhammad Gohar Javed, Sen Wang, Li Cheng", + "authors": [ + { + "first_name": "Chuan", + "last_name": "Guo" + }, + { + "first_name": "Yuxuan", + "last_name": "Mu" + }, + { + "first_name": "Muhammad", + "last_name": "Gohar Javed" + }, + { + "first_name": "Sen", + "last_name": "Wang" + }, + { + "first_name": "Li", + "last_name": "Cheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Inverse Rendering of Glossy Objects via the Neural Plenoptic Function and Radiance Fields", - "authors": "Haoyuan Wang, Wenbo Hu, Lei Zhu, Rynson W.H. Lau", + "authors": [ + { + "first_name": "Haoyuan", + "last_name": "Wang" + }, + { + "first_name": "Wenbo", + "last_name": "Hu" + }, + { + "first_name": "Lei", + "last_name": "Zhu" + }, + { + "first_name": "Rynson", + "last_name": "W.H. Lau" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Split to Merge: Unifying Separated Modalities for Unsupervised Domain Adaptation", - "authors": "Xinyao Li, Yuke Li, Zhekai Du, Fengling Li, Ke Lu, Jingjing Li", + "authors": [ + { + "first_name": "Xinyao", + "last_name": "Li" + }, + { + "first_name": "Yuke", + "last_name": "Li" + }, + { + "first_name": "Zhekai", + "last_name": "Du" + }, + { + "first_name": "Fengling", + "last_name": "Li" + }, + { + "first_name": "Ke", + "last_name": "Lu" + }, + { + "first_name": "Jingjing", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Fitting Flats to Flats", - "authors": "Gabriel Dogadov, Ugo Finnendahl, Marc Alexa", + "authors": [ + { + "first_name": "Gabriel", + "last_name": "Dogadov" + }, + { + "first_name": "Ugo", + "last_name": "Finnendahl" + }, + { + "first_name": "Marc", + "last_name": "Alexa" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Fusing Personal and Environmental Cues for Identification and Segmentation of First-Person Camera Wearers in Third-Person Views", - "authors": "Ziwei Zhao, Yuchen Wang, Chuhua Wang", + "authors": [ + { + "first_name": "Ziwei", + "last_name": "Zhao" + }, + { + "first_name": "Yuchen", + "last_name": "Wang" + }, + { + "first_name": "Chuhua", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Coupled Laplacian Eigenmaps for Locally-Aware 3D Rigid Point Cloud Matching", - "authors": "Matteo Bastico, Etienne Decencière, Laurent Corté, Yannick Tillier, David Ryckelynck", + "authors": [ + { + "first_name": "Matteo", + "last_name": "Bastico" + }, + { + "first_name": "Etienne", + "last_name": "Decencière" + }, + { + "first_name": "Laurent", + "last_name": "Corté" + }, + { + "first_name": "Yannick", + "last_name": "Tillier" + }, + { + "first_name": "David", + "last_name": "Ryckelynck" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Overcoming Generic Knowledge Loss with Selective Parameter Update", - "authors": "Wenxuan Zhang, Paul Janson, Rahaf Aljundi, Mohamed Elhoseiny", + "authors": [ + { + "first_name": "Wenxuan", + "last_name": "Zhang" + }, + { + "first_name": "Paul", + "last_name": "Janson" + }, + { + "first_name": "Rahaf", + "last_name": "Aljundi" + }, + { + "first_name": "Mohamed", + "last_name": "Elhoseiny" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Desigen: A Pipeline for Controllable Design Template Generation", - "authors": "Haohan Weng, Danqing Huang, Yu Qiao, Zheng Hu, Chin-Yew Lin, Tong Zhang, C. L. Philip Chen", + "authors": [ + { + "first_name": "Haohan", + "last_name": "Weng" + }, + { + "first_name": "Danqing", + "last_name": "Huang" + }, + { + "first_name": "Yu", + "last_name": "Qiao" + }, + { + "first_name": "Zheng", + "last_name": "Hu" + }, + { + "first_name": "Chin-Yew", + "last_name": "Lin" + }, + { + "first_name": "Tong", + "last_name": "Zhang" + }, + { + "first_name": "C.", + "last_name": "L. Philip Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Diff-BGM: A Diffusion Model for Video Background Music Generation", - "authors": "Sizhe Li, Yiming Qin, Minghang Zheng, Xin Jin, Yang Liu", + "authors": [ + { + "first_name": "Sizhe", + "last_name": "Li" + }, + { + "first_name": "Yiming", + "last_name": "Qin" + }, + { + "first_name": "Minghang", + "last_name": "Zheng" + }, + { + "first_name": "Xin", + "last_name": "Jin" + }, + { + "first_name": "Yang", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Looking Similar Sounding Different: Leveraging Counterfactual Cross-Modal Pairs for Audiovisual Representation Learning", - "authors": "Nikhil Singh, Chih-Wei Wu, Iroro Orife, Mahdi Kalayeh", + "authors": [ + { + "first_name": "Nikhil", + "last_name": "Singh" + }, + { + "first_name": "Chih-Wei", + "last_name": "Wu" + }, + { + "first_name": "Iroro", + "last_name": "Orife" + }, + { + "first_name": "Mahdi", + "last_name": "Kalayeh" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers", - "authors": "Sanghyeok Lee, Joonmyung Choi, Hyunwoo J. Kim", + "authors": [ + { + "first_name": "Sanghyeok", + "last_name": "Lee" + }, + { + "first_name": "Joonmyung", + "last_name": "Choi" + }, + { + "first_name": "Hyunwoo", + "last_name": "J. Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards HDR and HFR Video from Rolling-Mixed-Bit Spikings", - "authors": "Yakun Chang, Yeliduosi Xiaokaiti, Yujia Liu, Bin Fan, Zhaojun Huang, Tiejun Huang, Boxin Shi", + "authors": [ + { + "first_name": "Yakun", + "last_name": "Chang" + }, + { + "first_name": "Yeliduosi", + "last_name": "Xiaokaiti" + }, + { + "first_name": "Yujia", + "last_name": "Liu" + }, + { + "first_name": "Bin", + "last_name": "Fan" + }, + { + "first_name": "Zhaojun", + "last_name": "Huang" + }, + { + "first_name": "Tiejun", + "last_name": "Huang" + }, + { + "first_name": "Boxin", + "last_name": "Shi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Scaling Up Video Summarization Pretraining with Large Language Models", - "authors": "Dawit Mureja Argaw, Seunghyun Yoon, Fabian Caba Heilbron, Hanieh Deilamsalehy, Trung Bui, Zhaowen Wang, Franck Dernoncourt, Joon Son Chung", + "authors": [ + { + "first_name": "Dawit", + "last_name": "Mureja Argaw" + }, + { + "first_name": "Seunghyun", + "last_name": "Yoon" + }, + { + "first_name": "Fabian", + "last_name": "Caba Heilbron" + }, + { + "first_name": "Hanieh", + "last_name": "Deilamsalehy" + }, + { + "first_name": "Trung", + "last_name": "Bui" + }, + { + "first_name": "Zhaowen", + "last_name": "Wang" + }, + { + "first_name": "Franck", + "last_name": "Dernoncourt" + }, + { + "first_name": "Joon", + "last_name": "Son Chung" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Continuous Optical Zooming: A Benchmark for Arbitrary-Scale Image Super-Resolution in Real World", - "authors": "Huiyuan Fu, Fei Peng, Xianwei Li, Yejun Li, Xin Wang, Huadong Ma", + "authors": [ + { + "first_name": "Huiyuan", + "last_name": "Fu" + }, + { + "first_name": "Fei", + "last_name": "Peng" + }, + { + "first_name": "Xianwei", + "last_name": "Li" + }, + { + "first_name": "Yejun", + "last_name": "Li" + }, + { + "first_name": "Xin", + "last_name": "Wang" + }, + { + "first_name": "Huadong", + "last_name": "Ma" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Sharingan: A Transformer Architecture for Multi-Person Gaze Following", - "authors": "Samy Tafasca, Anshul Gupta, Jean-Marc Odobez", + "authors": [ + { + "first_name": "Samy", + "last_name": "Tafasca" + }, + { + "first_name": "Anshul", + "last_name": "Gupta" + }, + { + "first_name": "Jean-Marc", + "last_name": "Odobez" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ViewFusion: Towards Multi-View Consistency via Interpolated Denoising", - "authors": "Xianghui Yang, Yan Zuo, Sameera Ramasinghe, Loris Bazzani, Gil Avraham, Anton van den Hengel", + "authors": [ + { + "first_name": "Xianghui", + "last_name": "Yang" + }, + { + "first_name": "Yan", + "last_name": "Zuo" + }, + { + "first_name": "Sameera", + "last_name": "Ramasinghe" + }, + { + "first_name": "Loris", + "last_name": "Bazzani" + }, + { + "first_name": "Gil", + "last_name": "Avraham" + }, + { + "first_name": "Anton", + "last_name": "van den Hengel" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SketchINR: A First Look into Sketches as Implicit Neural Representations", - "authors": "Hmrishav Bandyopadhyay, Ayan Kumar Bhunia, Pinaki Nath Chowdhury, Aneeshan Sain, Tao Xiang, Timothy Hospedales, Yi-Zhe Song", + "authors": [ + { + "first_name": "Hmrishav", + "last_name": "Bandyopadhyay" + }, + { + "first_name": "Ayan", + "last_name": "Kumar Bhunia" + }, + { + "first_name": "Pinaki", + "last_name": "Nath Chowdhury" + }, + { + "first_name": "Aneeshan", + "last_name": "Sain" + }, + { + "first_name": "Tao", + "last_name": "Xiang" + }, + { + "first_name": "Timothy", + "last_name": "Hospedales" + }, + { + "first_name": "Yi-Zhe", + "last_name": "Song" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Open-Vocabulary Segmentation with Semantic-Assisted Calibration", - "authors": "Yong Liu, Sule Bai, Guanbin Li, Yitong Wang, Yansong Tang", + "authors": [ + { + "first_name": "Yong", + "last_name": "Liu" + }, + { + "first_name": "Sule", + "last_name": "Bai" + }, + { + "first_name": "Guanbin", + "last_name": "Li" + }, + { + "first_name": "Yitong", + "last_name": "Wang" + }, + { + "first_name": "Yansong", + "last_name": "Tang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MatchU: Matching Unseen Objects for 6D Pose Estimation from RGB-D Images", - "authors": "Junwen Huang, Hao Yu, Kuan-Ting Yu, Nassir Navab, Slobodan Ilic, Benjamin Busam", + "authors": [ + { + "first_name": "Junwen", + "last_name": "Huang" + }, + { + "first_name": "Hao", + "last_name": "Yu" + }, + { + "first_name": "Kuan-Ting", + "last_name": "Yu" + }, + { + "first_name": "Nassir", + "last_name": "Navab" + }, + { + "first_name": "Slobodan", + "last_name": "Ilic" + }, + { + "first_name": "Benjamin", + "last_name": "Busam" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards a Perceptual Evaluation Framework for Lighting Estimation", - "authors": "Justine Giroux, Mohammad Reza Karimi Dastjerdi, Yannick Hold-Geoffroy, Javier Vazquez-Corral, Jean-François Lalonde", + "authors": [ + { + "first_name": "Justine", + "last_name": "Giroux" + }, + { + "first_name": "Mohammad", + "last_name": "Reza Karimi Dastjerdi" + }, + { + "first_name": "Yannick", + "last_name": "Hold-Geoffroy" + }, + { + "first_name": "Javier", + "last_name": "Vazquez-Corral" + }, + { + "first_name": "Jean-François", + "last_name": "Lalonde" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Bridging the Synthetic-to-Authentic Gap: Distortion-Guided Unsupervised Domain Adaptation for Blind Image Quality Assessment", - "authors": "Aobo Li, Jinjian Wu, Yongxu Liu, Leida Li", + "authors": [ + { + "first_name": "Aobo", + "last_name": "Li" + }, + { + "first_name": "Jinjian", + "last_name": "Wu" + }, + { + "first_name": "Yongxu", + "last_name": "Liu" + }, + { + "first_name": "Leida", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Coherent Temporal Synthesis for Incremental Action Segmentation", - "authors": "Guodong Ding, Hans Golong, Angela Yao", + "authors": [ + { + "first_name": "Guodong", + "last_name": "Ding" + }, + { + "first_name": "Hans", + "last_name": "Golong" + }, + { + "first_name": "Angela", + "last_name": "Yao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HiFi4G: High-Fidelity Human Performance Rendering via Compact Gaussian Splatting", - "authors": "Yuheng Jiang, Zhehao Shen, Penghao Wang, Zhuo Su, Yu Hong, Yingliang Zhang, Jingyi Yu, Lan Xu", + "authors": [ + { + "first_name": "Yuheng", + "last_name": "Jiang" + }, + { + "first_name": "Zhehao", + "last_name": "Shen" + }, + { + "first_name": "Penghao", + "last_name": "Wang" + }, + { + "first_name": "Zhuo", + "last_name": "Su" + }, + { + "first_name": "Yu", + "last_name": "Hong" + }, + { + "first_name": "Yingliang", + "last_name": "Zhang" + }, + { + "first_name": "Jingyi", + "last_name": "Yu" + }, + { + "first_name": "Lan", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "G-FARS: Gradient-Field-based Auto-Regressive Sampling for 3D Part Grouping", - "authors": "Junfeng Cheng, Tania Stathaki", + "authors": [ + { + "first_name": "Junfeng", + "last_name": "Cheng" + }, + { + "first_name": "Tania", + "last_name": "Stathaki" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards High-fidelity Artistic Image Vectorization via Texture-Encapsulated Shape Parameterization", - "authors": "Ye Chen, Bingbing Ni, Jinfan Liu, Xiaoyang Huang, Xuanhong Chen", + "authors": [ + { + "first_name": "Ye", + "last_name": "Chen" + }, + { + "first_name": "Bingbing", + "last_name": "Ni" + }, + { + "first_name": "Jinfan", + "last_name": "Liu" + }, + { + "first_name": "Xiaoyang", + "last_name": "Huang" + }, + { + "first_name": "Xuanhong", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "On Exact Inversion of DPM-Solvers", - "authors": "Seongmin Hong, Kyeonghyun Lee, Suh Yoon Jeon, Hyewon Bae, Se Young Chun", + "authors": [ + { + "first_name": "Seongmin", + "last_name": "Hong" + }, + { + "first_name": "Kyeonghyun", + "last_name": "Lee" + }, + { + "first_name": "Suh", + "last_name": "Yoon Jeon" + }, + { + "first_name": "Hyewon", + "last_name": "Bae" + }, + { + "first_name": "Se", + "last_name": "Young Chun" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything", - "authors": "Yunyang Xiong, Bala Varadarajan, Lemeng Wu, Xiaoyu Xiang, Fanyi Xiao, Chenchen Zhu, Xiaoliang Dai, Dilin Wang, Fei Sun, Forrest Iandola, Raghuraman Krishnamoorthi, Vikas Chandra", + "authors": [ + { + "first_name": "Yunyang", + "last_name": "Xiong" + }, + { + "first_name": "Bala", + "last_name": "Varadarajan" + }, + { + "first_name": "Lemeng", + "last_name": "Wu" + }, + { + "first_name": "Xiaoyu", + "last_name": "Xiang" + }, + { + "first_name": "Fanyi", + "last_name": "Xiao" + }, + { + "first_name": "Chenchen", + "last_name": "Zhu" + }, + { + "first_name": "Xiaoliang", + "last_name": "Dai" + }, + { + "first_name": "Dilin", + "last_name": "Wang" + }, + { + "first_name": "Fei", + "last_name": "Sun" + }, + { + "first_name": "Forrest", + "last_name": "Iandola" + }, + { + "first_name": "Raghuraman", + "last_name": "Krishnamoorthi" + }, + { + "first_name": "Vikas", + "last_name": "Chandra" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ChatScene: Knowledge-Enabled Safety-Critical Scenario Generation for Autonomous Vehicles", - "authors": "Jiawei Zhang, Chejian Xu, Bo Li", + "authors": [ + { + "first_name": "Jiawei", + "last_name": "Zhang" + }, + { + "first_name": "Chejian", + "last_name": "Xu" + }, + { + "first_name": "Bo", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CAMEL: CAusal Motion Enhancement Tailored for Lifting Text-driven Video Editing", - "authors": "Guiwei Zhang, Tianyu Zhang, Guanglin Niu, Zichang Tan, Yalong Bai, Qing Yang", + "authors": [ + { + "first_name": "Guiwei", + "last_name": "Zhang" + }, + { + "first_name": "Tianyu", + "last_name": "Zhang" + }, + { + "first_name": "Guanglin", + "last_name": "Niu" + }, + { + "first_name": "Zichang", + "last_name": "Tan" + }, + { + "first_name": "Yalong", + "last_name": "Bai" + }, + { + "first_name": "Qing", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Teeth-SEG: An Efficient Instance Segmentation Framework for Orthodontic Treatment based on Multi-Scale Aggregation and Anthropic Prior Knowledge", - "authors": "Bo Zou, Shaofeng Wang, Hao Liu, Gaoyue Sun, Yajie Wang, FeiFei Zuo, Chengbin Quan, Youjian Zhao", + "authors": [ + { + "first_name": "Bo", + "last_name": "Zou" + }, + { + "first_name": "Shaofeng", + "last_name": "Wang" + }, + { + "first_name": "Hao", + "last_name": "Liu" + }, + { + "first_name": "Gaoyue", + "last_name": "Sun" + }, + { + "first_name": "Yajie", + "last_name": "Wang" + }, + { + "first_name": "FeiFei", + "last_name": "Zuo" + }, + { + "first_name": "Chengbin", + "last_name": "Quan" + }, + { + "first_name": "Youjian", + "last_name": "Zhao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FocSAM: Delving Deeply into Focused Objects in Segmenting Anything", - "authors": "You Huang, Zongyu Lan, Liujuan Cao, Xianming Lin, Shengchuan Zhang, Guannan Jiang, Rongrong Ji", + "authors": [ + { + "first_name": "You", + "last_name": "Huang" + }, + { + "first_name": "Zongyu", + "last_name": "Lan" + }, + { + "first_name": "Liujuan", + "last_name": "Cao" + }, + { + "first_name": "Xianming", + "last_name": "Lin" + }, + { + "first_name": "Shengchuan", + "last_name": "Zhang" + }, + { + "first_name": "Guannan", + "last_name": "Jiang" + }, + { + "first_name": "Rongrong", + "last_name": "Ji" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DMR: Decomposed Multi-Modality Representations for Frames and Events Fusion in Visual Reinforcement Learning", - "authors": "Haoran Xu, Peixi Peng, Guang Tan, Yuan Li, Xinhai Xu, Yonghong Tian", + "authors": [ + { + "first_name": "Haoran", + "last_name": "Xu" + }, + { + "first_name": "Peixi", + "last_name": "Peng" + }, + { + "first_name": "Guang", + "last_name": "Tan" + }, + { + "first_name": "Yuan", + "last_name": "Li" + }, + { + "first_name": "Xinhai", + "last_name": "Xu" + }, + { + "first_name": "Yonghong", + "last_name": "Tian" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DiffuseMix: Label-Preserving Data Augmentation with Diffusion Models", - "authors": "Khawar Islam, Muhammad Zaigham Zaheer, Arif Mahmood, Karthik Nandakumar", + "authors": [ + { + "first_name": "Khawar", + "last_name": "Islam" + }, + { + "first_name": "Muhammad", + "last_name": "Zaigham Zaheer" + }, + { + "first_name": "Arif", + "last_name": "Mahmood" + }, + { + "first_name": "Karthik", + "last_name": "Nandakumar" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PRDP: Proximal Reward Difference Prediction for Large-Scale Reward Finetuning of Diffusion Models", - "authors": "Fei Deng, Qifei Wang, Wei Wei, Tingbo Hou, Matthias Grundmann", + "authors": [ + { + "first_name": "Fei", + "last_name": "Deng" + }, + { + "first_name": "Qifei", + "last_name": "Wang" + }, + { + "first_name": "Wei", + "last_name": "Wei" + }, + { + "first_name": "Tingbo", + "last_name": "Hou" + }, + { + "first_name": "Matthias", + "last_name": "Grundmann" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FREE: Faster and Better Data-Free Meta-Learning", - "authors": "Yongxian Wei, Zixuan Hu, Zhenyi Wang, Li Shen, Chun Yuan, Dacheng Tao", + "authors": [ + { + "first_name": "Yongxian", + "last_name": "Wei" + }, + { + "first_name": "Zixuan", + "last_name": "Hu" + }, + { + "first_name": "Zhenyi", + "last_name": "Wang" + }, + { + "first_name": "Li", + "last_name": "Shen" + }, + { + "first_name": "Chun", + "last_name": "Yuan" + }, + { + "first_name": "Dacheng", + "last_name": "Tao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Bayesian Diffusion Models for 3D Shape Reconstruction", - "authors": "Haiyang Xu, Yu Lei, Zeyuan Chen, Xiang Zhang, Yue Zhao, Yilin Wang, Zhuowen Tu", + "authors": [ + { + "first_name": "Haiyang", + "last_name": "Xu" + }, + { + "first_name": "Yu", + "last_name": "Lei" + }, + { + "first_name": "Zeyuan", + "last_name": "Chen" + }, + { + "first_name": "Xiang", + "last_name": "Zhang" + }, + { + "first_name": "Yue", + "last_name": "Zhao" + }, + { + "first_name": "Yilin", + "last_name": "Wang" + }, + { + "first_name": "Zhuowen", + "last_name": "Tu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Task-Customized Mixture of Adapters for General Image Fusion", - "authors": "Pengfei Zhu, Yang Sun, Bing Cao, Qinghua Hu", + "authors": [ + { + "first_name": "Pengfei", + "last_name": "Zhu" + }, + { + "first_name": "Yang", + "last_name": "Sun" + }, + { + "first_name": "Bing", + "last_name": "Cao" + }, + { + "first_name": "Qinghua", + "last_name": "Hu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Bi-SSC: Geometric-Semantic Bidirectional Fusion for Camera-based 3D Semantic Scene Completion", - "authors": "Yujie Xue, Ruihui Li, Fan Wu, Zhuo Tang, Kenli Li, Mingxing Duan", + "authors": [ + { + "first_name": "Yujie", + "last_name": "Xue" + }, + { + "first_name": "Ruihui", + "last_name": "Li" + }, + { + "first_name": "Fan", + "last_name": "Wu" + }, + { + "first_name": "Zhuo", + "last_name": "Tang" + }, + { + "first_name": "Kenli", + "last_name": "Li" + }, + { + "first_name": "Mingxing", + "last_name": "Duan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CrossKD: Cross-Head Knowledge Distillation for Object Detection", - "authors": "Jiabao Wang, Yuming Chen, Zhaohui Zheng, Xiang Li, Ming-Ming Cheng, Qibin Hou", + "authors": [ + { + "first_name": "Jiabao", + "last_name": "Wang" + }, + { + "first_name": "Yuming", + "last_name": "Chen" + }, + { + "first_name": "Zhaohui", + "last_name": "Zheng" + }, + { + "first_name": "Xiang", + "last_name": "Li" + }, + { + "first_name": "Ming-Ming", + "last_name": "Cheng" + }, + { + "first_name": "Qibin", + "last_name": "Hou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Bi-level Learning of Task-Specific Decoders for Joint Registration and One-Shot Medical Image Segmentation", - "authors": "Xin Fan, Xiaolin Wang, Jiaxin Gao, Jia Wang, Zhongxuan Luo, Risheng Liu", + "authors": [ + { + "first_name": "Xin", + "last_name": "Fan" + }, + { + "first_name": "Xiaolin", + "last_name": "Wang" + }, + { + "first_name": "Jiaxin", + "last_name": "Gao" + }, + { + "first_name": "Jia", + "last_name": "Wang" + }, + { + "first_name": "Zhongxuan", + "last_name": "Luo" + }, + { + "first_name": "Risheng", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Parameter Efficient Self-Supervised Geospatial Domain Adaptation", - "authors": "Linus Scheibenreif, Michael Mommert, Damian Borth", + "authors": [ + { + "first_name": "Linus", + "last_name": "Scheibenreif" + }, + { + "first_name": "Michael", + "last_name": "Mommert" + }, + { + "first_name": "Damian", + "last_name": "Borth" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Defense without Forgetting: Continual Adversarial Defense with Anisotropic & Isotropic Pseudo Replay", - "authors": "Yuhang Zhou, Zhongyun Hua", + "authors": [ + { + "first_name": "Yuhang", + "last_name": "Zhou" + }, + { + "first_name": "Zhongyun", + "last_name": "Hua" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "EscherNet: A Generative Model for Scalable View Synthesis", - "authors": "Xin Kong, Shikun Liu, Xiaoyang Lyu, Marwan Taher, Xiaojuan Qi, Andrew J. Davison", + "authors": [ + { + "first_name": "Xin", + "last_name": "Kong" + }, + { + "first_name": "Shikun", + "last_name": "Liu" + }, + { + "first_name": "Xiaoyang", + "last_name": "Lyu" + }, + { + "first_name": "Marwan", + "last_name": "Taher" + }, + { + "first_name": "Xiaojuan", + "last_name": "Qi" + }, + { + "first_name": "Andrew", + "last_name": "J. Davison" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MeaCap: Memory-Augmented Zero-shot Image Captioning", - "authors": "Zequn Zeng, Yan Xie, Hao Zhang, Chiyu Chen, Bo Chen, Zhengjue Wang", + "authors": [ + { + "first_name": "Zequn", + "last_name": "Zeng" + }, + { + "first_name": "Yan", + "last_name": "Xie" + }, + { + "first_name": "Hao", + "last_name": "Zhang" + }, + { + "first_name": "Chiyu", + "last_name": "Chen" + }, + { + "first_name": "Bo", + "last_name": "Chen" + }, + { + "first_name": "Zhengjue", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Artist-Friendly Relightable and Animatable Neural Heads", - "authors": "Yingyan Xu, Prashanth Chandran, Sebastian Weiss, Markus Gross, Gaspard Zoss, Derek Bradley", + "authors": [ + { + "first_name": "Yingyan", + "last_name": "Xu" + }, + { + "first_name": "Prashanth", + "last_name": "Chandran" + }, + { + "first_name": "Sebastian", + "last_name": "Weiss" + }, + { + "first_name": "Markus", + "last_name": "Gross" + }, + { + "first_name": "Gaspard", + "last_name": "Zoss" + }, + { + "first_name": "Derek", + "last_name": "Bradley" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Elite360D: Towards Efficient 360 Depth Estimation via Semantic- and Distance-Aware Bi-Projection Fusion", - "authors": "Hao Ai, Lin Wang", + "authors": [ + { + "first_name": "Hao", + "last_name": "Ai" + }, + { + "first_name": "Lin", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "From Feature to Gaze: A Generalizable Replacement of Linear Layer for Gaze Estimation", - "authors": "Yiwei Bao, Feng Lu", + "authors": [ + { + "first_name": "Yiwei", + "last_name": "Bao" + }, + { + "first_name": "Feng", + "last_name": "Lu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Curriculum Point Prompting for Weakly-Supervised Referring Image Segmentation", - "authors": "Qiyuan Dai, Sibei Yang", + "authors": [ + { + "first_name": "Qiyuan", + "last_name": "Dai" + }, + { + "first_name": "Sibei", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "EventDance: Unsupervised Source-free Cross-modal Adaptation for Event-based Object Recognition", - "authors": "Xu Zheng, Lin Wang", + "authors": [ + { + "first_name": "Xu", + "last_name": "Zheng" + }, + { + "first_name": "Lin", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CycleINR: Cycle Implicit Neural Representation for Arbitrary-Scale Volumetric Super-Resolution of Medical Data", - "authors": "Wei Fang, Yuxing Tang, Heng Guo, Mingze Yuan, Tony C. W. Mok, Ke Yan, Jiawen Yao, Xin Chen, Zaiyi Liu, Le Lu, Ling Zhang, Minfeng Xu", + "authors": [ + { + "first_name": "Wei", + "last_name": "Fang" + }, + { + "first_name": "Yuxing", + "last_name": "Tang" + }, + { + "first_name": "Heng", + "last_name": "Guo" + }, + { + "first_name": "Mingze", + "last_name": "Yuan" + }, + { + "first_name": "Tony", + "last_name": "C. W. Mok" + }, + { + "first_name": "Ke", + "last_name": "Yan" + }, + { + "first_name": "Jiawen", + "last_name": "Yao" + }, + { + "first_name": "Xin", + "last_name": "Chen" + }, + { + "first_name": "Zaiyi", + "last_name": "Liu" + }, + { + "first_name": "Le", + "last_name": "Lu" + }, + { + "first_name": "Ling", + "last_name": "Zhang" + }, + { + "first_name": "Minfeng", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Boosting Image Restoration via Priors from Pre-trained Models", - "authors": "Xiaogang Xu, Shu Kong, Tao Hu, Zhe Liu, Hujun Bao", + "authors": [ + { + "first_name": "Xiaogang", + "last_name": "Xu" + }, + { + "first_name": "Shu", + "last_name": "Kong" + }, + { + "first_name": "Tao", + "last_name": "Hu" + }, + { + "first_name": "Zhe", + "last_name": "Liu" + }, + { + "first_name": "Hujun", + "last_name": "Bao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "VRetouchEr: Learning Cross-frame Feature Interdependence with Imperfection Flow for Face Retouching in Videos", - "authors": "Wen Xue, Le Jiang, Lianxin Xie, Si Wu, Yong Xu, Hau San Wong", + "authors": [ + { + "first_name": "Wen", + "last_name": "Xue" + }, + { + "first_name": "Le", + "last_name": "Jiang" + }, + { + "first_name": "Lianxin", + "last_name": "Xie" + }, + { + "first_name": "Si", + "last_name": "Wu" + }, + { + "first_name": "Yong", + "last_name": "Xu" + }, + { + "first_name": "Hau", + "last_name": "San Wong" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Transferable Structural Sparse Adversarial Attack Via Exact Group Sparsity Training", - "authors": "Di Ming, Peng Ren, Yunlong Wang, Xin Feng", + "authors": [ + { + "first_name": "Di", + "last_name": "Ming" + }, + { + "first_name": "Peng", + "last_name": "Ren" + }, + { + "first_name": "Yunlong", + "last_name": "Wang" + }, + { + "first_name": "Xin", + "last_name": "Feng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Holistic Autonomous Driving Understanding by Bird's-Eye-View Injected Multi-Modal Large Models", - "authors": "Xinpeng Ding, Jianhua Han, Hang Xu, Xiaodan Liang, Wei Zhang, Xiaomeng Li", + "authors": [ + { + "first_name": "Xinpeng", + "last_name": "Ding" + }, + { + "first_name": "Jianhua", + "last_name": "Han" + }, + { + "first_name": "Hang", + "last_name": "Xu" + }, + { + "first_name": "Xiaodan", + "last_name": "Liang" + }, + { + "first_name": "Wei", + "last_name": "Zhang" + }, + { + "first_name": "Xiaomeng", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Arbitrary-Scale Image Generation and Upsampling using Latent Diffusion Model and Implicit Neural Decoder", - "authors": "Jinseok Kim, Tae-Kyun Kim", + "authors": [ + { + "first_name": "Jinseok", + "last_name": "Kim" + }, + { + "first_name": "Tae-Kyun", + "last_name": "Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Unsupervised Occupancy Learning from Sparse Point Cloud", - "authors": "Amine Ouasfi, Adnane Boukhayma", + "authors": [ + { + "first_name": "Amine", + "last_name": "Ouasfi" + }, + { + "first_name": "Adnane", + "last_name": "Boukhayma" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Extreme Point Supervised Instance Segmentation", - "authors": "Hyeonjun Lee, Sehyun Hwang, Suha Kwak", + "authors": [ + { + "first_name": "Hyeonjun", + "last_name": "Lee" + }, + { + "first_name": "Sehyun", + "last_name": "Hwang" + }, + { + "first_name": "Suha", + "last_name": "Kwak" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "3DInAction: Understanding Human Actions in 3D Point Clouds", - "authors": "Yizhak Ben-Shabat, Oren Shrout, Stephen Gould", + "authors": [ + { + "first_name": "Yizhak", + "last_name": "Ben-Shabat" + }, + { + "first_name": "Oren", + "last_name": "Shrout" + }, + { + "first_name": "Stephen", + "last_name": "Gould" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Cache Me if You Can: Accelerating Diffusion Models through Block Caching", - "authors": "Felix Wimbauer, Bichen Wu, Edgar Schoenfeld, Xiaoliang Dai, Ji Hou, Zijian He, Artsiom Sanakoyeu, Peizhao Zhang, Sam Tsai, Jonas Kohler, Christian Rupprecht, Daniel Cremers, Peter Vajda, Jialiang Wang", + "authors": [ + { + "first_name": "Felix", + "last_name": "Wimbauer" + }, + { + "first_name": "Bichen", + "last_name": "Wu" + }, + { + "first_name": "Edgar", + "last_name": "Schoenfeld" + }, + { + "first_name": "Xiaoliang", + "last_name": "Dai" + }, + { + "first_name": "Ji", + "last_name": "Hou" + }, + { + "first_name": "Zijian", + "last_name": "He" + }, + { + "first_name": "Artsiom", + "last_name": "Sanakoyeu" + }, + { + "first_name": "Peizhao", + "last_name": "Zhang" + }, + { + "first_name": "Sam", + "last_name": "Tsai" + }, + { + "first_name": "Jonas", + "last_name": "Kohler" + }, + { + "first_name": "Christian", + "last_name": "Rupprecht" + }, + { + "first_name": "Daniel", + "last_name": "Cremers" + }, + { + "first_name": "Peter", + "last_name": "Vajda" + }, + { + "first_name": "Jialiang", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MedM2G: Unifying Medical Multi-Modal Generation via Cross-Guided Diffusion with Visual Invariant", - "authors": "Chenlu Zhan, Yu Lin, Gaoang Wang, Hongwei Wang, Jian Wu", + "authors": [ + { + "first_name": "Chenlu", + "last_name": "Zhan" + }, + { + "first_name": "Yu", + "last_name": "Lin" + }, + { + "first_name": "Gaoang", + "last_name": "Wang" + }, + { + "first_name": "Hongwei", + "last_name": "Wang" + }, + { + "first_name": "Jian", + "last_name": "Wu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SDDGR: Stable Diffusion-based Deep Generative Replay for Class Incremental Object Detection", - "authors": "Junsu Kim, Hoseong Cho, Jihyeon Kim, Yihalem Yimolal Tiruneh, Seungryul Baek", + "authors": [ + { + "first_name": "Junsu", + "last_name": "Kim" + }, + { + "first_name": "Hoseong", + "last_name": "Cho" + }, + { + "first_name": "Jihyeon", + "last_name": "Kim" + }, + { + "first_name": "Yihalem", + "last_name": "Yimolal Tiruneh" + }, + { + "first_name": "Seungryul", + "last_name": "Baek" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Neural Parametric Gaussians for Monocular Non-Rigid Object Reconstruction", - "authors": "Devikalyan Das, Christopher Wewer, Raza Yunus, Eddy Ilg, Jan Eric Lenssen", + "authors": [ + { + "first_name": "Devikalyan", + "last_name": "Das" + }, + { + "first_name": "Christopher", + "last_name": "Wewer" + }, + { + "first_name": "Raza", + "last_name": "Yunus" + }, + { + "first_name": "Eddy", + "last_name": "Ilg" + }, + { + "first_name": "Jan", + "last_name": "Eric Lenssen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous Driving", - "authors": "Junhao Zheng, Chenhao Lin, Jiahao Sun, Zhengyu Zhao, Qian Li, Chao Shen", + "authors": [ + { + "first_name": "Junhao", + "last_name": "Zheng" + }, + { + "first_name": "Chenhao", + "last_name": "Lin" + }, + { + "first_name": "Jiahao", + "last_name": "Sun" + }, + { + "first_name": "Zhengyu", + "last_name": "Zhao" + }, + { + "first_name": "Qian", + "last_name": "Li" + }, + { + "first_name": "Chao", + "last_name": "Shen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Adaptive Random Feature Regularization on Fine-tuning Deep Neural Networks", - "authors": "Shin'ya Yamaguchi, Sekitoshi Kanai, Kazuki Adachi, Daiki Chijiwa", + "authors": [ + { + "first_name": "Shin'ya", + "last_name": "Yamaguchi" + }, + { + "first_name": "Sekitoshi", + "last_name": "Kanai" + }, + { + "first_name": "Kazuki", + "last_name": "Adachi" + }, + { + "first_name": "Daiki", + "last_name": "Chijiwa" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PH-Net: Semi-Supervised Breast Lesion Segmentation via Patch-wise Hardness", - "authors": "Siyao Jiang, Huisi Wu, Junyang Chen, Qin Zhang, Jing Qin", + "authors": [ + { + "first_name": "Siyao", + "last_name": "Jiang" + }, + { + "first_name": "Huisi", + "last_name": "Wu" + }, + { + "first_name": "Junyang", + "last_name": "Chen" + }, + { + "first_name": "Qin", + "last_name": "Zhang" + }, + { + "first_name": "Jing", + "last_name": "Qin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Multimodal Prompt Perceiver: Empower Adaptiveness Generalizability and Fidelity for All-in-One Image Restoration", - "authors": "Yuang Ai, Huaibo Huang, Xiaoqiang Zhou, Jiexiang Wang, Ran He", + "authors": [ + { + "first_name": "Yuang", + "last_name": "Ai" + }, + { + "first_name": "Huaibo", + "last_name": "Huang" + }, + { + "first_name": "Xiaoqiang", + "last_name": "Zhou" + }, + { + "first_name": "Jiexiang", + "last_name": "Wang" + }, + { + "first_name": "Ran", + "last_name": "He" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ExACT: Language-guided Conceptual Reasoning and Uncertainty Estimation for Event-based Action Recognition and More", - "authors": "Jiazhou Zhou, Xu Zheng, Yuanhuiyi Lyu, Lin Wang", + "authors": [ + { + "first_name": "Jiazhou", + "last_name": "Zhou" + }, + { + "first_name": "Xu", + "last_name": "Zheng" + }, + { + "first_name": "Yuanhuiyi", + "last_name": "Lyu" + }, + { + "first_name": "Lin", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Color Shift Estimation-and-Correction for Image Enhancement", - "authors": "Yiyu Li, Ke Xu, Gerhard Petrus Hancke, Rynson W.H. Lau", + "authors": [ + { + "first_name": "Yiyu", + "last_name": "Li" + }, + { + "first_name": "Ke", + "last_name": "Xu" + }, + { + "first_name": "Gerhard", + "last_name": "Petrus Hancke" + }, + { + "first_name": "Rynson", + "last_name": "W.H. Lau" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Improving Visual Recognition with Hyperbolical Visual Hierarchy Mapping", - "authors": "Hyeongjun Kwon, Jinhyun Jang, Jin Kim, Kwonyoung Kim, Kwanghoon Sohn", + "authors": [ + { + "first_name": "Hyeongjun", + "last_name": "Kwon" + }, + { + "first_name": "Jinhyun", + "last_name": "Jang" + }, + { + "first_name": "Jin", + "last_name": "Kim" + }, + { + "first_name": "Kwonyoung", + "last_name": "Kim" + }, + { + "first_name": "Kwanghoon", + "last_name": "Sohn" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ParameterNet: Parameters Are All You Need for Large-scale Visual Pretraining of Mobile Networks", - "authors": "Kai Han, Yunhe Wang, Jianyuan Guo, Enhua Wu", + "authors": [ + { + "first_name": "Kai", + "last_name": "Han" + }, + { + "first_name": "Yunhe", + "last_name": "Wang" + }, + { + "first_name": "Jianyuan", + "last_name": "Guo" + }, + { + "first_name": "Enhua", + "last_name": "Wu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation", - "authors": "Bingxin Ke, Anton Obukhov, Shengyu Huang, Nando Metzger, Rodrigo Caye Daudt, Konrad Schindler", + "authors": [ + { + "first_name": "Bingxin", + "last_name": "Ke" + }, + { + "first_name": "Anton", + "last_name": "Obukhov" + }, + { + "first_name": "Shengyu", + "last_name": "Huang" + }, + { + "first_name": "Nando", + "last_name": "Metzger" + }, + { + "first_name": "Rodrigo", + "last_name": "Caye Daudt" + }, + { + "first_name": "Konrad", + "last_name": "Schindler" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Identifying Important Group of Pixels using Interactions", - "authors": "Kosuke Sumiyasu, Kazuhiko Kawamoto, Hiroshi Kera", + "authors": [ + { + "first_name": "Kosuke", + "last_name": "Sumiyasu" + }, + { + "first_name": "Kazuhiko", + "last_name": "Kawamoto" + }, + { + "first_name": "Hiroshi", + "last_name": "Kera" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Network", - "authors": "Wenqiao Li, Xiaohao Xu, Yao Gu, Bozhong Zheng, Shenghua Gao, Yingna Wu", + "authors": [ + { + "first_name": "Wenqiao", + "last_name": "Li" + }, + { + "first_name": "Xiaohao", + "last_name": "Xu" + }, + { + "first_name": "Yao", + "last_name": "Gu" + }, + { + "first_name": "Bozhong", + "last_name": "Zheng" + }, + { + "first_name": "Shenghua", + "last_name": "Gao" + }, + { + "first_name": "Yingna", + "last_name": "Wu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Cam4DOcc: Benchmark for Camera-Only 4D Occupancy Forecasting in Autonomous Driving Applications", - "authors": "Junyi Ma, Xieyuanli Chen, Jiawei Huang, Jingyi Xu, Zhen Luo, Jintao Xu, Weihao Gu, Rui Ai, Hesheng Wang", + "authors": [ + { + "first_name": "Junyi", + "last_name": "Ma" + }, + { + "first_name": "Xieyuanli", + "last_name": "Chen" + }, + { + "first_name": "Jiawei", + "last_name": "Huang" + }, + { + "first_name": "Jingyi", + "last_name": "Xu" + }, + { + "first_name": "Zhen", + "last_name": "Luo" + }, + { + "first_name": "Jintao", + "last_name": "Xu" + }, + { + "first_name": "Weihao", + "last_name": "Gu" + }, + { + "first_name": "Rui", + "last_name": "Ai" + }, + { + "first_name": "Hesheng", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DIOD: Self-Distillation Meets Object Discovery", - "authors": "Sandra Kara, Hejer Ammar, Julien Denize, Florian Chabot, Quoc-Cuong Pham", + "authors": [ + { + "first_name": "Sandra", + "last_name": "Kara" + }, + { + "first_name": "Hejer", + "last_name": "Ammar" + }, + { + "first_name": "Julien", + "last_name": "Denize" + }, + { + "first_name": "Florian", + "last_name": "Chabot" + }, + { + "first_name": "Quoc-Cuong", + "last_name": "Pham" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GoMAvatar: Efficient Animatable Human Modeling from Monocular Video Using Gaussians-on-Mesh", - "authors": "Jing Wen, Xiaoming Zhao, Zhongzheng Ren, Alexander G. Schwing, Shenlong Wang", + "authors": [ + { + "first_name": "Jing", + "last_name": "Wen" + }, + { + "first_name": "Xiaoming", + "last_name": "Zhao" + }, + { + "first_name": "Zhongzheng", + "last_name": "Ren" + }, + { + "first_name": "Alexander", + "last_name": "G. Schwing" + }, + { + "first_name": "Shenlong", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Neural Redshift: Random Networks are not Random Functions", - "authors": "Damien Teney, Armand Mihai Nicolicioiu, Valentin Hartmann, Ehsan Abbasnejad", + "authors": [ + { + "first_name": "Damien", + "last_name": "Teney" + }, + { + "first_name": "Armand", + "last_name": "Mihai Nicolicioiu" + }, + { + "first_name": "Valentin", + "last_name": "Hartmann" + }, + { + "first_name": "Ehsan", + "last_name": "Abbasnejad" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splatting", - "authors": "Xian Liu, Xiaohang Zhan, Jiaxiang Tang, Ying Shan, Gang Zeng, Dahua Lin, Xihui Liu, Ziwei Liu", + "authors": [ + { + "first_name": "Xian", + "last_name": "Liu" + }, + { + "first_name": "Xiaohang", + "last_name": "Zhan" + }, + { + "first_name": "Jiaxiang", + "last_name": "Tang" + }, + { + "first_name": "Ying", + "last_name": "Shan" + }, + { + "first_name": "Gang", + "last_name": "Zeng" + }, + { + "first_name": "Dahua", + "last_name": "Lin" + }, + { + "first_name": "Xihui", + "last_name": "Liu" + }, + { + "first_name": "Ziwei", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DIEM: Decomposition-Integration Enhancing Multimodal Insights", - "authors": "Xinyi Jiang, Guoming Wang, Junhao Guo, Juncheng Li, Wenqiao Zhang, Rongxing Lu, Siliang Tang", + "authors": [ + { + "first_name": "Xinyi", + "last_name": "Jiang" + }, + { + "first_name": "Guoming", + "last_name": "Wang" + }, + { + "first_name": "Junhao", + "last_name": "Guo" + }, + { + "first_name": "Juncheng", + "last_name": "Li" + }, + { + "first_name": "Wenqiao", + "last_name": "Zhang" + }, + { + "first_name": "Rongxing", + "last_name": "Lu" + }, + { + "first_name": "Siliang", + "last_name": "Tang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CosmicMan: A Text-to-Image Foundation Model for Humans", - "authors": "Shikai Li, Jianglin Fu, Kaiyuan Liu, Wentao Wang, Kwan-Yee Lin, Wayne Wu", + "authors": [ + { + "first_name": "Shikai", + "last_name": "Li" + }, + { + "first_name": "Jianglin", + "last_name": "Fu" + }, + { + "first_name": "Kaiyuan", + "last_name": "Liu" + }, + { + "first_name": "Wentao", + "last_name": "Wang" + }, + { + "first_name": "Kwan-Yee", + "last_name": "Lin" + }, + { + "first_name": "Wayne", + "last_name": "Wu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LLMs are Good Sign Language Translators", - "authors": "Jia Gong, Lin Geng Foo, Yixuan He, Hossein Rahmani, Jun Liu", + "authors": [ + { + "first_name": "Jia", + "last_name": "Gong" + }, + { + "first_name": "Lin", + "last_name": "Geng Foo" + }, + { + "first_name": "Yixuan", + "last_name": "He" + }, + { + "first_name": "Hossein", + "last_name": "Rahmani" + }, + { + "first_name": "Jun", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Contrastive Pre-Training with Multi-View Fusion for No-Reference Point Cloud Quality Assessment", - "authors": "Ziyu Shan, Yujie Zhang, Qi Yang, Haichen Yang, Yiling Xu, Jenq-Neng Hwang, Xiaozhong Xu, Shan Liu", + "authors": [ + { + "first_name": "Ziyu", + "last_name": "Shan" + }, + { + "first_name": "Yujie", + "last_name": "Zhang" + }, + { + "first_name": "Qi", + "last_name": "Yang" + }, + { + "first_name": "Haichen", + "last_name": "Yang" + }, + { + "first_name": "Yiling", + "last_name": "Xu" + }, + { + "first_name": "Jenq-Neng", + "last_name": "Hwang" + }, + { + "first_name": "Xiaozhong", + "last_name": "Xu" + }, + { + "first_name": "Shan", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "JDEC: JPEG Decoding via Enhanced Continuous Cosine Coefficients", - "authors": "Woo Kyoung Han, Sunghoon Im, Jaedeok Kim, Kyong Hwan Jin", + "authors": [ + { + "first_name": "Woo", + "last_name": "Kyoung Han" + }, + { + "first_name": "Sunghoon", + "last_name": "Im" + }, + { + "first_name": "Jaedeok", + "last_name": "Kim" + }, + { + "first_name": "Kyong", + "last_name": "Hwan Jin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Revisiting the Domain Shift and Sample Uncertainty in Multi-source Active Domain Transfer", - "authors": "Wenqiao Zhang, Zheqi Lv, Hao Zhou, Jia-Wei Liu, Juncheng Li, Mengze Li, Yunfei Li, Dongping Zhang, Yueting Zhuang, Siliang Tang", + "authors": [ + { + "first_name": "Wenqiao", + "last_name": "Zhang" + }, + { + "first_name": "Zheqi", + "last_name": "Lv" + }, + { + "first_name": "Hao", + "last_name": "Zhou" + }, + { + "first_name": "Jia-Wei", + "last_name": "Liu" + }, + { + "first_name": "Juncheng", + "last_name": "Li" + }, + { + "first_name": "Mengze", + "last_name": "Li" + }, + { + "first_name": "Yunfei", + "last_name": "Li" + }, + { + "first_name": "Dongping", + "last_name": "Zhang" + }, + { + "first_name": "Yueting", + "last_name": "Zhuang" + }, + { + "first_name": "Siliang", + "last_name": "Tang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning Continual Compatible Representation for Re-indexing Free Lifelong Person Re-identification", - "authors": "Zhenyu Cui, Jiahuan Zhou, Xun Wang, Manyu Zhu, Yuxin Peng", + "authors": [ + { + "first_name": "Zhenyu", + "last_name": "Cui" + }, + { + "first_name": "Jiahuan", + "last_name": "Zhou" + }, + { + "first_name": "Xun", + "last_name": "Wang" + }, + { + "first_name": "Manyu", + "last_name": "Zhu" + }, + { + "first_name": "Yuxin", + "last_name": "Peng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Revisiting Spatial-Frequency Information Integration from a Hierarchical Perspective for Panchromatic and Multi-Spectral Image Fusion", - "authors": "Jiangtong Tan, Jie Huang, Naishan Zheng, Man Zhou, Keyu Yan, Danfeng Hong, Feng Zhao", + "authors": [ + { + "first_name": "Jiangtong", + "last_name": "Tan" + }, + { + "first_name": "Jie", + "last_name": "Huang" + }, + { + "first_name": "Naishan", + "last_name": "Zheng" + }, + { + "first_name": "Man", + "last_name": "Zhou" + }, + { + "first_name": "Keyu", + "last_name": "Yan" + }, + { + "first_name": "Danfeng", + "last_name": "Hong" + }, + { + "first_name": "Feng", + "last_name": "Zhao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "BSNet: Box-Supervised Simulation-assisted Mean Teacher for 3D Instance Segmentation", - "authors": "Jiahao Lu, Jiacheng Deng, Tianzhu Zhang", + "authors": [ + { + "first_name": "Jiahao", + "last_name": "Lu" + }, + { + "first_name": "Jiacheng", + "last_name": "Deng" + }, + { + "first_name": "Tianzhu", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Adaptive Slot Attention: Object Discovery with Dynamic Slot Number", - "authors": "Ke Fan, Zechen Bai, Tianjun Xiao, Tong He, Max Horn, Yanwei Fu, Francesco Locatello, Zheng Zhang", + "authors": [ + { + "first_name": "Ke", + "last_name": "Fan" + }, + { + "first_name": "Zechen", + "last_name": "Bai" + }, + { + "first_name": "Tianjun", + "last_name": "Xiao" + }, + { + "first_name": "Tong", + "last_name": "He" + }, + { + "first_name": "Max", + "last_name": "Horn" + }, + { + "first_name": "Yanwei", + "last_name": "Fu" + }, + { + "first_name": "Francesco", + "last_name": "Locatello" + }, + { + "first_name": "Zheng", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CORES: Convolutional Response-based Score for Out-of-distribution Detection", - "authors": "Keke Tang, Chao Hou, Weilong Peng, Runnan Chen, Peican Zhu, Wenping Wang, Zhihong Tian", + "authors": [ + { + "first_name": "Keke", + "last_name": "Tang" + }, + { + "first_name": "Chao", + "last_name": "Hou" + }, + { + "first_name": "Weilong", + "last_name": "Peng" + }, + { + "first_name": "Runnan", + "last_name": "Chen" + }, + { + "first_name": "Peican", + "last_name": "Zhu" + }, + { + "first_name": "Wenping", + "last_name": "Wang" + }, + { + "first_name": "Zhihong", + "last_name": "Tian" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Task-Driven Wavelets using Constrained Empirical Risk Minimization", - "authors": "Eric Marcus, Ray Sheombarsing, Jan-Jakob Sonke, Jonas Teuwen", + "authors": [ + { + "first_name": "Eric", + "last_name": "Marcus" + }, + { + "first_name": "Ray", + "last_name": "Sheombarsing" + }, + { + "first_name": "Jan-Jakob", + "last_name": "Sonke" + }, + { + "first_name": "Jonas", + "last_name": "Teuwen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HOI-M^3: Capture Multiple Humans and Objects Interaction within Contextual Environment", - "authors": "Juze Zhang, Jingyan Zhang, Zining Song, Zhanhe Shi, Chengfeng Zhao, Ye Shi, Jingyi Yu, Lan Xu, Jingya Wang", + "authors": [ + { + "first_name": "Juze", + "last_name": "Zhang" + }, + { + "first_name": "Jingyan", + "last_name": "Zhang" + }, + { + "first_name": "Zining", + "last_name": "Song" + }, + { + "first_name": "Zhanhe", + "last_name": "Shi" + }, + { + "first_name": "Chengfeng", + "last_name": "Zhao" + }, + { + "first_name": "Ye", + "last_name": "Shi" + }, + { + "first_name": "Jingyi", + "last_name": "Yu" + }, + { + "first_name": "Lan", + "last_name": "Xu" + }, + { + "first_name": "Jingya", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Interactive3D: Create What You Want by Interactive 3D Generation", - "authors": "Shaocong Dong, Lihe Ding, Zhanpeng Huang, Zibin Wang, Tianfan Xue, Dan Xu", + "authors": [ + { + "first_name": "Shaocong", + "last_name": "Dong" + }, + { + "first_name": "Lihe", + "last_name": "Ding" + }, + { + "first_name": "Zhanpeng", + "last_name": "Huang" + }, + { + "first_name": "Zibin", + "last_name": "Wang" + }, + { + "first_name": "Tianfan", + "last_name": "Xue" + }, + { + "first_name": "Dan", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DeiT-LT: Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets", - "authors": "Harsh Rangwani, Pradipto Mondal, Mayank Mishra, Ashish Ramayee Asokan, R. Venkatesh Babu", + "authors": [ + { + "first_name": "Harsh", + "last_name": "Rangwani" + }, + { + "first_name": "Pradipto", + "last_name": "Mondal" + }, + { + "first_name": "Mayank", + "last_name": "Mishra" + }, + { + "first_name": "Ashish", + "last_name": "Ramayee Asokan" + }, + { + "first_name": "R.", + "last_name": "Venkatesh Babu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Accurate Spatial Gene Expression Prediction by Integrating Multi-Resolution Features", - "authors": "Youngmin Chung, Ji Hun Ha, Kyeong Chan Im, Joo Sang Lee", + "authors": [ + { + "first_name": "Youngmin", + "last_name": "Chung" + }, + { + "first_name": "Ji", + "last_name": "Hun Ha" + }, + { + "first_name": "Kyeong", + "last_name": "Chan Im" + }, + { + "first_name": "Joo", + "last_name": "Sang Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FCS: Feature Calibration and Separation for Non-Exemplar Class Incremental Learning", - "authors": "Qiwei Li, Yuxin Peng, Jiahuan Zhou", + "authors": [ + { + "first_name": "Qiwei", + "last_name": "Li" + }, + { + "first_name": "Yuxin", + "last_name": "Peng" + }, + { + "first_name": "Jiahuan", + "last_name": "Zhou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Task2Box: Box Embeddings for Modeling Asymmetric Task Relationships", - "authors": "Rangel Daroya, Aaron Sun, Subhransu Maji", + "authors": [ + { + "first_name": "Rangel", + "last_name": "Daroya" + }, + { + "first_name": "Aaron", + "last_name": "Sun" + }, + { + "first_name": "Subhransu", + "last_name": "Maji" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Behind the Veil: Enhanced Indoor 3D Scene Reconstruction with Occluded Surfaces Completion", - "authors": "Su Sun, Cheng Zhao, Yuliang Guo, Ruoyu Wang, Xinyu Huang, Yingjie Victor Chen, Liu Ren", + "authors": [ + { + "first_name": "Su", + "last_name": "Sun" + }, + { + "first_name": "Cheng", + "last_name": "Zhao" + }, + { + "first_name": "Yuliang", + "last_name": "Guo" + }, + { + "first_name": "Ruoyu", + "last_name": "Wang" + }, + { + "first_name": "Xinyu", + "last_name": "Huang" + }, + { + "first_name": "Yingjie", + "last_name": "Victor Chen" + }, + { + "first_name": "Liu", + "last_name": "Ren" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "VideoGrounding-DINO: Towards Open-Vocabulary Spatio-Temporal Video Grounding", - "authors": "Syed Talal Wasim, Muzammal Naseer, Salman Khan, Ming-Hsuan Yang, Fahad Shahbaz Khan", + "authors": [ + { + "first_name": "Syed", + "last_name": "Talal Wasim" + }, + { + "first_name": "Muzammal", + "last_name": "Naseer" + }, + { + "first_name": "Salman", + "last_name": "Khan" + }, + { + "first_name": "Ming-Hsuan", + "last_name": "Yang" + }, + { + "first_name": "Fahad", + "last_name": "Shahbaz Khan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "OmniLocalRF: Omnidirectional Local Radiance Fields from Dynamic Videos", - "authors": "Dongyoung Choi, Hyeonjoong Jang, Min H. Kim", + "authors": [ + { + "first_name": "Dongyoung", + "last_name": "Choi" + }, + { + "first_name": "Hyeonjoong", + "last_name": "Jang" + }, + { + "first_name": "Min", + "last_name": "H. Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LoS: Local Structure-Guided Stereo Matching", - "authors": "Kunhong Li, Longguang Wang, Ye Zhang, Kaiwen Xue, Shunbo Zhou, Yulan Guo", + "authors": [ + { + "first_name": "Kunhong", + "last_name": "Li" + }, + { + "first_name": "Longguang", + "last_name": "Wang" + }, + { + "first_name": "Ye", + "last_name": "Zhang" + }, + { + "first_name": "Kaiwen", + "last_name": "Xue" + }, + { + "first_name": "Shunbo", + "last_name": "Zhou" + }, + { + "first_name": "Yulan", + "last_name": "Guo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Semantic Human Mesh Reconstruction with Textures", - "authors": "Xiaoyu Zhan, Jianxin Yang, Yuanqi Li, Jie Guo, Yanwen Guo, Wenping Wang", + "authors": [ + { + "first_name": "Xiaoyu", + "last_name": "Zhan" + }, + { + "first_name": "Jianxin", + "last_name": "Yang" + }, + { + "first_name": "Yuanqi", + "last_name": "Li" + }, + { + "first_name": "Jie", + "last_name": "Guo" + }, + { + "first_name": "Yanwen", + "last_name": "Guo" + }, + { + "first_name": "Wenping", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Think Twice Before Selection: Federated Evidential Active Learning for Medical Image Analysis with Domain Shifts", - "authors": "Jiayi Chen, Benteng Ma, Hengfei Cui, Yong Xia", + "authors": [ + { + "first_name": "Jiayi", + "last_name": "Chen" + }, + { + "first_name": "Benteng", + "last_name": "Ma" + }, + { + "first_name": "Hengfei", + "last_name": "Cui" + }, + { + "first_name": "Yong", + "last_name": "Xia" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Probing the 3D Awareness of Visual Foundation Models", - "authors": "Mohamed El Banani, Amit Raj, Kevis-Kokitsi Maninis, Abhishek Kar, Yuanzhen Li, Michael Rubinstein, Deqing Sun, Leonidas Guibas, Justin Johnson, Varun Jampani", + "authors": [ + { + "first_name": "Mohamed", + "last_name": "El Banani" + }, + { + "first_name": "Amit", + "last_name": "Raj" + }, + { + "first_name": "Kevis-Kokitsi", + "last_name": "Maninis" + }, + { + "first_name": "Abhishek", + "last_name": "Kar" + }, + { + "first_name": "Yuanzhen", + "last_name": "Li" + }, + { + "first_name": "Michael", + "last_name": "Rubinstein" + }, + { + "first_name": "Deqing", + "last_name": "Sun" + }, + { + "first_name": "Leonidas", + "last_name": "Guibas" + }, + { + "first_name": "Justin", + "last_name": "Johnson" + }, + { + "first_name": "Varun", + "last_name": "Jampani" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PIA: Your Personalized Image Animator via Plug-and-Play Modules in Text-to-Image Models", - "authors": "Yiming Zhang, Zhening Xing, Yanhong Zeng, Youqing Fang, Kai Chen", + "authors": [ + { + "first_name": "Yiming", + "last_name": "Zhang" + }, + { + "first_name": "Zhening", + "last_name": "Xing" + }, + { + "first_name": "Yanhong", + "last_name": "Zeng" + }, + { + "first_name": "Youqing", + "last_name": "Fang" + }, + { + "first_name": "Kai", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "When Visual Grounding Meets Gigapixel-level Large-scale Scenes: Benchmark and Approach", - "authors": "Tao Ma, Bing Bai, Haozhe Lin, Heyuan Wang, Yu Wang, Lin Luo, Lu Fang", + "authors": [ + { + "first_name": "Tao", + "last_name": "Ma" + }, + { + "first_name": "Bing", + "last_name": "Bai" + }, + { + "first_name": "Haozhe", + "last_name": "Lin" + }, + { + "first_name": "Heyuan", + "last_name": "Wang" + }, + { + "first_name": "Yu", + "last_name": "Wang" + }, + { + "first_name": "Lin", + "last_name": "Luo" + }, + { + "first_name": "Lu", + "last_name": "Fang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "NeRF Analogies: Example-Based Visual Attribute Transfer for NeRFs", - "authors": "Michael Fischer, Zhengqin Li, Thu Nguyen-Phuoc, Aljaz Bozic, Zhao Dong, Carl Marshall, Tobias Ritschel", + "authors": [ + { + "first_name": "Michael", + "last_name": "Fischer" + }, + { + "first_name": "Zhengqin", + "last_name": "Li" + }, + { + "first_name": "Thu", + "last_name": "Nguyen-Phuoc" + }, + { + "first_name": "Aljaz", + "last_name": "Bozic" + }, + { + "first_name": "Zhao", + "last_name": "Dong" + }, + { + "first_name": "Carl", + "last_name": "Marshall" + }, + { + "first_name": "Tobias", + "last_name": "Ritschel" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Mind Artist: Creating Artistic Snapshots with Human Thought", - "authors": "Jiaxuan Chen, Yu Qi, Yueming Wang, Gang Pan", + "authors": [ + { + "first_name": "Jiaxuan", + "last_name": "Chen" + }, + { + "first_name": "Yu", + "last_name": "Qi" + }, + { + "first_name": "Yueming", + "last_name": "Wang" + }, + { + "first_name": "Gang", + "last_name": "Pan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ViTamin: Designing Scalable Vision Models in the Vision-Language Era", - "authors": "Jieneng Chen, Qihang Yu, Xiaohui Shen, Alan Yuille, Liang-Chieh Chen", + "authors": [ + { + "first_name": "Jieneng", + "last_name": "Chen" + }, + { + "first_name": "Qihang", + "last_name": "Yu" + }, + { + "first_name": "Xiaohui", + "last_name": "Shen" + }, + { + "first_name": "Alan", + "last_name": "Yuille" + }, + { + "first_name": "Liang-Chieh", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Accept the Modality Gap: An Exploration in the Hyperbolic Space", - "authors": "Sameera Ramasinghe, Violetta Shevchenko, Gil Avraham, Ajanthan Thalaiyasingam", + "authors": [ + { + "first_name": "Sameera", + "last_name": "Ramasinghe" + }, + { + "first_name": "Violetta", + "last_name": "Shevchenko" + }, + { + "first_name": "Gil", + "last_name": "Avraham" + }, + { + "first_name": "Ajanthan", + "last_name": "Thalaiyasingam" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Unraveling Instance Associations: A Closer Look for Audio-Visual Segmentation", - "authors": "Yuanhong Chen, Yuyuan Liu, Hu Wang, Fengbei Liu, Chong Wang, Helen Frazer, Gustavo Carneiro", + "authors": [ + { + "first_name": "Yuanhong", + "last_name": "Chen" + }, + { + "first_name": "Yuyuan", + "last_name": "Liu" + }, + { + "first_name": "Hu", + "last_name": "Wang" + }, + { + "first_name": "Fengbei", + "last_name": "Liu" + }, + { + "first_name": "Chong", + "last_name": "Wang" + }, + { + "first_name": "Helen", + "last_name": "Frazer" + }, + { + "first_name": "Gustavo", + "last_name": "Carneiro" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Few-Shot Object Detection with Foundation Models", - "authors": "Guangxing Han, Ser-Nam Lim", + "authors": [ + { + "first_name": "Guangxing", + "last_name": "Han" + }, + { + "first_name": "Ser-Nam", + "last_name": "Lim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FedMef: Towards Memory-efficient Federated Dynamic Pruning", - "authors": "Hong Huang, Weiming Zhuang, Chen Chen, Lingjuan Lyu", + "authors": [ + { + "first_name": "Hong", + "last_name": "Huang" + }, + { + "first_name": "Weiming", + "last_name": "Zhuang" + }, + { + "first_name": "Chen", + "last_name": "Chen" + }, + { + "first_name": "Lingjuan", + "last_name": "Lyu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Seeing the Unseen: Visual Common Sense for Semantic Placement", - "authors": "Ram Ramrakhya, Aniruddha Kembhavi, Dhruv Batra, Zsolt Kira, Kuo-Hao Zeng, Luca Weihs", + "authors": [ + { + "first_name": "Ram", + "last_name": "Ramrakhya" + }, + { + "first_name": "Aniruddha", + "last_name": "Kembhavi" + }, + { + "first_name": "Dhruv", + "last_name": "Batra" + }, + { + "first_name": "Zsolt", + "last_name": "Kira" + }, + { + "first_name": "Kuo-Hao", + "last_name": "Zeng" + }, + { + "first_name": "Luca", + "last_name": "Weihs" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Texture-Preserving Diffusion Models for High-Fidelity Virtual Try-On", - "authors": "Xu Yang, Changxing Ding, Zhibin Hong, Junhao Huang, Jin Tao, Xiangmin Xu", + "authors": [ + { + "first_name": "Xu", + "last_name": "Yang" + }, + { + "first_name": "Changxing", + "last_name": "Ding" + }, + { + "first_name": "Zhibin", + "last_name": "Hong" + }, + { + "first_name": "Junhao", + "last_name": "Huang" + }, + { + "first_name": "Jin", + "last_name": "Tao" + }, + { + "first_name": "Xiangmin", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PracticalDG: Perturbation Distillation on Vision-Language Models for Hybrid Domain Generalization", - "authors": "Zining Chen, Weiqiu Wang, Zhicheng Zhao, Fei Su, Aidong Men, Hongying Meng", + "authors": [ + { + "first_name": "Zining", + "last_name": "Chen" + }, + { + "first_name": "Weiqiu", + "last_name": "Wang" + }, + { + "first_name": "Zhicheng", + "last_name": "Zhao" + }, + { + "first_name": "Fei", + "last_name": "Su" + }, + { + "first_name": "Aidong", + "last_name": "Men" + }, + { + "first_name": "Hongying", + "last_name": "Meng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SODA: Bottleneck Diffusion Models for Representation Learning", - "authors": "Drew A. Hudson, Daniel Zoran, Mateusz Malinowski, Andrew K. Lampinen, Andrew Jaegle, James L. McClelland, Loic Matthey, Felix Hill, Alexander Lerchner", + "authors": [ + { + "first_name": "Drew", + "last_name": "A. Hudson" + }, + { + "first_name": "Daniel", + "last_name": "Zoran" + }, + { + "first_name": "Mateusz", + "last_name": "Malinowski" + }, + { + "first_name": "Andrew", + "last_name": "K. Lampinen" + }, + { + "first_name": "Andrew", + "last_name": "Jaegle" + }, + { + "first_name": "James", + "last_name": "L. McClelland" + }, + { + "first_name": "Loic", + "last_name": "Matthey" + }, + { + "first_name": "Felix", + "last_name": "Hill" + }, + { + "first_name": "Alexander", + "last_name": "Lerchner" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards Robust Event-guided Low-Light Image Enhancement: A Large-Scale Real-World Event-Image Dataset and Novel Approach", - "authors": "Guoqiang Liang, Kanghao Chen, Hangyu Li, Yunfan Lu, Lin Wang", + "authors": [ + { + "first_name": "Guoqiang", + "last_name": "Liang" + }, + { + "first_name": "Kanghao", + "last_name": "Chen" + }, + { + "first_name": "Hangyu", + "last_name": "Li" + }, + { + "first_name": "Yunfan", + "last_name": "Lu" + }, + { + "first_name": "Lin", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Zero-Reference Low-Light Enhancement via Physical Quadruple Priors", - "authors": "Wenjing Wang, Huan Yang, Jianlong Fu, Jiaying Liu", + "authors": [ + { + "first_name": "Wenjing", + "last_name": "Wang" + }, + { + "first_name": "Huan", + "last_name": "Yang" + }, + { + "first_name": "Jianlong", + "last_name": "Fu" + }, + { + "first_name": "Jiaying", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LLaMA-Excitor: General Instruction Tuning via Indirect Feature Interaction", - "authors": "Bo Zou, Chao Yang, Yu Qiao, Chengbin Quan, Youjian Zhao", + "authors": [ + { + "first_name": "Bo", + "last_name": "Zou" + }, + { + "first_name": "Chao", + "last_name": "Yang" + }, + { + "first_name": "Yu", + "last_name": "Qiao" + }, + { + "first_name": "Chengbin", + "last_name": "Quan" + }, + { + "first_name": "Youjian", + "last_name": "Zhao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "NeRFCodec: Neural Feature Compression Meets Neural Radiance Fields for Memory-Efficient Scene Representation", - "authors": "Sicheng Li, Hao Li, Yiyi Liao, Lu Yu", + "authors": [ + { + "first_name": "Sicheng", + "last_name": "Li" + }, + { + "first_name": "Hao", + "last_name": "Li" + }, + { + "first_name": "Yiyi", + "last_name": "Liao" + }, + { + "first_name": "Lu", + "last_name": "Yu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "From a Bird's Eye View to See: Joint Camera and Subject Registration without the Camera Calibration", - "authors": "Zekun Qian, Ruize Han, Wei Feng, Song Wang", + "authors": [ + { + "first_name": "Zekun", + "last_name": "Qian" + }, + { + "first_name": "Ruize", + "last_name": "Han" + }, + { + "first_name": "Wei", + "last_name": "Feng" + }, + { + "first_name": "Song", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Steerers: A Framework for Rotation Equivariant Keypoint Descriptors", - "authors": "Georg Bökman, Johan Edstedt, Michael Felsberg, Fredrik Kahl", + "authors": [ + { + "first_name": "Georg", + "last_name": "Bökman" + }, + { + "first_name": "Johan", + "last_name": "Edstedt" + }, + { + "first_name": "Michael", + "last_name": "Felsberg" + }, + { + "first_name": "Fredrik", + "last_name": "Kahl" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Efficient Dataset Distillation via Minimax Diffusion", - "authors": "Jianyang Gu, Saeed Vahidian, Vyacheslav Kungurtsev, Haonan Wang, Wei Jiang, Yang You, Yiran Chen", + "authors": [ + { + "first_name": "Jianyang", + "last_name": "Gu" + }, + { + "first_name": "Saeed", + "last_name": "Vahidian" + }, + { + "first_name": "Vyacheslav", + "last_name": "Kungurtsev" + }, + { + "first_name": "Haonan", + "last_name": "Wang" + }, + { + "first_name": "Wei", + "last_name": "Jiang" + }, + { + "first_name": "Yang", + "last_name": "You" + }, + { + "first_name": "Yiran", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Posterior Distillation Sampling", - "authors": "Juil Koo, Chanho Park, Minhyuk Sung", + "authors": [ + { + "first_name": "Juil", + "last_name": "Koo" + }, + { + "first_name": "Chanho", + "last_name": "Park" + }, + { + "first_name": "Minhyuk", + "last_name": "Sung" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields", - "authors": "Haozhe Qi, Chen Zhao, Mathieu Salzmann, Alexander Mathis", + "authors": [ + { + "first_name": "Haozhe", + "last_name": "Qi" + }, + { + "first_name": "Chen", + "last_name": "Zhao" + }, + { + "first_name": "Mathieu", + "last_name": "Salzmann" + }, + { + "first_name": "Alexander", + "last_name": "Mathis" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Enhancing Video Super-Resolution via Implicit Resampling-based Alignment", - "authors": "Kai Xu, Ziwei Yu, Xin Wang, Michael Bi Mi, Angela Yao", + "authors": [ + { + "first_name": "Kai", + "last_name": "Xu" + }, + { + "first_name": "Ziwei", + "last_name": "Yu" + }, + { + "first_name": "Xin", + "last_name": "Wang" + }, + { + "first_name": "Michael", + "last_name": "Bi Mi" + }, + { + "first_name": "Angela", + "last_name": "Yao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DiffPortrait3D: Controllable Diffusion for Zero-Shot Portrait View Synthesis", - "authors": "Yuming Gu, Hongyi Xu, You Xie, Guoxian Song, Yichun Shi, Di Chang, Jing Yang, Linjie Luo", + "authors": [ + { + "first_name": "Yuming", + "last_name": "Gu" + }, + { + "first_name": "Hongyi", + "last_name": "Xu" + }, + { + "first_name": "You", + "last_name": "Xie" + }, + { + "first_name": "Guoxian", + "last_name": "Song" + }, + { + "first_name": "Yichun", + "last_name": "Shi" + }, + { + "first_name": "Di", + "last_name": "Chang" + }, + { + "first_name": "Jing", + "last_name": "Yang" + }, + { + "first_name": "Linjie", + "last_name": "Luo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Rethinking Transformers Pre-training for Multi-Spectral Satellite Imagery", - "authors": "Mubashir Noman, Muzammal Naseer, Hisham Cholakkal, Rao Muhammad Anwer, Salman Khan, Fahad Shahbaz Khan", + "authors": [ + { + "first_name": "Mubashir", + "last_name": "Noman" + }, + { + "first_name": "Muzammal", + "last_name": "Naseer" + }, + { + "first_name": "Hisham", + "last_name": "Cholakkal" + }, + { + "first_name": "Rao", + "last_name": "Muhammad Anwer" + }, + { + "first_name": "Salman", + "last_name": "Khan" + }, + { + "first_name": "Fahad", + "last_name": "Shahbaz Khan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generation", - "authors": "Kibum Kim, Kanghoon Yoon, Jaehyeong Jeon, Yeonjun In, Jinyoung Moon, Donghyun Kim, Chanyoung Park", + "authors": [ + { + "first_name": "Kibum", + "last_name": "Kim" + }, + { + "first_name": "Kanghoon", + "last_name": "Yoon" + }, + { + "first_name": "Jaehyeong", + "last_name": "Jeon" + }, + { + "first_name": "Yeonjun", + "last_name": "In" + }, + { + "first_name": "Jinyoung", + "last_name": "Moon" + }, + { + "first_name": "Donghyun", + "last_name": "Kim" + }, + { + "first_name": "Chanyoung", + "last_name": "Park" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Parameter Efficient Fine-tuning via Cross Block Orchestration for Segment Anything Model", - "authors": "Zelin Peng, Zhengqin Xu, Zhilin Zeng, Lingxi Xie, Qi Tian, Wei Shen", + "authors": [ + { + "first_name": "Zelin", + "last_name": "Peng" + }, + { + "first_name": "Zhengqin", + "last_name": "Xu" + }, + { + "first_name": "Zhilin", + "last_name": "Zeng" + }, + { + "first_name": "Lingxi", + "last_name": "Xie" + }, + { + "first_name": "Qi", + "last_name": "Tian" + }, + { + "first_name": "Wei", + "last_name": "Shen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Neural Directional Encoding for Efficient and Accurate View-Dependent Appearance Modeling", - "authors": "Liwen Wu, Sai Bi, Zexiang Xu, Fujun Luan, Kai Zhang, Iliyan Georgiev, Kalyan Sunkavalli, Ravi Ramamoorthi", + "authors": [ + { + "first_name": "Liwen", + "last_name": "Wu" + }, + { + "first_name": "Sai", + "last_name": "Bi" + }, + { + "first_name": "Zexiang", + "last_name": "Xu" + }, + { + "first_name": "Fujun", + "last_name": "Luan" + }, + { + "first_name": "Kai", + "last_name": "Zhang" + }, + { + "first_name": "Iliyan", + "last_name": "Georgiev" + }, + { + "first_name": "Kalyan", + "last_name": "Sunkavalli" + }, + { + "first_name": "Ravi", + "last_name": "Ramamoorthi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Masked and Shuffled Blind Spot Denoising for Real-World Images", - "authors": "Hamadi Chihaoui, Paolo Favaro", + "authors": [ + { + "first_name": "Hamadi", + "last_name": "Chihaoui" + }, + { + "first_name": "Paolo", + "last_name": "Favaro" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Label Propagation for Zero-shot Classification with Vision-Language Models", - "authors": "Vladan Stojni?, Yannis Kalantidis, Giorgos Tolias", + "authors": [ + { + "first_name": "Vladan", + "last_name": "Stojni?" + }, + { + "first_name": "Yannis", + "last_name": "Kalantidis" + }, + { + "first_name": "Giorgos", + "last_name": "Tolias" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DiffusionAvatars: Deferred Diffusion for High-fidelity 3D Head Avatars", - "authors": "Tobias Kirschstein, Simon Giebenhain, Matthias Nießner", + "authors": [ + { + "first_name": "Tobias", + "last_name": "Kirschstein" + }, + { + "first_name": "Simon", + "last_name": "Giebenhain" + }, + { + "first_name": "Matthias", + "last_name": "Nießner" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Data-Free Quantization via Pseudo-label Filtering", - "authors": "Chunxiao Fan, Ziqi Wang, Dan Guo, Meng Wang", + "authors": [ + { + "first_name": "Chunxiao", + "last_name": "Fan" + }, + { + "first_name": "Ziqi", + "last_name": "Wang" + }, + { + "first_name": "Dan", + "last_name": "Guo" + }, + { + "first_name": "Meng", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Revisiting Global Translation Estimation with Feature Tracks", - "authors": "Peilin Tao, Hainan Cui, Mengqi Rong, Shuhan Shen", + "authors": [ + { + "first_name": "Peilin", + "last_name": "Tao" + }, + { + "first_name": "Hainan", + "last_name": "Cui" + }, + { + "first_name": "Mengqi", + "last_name": "Rong" + }, + { + "first_name": "Shuhan", + "last_name": "Shen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Open-Set Domain Adaptation for Semantic Segmentation", - "authors": "Seun-An Choe, Ah-Hyung Shin, Keon-Hee Park, Jinwoo Choi, Gyeong-Moon Park", + "authors": [ + { + "first_name": "Seun-An", + "last_name": "Choe" + }, + { + "first_name": "Ah-Hyung", + "last_name": "Shin" + }, + { + "first_name": "Keon-Hee", + "last_name": "Park" + }, + { + "first_name": "Jinwoo", + "last_name": "Choi" + }, + { + "first_name": "Gyeong-Moon", + "last_name": "Park" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Generative Powers of Ten", - "authors": "Xiaojuan Wang, Janne Kontkanen, Brian Curless, Steven M. Seitz, Ira Kemelmacher-Shlizerman, Ben Mildenhall, Pratul Srinivasan, Dor Verbin, Aleksander Holynski", + "authors": [ + { + "first_name": "Xiaojuan", + "last_name": "Wang" + }, + { + "first_name": "Janne", + "last_name": "Kontkanen" + }, + { + "first_name": "Brian", + "last_name": "Curless" + }, + { + "first_name": "Steven", + "last_name": "M. Seitz" + }, + { + "first_name": "Ira", + "last_name": "Kemelmacher-Shlizerman" + }, + { + "first_name": "Ben", + "last_name": "Mildenhall" + }, + { + "first_name": "Pratul", + "last_name": "Srinivasan" + }, + { + "first_name": "Dor", + "last_name": "Verbin" + }, + { + "first_name": "Aleksander", + "last_name": "Holynski" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "H-ViT: A Hierarchical Vision Transformer for Deformable Image Registration", - "authors": "Morteza Ghahremani, Mohammad Khateri, Bailiang Jian, Benedikt Wiestler, Ehsan Adeli, Christian Wachinger", + "authors": [ + { + "first_name": "Morteza", + "last_name": "Ghahremani" + }, + { + "first_name": "Mohammad", + "last_name": "Khateri" + }, + { + "first_name": "Bailiang", + "last_name": "Jian" + }, + { + "first_name": "Benedikt", + "last_name": "Wiestler" + }, + { + "first_name": "Ehsan", + "last_name": "Adeli" + }, + { + "first_name": "Christian", + "last_name": "Wachinger" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-training", - "authors": "Yipeng Gao, Zeyu Wang, Wei-Shi Zheng, Cihang Xie, Yuyin Zhou", + "authors": [ + { + "first_name": "Yipeng", + "last_name": "Gao" + }, + { + "first_name": "Zeyu", + "last_name": "Wang" + }, + { + "first_name": "Wei-Shi", + "last_name": "Zheng" + }, + { + "first_name": "Cihang", + "last_name": "Xie" + }, + { + "first_name": "Yuyin", + "last_name": "Zhou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Probing Synergistic High-Order Interaction in Infrared and Visible Image Fusion", - "authors": "Naishan Zheng, Man Zhou, Jie Huang, Junming Hou, Haoying Li, Yuan Xu, Feng Zhao", + "authors": [ + { + "first_name": "Naishan", + "last_name": "Zheng" + }, + { + "first_name": "Man", + "last_name": "Zhou" + }, + { + "first_name": "Jie", + "last_name": "Huang" + }, + { + "first_name": "Junming", + "last_name": "Hou" + }, + { + "first_name": "Haoying", + "last_name": "Li" + }, + { + "first_name": "Yuan", + "last_name": "Xu" + }, + { + "first_name": "Feng", + "last_name": "Zhao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "VideoLLM-online: Online Video Large Language Model for Streaming Video", - "authors": "Joya Chen, Zhaoyang Lv, Shiwei Wu, Kevin Qinghong Lin, Chenan Song, Difei Gao, Jia-Wei Liu, Ziteng Gao, Dongxing Mao, Mike Zheng Shou", + "authors": [ + { + "first_name": "Joya", + "last_name": "Chen" + }, + { + "first_name": "Zhaoyang", + "last_name": "Lv" + }, + { + "first_name": "Shiwei", + "last_name": "Wu" + }, + { + "first_name": "Kevin", + "last_name": "Qinghong Lin" + }, + { + "first_name": "Chenan", + "last_name": "Song" + }, + { + "first_name": "Difei", + "last_name": "Gao" + }, + { + "first_name": "Jia-Wei", + "last_name": "Liu" + }, + { + "first_name": "Ziteng", + "last_name": "Gao" + }, + { + "first_name": "Dongxing", + "last_name": "Mao" + }, + { + "first_name": "Mike", + "last_name": "Zheng Shou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Text-conditional Attribute Alignment across Latent Spaces for 3D Controllable Face Image Synthesis", - "authors": "Feifan Xu, Rui Li, Si Wu, Yong Xu, Hau San Wong", + "authors": [ + { + "first_name": "Feifan", + "last_name": "Xu" + }, + { + "first_name": "Rui", + "last_name": "Li" + }, + { + "first_name": "Si", + "last_name": "Wu" + }, + { + "first_name": "Yong", + "last_name": "Xu" + }, + { + "first_name": "Hau", + "last_name": "San Wong" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ESCAPE: Encoding Super-keypoints for Category-Agnostic Pose Estimation", - "authors": "Khoi Duc Nguyen, Chen Li, Gim Hee Lee", + "authors": [ + { + "first_name": "Khoi", + "last_name": "Duc Nguyen" + }, + { + "first_name": "Chen", + "last_name": "Li" + }, + { + "first_name": "Gim", + "last_name": "Hee Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Correcting Diffusion Generation through Resampling", - "authors": "Yujian Liu, Yang Zhang, Tommi Jaakkola, Shiyu Chang", + "authors": [ + { + "first_name": "Yujian", + "last_name": "Liu" + }, + { + "first_name": "Yang", + "last_name": "Zhang" + }, + { + "first_name": "Tommi", + "last_name": "Jaakkola" + }, + { + "first_name": "Shiyu", + "last_name": "Chang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards Better Vision-Inspired Vision-Language Models", - "authors": "Yun-Hao Cao, Kaixiang Ji, Ziyuan Huang, Chuanyang Zheng, Jiajia Liu, Jian Wang, Jingdong Chen, Ming Yang", + "authors": [ + { + "first_name": "Yun-Hao", + "last_name": "Cao" + }, + { + "first_name": "Kaixiang", + "last_name": "Ji" + }, + { + "first_name": "Ziyuan", + "last_name": "Huang" + }, + { + "first_name": "Chuanyang", + "last_name": "Zheng" + }, + { + "first_name": "Jiajia", + "last_name": "Liu" + }, + { + "first_name": "Jian", + "last_name": "Wang" + }, + { + "first_name": "Jingdong", + "last_name": "Chen" + }, + { + "first_name": "Ming", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "VSRD: Instance-Aware Volumetric Silhouette Rendering for Weakly Supervised 3D Object Detection", - "authors": "Zihua Liu, Hiroki Sakuma, Masatoshi Okutomi", + "authors": [ + { + "first_name": "Zihua", + "last_name": "Liu" + }, + { + "first_name": "Hiroki", + "last_name": "Sakuma" + }, + { + "first_name": "Masatoshi", + "last_name": "Okutomi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "RILA: Reflective and Imaginative Language Agent for Zero-Shot Semantic Audio-Visual Navigation", - "authors": "Zeyuan Yang, Jiageng Liu, Peihao Chen, Anoop Cherian, Tim K. Marks, Jonathan Le Roux, Chuang Gan", + "authors": [ + { + "first_name": "Zeyuan", + "last_name": "Yang" + }, + { + "first_name": "Jiageng", + "last_name": "Liu" + }, + { + "first_name": "Peihao", + "last_name": "Chen" + }, + { + "first_name": "Anoop", + "last_name": "Cherian" + }, + { + "first_name": "Tim", + "last_name": "K. Marks" + }, + { + "first_name": "Jonathan", + "last_name": "Le Roux" + }, + { + "first_name": "Chuang", + "last_name": "Gan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Endow SAM with Keen Eyes: Temporal-spatial Prompt Learning for Video Camouflaged Object Detection", - "authors": "Wenjun Hui, Zhenfeng Zhu, Shuai Zheng, Yao Zhao", + "authors": [ + { + "first_name": "Wenjun", + "last_name": "Hui" + }, + { + "first_name": "Zhenfeng", + "last_name": "Zhu" + }, + { + "first_name": "Shuai", + "last_name": "Zheng" + }, + { + "first_name": "Yao", + "last_name": "Zhao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "TULIP: Multi-camera 3D Precision Assessment of Parkinson's Disease", - "authors": "Kyungdo Kim, Sihan Lyu, Sneha Mantri, Timothy W. Dunn", + "authors": [ + { + "first_name": "Kyungdo", + "last_name": "Kim" + }, + { + "first_name": "Sihan", + "last_name": "Lyu" + }, + { + "first_name": "Sneha", + "last_name": "Mantri" + }, + { + "first_name": "Timothy", + "last_name": "W. Dunn" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HybridNeRF: Efficient Neural Rendering via Adaptive Volumetric Surfaces", - "authors": "Haithem Turki, Vasu Agrawal, Samuel Rota Bulò, Lorenzo Porzi, Peter Kontschieder, Deva Ramanan, Michael Zollhöfer, Christian Richardt", + "authors": [ + { + "first_name": "Haithem", + "last_name": "Turki" + }, + { + "first_name": "Vasu", + "last_name": "Agrawal" + }, + { + "first_name": "Samuel", + "last_name": "Rota Bulò" + }, + { + "first_name": "Lorenzo", + "last_name": "Porzi" + }, + { + "first_name": "Peter", + "last_name": "Kontschieder" + }, + { + "first_name": "Deva", + "last_name": "Ramanan" + }, + { + "first_name": "Michael", + "last_name": "Zollhöfer" + }, + { + "first_name": "Christian", + "last_name": "Richardt" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "AirPlanes: Accurate Plane Estimation via 3D-Consistent Embeddings", - "authors": "Jamie Watson, Filippo Aleotti, Mohamed Sayed, Zawar Qureshi, Oisin Mac Aodha, Gabriel Brostow, Michael Firman, Sara Vicente", + "authors": [ + { + "first_name": "Jamie", + "last_name": "Watson" + }, + { + "first_name": "Filippo", + "last_name": "Aleotti" + }, + { + "first_name": "Mohamed", + "last_name": "Sayed" + }, + { + "first_name": "Zawar", + "last_name": "Qureshi" + }, + { + "first_name": "Oisin", + "last_name": "Mac Aodha" + }, + { + "first_name": "Gabriel", + "last_name": "Brostow" + }, + { + "first_name": "Michael", + "last_name": "Firman" + }, + { + "first_name": "Sara", + "last_name": "Vicente" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detection", - "authors": "Huan Liu, Zichang Tan, Chuangchuang Tan, Yunchao Wei, Jingdong Wang, Yao Zhao", + "authors": [ + { + "first_name": "Huan", + "last_name": "Liu" + }, + { + "first_name": "Zichang", + "last_name": "Tan" + }, + { + "first_name": "Chuangchuang", + "last_name": "Tan" + }, + { + "first_name": "Yunchao", + "last_name": "Wei" + }, + { + "first_name": "Jingdong", + "last_name": "Wang" + }, + { + "first_name": "Yao", + "last_name": "Zhao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PostureHMR: Posture Transformation for 3D Human Mesh Recovery", - "authors": "Yu-Pei Song, Xiao Wu, Zhaoquan Yuan, Jian-Jun Qiao, Qiang Peng", + "authors": [ + { + "first_name": "Yu-Pei", + "last_name": "Song" + }, + { + "first_name": "Xiao", + "last_name": "Wu" + }, + { + "first_name": "Zhaoquan", + "last_name": "Yuan" + }, + { + "first_name": "Jian-Jun", + "last_name": "Qiao" + }, + { + "first_name": "Qiang", + "last_name": "Peng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Blur2Blur: Blur Conversion for Unsupervised Image Deblurring on Unknown Domains", - "authors": "Bang-Dang Pham, Phong Tran, Anh Tran, Cuong Pham, Rang Nguyen, Minh Hoai", + "authors": [ + { + "first_name": "Bang-Dang", + "last_name": "Pham" + }, + { + "first_name": "Phong", + "last_name": "Tran" + }, + { + "first_name": "Anh", + "last_name": "Tran" + }, + { + "first_name": "Cuong", + "last_name": "Pham" + }, + { + "first_name": "Rang", + "last_name": "Nguyen" + }, + { + "first_name": "Minh", + "last_name": "Hoai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysis", - "authors": "Xin Zhou, Dingkang Liang, Wei Xu, Xingkui Zhu, Yihan Xu, Zhikang Zou, Xiang Bai", + "authors": [ + { + "first_name": "Xin", + "last_name": "Zhou" + }, + { + "first_name": "Dingkang", + "last_name": "Liang" + }, + { + "first_name": "Wei", + "last_name": "Xu" + }, + { + "first_name": "Xingkui", + "last_name": "Zhu" + }, + { + "first_name": "Yihan", + "last_name": "Xu" + }, + { + "first_name": "Zhikang", + "last_name": "Zou" + }, + { + "first_name": "Xiang", + "last_name": "Bai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Exploring Vision Transformers for 3D Human Motion-Language Models with Motion Patches", - "authors": "Qing Yu, Mikihiro Tanaka, Kent Fujiwara", + "authors": [ + { + "first_name": "Qing", + "last_name": "Yu" + }, + { + "first_name": "Mikihiro", + "last_name": "Tanaka" + }, + { + "first_name": "Kent", + "last_name": "Fujiwara" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Motion-adaptive Separable Collaborative Filters for Blind Motion Deblurring", - "authors": "Chengxu Liu, Xuan Wang, Xiangyu Xu, Ruhao Tian, Shuai Li, Xueming Qian, Ming-Hsuan Yang", + "authors": [ + { + "first_name": "Chengxu", + "last_name": "Liu" + }, + { + "first_name": "Xuan", + "last_name": "Wang" + }, + { + "first_name": "Xiangyu", + "last_name": "Xu" + }, + { + "first_name": "Ruhao", + "last_name": "Tian" + }, + { + "first_name": "Shuai", + "last_name": "Li" + }, + { + "first_name": "Xueming", + "last_name": "Qian" + }, + { + "first_name": "Ming-Hsuan", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DART: Implicit Doppler Tomography for Radar Novel View Synthesis", - "authors": "Tianshu Huang, John Miller, Akarsh Prabhakara, Tao Jin, Tarana Laroia, Zico Kolter, Anthony Rowe", + "authors": [ + { + "first_name": "Tianshu", + "last_name": "Huang" + }, + { + "first_name": "John", + "last_name": "Miller" + }, + { + "first_name": "Akarsh", + "last_name": "Prabhakara" + }, + { + "first_name": "Tao", + "last_name": "Jin" + }, + { + "first_name": "Tarana", + "last_name": "Laroia" + }, + { + "first_name": "Zico", + "last_name": "Kolter" + }, + { + "first_name": "Anthony", + "last_name": "Rowe" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Wonder3D: Single Image to 3D using Cross-Domain Diffusion", - "authors": "Xiaoxiao Long, Yuan-Chen Guo, Cheng Lin, Yuan Liu, Zhiyang Dou, Lingjie Liu, Yuexin Ma, Song-Hai Zhang, Marc Habermann, Christian Theobalt, Wenping Wang", + "authors": [ + { + "first_name": "Xiaoxiao", + "last_name": "Long" + }, + { + "first_name": "Yuan-Chen", + "last_name": "Guo" + }, + { + "first_name": "Cheng", + "last_name": "Lin" + }, + { + "first_name": "Yuan", + "last_name": "Liu" + }, + { + "first_name": "Zhiyang", + "last_name": "Dou" + }, + { + "first_name": "Lingjie", + "last_name": "Liu" + }, + { + "first_name": "Yuexin", + "last_name": "Ma" + }, + { + "first_name": "Song-Hai", + "last_name": "Zhang" + }, + { + "first_name": "Marc", + "last_name": "Habermann" + }, + { + "first_name": "Christian", + "last_name": "Theobalt" + }, + { + "first_name": "Wenping", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Genuine Knowledge from Practice: Diffusion Test-Time Adaptation for Video Adverse Weather Removal", - "authors": "Yijun Yang, Hongtao Wu, Angelica I. Aviles-Rivero, Yulun Zhang, Jing Qin, Lei Zhu", + "authors": [ + { + "first_name": "Yijun", + "last_name": "Yang" + }, + { + "first_name": "Hongtao", + "last_name": "Wu" + }, + { + "first_name": "Angelica", + "last_name": "I. Aviles-Rivero" + }, + { + "first_name": "Yulun", + "last_name": "Zhang" + }, + { + "first_name": "Jing", + "last_name": "Qin" + }, + { + "first_name": "Lei", + "last_name": "Zhu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Gradient-based Parameter Selection for Efficient Fine-Tuning", - "authors": "Zhi Zhang, Qizhe Zhang, Zijun Gao, Renrui Zhang, Ekaterina Shutova, Shiji Zhou, Shanghang Zhang", + "authors": [ + { + "first_name": "Zhi", + "last_name": "Zhang" + }, + { + "first_name": "Qizhe", + "last_name": "Zhang" + }, + { + "first_name": "Zijun", + "last_name": "Gao" + }, + { + "first_name": "Renrui", + "last_name": "Zhang" + }, + { + "first_name": "Ekaterina", + "last_name": "Shutova" + }, + { + "first_name": "Shiji", + "last_name": "Zhou" + }, + { + "first_name": "Shanghang", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Clustering for Protein Representation Learning", - "authors": "Ruijie Quan, Wenguan Wang, Fan Ma, Hehe Fan, Yi Yang", + "authors": [ + { + "first_name": "Ruijie", + "last_name": "Quan" + }, + { + "first_name": "Wenguan", + "last_name": "Wang" + }, + { + "first_name": "Fan", + "last_name": "Ma" + }, + { + "first_name": "Hehe", + "last_name": "Fan" + }, + { + "first_name": "Yi", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentation", - "authors": "Boyuan Sun, Yuqi Yang, Le Zhang, Ming-Ming Cheng, Qibin Hou", + "authors": [ + { + "first_name": "Boyuan", + "last_name": "Sun" + }, + { + "first_name": "Yuqi", + "last_name": "Yang" + }, + { + "first_name": "Le", + "last_name": "Zhang" + }, + { + "first_name": "Ming-Ming", + "last_name": "Cheng" + }, + { + "first_name": "Qibin", + "last_name": "Hou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Estimating Extreme 3D Image Rotations using Cascaded Attention", - "authors": "Shay Dekel, Yosi Keller, Martin Cadik", + "authors": [ + { + "first_name": "Shay", + "last_name": "Dekel" + }, + { + "first_name": "Yosi", + "last_name": "Keller" + }, + { + "first_name": "Martin", + "last_name": "Cadik" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D", - "authors": "Lingteng Qiu, Guanying Chen, Xiaodong Gu, Qi Zuo, Mutian Xu, Yushuang Wu, Weihao Yuan, Zilong Dong, Liefeng Bo, Xiaoguang Han", + "authors": [ + { + "first_name": "Lingteng", + "last_name": "Qiu" + }, + { + "first_name": "Guanying", + "last_name": "Chen" + }, + { + "first_name": "Xiaodong", + "last_name": "Gu" + }, + { + "first_name": "Qi", + "last_name": "Zuo" + }, + { + "first_name": "Mutian", + "last_name": "Xu" + }, + { + "first_name": "Yushuang", + "last_name": "Wu" + }, + { + "first_name": "Weihao", + "last_name": "Yuan" + }, + { + "first_name": "Zilong", + "last_name": "Dong" + }, + { + "first_name": "Liefeng", + "last_name": "Bo" + }, + { + "first_name": "Xiaoguang", + "last_name": "Han" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Adapt or Perish: Adaptive Sparse Transformer with Attentive Feature Refinement for Image Restoration", - "authors": "Shihao Zhou, Duosheng Chen, Jinshan Pan, Jinglei Shi, Jufeng Yang", + "authors": [ + { + "first_name": "Shihao", + "last_name": "Zhou" + }, + { + "first_name": "Duosheng", + "last_name": "Chen" + }, + { + "first_name": "Jinshan", + "last_name": "Pan" + }, + { + "first_name": "Jinglei", + "last_name": "Shi" + }, + { + "first_name": "Jufeng", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "VINECS: Video-based Neural Character Skinning", - "authors": "Zhouyingcheng Liao, Vladislav Golyanik, Marc Habermann, Christian Theobalt", + "authors": [ + { + "first_name": "Zhouyingcheng", + "last_name": "Liao" + }, + { + "first_name": "Vladislav", + "last_name": "Golyanik" + }, + { + "first_name": "Marc", + "last_name": "Habermann" + }, + { + "first_name": "Christian", + "last_name": "Theobalt" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Zero-shot Referring Expression Comprehension via Structural Similarity Between Images and Captions", - "authors": "Zeyu Han, Fangrui Zhu, Qianru Lao, Huaizu Jiang", + "authors": [ + { + "first_name": "Zeyu", + "last_name": "Han" + }, + { + "first_name": "Fangrui", + "last_name": "Zhu" + }, + { + "first_name": "Qianru", + "last_name": "Lao" + }, + { + "first_name": "Huaizu", + "last_name": "Jiang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Domain Prompt Learning with Quaternion Networks", - "authors": "Qinglong Cao, Zhengqin Xu, Yuntian Chen, Chao Ma, Xiaokang Yang", + "authors": [ + { + "first_name": "Qinglong", + "last_name": "Cao" + }, + { + "first_name": "Zhengqin", + "last_name": "Xu" + }, + { + "first_name": "Yuntian", + "last_name": "Chen" + }, + { + "first_name": "Chao", + "last_name": "Ma" + }, + { + "first_name": "Xiaokang", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "BEHAVIOR Vision Suite: Customizable Dataset Generation via Simulation", - "authors": "Yunhao Ge, Yihe Tang, Jiashu Xu, Cem Gokmen, Chengshu Li, Wensi Ai, Benjamin Jose Martinez, Arman Aydin, Mona Anvari, Ayush K Chakravarthy, Hong-Xing Yu, Josiah Wong, Sanjana Srivastava, Sharon Lee, Shengxin Zha, Laurent Itti, Yunzhu Li, Roberto Martín-Martín, Miao Liu, Pengchuan Zhang, Ruohan Zhang, Li Fei-Fei, Jiajun Wu", + "authors": [ + { + "first_name": "Yunhao", + "last_name": "Ge" + }, + { + "first_name": "Yihe", + "last_name": "Tang" + }, + { + "first_name": "Jiashu", + "last_name": "Xu" + }, + { + "first_name": "Cem", + "last_name": "Gokmen" + }, + { + "first_name": "Chengshu", + "last_name": "Li" + }, + { + "first_name": "Wensi", + "last_name": "Ai" + }, + { + "first_name": "Benjamin", + "last_name": "Jose Martinez" + }, + { + "first_name": "Arman", + "last_name": "Aydin" + }, + { + "first_name": "Mona", + "last_name": "Anvari" + }, + { + "first_name": "Ayush", + "last_name": "K Chakravarthy" + }, + { + "first_name": "Hong-Xing", + "last_name": "Yu" + }, + { + "first_name": "Josiah", + "last_name": "Wong" + }, + { + "first_name": "Sanjana", + "last_name": "Srivastava" + }, + { + "first_name": "Sharon", + "last_name": "Lee" + }, + { + "first_name": "Shengxin", + "last_name": "Zha" + }, + { + "first_name": "Laurent", + "last_name": "Itti" + }, + { + "first_name": "Yunzhu", + "last_name": "Li" + }, + { + "first_name": "Roberto", + "last_name": "Martín-Martín" + }, + { + "first_name": "Miao", + "last_name": "Liu" + }, + { + "first_name": "Pengchuan", + "last_name": "Zhang" + }, + { + "first_name": "Ruohan", + "last_name": "Zhang" + }, + { + "first_name": "Li", + "last_name": "Fei-Fei" + }, + { + "first_name": "Jiajun", + "last_name": "Wu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformers", - "authors": "Zi-Xin Zou, Zhipeng Yu, Yuan-Chen Guo, Yangguang Li, Ding Liang, Yan-Pei Cao, Song-Hai Zhang", + "authors": [ + { + "first_name": "Zi-Xin", + "last_name": "Zou" + }, + { + "first_name": "Zhipeng", + "last_name": "Yu" + }, + { + "first_name": "Yuan-Chen", + "last_name": "Guo" + }, + { + "first_name": "Yangguang", + "last_name": "Li" + }, + { + "first_name": "Ding", + "last_name": "Liang" + }, + { + "first_name": "Yan-Pei", + "last_name": "Cao" + }, + { + "first_name": "Song-Hai", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "WateRF: Robust Watermarks in Radiance Fields for Protection of Copyrights", - "authors": "Youngdong Jang, Dong In Lee, MinHyuk Jang, Jong Wook Kim, Feng Yang, Sangpil Kim", + "authors": [ + { + "first_name": "Youngdong", + "last_name": "Jang" + }, + { + "first_name": "Dong", + "last_name": "In Lee" + }, + { + "first_name": "MinHyuk", + "last_name": "Jang" + }, + { + "first_name": "Jong", + "last_name": "Wook Kim" + }, + { + "first_name": "Feng", + "last_name": "Yang" + }, + { + "first_name": "Sangpil", + "last_name": "Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Gaussian-Flow: 4D Reconstruction with Dynamic 3D Gaussian Particle", - "authors": "Youtian Lin, Zuozhuo Dai, Siyu Zhu, Yao Yao", + "authors": [ + { + "first_name": "Youtian", + "last_name": "Lin" + }, + { + "first_name": "Zuozhuo", + "last_name": "Dai" + }, + { + "first_name": "Siyu", + "last_name": "Zhu" + }, + { + "first_name": "Yao", + "last_name": "Yao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Your Student is Better Than Expected: Adaptive Teacher-Student Collaboration for Text-Conditional Diffusion Models", - "authors": "Nikita Starodubcev, Dmitry Baranchuk, Artem Fedorov, Artem Babenko", + "authors": [ + { + "first_name": "Nikita", + "last_name": "Starodubcev" + }, + { + "first_name": "Dmitry", + "last_name": "Baranchuk" + }, + { + "first_name": "Artem", + "last_name": "Fedorov" + }, + { + "first_name": "Artem", + "last_name": "Babenko" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DiVAS: Video and Audio Synchronization with Dynamic Frame Rates", - "authors": "Clara Fernandez-Labrador, Mertcan Akçay, Eitan Abecassis, Joan Massich, Christopher Schroers", + "authors": [ + { + "first_name": "Clara", + "last_name": "Fernandez-Labrador" + }, + { + "first_name": "Mertcan", + "last_name": "Akçay" + }, + { + "first_name": "Eitan", + "last_name": "Abecassis" + }, + { + "first_name": "Joan", + "last_name": "Massich" + }, + { + "first_name": "Christopher", + "last_name": "Schroers" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SHViT: Single-Head Vision Transformer with Memory Efficient Macro Design", - "authors": "Seokju Yun, Youngmin Ro", + "authors": [ + { + "first_name": "Seokju", + "last_name": "Yun" + }, + { + "first_name": "Youngmin", + "last_name": "Ro" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HDRFlow: Real-Time HDR Video Reconstruction with Large Motions", - "authors": "Gangwei Xu, Yujin Wang, Jinwei Gu, Tianfan Xue, Xin Yang", + "authors": [ + { + "first_name": "Gangwei", + "last_name": "Xu" + }, + { + "first_name": "Yujin", + "last_name": "Wang" + }, + { + "first_name": "Jinwei", + "last_name": "Gu" + }, + { + "first_name": "Tianfan", + "last_name": "Xue" + }, + { + "first_name": "Xin", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SPIDeRS: Structured Polarization for Invisible Depth and Reflectance Sensing", - "authors": "Tomoki Ichikawa, Shohei Nobuhara, Ko Nishino", + "authors": [ + { + "first_name": "Tomoki", + "last_name": "Ichikawa" + }, + { + "first_name": "Shohei", + "last_name": "Nobuhara" + }, + { + "first_name": "Ko", + "last_name": "Nishino" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SuperNormal: Neural Surface Reconstruction via Multi-View Normal Integration", - "authors": "Xu Cao, Takafumi Taketomi", + "authors": [ + { + "first_name": "Xu", + "last_name": "Cao" + }, + { + "first_name": "Takafumi", + "last_name": "Taketomi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Instance-aware Contrastive Learning for Occluded Human Mesh Reconstruction", - "authors": "Mi-Gyeong Gwon, Gi-Mun Um, Won-Sik Cheong, Wonjun Kim", + "authors": [ + { + "first_name": "Mi-Gyeong", + "last_name": "Gwon" + }, + { + "first_name": "Gi-Mun", + "last_name": "Um" + }, + { + "first_name": "Won-Sik", + "last_name": "Cheong" + }, + { + "first_name": "Wonjun", + "last_name": "Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ADFactory: An Effective Framework for Generalizing Optical Flow with NeRF", - "authors": "Han Ling, Quansen Sun, Yinghui Sun, Xian Xu, Xinfeng Li", + "authors": [ + { + "first_name": "Han", + "last_name": "Ling" + }, + { + "first_name": "Quansen", + "last_name": "Sun" + }, + { + "first_name": "Yinghui", + "last_name": "Sun" + }, + { + "first_name": "Xian", + "last_name": "Xu" + }, + { + "first_name": "Xinfeng", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Robust Noisy Correspondence Learning with Equivariant Similarity Consistency", - "authors": "Yuchen Yang, Likai Wang, Erkun Yang, Cheng Deng", + "authors": [ + { + "first_name": "Yuchen", + "last_name": "Yang" + }, + { + "first_name": "Likai", + "last_name": "Wang" + }, + { + "first_name": "Erkun", + "last_name": "Yang" + }, + { + "first_name": "Cheng", + "last_name": "Deng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CommonCanvas: Open Diffusion Models Trained on Creative-Commons Images", - "authors": "Aaron Gokaslan, A. Feder Cooper, Jasmine Collins, Landan Seguin, Austin Jacobson, Mihir Patel, Jonathan Frankle, Cory Stephenson, Volodymyr Kuleshov", + "authors": [ + { + "first_name": "Aaron", + "last_name": "Gokaslan" + }, + { + "first_name": "A.", + "last_name": "Feder Cooper" + }, + { + "first_name": "Jasmine", + "last_name": "Collins" + }, + { + "first_name": "Landan", + "last_name": "Seguin" + }, + { + "first_name": "Austin", + "last_name": "Jacobson" + }, + { + "first_name": "Mihir", + "last_name": "Patel" + }, + { + "first_name": "Jonathan", + "last_name": "Frankle" + }, + { + "first_name": "Cory", + "last_name": "Stephenson" + }, + { + "first_name": "Volodymyr", + "last_name": "Kuleshov" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Prompt-Driven Referring Image Segmentation with Instance Contrasting", - "authors": "Chao Shang, Zichen Song, Heqian Qiu, Lanxiao Wang, Fanman Meng, Hongliang Li", + "authors": [ + { + "first_name": "Chao", + "last_name": "Shang" + }, + { + "first_name": "Zichen", + "last_name": "Song" + }, + { + "first_name": "Heqian", + "last_name": "Qiu" + }, + { + "first_name": "Lanxiao", + "last_name": "Wang" + }, + { + "first_name": "Fanman", + "last_name": "Meng" + }, + { + "first_name": "Hongliang", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Image Sculpting: Precise Object Editing with 3D Geometry Control", - "authors": "Jiraphon Yenphraphai, Xichen Pan, Sainan Liu, Daniele Panozzo, Saining Xie", + "authors": [ + { + "first_name": "Jiraphon", + "last_name": "Yenphraphai" + }, + { + "first_name": "Xichen", + "last_name": "Pan" + }, + { + "first_name": "Sainan", + "last_name": "Liu" + }, + { + "first_name": "Daniele", + "last_name": "Panozzo" + }, + { + "first_name": "Saining", + "last_name": "Xie" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Compositional Video Understanding with Spatiotemporal Structure-based Transformers", - "authors": "Hoyeoung Yun, Jinwoo Ahn, Minseo Kim, Eun-Sol Kim", + "authors": [ + { + "first_name": "Hoyeoung", + "last_name": "Yun" + }, + { + "first_name": "Jinwoo", + "last_name": "Ahn" + }, + { + "first_name": "Minseo", + "last_name": "Kim" + }, + { + "first_name": "Eun-Sol", + "last_name": "Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "3D LiDAR Mapping in Dynamic Environments using a 4D Implicit Neural Representation", - "authors": "Xingguang Zhong, Yue Pan, Cyrill Stachniss, Jens Behley", + "authors": [ + { + "first_name": "Xingguang", + "last_name": "Zhong" + }, + { + "first_name": "Yue", + "last_name": "Pan" + }, + { + "first_name": "Cyrill", + "last_name": "Stachniss" + }, + { + "first_name": "Jens", + "last_name": "Behley" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "What When and Where? Self-Supervised Spatio-Temporal Grounding in Untrimmed Multi-Action Videos from Narrated Instructions", - "authors": "Brian Chen, Nina Shvetsova, Andrew Rouditchenko, Daniel Kondermann, Samuel Thomas, Shih-Fu Chang, Rogerio Feris, James Glass, Hilde Kuehne", + "authors": [ + { + "first_name": "Brian", + "last_name": "Chen" + }, + { + "first_name": "Nina", + "last_name": "Shvetsova" + }, + { + "first_name": "Andrew", + "last_name": "Rouditchenko" + }, + { + "first_name": "Daniel", + "last_name": "Kondermann" + }, + { + "first_name": "Samuel", + "last_name": "Thomas" + }, + { + "first_name": "Shih-Fu", + "last_name": "Chang" + }, + { + "first_name": "Rogerio", + "last_name": "Feris" + }, + { + "first_name": "James", + "last_name": "Glass" + }, + { + "first_name": "Hilde", + "last_name": "Kuehne" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects", - "authors": "Bowen Wen, Wei Yang, Jan Kautz, Stan Birchfield", + "authors": [ + { + "first_name": "Bowen", + "last_name": "Wen" + }, + { + "first_name": "Wei", + "last_name": "Yang" + }, + { + "first_name": "Jan", + "last_name": "Kautz" + }, + { + "first_name": "Stan", + "last_name": "Birchfield" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "How Far Can We Compress Instant-NGP-Based NeRF?", - "authors": "Yihang Chen, Qianyi Wu, Mehrtash Harandi, Jianfei Cai", + "authors": [ + { + "first_name": "Yihang", + "last_name": "Chen" + }, + { + "first_name": "Qianyi", + "last_name": "Wu" + }, + { + "first_name": "Mehrtash", + "last_name": "Harandi" + }, + { + "first_name": "Jianfei", + "last_name": "Cai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PFStorer: Personalized Face Restoration and Super-Resolution", - "authors": "Tuomas Varanka, Tapani Toivonen, Soumya Tripathy, Guoying Zhao, Erman Acar", + "authors": [ + { + "first_name": "Tuomas", + "last_name": "Varanka" + }, + { + "first_name": "Tapani", + "last_name": "Toivonen" + }, + { + "first_name": "Soumya", + "last_name": "Tripathy" + }, + { + "first_name": "Guoying", + "last_name": "Zhao" + }, + { + "first_name": "Erman", + "last_name": "Acar" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "TextureDreamer: Image-Guided Texture Synthesis Through Geometry-Aware Diffusion", - "authors": "Yu-Ying Yeh, Jia-Bin Huang, Changil Kim, Lei Xiao, Thu Nguyen-Phuoc, Numair Khan, Cheng Zhang, Manmohan Chandraker, Carl S Marshall, Zhao Dong, Zhengqin Li", + "authors": [ + { + "first_name": "Yu-Ying", + "last_name": "Yeh" + }, + { + "first_name": "Jia-Bin", + "last_name": "Huang" + }, + { + "first_name": "Changil", + "last_name": "Kim" + }, + { + "first_name": "Lei", + "last_name": "Xiao" + }, + { + "first_name": "Thu", + "last_name": "Nguyen-Phuoc" + }, + { + "first_name": "Numair", + "last_name": "Khan" + }, + { + "first_name": "Cheng", + "last_name": "Zhang" + }, + { + "first_name": "Manmohan", + "last_name": "Chandraker" + }, + { + "first_name": "Carl", + "last_name": "S Marshall" + }, + { + "first_name": "Zhao", + "last_name": "Dong" + }, + { + "first_name": "Zhengqin", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Boosting Image Quality Assessment through Efficient Transformer Adaptation with Local Feature Enhancement", - "authors": "Kangmin Xu, Liang Liao, Jing Xiao, Chaofeng Chen, Haoning Wu, Qiong Yan, Weisi Lin", + "authors": [ + { + "first_name": "Kangmin", + "last_name": "Xu" + }, + { + "first_name": "Liang", + "last_name": "Liao" + }, + { + "first_name": "Jing", + "last_name": "Xiao" + }, + { + "first_name": "Chaofeng", + "last_name": "Chen" + }, + { + "first_name": "Haoning", + "last_name": "Wu" + }, + { + "first_name": "Qiong", + "last_name": "Yan" + }, + { + "first_name": "Weisi", + "last_name": "Lin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Hyperbolic Anomaly Detection", - "authors": "Huimin Li, Zhentao Chen, Yunhao Xu, Junlin Hu", + "authors": [ + { + "first_name": "Huimin", + "last_name": "Li" + }, + { + "first_name": "Zhentao", + "last_name": "Chen" + }, + { + "first_name": "Yunhao", + "last_name": "Xu" + }, + { + "first_name": "Junlin", + "last_name": "Hu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "VLP: Vision Language Planning for Autonomous Driving", - "authors": "Chenbin Pan, Burhaneddin Yaman, Tommaso Nesti, Abhirup Mallik, Alessandro G Allievi, Senem Velipasalar, Liu Ren", + "authors": [ + { + "first_name": "Chenbin", + "last_name": "Pan" + }, + { + "first_name": "Burhaneddin", + "last_name": "Yaman" + }, + { + "first_name": "Tommaso", + "last_name": "Nesti" + }, + { + "first_name": "Abhirup", + "last_name": "Mallik" + }, + { + "first_name": "Alessandro", + "last_name": "G Allievi" + }, + { + "first_name": "Senem", + "last_name": "Velipasalar" + }, + { + "first_name": "Liu", + "last_name": "Ren" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Attention Calibration for Disentangled Text-to-Image Personalization", - "authors": "Yanbing Zhang, Mengping Yang, Qin Zhou, Zhe Wang", + "authors": [ + { + "first_name": "Yanbing", + "last_name": "Zhang" + }, + { + "first_name": "Mengping", + "last_name": "Yang" + }, + { + "first_name": "Qin", + "last_name": "Zhou" + }, + { + "first_name": "Zhe", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ProMark: Proactive Diffusion Watermarking for Causal Attribution", - "authors": "Vishal Asnani, John Collomosse, Tu Bui, Xiaoming Liu, Shruti Agarwal", + "authors": [ + { + "first_name": "Vishal", + "last_name": "Asnani" + }, + { + "first_name": "John", + "last_name": "Collomosse" + }, + { + "first_name": "Tu", + "last_name": "Bui" + }, + { + "first_name": "Xiaoming", + "last_name": "Liu" + }, + { + "first_name": "Shruti", + "last_name": "Agarwal" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "One-Shot Structure-Aware Stylized Image Synthesis", - "authors": "Hansam Cho, Jonghyun Lee, Seunggyu Chang, Yonghyun Jeong", + "authors": [ + { + "first_name": "Hansam", + "last_name": "Cho" + }, + { + "first_name": "Jonghyun", + "last_name": "Lee" + }, + { + "first_name": "Seunggyu", + "last_name": "Chang" + }, + { + "first_name": "Yonghyun", + "last_name": "Jeong" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GPT4Point: A Unified Framework for Point-Language Understanding and Generation", - "authors": "Zhangyang Qi, Ye Fang, Zeyi Sun, Xiaoyang Wu, Tong Wu, Jiaqi Wang, Dahua Lin, Hengshuang Zhao", + "authors": [ + { + "first_name": "Zhangyang", + "last_name": "Qi" + }, + { + "first_name": "Ye", + "last_name": "Fang" + }, + { + "first_name": "Zeyi", + "last_name": "Sun" + }, + { + "first_name": "Xiaoyang", + "last_name": "Wu" + }, + { + "first_name": "Tong", + "last_name": "Wu" + }, + { + "first_name": "Jiaqi", + "last_name": "Wang" + }, + { + "first_name": "Dahua", + "last_name": "Lin" + }, + { + "first_name": "Hengshuang", + "last_name": "Zhao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SemCity: Semantic Scene Generation with Triplane Diffusion", - "authors": "Jumin Lee, Sebin Lee, Changho Jo, Woobin Im, Juhyeong Seon, Sung-Eui Yoon", + "authors": [ + { + "first_name": "Jumin", + "last_name": "Lee" + }, + { + "first_name": "Sebin", + "last_name": "Lee" + }, + { + "first_name": "Changho", + "last_name": "Jo" + }, + { + "first_name": "Woobin", + "last_name": "Im" + }, + { + "first_name": "Juhyeong", + "last_name": "Seon" + }, + { + "first_name": "Sung-Eui", + "last_name": "Yoon" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Improving Semantic Correspondence with Viewpoint-Guided Spherical Maps", - "authors": "Octave Mariotti, Oisin Mac Aodha, Hakan Bilen", + "authors": [ + { + "first_name": "Octave", + "last_name": "Mariotti" + }, + { + "first_name": "Oisin", + "last_name": "Mac Aodha" + }, + { + "first_name": "Hakan", + "last_name": "Bilen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MR-VNet: Media Restoration using Volterra Networks", - "authors": "Siddharth Roheda, Amit Unde, Loay Rashid", + "authors": [ + { + "first_name": "Siddharth", + "last_name": "Roheda" + }, + { + "first_name": "Amit", + "last_name": "Unde" + }, + { + "first_name": "Loay", + "last_name": "Rashid" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models", - "authors": "Yabin Zhang, Wenjie Zhu, Hui Tang, Zhiyuan Ma, Kaiyang Zhou, Lei Zhang", + "authors": [ + { + "first_name": "Yabin", + "last_name": "Zhang" + }, + { + "first_name": "Wenjie", + "last_name": "Zhu" + }, + { + "first_name": "Hui", + "last_name": "Tang" + }, + { + "first_name": "Zhiyuan", + "last_name": "Ma" + }, + { + "first_name": "Kaiyang", + "last_name": "Zhou" + }, + { + "first_name": "Lei", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Single Mesh Diffusion Models with Field Latents for Texture Generation", - "authors": "Thomas W. Mitchel, Carlos Esteves, Ameesh Makadia", + "authors": [ + { + "first_name": "Thomas", + "last_name": "W. Mitchel" + }, + { + "first_name": "Carlos", + "last_name": "Esteves" + }, + { + "first_name": "Ameesh", + "last_name": "Makadia" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LION: Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge", - "authors": "Gongwei Chen, Leyang Shen, Rui Shao, Xiang Deng, Liqiang Nie", + "authors": [ + { + "first_name": "Gongwei", + "last_name": "Chen" + }, + { + "first_name": "Leyang", + "last_name": "Shen" + }, + { + "first_name": "Rui", + "last_name": "Shao" + }, + { + "first_name": "Xiang", + "last_name": "Deng" + }, + { + "first_name": "Liqiang", + "last_name": "Nie" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning to Select Views for Efficient Multi-View Understanding", - "authors": "Yunzhong Hou, Stephen Gould, Liang Zheng", + "authors": [ + { + "first_name": "Yunzhong", + "last_name": "Hou" + }, + { + "first_name": "Stephen", + "last_name": "Gould" + }, + { + "first_name": "Liang", + "last_name": "Zheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Consistency and Uncertainty: Identifying Unreliable Responses From Black-Box Vision-Language Models for Selective Visual Question Answering", - "authors": "Zaid Khan, Yun Fu", + "authors": [ + { + "first_name": "Zaid", + "last_name": "Khan" + }, + { + "first_name": "Yun", + "last_name": "Fu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SAI3D: Segment Any Instance in 3D Scenes", - "authors": "Yingda Yin, Yuzheng Liu, Yang Xiao, Daniel Cohen-Or, Jingwei Huang, Baoquan Chen", + "authors": [ + { + "first_name": "Yingda", + "last_name": "Yin" + }, + { + "first_name": "Yuzheng", + "last_name": "Liu" + }, + { + "first_name": "Yang", + "last_name": "Xiao" + }, + { + "first_name": "Daniel", + "last_name": "Cohen-Or" + }, + { + "first_name": "Jingwei", + "last_name": "Huang" + }, + { + "first_name": "Baoquan", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Implicit Motion Function", - "authors": "Yue Gao, Jiahao Li, Lei Chu, Yan Lu", + "authors": [ + { + "first_name": "Yue", + "last_name": "Gao" + }, + { + "first_name": "Jiahao", + "last_name": "Li" + }, + { + "first_name": "Lei", + "last_name": "Chu" + }, + { + "first_name": "Yan", + "last_name": "Lu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Unified Entropy Optimization for Open-Set Test-Time Adaptation", - "authors": "Zhengqing Gao, Xu-Yao Zhang, Cheng-Lin Liu", + "authors": [ + { + "first_name": "Zhengqing", + "last_name": "Gao" + }, + { + "first_name": "Xu-Yao", + "last_name": "Zhang" + }, + { + "first_name": "Cheng-Lin", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "TexOct: Generating Textures of 3D Models with Octree-based Diffusion", - "authors": "Jialun Liu, Chenming Wu, Xinqi Liu, Xing Liu, Jinbo Wu, Haotian Peng, Chen Zhao, Haocheng Feng, Jingtuo Liu, Errui Ding", + "authors": [ + { + "first_name": "Jialun", + "last_name": "Liu" + }, + { + "first_name": "Chenming", + "last_name": "Wu" + }, + { + "first_name": "Xinqi", + "last_name": "Liu" + }, + { + "first_name": "Xing", + "last_name": "Liu" + }, + { + "first_name": "Jinbo", + "last_name": "Wu" + }, + { + "first_name": "Haotian", + "last_name": "Peng" + }, + { + "first_name": "Chen", + "last_name": "Zhao" + }, + { + "first_name": "Haocheng", + "last_name": "Feng" + }, + { + "first_name": "Jingtuo", + "last_name": "Liu" + }, + { + "first_name": "Errui", + "last_name": "Ding" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Anatomically Constrained Implicit Face Models", - "authors": "Prashanth Chandran, Gaspard Zoss", + "authors": [ + { + "first_name": "Prashanth", + "last_name": "Chandran" + }, + { + "first_name": "Gaspard", + "last_name": "Zoss" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning", - "authors": "Da-Wei Zhou, Hai-Long Sun, Han-Jia Ye, De-Chuan Zhan", + "authors": [ + { + "first_name": "Da-Wei", + "last_name": "Zhou" + }, + { + "first_name": "Hai-Long", + "last_name": "Sun" + }, + { + "first_name": "Han-Jia", + "last_name": "Ye" + }, + { + "first_name": "De-Chuan", + "last_name": "Zhan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Capturing Closely Interacted Two-Person Motions with Reaction Priors", - "authors": "Qi Fang, Yinghui Fan, Yanjun Li, Junting Dong, Dingwei Wu, Weidong Zhang, Kang Chen", + "authors": [ + { + "first_name": "Qi", + "last_name": "Fang" + }, + { + "first_name": "Yinghui", + "last_name": "Fan" + }, + { + "first_name": "Yanjun", + "last_name": "Li" + }, + { + "first_name": "Junting", + "last_name": "Dong" + }, + { + "first_name": "Dingwei", + "last_name": "Wu" + }, + { + "first_name": "Weidong", + "last_name": "Zhang" + }, + { + "first_name": "Kang", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "RobustSAM: Segment Anything Robustly on Degraded Images", - "authors": "Wei-Ting Chen, Yu-Jiet Vong, Sy-Yen Kuo, Sizhou Ma, Jian Wang", + "authors": [ + { + "first_name": "Wei-Ting", + "last_name": "Chen" + }, + { + "first_name": "Yu-Jiet", + "last_name": "Vong" + }, + { + "first_name": "Sy-Yen", + "last_name": "Kuo" + }, + { + "first_name": "Sizhou", + "last_name": "Ma" + }, + { + "first_name": "Jian", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MultiDiff: Consistent Novel View Synthesis from a Single Image", - "authors": "Norman Müller, Katja Schwarz, Barbara Rössle, Lorenzo Porzi, Samuel Rota Bulò, Matthias Nießner, Peter Kontschieder", + "authors": [ + { + "first_name": "Norman", + "last_name": "Müller" + }, + { + "first_name": "Katja", + "last_name": "Schwarz" + }, + { + "first_name": "Barbara", + "last_name": "Rössle" + }, + { + "first_name": "Lorenzo", + "last_name": "Porzi" + }, + { + "first_name": "Samuel", + "last_name": "Rota Bulò" + }, + { + "first_name": "Matthias", + "last_name": "Nießner" + }, + { + "first_name": "Peter", + "last_name": "Kontschieder" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "In-N-Out: Faithful 3D GAN Inversion with Volumetric Decomposition for Face Editing", - "authors": "Yiran Xu, Zhixin Shu, Cameron Smith, Seoung Wug Oh, Jia-Bin Huang", + "authors": [ + { + "first_name": "Yiran", + "last_name": "Xu" + }, + { + "first_name": "Zhixin", + "last_name": "Shu" + }, + { + "first_name": "Cameron", + "last_name": "Smith" + }, + { + "first_name": "Seoung", + "last_name": "Wug Oh" + }, + { + "first_name": "Jia-Bin", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Atom-Level Optical Chemical Structure Recognition with Limited Supervision", - "authors": "Martijn Oldenhof, Edward De Brouwer, Adam Arany, Yves Moreau", + "authors": [ + { + "first_name": "Martijn", + "last_name": "Oldenhof" + }, + { + "first_name": "Edward", + "last_name": "De Brouwer" + }, + { + "first_name": "Adam", + "last_name": "Arany" + }, + { + "first_name": "Yves", + "last_name": "Moreau" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "L4D-Track: Language-to-4D Modeling Towards 6-DoF Tracking and Shape Reconstruction in 3D Point Cloud Stream", - "authors": "Jingtao Sun, Yaonan Wang, Mingtao Feng, Yulan Guo, Ajmal Mian, Mike Zheng Shou", + "authors": [ + { + "first_name": "Jingtao", + "last_name": "Sun" + }, + { + "first_name": "Yaonan", + "last_name": "Wang" + }, + { + "first_name": "Mingtao", + "last_name": "Feng" + }, + { + "first_name": "Yulan", + "last_name": "Guo" + }, + { + "first_name": "Ajmal", + "last_name": "Mian" + }, + { + "first_name": "Mike", + "last_name": "Zheng Shou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "General Point Model Pretraining with Autoencoding and Autoregressive", - "authors": "Zhe Li, Zhangyang Gao, Cheng Tan, Bocheng Ren, Laurence T. Yang, Stan Z. Li", + "authors": [ + { + "first_name": "Zhe", + "last_name": "Li" + }, + { + "first_name": "Zhangyang", + "last_name": "Gao" + }, + { + "first_name": "Cheng", + "last_name": "Tan" + }, + { + "first_name": "Bocheng", + "last_name": "Ren" + }, + { + "first_name": "Laurence", + "last_name": "T. Yang" + }, + { + "first_name": "Stan", + "last_name": "Z. Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Combining Frame and GOP Embeddings for Neural Video Representation", - "authors": "Jens Eirik Saethre, Roberto Azevedo, Christopher Schroers", + "authors": [ + { + "first_name": "Jens", + "last_name": "Eirik Saethre" + }, + { + "first_name": "Roberto", + "last_name": "Azevedo" + }, + { + "first_name": "Christopher", + "last_name": "Schroers" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LiDAR-based Person Re-identification", - "authors": "Wenxuan Guo, Zhiyu Pan, Yingping Liang, Ziheng Xi, Zhicheng Zhong, Jianjiang Feng, Jie Zhou", + "authors": [ + { + "first_name": "Wenxuan", + "last_name": "Guo" + }, + { + "first_name": "Zhiyu", + "last_name": "Pan" + }, + { + "first_name": "Yingping", + "last_name": "Liang" + }, + { + "first_name": "Ziheng", + "last_name": "Xi" + }, + { + "first_name": "Zhicheng", + "last_name": "Zhong" + }, + { + "first_name": "Jianjiang", + "last_name": "Feng" + }, + { + "first_name": "Jie", + "last_name": "Zhou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Fantastic Animals and Where to Find Them: Segment Any Marine Animal with Dual SAM", - "authors": "Pingping Zhang, Tianyu Yan, Yang Liu, Huchuan Lu", + "authors": [ + { + "first_name": "Pingping", + "last_name": "Zhang" + }, + { + "first_name": "Tianyu", + "last_name": "Yan" + }, + { + "first_name": "Yang", + "last_name": "Liu" + }, + { + "first_name": "Huchuan", + "last_name": "Lu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Seeing and Hearing: Open-domain Visual-Audio Generation with Diffusion Latent Aligners", - "authors": "Yazhou Xing, Yingqing He, Zeyue Tian, Xintao Wang, Qifeng Chen", + "authors": [ + { + "first_name": "Yazhou", + "last_name": "Xing" + }, + { + "first_name": "Yingqing", + "last_name": "He" + }, + { + "first_name": "Zeyue", + "last_name": "Tian" + }, + { + "first_name": "Xintao", + "last_name": "Wang" + }, + { + "first_name": "Qifeng", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Model Adaptation for Time Constrained Embodied Control", - "authors": "Jaehyun Song, Minjong Yoo, Honguk Woo", + "authors": [ + { + "first_name": "Jaehyun", + "last_name": "Song" + }, + { + "first_name": "Minjong", + "last_name": "Yoo" + }, + { + "first_name": "Honguk", + "last_name": "Woo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Objects as Volumes: A Stochastic Geometry View of Opaque Solids", - "authors": "Bailey Miller, Hanyu Chen, Alice Lai, Ioannis Gkioulekas", + "authors": [ + { + "first_name": "Bailey", + "last_name": "Miller" + }, + { + "first_name": "Hanyu", + "last_name": "Chen" + }, + { + "first_name": "Alice", + "last_name": "Lai" + }, + { + "first_name": "Ioannis", + "last_name": "Gkioulekas" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ActiveDC: Distribution Calibration for Active Finetuning", - "authors": "Wenshuai Xu, Zhenghui Hu, Yu Lu, Jinzhou Meng, Qingjie Liu, Yunhong Wang", + "authors": [ + { + "first_name": "Wenshuai", + "last_name": "Xu" + }, + { + "first_name": "Zhenghui", + "last_name": "Hu" + }, + { + "first_name": "Yu", + "last_name": "Lu" + }, + { + "first_name": "Jinzhou", + "last_name": "Meng" + }, + { + "first_name": "Qingjie", + "last_name": "Liu" + }, + { + "first_name": "Yunhong", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Seeing Unseen: Discover Novel Biomedical Concepts via Geometry-Constrained Probabilistic Modeling", - "authors": "Jianan Fan, Dongnan Liu, Hang Chang, Heng Huang, Mei Chen, Weidong Cai", + "authors": [ + { + "first_name": "Jianan", + "last_name": "Fan" + }, + { + "first_name": "Dongnan", + "last_name": "Liu" + }, + { + "first_name": "Hang", + "last_name": "Chang" + }, + { + "first_name": "Heng", + "last_name": "Huang" + }, + { + "first_name": "Mei", + "last_name": "Chen" + }, + { + "first_name": "Weidong", + "last_name": "Cai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Captures", - "authors": "Zhangyang Xiong, Chenghong Li, Kenkun Liu, Hongjie Liao, Jianqiao Hu, Junyi Zhu, Shuliang Ning, Lingteng Qiu, Chongjie Wang, Shijie Wang, Shuguang Cui, Xiaoguang Han", + "authors": [ + { + "first_name": "Zhangyang", + "last_name": "Xiong" + }, + { + "first_name": "Chenghong", + "last_name": "Li" + }, + { + "first_name": "Kenkun", + "last_name": "Liu" + }, + { + "first_name": "Hongjie", + "last_name": "Liao" + }, + { + "first_name": "Jianqiao", + "last_name": "Hu" + }, + { + "first_name": "Junyi", + "last_name": "Zhu" + }, + { + "first_name": "Shuliang", + "last_name": "Ning" + }, + { + "first_name": "Lingteng", + "last_name": "Qiu" + }, + { + "first_name": "Chongjie", + "last_name": "Wang" + }, + { + "first_name": "Shijie", + "last_name": "Wang" + }, + { + "first_name": "Shuguang", + "last_name": "Cui" + }, + { + "first_name": "Xiaoguang", + "last_name": "Han" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Communication-Efficient Federated Learning with Accelerated Client Gradient", - "authors": "Geeho Kim, Jinkyu Kim, Bohyung Han", + "authors": [ + { + "first_name": "Geeho", + "last_name": "Kim" + }, + { + "first_name": "Jinkyu", + "last_name": "Kim" + }, + { + "first_name": "Bohyung", + "last_name": "Han" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LLMs are Good Action Recognizers", - "authors": "Haoxuan Qu, Yujun Cai, Jun Liu", + "authors": [ + { + "first_name": "Haoxuan", + "last_name": "Qu" + }, + { + "first_name": "Yujun", + "last_name": "Cai" + }, + { + "first_name": "Jun", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "NoiseCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions in Diffusion Models", - "authors": "Yusuf Dalva, Pinar Yanardag", + "authors": [ + { + "first_name": "Yusuf", + "last_name": "Dalva" + }, + { + "first_name": "Pinar", + "last_name": "Yanardag" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SpecNeRF: Gaussian Directional Encoding for Specular Reflections", - "authors": "Li Ma, Vasu Agrawal, Haithem Turki, Changil Kim, Chen Gao, Pedro Sander, Michael Zollhöfer, Christian Richardt", + "authors": [ + { + "first_name": "Li", + "last_name": "Ma" + }, + { + "first_name": "Vasu", + "last_name": "Agrawal" + }, + { + "first_name": "Haithem", + "last_name": "Turki" + }, + { + "first_name": "Changil", + "last_name": "Kim" + }, + { + "first_name": "Chen", + "last_name": "Gao" + }, + { + "first_name": "Pedro", + "last_name": "Sander" + }, + { + "first_name": "Michael", + "last_name": "Zollhöfer" + }, + { + "first_name": "Christian", + "last_name": "Richardt" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Improving Subject-Driven Image Synthesis with Subject-Agnostic Guidance", - "authors": "Kelvin C.K. Chan, Yang Zhao, Xuhui Jia, Ming-Hsuan Yang, Huisheng Wang", + "authors": [ + { + "first_name": "Kelvin", + "last_name": "C.K. Chan" + }, + { + "first_name": "Yang", + "last_name": "Zhao" + }, + { + "first_name": "Xuhui", + "last_name": "Jia" + }, + { + "first_name": "Ming-Hsuan", + "last_name": "Yang" + }, + { + "first_name": "Huisheng", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Diffusion Model Alignment Using Direct Preference Optimization", - "authors": "Bram Wallace, Meihua Dang, Rafael Rafailov, Linqi Zhou, Aaron Lou, Senthil Purushwalkam, Stefano Ermon, Caiming Xiong, Shafiq Joty, Nikhil Naik", + "authors": [ + { + "first_name": "Bram", + "last_name": "Wallace" + }, + { + "first_name": "Meihua", + "last_name": "Dang" + }, + { + "first_name": "Rafael", + "last_name": "Rafailov" + }, + { + "first_name": "Linqi", + "last_name": "Zhou" + }, + { + "first_name": "Aaron", + "last_name": "Lou" + }, + { + "first_name": "Senthil", + "last_name": "Purushwalkam" + }, + { + "first_name": "Stefano", + "last_name": "Ermon" + }, + { + "first_name": "Caiming", + "last_name": "Xiong" + }, + { + "first_name": "Shafiq", + "last_name": "Joty" + }, + { + "first_name": "Nikhil", + "last_name": "Naik" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Interactive Continual Learning: Fast and Slow Thinking", - "authors": "Biqing Qi, Xinquan Chen, Junqi Gao, Dong Li, Jianxing Liu, Ligang Wu, Bowen Zhou", + "authors": [ + { + "first_name": "Biqing", + "last_name": "Qi" + }, + { + "first_name": "Xinquan", + "last_name": "Chen" + }, + { + "first_name": "Junqi", + "last_name": "Gao" + }, + { + "first_name": "Dong", + "last_name": "Li" + }, + { + "first_name": "Jianxing", + "last_name": "Liu" + }, + { + "first_name": "Ligang", + "last_name": "Wu" + }, + { + "first_name": "Bowen", + "last_name": "Zhou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Image", - "authors": "Kyle Sargent, Zizhang Li, Tanmay Shah, Charles Herrmann, Hong-Xing Yu, Yunzhi Zhang, Eric Ryan Chan, Dmitry Lagun, Li Fei-Fei, Deqing Sun, Jiajun Wu", + "authors": [ + { + "first_name": "Kyle", + "last_name": "Sargent" + }, + { + "first_name": "Zizhang", + "last_name": "Li" + }, + { + "first_name": "Tanmay", + "last_name": "Shah" + }, + { + "first_name": "Charles", + "last_name": "Herrmann" + }, + { + "first_name": "Hong-Xing", + "last_name": "Yu" + }, + { + "first_name": "Yunzhi", + "last_name": "Zhang" + }, + { + "first_name": "Eric", + "last_name": "Ryan Chan" + }, + { + "first_name": "Dmitry", + "last_name": "Lagun" + }, + { + "first_name": "Li", + "last_name": "Fei-Fei" + }, + { + "first_name": "Deqing", + "last_name": "Sun" + }, + { + "first_name": "Jiajun", + "last_name": "Wu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Restoration by Generation with Constrained Priors", - "authors": "Zheng Ding, Xuaner Zhang, Zhuowen Tu, Zhihao Xia", + "authors": [ + { + "first_name": "Zheng", + "last_name": "Ding" + }, + { + "first_name": "Xuaner", + "last_name": "Zhang" + }, + { + "first_name": "Zhuowen", + "last_name": "Tu" + }, + { + "first_name": "Zhihao", + "last_name": "Xia" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Snapshot Lidar: Fourier Embedding of Amplitude and Phase for Single-Image Depth Reconstruction", - "authors": "Sarah Friday, Yunzi Shi, Yaswanth Cherivirala, Vishwanath Saragadam, Adithya Pediredla", + "authors": [ + { + "first_name": "Sarah", + "last_name": "Friday" + }, + { + "first_name": "Yunzi", + "last_name": "Shi" + }, + { + "first_name": "Yaswanth", + "last_name": "Cherivirala" + }, + { + "first_name": "Vishwanath", + "last_name": "Saragadam" + }, + { + "first_name": "Adithya", + "last_name": "Pediredla" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Convolutional Prompting meets Language Models for Continual Learning", - "authors": "Anurag Roy, Riddhiman Moulick, Vinay K. Verma, Saptarshi Ghosh, Abir Das", + "authors": [ + { + "first_name": "Anurag", + "last_name": "Roy" + }, + { + "first_name": "Riddhiman", + "last_name": "Moulick" + }, + { + "first_name": "Vinay", + "last_name": "K. Verma" + }, + { + "first_name": "Saptarshi", + "last_name": "Ghosh" + }, + { + "first_name": "Abir", + "last_name": "Das" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Blur-aware Spatio-temporal Sparse Transformer for Video Deblurring", - "authors": "Huicong Zhang, Haozhe Xie, Hongxun Yao", + "authors": [ + { + "first_name": "Huicong", + "last_name": "Zhang" + }, + { + "first_name": "Haozhe", + "last_name": "Xie" + }, + { + "first_name": "Hongxun", + "last_name": "Yao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards Learning a Generalist Model for Embodied Navigation", - "authors": "Duo Zheng, Shijia Huang, Lin Zhao, Yiwu Zhong, Liwei Wang", + "authors": [ + { + "first_name": "Duo", + "last_name": "Zheng" + }, + { + "first_name": "Shijia", + "last_name": "Huang" + }, + { + "first_name": "Lin", + "last_name": "Zhao" + }, + { + "first_name": "Yiwu", + "last_name": "Zhong" + }, + { + "first_name": "Liwei", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DiffusionPoser: Real-time Human Motion Reconstruction From Arbitrary Sparse Sensors Using Autoregressive Diffusion", - "authors": "Tom Van Wouwe, Seunghwan Lee, Antoine Falisse, Scott Delp, C. Karen Liu", + "authors": [ + { + "first_name": "Tom", + "last_name": "Van Wouwe" + }, + { + "first_name": "Seunghwan", + "last_name": "Lee" + }, + { + "first_name": "Antoine", + "last_name": "Falisse" + }, + { + "first_name": "Scott", + "last_name": "Delp" + }, + { + "first_name": "C.", + "last_name": "Karen Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MANUS: Markerless Grasp Capture using Articulated 3D Gaussians", - "authors": "Chandradeep Pokhariya, Ishaan Nikhil Shah, Angela Xing, Zekun Li, Kefan Chen, Avinash Sharma, Srinath Sridhar", + "authors": [ + { + "first_name": "Chandradeep", + "last_name": "Pokhariya" + }, + { + "first_name": "Ishaan", + "last_name": "Nikhil Shah" + }, + { + "first_name": "Angela", + "last_name": "Xing" + }, + { + "first_name": "Zekun", + "last_name": "Li" + }, + { + "first_name": "Kefan", + "last_name": "Chen" + }, + { + "first_name": "Avinash", + "last_name": "Sharma" + }, + { + "first_name": "Srinath", + "last_name": "Sridhar" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Distilling Semantic Priors from SAM to Efficient Image Restoration Models", - "authors": "Quan Zhang, Xiaoyu Liu, Wei Li, Hanting Chen, Junchao Liu, Jie Hu, Zhiwei Xiong, Chun Yuan, Yunhe Wang", + "authors": [ + { + "first_name": "Quan", + "last_name": "Zhang" + }, + { + "first_name": "Xiaoyu", + "last_name": "Liu" + }, + { + "first_name": "Wei", + "last_name": "Li" + }, + { + "first_name": "Hanting", + "last_name": "Chen" + }, + { + "first_name": "Junchao", + "last_name": "Liu" + }, + { + "first_name": "Jie", + "last_name": "Hu" + }, + { + "first_name": "Zhiwei", + "last_name": "Xiong" + }, + { + "first_name": "Chun", + "last_name": "Yuan" + }, + { + "first_name": "Yunhe", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning Intra-view and Cross-view Geometric Knowledge for Stereo Matching", - "authors": "Rui Gong, Weide Liu, Zaiwang Gu, Xulei Yang, Jun Cheng", + "authors": [ + { + "first_name": "Rui", + "last_name": "Gong" + }, + { + "first_name": "Weide", + "last_name": "Liu" + }, + { + "first_name": "Zaiwang", + "last_name": "Gu" + }, + { + "first_name": "Xulei", + "last_name": "Yang" + }, + { + "first_name": "Jun", + "last_name": "Cheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Rethinking the Evaluation Protocol of Domain Generalization", - "authors": "Han Yu, Xingxuan Zhang, Renzhe Xu, Jiashuo Liu, Yue He, Peng Cui", + "authors": [ + { + "first_name": "Han", + "last_name": "Yu" + }, + { + "first_name": "Xingxuan", + "last_name": "Zhang" + }, + { + "first_name": "Renzhe", + "last_name": "Xu" + }, + { + "first_name": "Jiashuo", + "last_name": "Liu" + }, + { + "first_name": "Yue", + "last_name": "He" + }, + { + "first_name": "Peng", + "last_name": "Cui" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Aligning Logits Generatively for Principled Black-Box Knowledge Distillation", - "authors": "Jing Ma, Xiang Xiang, Ke Wang, Yuchuan Wu, Yongbin Li", + "authors": [ + { + "first_name": "Jing", + "last_name": "Ma" + }, + { + "first_name": "Xiang", + "last_name": "Xiang" + }, + { + "first_name": "Ke", + "last_name": "Wang" + }, + { + "first_name": "Yuchuan", + "last_name": "Wu" + }, + { + "first_name": "Yongbin", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "BerfScene: Bev-conditioned Equivariant Radiance Fields for Infinite 3D Scene Generation", - "authors": "Qihang Zhang, Yinghao Xu, Yujun Shen, Bo Dai, Bolei Zhou, Ceyuan Yang", + "authors": [ + { + "first_name": "Qihang", + "last_name": "Zhang" + }, + { + "first_name": "Yinghao", + "last_name": "Xu" + }, + { + "first_name": "Yujun", + "last_name": "Shen" + }, + { + "first_name": "Bo", + "last_name": "Dai" + }, + { + "first_name": "Bolei", + "last_name": "Zhou" + }, + { + "first_name": "Ceyuan", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "3D Facial Expressions through Analysis-by-Neural-Synthesis", - "authors": "George Retsinas, Panagiotis P. Filntisis, Radek Danecek, Victoria F. Abrevaya, Anastasios Roussos, Timo Bolkart, Petros Maragos", + "authors": [ + { + "first_name": "George", + "last_name": "Retsinas" + }, + { + "first_name": "Panagiotis", + "last_name": "P. Filntisis" + }, + { + "first_name": "Radek", + "last_name": "Danecek" + }, + { + "first_name": "Victoria", + "last_name": "F. Abrevaya" + }, + { + "first_name": "Anastasios", + "last_name": "Roussos" + }, + { + "first_name": "Timo", + "last_name": "Bolkart" + }, + { + "first_name": "Petros", + "last_name": "Maragos" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HoloVIC: Large-scale Dataset and Benchmark for Multi-Sensor Holographic Intersection and Vehicle-Infrastructure Cooperative", - "authors": "Cong Ma, Lei Qiao, Chengkai Zhu, Kai Liu, Zelong Kong, Qing Li, Xueqi Zhou, Yuheng Kan, Wei Wu", + "authors": [ + { + "first_name": "Cong", + "last_name": "Ma" + }, + { + "first_name": "Lei", + "last_name": "Qiao" + }, + { + "first_name": "Chengkai", + "last_name": "Zhu" + }, + { + "first_name": "Kai", + "last_name": "Liu" + }, + { + "first_name": "Zelong", + "last_name": "Kong" + }, + { + "first_name": "Qing", + "last_name": "Li" + }, + { + "first_name": "Xueqi", + "last_name": "Zhou" + }, + { + "first_name": "Yuheng", + "last_name": "Kan" + }, + { + "first_name": "Wei", + "last_name": "Wu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Unleashing the Potential of SAM for Medical Adaptation via Hierarchical Decoding", - "authors": "Zhiheng Cheng, Qingyue Wei, Hongru Zhu, Yan Wang, Liangqiong Qu, Wei Shao, Yuyin Zhou", + "authors": [ + { + "first_name": "Zhiheng", + "last_name": "Cheng" + }, + { + "first_name": "Qingyue", + "last_name": "Wei" + }, + { + "first_name": "Hongru", + "last_name": "Zhu" + }, + { + "first_name": "Yan", + "last_name": "Wang" + }, + { + "first_name": "Liangqiong", + "last_name": "Qu" + }, + { + "first_name": "Wei", + "last_name": "Shao" + }, + { + "first_name": "Yuyin", + "last_name": "Zhou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Puff-Net: Efficient Style Transfer with Pure Content and Style Feature Fusion Network", - "authors": "Sizhe Zheng, Pan Gao, Peng Zhou, Jie Qin", + "authors": [ + { + "first_name": "Sizhe", + "last_name": "Zheng" + }, + { + "first_name": "Pan", + "last_name": "Gao" + }, + { + "first_name": "Peng", + "last_name": "Zhou" + }, + { + "first_name": "Jie", + "last_name": "Qin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards Progressive Multi-Frequency Representation for Image Warping", - "authors": "Jun Xiao, Zihang Lyu, Cong Zhang, Yakun Ju, Changjian Shui, Kin-Man Lam", + "authors": [ + { + "first_name": "Jun", + "last_name": "Xiao" + }, + { + "first_name": "Zihang", + "last_name": "Lyu" + }, + { + "first_name": "Cong", + "last_name": "Zhang" + }, + { + "first_name": "Yakun", + "last_name": "Ju" + }, + { + "first_name": "Changjian", + "last_name": "Shui" + }, + { + "first_name": "Kin-Man", + "last_name": "Lam" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning to Control Camera Exposure via Reinforcement Learning", - "authors": "Kyunghyun Lee, Ukcheol Shin, Byeong-Uk Lee", + "authors": [ + { + "first_name": "Kyunghyun", + "last_name": "Lee" + }, + { + "first_name": "Ukcheol", + "last_name": "Shin" + }, + { + "first_name": "Byeong-Uk", + "last_name": "Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Splatter Image: Ultra-Fast Single-View 3D Reconstruction", - "authors": "Stanislaw Szymanowicz, Chrisitian Rupprecht, Andrea Vedaldi", + "authors": [ + { + "first_name": "Stanislaw", + "last_name": "Szymanowicz" + }, + { + "first_name": "Chrisitian", + "last_name": "Rupprecht" + }, + { + "first_name": "Andrea", + "last_name": "Vedaldi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Modeling Collaborator: Enabling Subjective Vision Classification With Minimal Human Effort via LLM Tool-Use", - "authors": "Imad Eddine Toubal, Aditya Avinash, Neil Gordon Alldrin, Jan Dlabal, Wenlei Zhou, Enming Luo, Otilia Stretcu, Hao Xiong, Chun-Ta Lu, Howard Zhou, Ranjay Krishna, Ariel Fuxman, Tom Duerig", + "authors": [ + { + "first_name": "Imad", + "last_name": "Eddine Toubal" + }, + { + "first_name": "Aditya", + "last_name": "Avinash" + }, + { + "first_name": "Neil", + "last_name": "Gordon Alldrin" + }, + { + "first_name": "Jan", + "last_name": "Dlabal" + }, + { + "first_name": "Wenlei", + "last_name": "Zhou" + }, + { + "first_name": "Enming", + "last_name": "Luo" + }, + { + "first_name": "Otilia", + "last_name": "Stretcu" + }, + { + "first_name": "Hao", + "last_name": "Xiong" + }, + { + "first_name": "Chun-Ta", + "last_name": "Lu" + }, + { + "first_name": "Howard", + "last_name": "Zhou" + }, + { + "first_name": "Ranjay", + "last_name": "Krishna" + }, + { + "first_name": "Ariel", + "last_name": "Fuxman" + }, + { + "first_name": "Tom", + "last_name": "Duerig" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "RNb-NeuS: Reflectance and Normal-based Multi-View 3D Reconstruction", - "authors": "Baptiste Brument, Robin Bruneau, Yvain Quéau, Jean Mélou, François Bernard Lauze, Jean-Denis Durou, Lilian Calvet", + "authors": [ + { + "first_name": "Baptiste", + "last_name": "Brument" + }, + { + "first_name": "Robin", + "last_name": "Bruneau" + }, + { + "first_name": "Yvain", + "last_name": "Quéau" + }, + { + "first_name": "Jean", + "last_name": "Mélou" + }, + { + "first_name": "François", + "last_name": "Bernard Lauze" + }, + { + "first_name": "Jean-Denis", + "last_name": "Durou" + }, + { + "first_name": "Lilian", + "last_name": "Calvet" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning", - "authors": "Siyuan Cheng, Guanhong Tao, Yingqi Liu, Guangyu Shen, Shengwei An, Shiwei Feng, Xiangzhe Xu, Kaiyuan Zhang, Shiqing Ma, Xiangyu Zhang", + "authors": [ + { + "first_name": "Siyuan", + "last_name": "Cheng" + }, + { + "first_name": "Guanhong", + "last_name": "Tao" + }, + { + "first_name": "Yingqi", + "last_name": "Liu" + }, + { + "first_name": "Guangyu", + "last_name": "Shen" + }, + { + "first_name": "Shengwei", + "last_name": "An" + }, + { + "first_name": "Shiwei", + "last_name": "Feng" + }, + { + "first_name": "Xiangzhe", + "last_name": "Xu" + }, + { + "first_name": "Kaiyuan", + "last_name": "Zhang" + }, + { + "first_name": "Shiqing", + "last_name": "Ma" + }, + { + "first_name": "Xiangyu", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GeoReF: Geometric Alignment Across Shape Variation for Category-level Object Pose Refinement", - "authors": "Linfang Zheng, Tze Ho Elden Tse, Chen Wang, Yinghan Sun, Hua Chen, Ales Leonardis, Wei Zhang, Hyung Jin Chang", + "authors": [ + { + "first_name": "Linfang", + "last_name": "Zheng" + }, + { + "first_name": "Tze", + "last_name": "Ho Elden Tse" + }, + { + "first_name": "Chen", + "last_name": "Wang" + }, + { + "first_name": "Yinghan", + "last_name": "Sun" + }, + { + "first_name": "Hua", + "last_name": "Chen" + }, + { + "first_name": "Ales", + "last_name": "Leonardis" + }, + { + "first_name": "Wei", + "last_name": "Zhang" + }, + { + "first_name": "Hyung", + "last_name": "Jin Chang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LAN: Learning to Adapt Noise for Image Denoising", - "authors": "Changjin Kim, Tae Hyun Kim, Sungyong Baik", + "authors": [ + { + "first_name": "Changjin", + "last_name": "Kim" + }, + { + "first_name": "Tae", + "last_name": "Hyun Kim" + }, + { + "first_name": "Sungyong", + "last_name": "Baik" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Scaling Up Dynamic Human-Scene Interaction Modeling", - "authors": "Nan Jiang, Zhiyuan Zhang, Hongjie Li, Xiaoxuan Ma, Zan Wang, Yixin Chen, Tengyu Liu, Yixin Zhu, Siyuan Huang", + "authors": [ + { + "first_name": "Nan", + "last_name": "Jiang" + }, + { + "first_name": "Zhiyuan", + "last_name": "Zhang" + }, + { + "first_name": "Hongjie", + "last_name": "Li" + }, + { + "first_name": "Xiaoxuan", + "last_name": "Ma" + }, + { + "first_name": "Zan", + "last_name": "Wang" + }, + { + "first_name": "Yixin", + "last_name": "Chen" + }, + { + "first_name": "Tengyu", + "last_name": "Liu" + }, + { + "first_name": "Yixin", + "last_name": "Zhu" + }, + { + "first_name": "Siyuan", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Semantic-aware SAM for Point-Prompted Instance Segmentation", - "authors": "Zhaoyang Wei, Pengfei Chen, Xuehui Yu, Guorong Li, Jianbin Jiao, Zhenjun Han", + "authors": [ + { + "first_name": "Zhaoyang", + "last_name": "Wei" + }, + { + "first_name": "Pengfei", + "last_name": "Chen" + }, + { + "first_name": "Xuehui", + "last_name": "Yu" + }, + { + "first_name": "Guorong", + "last_name": "Li" + }, + { + "first_name": "Jianbin", + "last_name": "Jiao" + }, + { + "first_name": "Zhenjun", + "last_name": "Han" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning Group Activity Features Through Person Attribute Prediction", - "authors": "Chihiro Nakatani, Hiroaki Kawashima, Norimichi Ukita", + "authors": [ + { + "first_name": "Chihiro", + "last_name": "Nakatani" + }, + { + "first_name": "Hiroaki", + "last_name": "Kawashima" + }, + { + "first_name": "Norimichi", + "last_name": "Ukita" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HUNTER: Unsupervised Human-centric 3D Detection via Transferring Knowledge from Synthetic Instances to Real Scenes", - "authors": "Yichen Yao, Zimo Jiang, Yujing Sun, Zhencai Zhu, Xinge Zhu, Runnan Chen, Yuexin Ma", + "authors": [ + { + "first_name": "Yichen", + "last_name": "Yao" + }, + { + "first_name": "Zimo", + "last_name": "Jiang" + }, + { + "first_name": "Yujing", + "last_name": "Sun" + }, + { + "first_name": "Zhencai", + "last_name": "Zhu" + }, + { + "first_name": "Xinge", + "last_name": "Zhu" + }, + { + "first_name": "Runnan", + "last_name": "Chen" + }, + { + "first_name": "Yuexin", + "last_name": "Ma" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Improving Transferable Targeted Adversarial Attacks with Model Self-Enhancement", - "authors": "Han Wu, Guanyan Ou, Weibin Wu, Zibin Zheng", + "authors": [ + { + "first_name": "Han", + "last_name": "Wu" + }, + { + "first_name": "Guanyan", + "last_name": "Ou" + }, + { + "first_name": "Weibin", + "last_name": "Wu" + }, + { + "first_name": "Zibin", + "last_name": "Zheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Unsupervised Learning of Category-Level 3D Pose from Object-Centric Videos", - "authors": "Leonhard Sommer, Artur Jesslen, Eddy Ilg, Adam Kortylewski", + "authors": [ + { + "first_name": "Leonhard", + "last_name": "Sommer" + }, + { + "first_name": "Artur", + "last_name": "Jesslen" + }, + { + "first_name": "Eddy", + "last_name": "Ilg" + }, + { + "first_name": "Adam", + "last_name": "Kortylewski" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Plug-and-Play Diffusion Distillation", - "authors": "Yi-Ting Hsiao, Siavash Khodadadeh, Kevin Duarte, Wei-An Lin, Hui Qu, Mingi Kwon, Ratheesh Kalarot", + "authors": [ + { + "first_name": "Yi-Ting", + "last_name": "Hsiao" + }, + { + "first_name": "Siavash", + "last_name": "Khodadadeh" + }, + { + "first_name": "Kevin", + "last_name": "Duarte" + }, + { + "first_name": "Wei-An", + "last_name": "Lin" + }, + { + "first_name": "Hui", + "last_name": "Qu" + }, + { + "first_name": "Mingi", + "last_name": "Kwon" + }, + { + "first_name": "Ratheesh", + "last_name": "Kalarot" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MindBridge: A Cross-Subject Brain Decoding Framework", - "authors": "Shizun Wang, Songhua Liu, Zhenxiong Tan, Xinchao Wang", + "authors": [ + { + "first_name": "Shizun", + "last_name": "Wang" + }, + { + "first_name": "Songhua", + "last_name": "Liu" + }, + { + "first_name": "Zhenxiong", + "last_name": "Tan" + }, + { + "first_name": "Xinchao", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Make Pixels Dance: High-Dynamic Video Generation", - "authors": "Yan Zeng, Guoqiang Wei, Jiani Zheng, Jiaxin Zou, Yang Wei, Yuchen Zhang, Hang Li", + "authors": [ + { + "first_name": "Yan", + "last_name": "Zeng" + }, + { + "first_name": "Guoqiang", + "last_name": "Wei" + }, + { + "first_name": "Jiani", + "last_name": "Zheng" + }, + { + "first_name": "Jiaxin", + "last_name": "Zou" + }, + { + "first_name": "Yang", + "last_name": "Wei" + }, + { + "first_name": "Yuchen", + "last_name": "Zhang" + }, + { + "first_name": "Hang", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MM-Narrator: Narrating Long-form Videos with Multimodal In-Context Learning", - "authors": "Chaoyi Zhang, Kevin Lin, Zhengyuan Yang, Jianfeng Wang, Linjie Li, Chung-Ching Lin, Zicheng Liu, Lijuan Wang", + "authors": [ + { + "first_name": "Chaoyi", + "last_name": "Zhang" + }, + { + "first_name": "Kevin", + "last_name": "Lin" + }, + { + "first_name": "Zhengyuan", + "last_name": "Yang" + }, + { + "first_name": "Jianfeng", + "last_name": "Wang" + }, + { + "first_name": "Linjie", + "last_name": "Li" + }, + { + "first_name": "Chung-Ching", + "last_name": "Lin" + }, + { + "first_name": "Zicheng", + "last_name": "Liu" + }, + { + "first_name": "Lijuan", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Morphable Diffusion: 3D-Consistent Diffusion for Single-image Avatar Creation", - "authors": "Xiyi Chen, Marko Mihajlovic, Shaofei Wang, Sergey Prokudin, Siyu Tang", + "authors": [ + { + "first_name": "Xiyi", + "last_name": "Chen" + }, + { + "first_name": "Marko", + "last_name": "Mihajlovic" + }, + { + "first_name": "Shaofei", + "last_name": "Wang" + }, + { + "first_name": "Sergey", + "last_name": "Prokudin" + }, + { + "first_name": "Siyu", + "last_name": "Tang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Fully Convolutional Slice-to-Volume Reconstruction for Single-Stack MRI", - "authors": "Sean I. Young, Yael Balbastre, Bruce Fischl, Polina Golland, Juan Eugenio Iglesias", + "authors": [ + { + "first_name": "Sean", + "last_name": "I. Young" + }, + { + "first_name": "Yael", + "last_name": "Balbastre" + }, + { + "first_name": "Bruce", + "last_name": "Fischl" + }, + { + "first_name": "Polina", + "last_name": "Golland" + }, + { + "first_name": "Juan", + "last_name": "Eugenio Iglesias" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Enhance Image Classification via Inter-Class Image Mixup with Diffusion Model", - "authors": "Zhicai Wang, Longhui Wei, Tan Wang, Heyu Chen, Yanbin Hao, Xiang Wang, Xiangnan He, Qi Tian", + "authors": [ + { + "first_name": "Zhicai", + "last_name": "Wang" + }, + { + "first_name": "Longhui", + "last_name": "Wei" + }, + { + "first_name": "Tan", + "last_name": "Wang" + }, + { + "first_name": "Heyu", + "last_name": "Chen" + }, + { + "first_name": "Yanbin", + "last_name": "Hao" + }, + { + "first_name": "Xiang", + "last_name": "Wang" + }, + { + "first_name": "Xiangnan", + "last_name": "He" + }, + { + "first_name": "Qi", + "last_name": "Tian" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "A&B BNN: Add&Bit-Operation-Only Hardware-Friendly Binary Neural Network", - "authors": "Ruichen Ma, Guanchao Qiao, Yian Liu, Liwei Meng, Ning Ning, Yang Liu, Shaogang Hu", + "authors": [ + { + "first_name": "Ruichen", + "last_name": "Ma" + }, + { + "first_name": "Guanchao", + "last_name": "Qiao" + }, + { + "first_name": "Yian", + "last_name": "Liu" + }, + { + "first_name": "Liwei", + "last_name": "Meng" + }, + { + "first_name": "Ning", + "last_name": "Ning" + }, + { + "first_name": "Yang", + "last_name": "Liu" + }, + { + "first_name": "Shaogang", + "last_name": "Hu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Alpha-CLIP: A CLIP Model Focusing on Wherever You Want", - "authors": "Zeyi Sun, Ye Fang, Tong Wu, Pan Zhang, Yuhang Zang, Shu Kong, Yuanjun Xiong, Dahua Lin, Jiaqi Wang", + "authors": [ + { + "first_name": "Zeyi", + "last_name": "Sun" + }, + { + "first_name": "Ye", + "last_name": "Fang" + }, + { + "first_name": "Tong", + "last_name": "Wu" + }, + { + "first_name": "Pan", + "last_name": "Zhang" + }, + { + "first_name": "Yuhang", + "last_name": "Zang" + }, + { + "first_name": "Shu", + "last_name": "Kong" + }, + { + "first_name": "Yuanjun", + "last_name": "Xiong" + }, + { + "first_name": "Dahua", + "last_name": "Lin" + }, + { + "first_name": "Jiaqi", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FutureHuman3D: Forecasting Complex Long-Term 3D Human Behavior from Video Observations", - "authors": "Christian Diller, Thomas Funkhouser, Angela Dai", + "authors": [ + { + "first_name": "Christian", + "last_name": "Diller" + }, + { + "first_name": "Thomas", + "last_name": "Funkhouser" + }, + { + "first_name": "Angela", + "last_name": "Dai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "NightCC: Nighttime Color Constancy via Adaptive Channel Masking", - "authors": "Shuwei Li, Robby T. Tan", + "authors": [ + { + "first_name": "Shuwei", + "last_name": "Li" + }, + { + "first_name": "Robby", + "last_name": "T. Tan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Task-aligned Part-aware Panoptic Segmentation through Joint Object-Part Representations", - "authors": "Daan de Geus, Gijs Dubbelman", + "authors": [ + { + "first_name": "Daan", + "last_name": "de Geus" + }, + { + "first_name": "Gijs", + "last_name": "Dubbelman" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "From Activation to Initialization: Scaling Insights for Optimizing Neural Fields", - "authors": "Hemanth Saratchandran, Sameera Ramasinghe, Simon Lucey", + "authors": [ + { + "first_name": "Hemanth", + "last_name": "Saratchandran" + }, + { + "first_name": "Sameera", + "last_name": "Ramasinghe" + }, + { + "first_name": "Simon", + "last_name": "Lucey" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "UnScene3D: Unsupervised 3D Instance Segmentation for Indoor Scenes", - "authors": "David Rozenberszki, Or Litany, Angela Dai", + "authors": [ + { + "first_name": "David", + "last_name": "Rozenberszki" + }, + { + "first_name": "Or", + "last_name": "Litany" + }, + { + "first_name": "Angela", + "last_name": "Dai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks", - "authors": "Boheng Li, Yishuo Cai, Haowei Li, Feng Xue, Zhifeng Li, Yiming Li", + "authors": [ + { + "first_name": "Boheng", + "last_name": "Li" + }, + { + "first_name": "Yishuo", + "last_name": "Cai" + }, + { + "first_name": "Haowei", + "last_name": "Li" + }, + { + "first_name": "Feng", + "last_name": "Xue" + }, + { + "first_name": "Zhifeng", + "last_name": "Li" + }, + { + "first_name": "Yiming", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DiffAvatar: Simulation-Ready Garment Optimization with Differentiable Simulation", - "authors": "Yifei Li, Hsiao-yu Chen, Egor Larionov, Nikolaos Sarafianos, Wojciech Matusik, Tuur Stuyck", + "authors": [ + { + "first_name": "Yifei", + "last_name": "Li" + }, + { + "first_name": "Hsiao-yu", + "last_name": "Chen" + }, + { + "first_name": "Egor", + "last_name": "Larionov" + }, + { + "first_name": "Nikolaos", + "last_name": "Sarafianos" + }, + { + "first_name": "Wojciech", + "last_name": "Matusik" + }, + { + "first_name": "Tuur", + "last_name": "Stuyck" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "AlignSAM: Aligning Segment Anything Model to Open Context via Reinforcement Learning", - "authors": "Duojun Huang, Xinyu Xiong, Jie Ma, Jichang Li, Zequn Jie, Lin Ma, Guanbin Li", + "authors": [ + { + "first_name": "Duojun", + "last_name": "Huang" + }, + { + "first_name": "Xinyu", + "last_name": "Xiong" + }, + { + "first_name": "Jie", + "last_name": "Ma" + }, + { + "first_name": "Jichang", + "last_name": "Li" + }, + { + "first_name": "Zequn", + "last_name": "Jie" + }, + { + "first_name": "Lin", + "last_name": "Ma" + }, + { + "first_name": "Guanbin", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "A Simple Recipe for Language-guided Domain Generalized Segmentation", - "authors": "Mohammad Fahes, Tuan-Hung Vu, Andrei Bursuc, Patrick Pérez, Raoul de Charette", + "authors": [ + { + "first_name": "Mohammad", + "last_name": "Fahes" + }, + { + "first_name": "Tuan-Hung", + "last_name": "Vu" + }, + { + "first_name": "Andrei", + "last_name": "Bursuc" + }, + { + "first_name": "Patrick", + "last_name": "Pérez" + }, + { + "first_name": "Raoul", + "last_name": "de Charette" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning Spatial Adaptation and Temporal Coherence in Diffusion Models for Video Super-Resolution", - "authors": "Zhikai Chen, Fuchen Long, Zhaofan Qiu, Ting Yao, Wengang Zhou, Jiebo Luo, Tao Mei", + "authors": [ + { + "first_name": "Zhikai", + "last_name": "Chen" + }, + { + "first_name": "Fuchen", + "last_name": "Long" + }, + { + "first_name": "Zhaofan", + "last_name": "Qiu" + }, + { + "first_name": "Ting", + "last_name": "Yao" + }, + { + "first_name": "Wengang", + "last_name": "Zhou" + }, + { + "first_name": "Jiebo", + "last_name": "Luo" + }, + { + "first_name": "Tao", + "last_name": "Mei" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Multiagent Multitraversal Multimodal Self-Driving: Open MARS Dataset", - "authors": "Yiming Li, Zhiheng Li, Nuo Chen, Moonjun Gong, Zonglin Lyu, Zehong Wang, Peili Jiang, Chen Feng", + "authors": [ + { + "first_name": "Yiming", + "last_name": "Li" + }, + { + "first_name": "Zhiheng", + "last_name": "Li" + }, + { + "first_name": "Nuo", + "last_name": "Chen" + }, + { + "first_name": "Moonjun", + "last_name": "Gong" + }, + { + "first_name": "Zonglin", + "last_name": "Lyu" + }, + { + "first_name": "Zehong", + "last_name": "Wang" + }, + { + "first_name": "Peili", + "last_name": "Jiang" + }, + { + "first_name": "Chen", + "last_name": "Feng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "From Variance to Veracity: Unbundling and Mitigating Gradient Variance in Differentiable Bundle Adjustment Layers", - "authors": "Swaminathan Gurumurthy, Karnik Ram, Bingqing Chen, Zachary Manchester, Zico Kolter", + "authors": [ + { + "first_name": "Swaminathan", + "last_name": "Gurumurthy" + }, + { + "first_name": "Karnik", + "last_name": "Ram" + }, + { + "first_name": "Bingqing", + "last_name": "Chen" + }, + { + "first_name": "Zachary", + "last_name": "Manchester" + }, + { + "first_name": "Zico", + "last_name": "Kolter" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Denoising Point Clouds in Latent Space via Graph Convolution and Invertible Neural Network", - "authors": "Aihua Mao, Biao Yan, Zijing Ma, Ying He", + "authors": [ + { + "first_name": "Aihua", + "last_name": "Mao" + }, + { + "first_name": "Biao", + "last_name": "Yan" + }, + { + "first_name": "Zijing", + "last_name": "Ma" + }, + { + "first_name": "Ying", + "last_name": "He" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ADA-Track: End-to-End Multi-Camera 3D Multi-Object Tracking with Alternating Detection and Association", - "authors": "Shuxiao Ding, Lukas Schneider, Marius Cordts, Juergen Gall", + "authors": [ + { + "first_name": "Shuxiao", + "last_name": "Ding" + }, + { + "first_name": "Lukas", + "last_name": "Schneider" + }, + { + "first_name": "Marius", + "last_name": "Cordts" + }, + { + "first_name": "Juergen", + "last_name": "Gall" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HIR-Diff: Unsupervised Hyperspectral Image Restoration Via Improved Diffusion Models", - "authors": "Li Pang, Xiangyu Rui, Long Cui, Hongzhong Wang, Deyu Meng, Xiangyong Cao", + "authors": [ + { + "first_name": "Li", + "last_name": "Pang" + }, + { + "first_name": "Xiangyu", + "last_name": "Rui" + }, + { + "first_name": "Long", + "last_name": "Cui" + }, + { + "first_name": "Hongzhong", + "last_name": "Wang" + }, + { + "first_name": "Deyu", + "last_name": "Meng" + }, + { + "first_name": "Xiangyong", + "last_name": "Cao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Mind The Edge: Refining Depth Edges in Sparsely-Supervised Monocular Depth Estimation", - "authors": "Lior Talker, Aviad Cohen, Erez Yosef, Alexandra Dana, Michael Dinerstein", + "authors": [ + { + "first_name": "Lior", + "last_name": "Talker" + }, + { + "first_name": "Aviad", + "last_name": "Cohen" + }, + { + "first_name": "Erez", + "last_name": "Yosef" + }, + { + "first_name": "Alexandra", + "last_name": "Dana" + }, + { + "first_name": "Michael", + "last_name": "Dinerstein" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Attention-Driven Training-Free Efficiency Enhancement of Diffusion Models", - "authors": "Hongjie Wang, Difan Liu, Yan Kang, Yijun Li, Zhe Lin, Niraj K. Jha, Yuchen Liu", + "authors": [ + { + "first_name": "Hongjie", + "last_name": "Wang" + }, + { + "first_name": "Difan", + "last_name": "Liu" + }, + { + "first_name": "Yan", + "last_name": "Kang" + }, + { + "first_name": "Yijun", + "last_name": "Li" + }, + { + "first_name": "Zhe", + "last_name": "Lin" + }, + { + "first_name": "Niraj", + "last_name": "K. Jha" + }, + { + "first_name": "Yuchen", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CPR: Retrieval Augmented Generation for Copyright Protection", - "authors": "Aditya Golatkar, Alessandro Achille, Luca Zancato, Yu-Xiang Wang, Ashwin Swaminathan, Stefano Soatto", + "authors": [ + { + "first_name": "Aditya", + "last_name": "Golatkar" + }, + { + "first_name": "Alessandro", + "last_name": "Achille" + }, + { + "first_name": "Luca", + "last_name": "Zancato" + }, + { + "first_name": "Yu-Xiang", + "last_name": "Wang" + }, + { + "first_name": "Ashwin", + "last_name": "Swaminathan" + }, + { + "first_name": "Stefano", + "last_name": "Soatto" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FreeDrag: Feature Dragging for Reliable Point-based Image Editing", - "authors": "Pengyang Ling, Lin Chen, Pan Zhang, Huaian Chen, Yi Jin, Jinjin Zheng", + "authors": [ + { + "first_name": "Pengyang", + "last_name": "Ling" + }, + { + "first_name": "Lin", + "last_name": "Chen" + }, + { + "first_name": "Pan", + "last_name": "Zhang" + }, + { + "first_name": "Huaian", + "last_name": "Chen" + }, + { + "first_name": "Yi", + "last_name": "Jin" + }, + { + "first_name": "Jinjin", + "last_name": "Zheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Image-Text Co-Decomposition for Text-Supervised Semantic Segmentation", - "authors": "Ji-Jia Wu, Andy Chia-Hao Chang, Chieh-Yu Chuang, Chun-Pei Chen, Yu-Lun Liu, Min-Hung Chen, Hou-Ning Hu, Yung-Yu Chuang, Yen-Yu Lin", + "authors": [ + { + "first_name": "Ji-Jia", + "last_name": "Wu" + }, + { + "first_name": "Andy", + "last_name": "Chia-Hao Chang" + }, + { + "first_name": "Chieh-Yu", + "last_name": "Chuang" + }, + { + "first_name": "Chun-Pei", + "last_name": "Chen" + }, + { + "first_name": "Yu-Lun", + "last_name": "Liu" + }, + { + "first_name": "Min-Hung", + "last_name": "Chen" + }, + { + "first_name": "Hou-Ning", + "last_name": "Hu" + }, + { + "first_name": "Yung-Yu", + "last_name": "Chuang" + }, + { + "first_name": "Yen-Yu", + "last_name": "Lin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Orchestrate Latent Expertise: Advancing Online Continual Learning with Multi-Level Supervision and Reverse Self-Distillation", - "authors": "Hongwei Yan, Liyuan Wang, Kaisheng Ma, Yi Zhong", + "authors": [ + { + "first_name": "Hongwei", + "last_name": "Yan" + }, + { + "first_name": "Liyuan", + "last_name": "Wang" + }, + { + "first_name": "Kaisheng", + "last_name": "Ma" + }, + { + "first_name": "Yi", + "last_name": "Zhong" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Vision-and-Language Navigation via Causal Learning", - "authors": "Liuyi Wang, Zongtao He, Ronghao Dang, Mengjiao Shen, Chengju Liu, Qijun Chen", + "authors": [ + { + "first_name": "Liuyi", + "last_name": "Wang" + }, + { + "first_name": "Zongtao", + "last_name": "He" + }, + { + "first_name": "Ronghao", + "last_name": "Dang" + }, + { + "first_name": "Mengjiao", + "last_name": "Shen" + }, + { + "first_name": "Chengju", + "last_name": "Liu" + }, + { + "first_name": "Qijun", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange", - "authors": "Yanhao Wu, Tong Zhang, Wei Ke, Congpei Qiu, Sabine Süsstrunk, Mathieu Salzmann", + "authors": [ + { + "first_name": "Yanhao", + "last_name": "Wu" + }, + { + "first_name": "Tong", + "last_name": "Zhang" + }, + { + "first_name": "Wei", + "last_name": "Ke" + }, + { + "first_name": "Congpei", + "last_name": "Qiu" + }, + { + "first_name": "Sabine", + "last_name": "Süsstrunk" + }, + { + "first_name": "Mathieu", + "last_name": "Salzmann" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Confronting Ambiguity in 6D Object Pose Estimation via Score-Based Diffusion on SE(3)", - "authors": "Tsu-Ching Hsiao, Hao-Wei Chen, Hsuan-Kung Yang, Chun-Yi Lee", + "authors": [ + { + "first_name": "Tsu-Ching", + "last_name": "Hsiao" + }, + { + "first_name": "Hao-Wei", + "last_name": "Chen" + }, + { + "first_name": "Hsuan-Kung", + "last_name": "Yang" + }, + { + "first_name": "Chun-Yi", + "last_name": "Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Visual Anagrams: Generating Multi-View Optical Illusions with Diffusion Models", - "authors": "Daniel Geng, Inbum Park, Andrew Owens", + "authors": [ + { + "first_name": "Daniel", + "last_name": "Geng" + }, + { + "first_name": "Inbum", + "last_name": "Park" + }, + { + "first_name": "Andrew", + "last_name": "Owens" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Unveiling Parts Beyond Objects: Towards Finer-Granularity Referring Expression Segmentation", - "authors": "Wenxuan Wang, Tongtian Yue, Yisi Zhang, Longteng Guo, Xingjian He, Xinlong Wang, Jing Liu", + "authors": [ + { + "first_name": "Wenxuan", + "last_name": "Wang" + }, + { + "first_name": "Tongtian", + "last_name": "Yue" + }, + { + "first_name": "Yisi", + "last_name": "Zhang" + }, + { + "first_name": "Longteng", + "last_name": "Guo" + }, + { + "first_name": "Xingjian", + "last_name": "He" + }, + { + "first_name": "Xinlong", + "last_name": "Wang" + }, + { + "first_name": "Jing", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DiffInDScene: Diffusion-based High-Quality 3D Indoor Scene Generation", - "authors": "Xiaoliang Ju, Zhaoyang Huang, Yijin Li, Guofeng Zhang, Yu Qiao, Hongsheng Li", + "authors": [ + { + "first_name": "Xiaoliang", + "last_name": "Ju" + }, + { + "first_name": "Zhaoyang", + "last_name": "Huang" + }, + { + "first_name": "Yijin", + "last_name": "Li" + }, + { + "first_name": "Guofeng", + "last_name": "Zhang" + }, + { + "first_name": "Yu", + "last_name": "Qiao" + }, + { + "first_name": "Hongsheng", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MAPSeg: Unified Unsupervised Domain Adaptation for Heterogeneous Medical Image Segmentation Based on 3D Masked Autoencoding and Pseudo-Labeling", - "authors": "Xuzhe Zhang, Yuhao Wu, Elsa Angelini, Ang Li, Jia Guo, Jerod M. Rasmussen, Thomas G. O'Connor, Pathik D. Wadhwa, Andrea Parolin Jackowski, Hai Li, Jonathan Posner, Andrew F. Laine, Yun Wang", + "authors": [ + { + "first_name": "Xuzhe", + "last_name": "Zhang" + }, + { + "first_name": "Yuhao", + "last_name": "Wu" + }, + { + "first_name": "Elsa", + "last_name": "Angelini" + }, + { + "first_name": "Ang", + "last_name": "Li" + }, + { + "first_name": "Jia", + "last_name": "Guo" + }, + { + "first_name": "Jerod", + "last_name": "M. Rasmussen" + }, + { + "first_name": "Thomas", + "last_name": "G. O'Connor" + }, + { + "first_name": "Pathik", + "last_name": "D. Wadhwa" + }, + { + "first_name": "Andrea", + "last_name": "Parolin Jackowski" + }, + { + "first_name": "Hai", + "last_name": "Li" + }, + { + "first_name": "Jonathan", + "last_name": "Posner" + }, + { + "first_name": "Andrew", + "last_name": "F. Laine" + }, + { + "first_name": "Yun", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Leveraging Predicate and Triplet Learning for Scene Graph Generation", - "authors": "Jiankai Li, Yunhong Wang, Xiefan Guo, Ruijie Yang, Weixin Li", + "authors": [ + { + "first_name": "Jiankai", + "last_name": "Li" + }, + { + "first_name": "Yunhong", + "last_name": "Wang" + }, + { + "first_name": "Xiefan", + "last_name": "Guo" + }, + { + "first_name": "Ruijie", + "last_name": "Yang" + }, + { + "first_name": "Weixin", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DaReNeRF: Direction-aware Representation for Dynamic Scenes", - "authors": "Ange Lou, Benjamin Planche, Zhongpai Gao, Yamin Li, Tianyu Luan, Hao Ding, Terrence Chen, Jack Noble, Ziyan Wu", + "authors": [ + { + "first_name": "Ange", + "last_name": "Lou" + }, + { + "first_name": "Benjamin", + "last_name": "Planche" + }, + { + "first_name": "Zhongpai", + "last_name": "Gao" + }, + { + "first_name": "Yamin", + "last_name": "Li" + }, + { + "first_name": "Tianyu", + "last_name": "Luan" + }, + { + "first_name": "Hao", + "last_name": "Ding" + }, + { + "first_name": "Terrence", + "last_name": "Chen" + }, + { + "first_name": "Jack", + "last_name": "Noble" + }, + { + "first_name": "Ziyan", + "last_name": "Wu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SfmCAD: Unsupervised CAD Reconstruction by Learning Sketch-based Feature Modeling Operations", - "authors": "Pu Li, Jianwei Guo, Huibin Li, Bedrich Benes, Dong-Ming Yan", + "authors": [ + { + "first_name": "Pu", + "last_name": "Li" + }, + { + "first_name": "Jianwei", + "last_name": "Guo" + }, + { + "first_name": "Huibin", + "last_name": "Li" + }, + { + "first_name": "Bedrich", + "last_name": "Benes" + }, + { + "first_name": "Dong-Ming", + "last_name": "Yan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CoDi-2: In-Context Interleaved and Interactive Any-to-Any Generation", - "authors": "Zineng Tang, Ziyi Yang, Mahmoud Khademi, Yang Liu, Chenguang Zhu, Mohit Bansal", + "authors": [ + { + "first_name": "Zineng", + "last_name": "Tang" + }, + { + "first_name": "Ziyi", + "last_name": "Yang" + }, + { + "first_name": "Mahmoud", + "last_name": "Khademi" + }, + { + "first_name": "Yang", + "last_name": "Liu" + }, + { + "first_name": "Chenguang", + "last_name": "Zhu" + }, + { + "first_name": "Mohit", + "last_name": "Bansal" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Tuning Stable Rank Shrinkage: Aiming at the Overlooked Structural Risk in Fine-tuning", - "authors": "Sicong Shen, Yang Zhou, Bingzheng Wei, Eric I-Chao Chang, Yan Xu", + "authors": [ + { + "first_name": "Sicong", + "last_name": "Shen" + }, + { + "first_name": "Yang", + "last_name": "Zhou" + }, + { + "first_name": "Bingzheng", + "last_name": "Wei" + }, + { + "first_name": "Eric", + "last_name": "I-Chao Chang" + }, + { + "first_name": "Yan", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Differentiable Display Photometric Stereo", - "authors": "Seokjun Choi, Seungwoo Yoon, Giljoo Nam, Seungyong Lee, Seung-Hwan Baek", + "authors": [ + { + "first_name": "Seokjun", + "last_name": "Choi" + }, + { + "first_name": "Seungwoo", + "last_name": "Yoon" + }, + { + "first_name": "Giljoo", + "last_name": "Nam" + }, + { + "first_name": "Seungyong", + "last_name": "Lee" + }, + { + "first_name": "Seung-Hwan", + "last_name": "Baek" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "In-distribution Public Data Synthesis with Diffusion Models for Differentially Private Image Classification", - "authors": "Jinseong Park, Yujin Choi, Jaewook Lee", + "authors": [ + { + "first_name": "Jinseong", + "last_name": "Park" + }, + { + "first_name": "Yujin", + "last_name": "Choi" + }, + { + "first_name": "Jaewook", + "last_name": "Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning Degradation-unaware Representation with Prior-based Latent Transformations for Blind Face Restoration", - "authors": "Lianxin Xie, Csbingbing Zheng, Wen Xue, Le Jiang, Cheng Liu, Si Wu, Hau San Wong", + "authors": [ + { + "first_name": "Lianxin", + "last_name": "Xie" + }, + { + "first_name": "Csbingbing", + "last_name": "Zheng" + }, + { + "first_name": "Wen", + "last_name": "Xue" + }, + { + "first_name": "Le", + "last_name": "Jiang" + }, + { + "first_name": "Cheng", + "last_name": "Liu" + }, + { + "first_name": "Si", + "last_name": "Wu" + }, + { + "first_name": "Hau", + "last_name": "San Wong" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels", - "authors": "Tuo Feng, Wenguan Wang, Fan Ma, Yi Yang", + "authors": [ + { + "first_name": "Tuo", + "last_name": "Feng" + }, + { + "first_name": "Wenguan", + "last_name": "Wang" + }, + { + "first_name": "Fan", + "last_name": "Ma" + }, + { + "first_name": "Yi", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Faces that Speak: Jointly Synthesising Talking Face and Speech from Text", - "authors": "Youngjoon Jang, Ji-Hoon Kim, Junseok Ahn, Doyeop Kwak, Hong-Sun Yang, Yoon-Cheol Ju, Il-Hwan Kim, Byeong-Yeol Kim, Joon Son Chung", + "authors": [ + { + "first_name": "Youngjoon", + "last_name": "Jang" + }, + { + "first_name": "Ji-Hoon", + "last_name": "Kim" + }, + { + "first_name": "Junseok", + "last_name": "Ahn" + }, + { + "first_name": "Doyeop", + "last_name": "Kwak" + }, + { + "first_name": "Hong-Sun", + "last_name": "Yang" + }, + { + "first_name": "Yoon-Cheol", + "last_name": "Ju" + }, + { + "first_name": "Il-Hwan", + "last_name": "Kim" + }, + { + "first_name": "Byeong-Yeol", + "last_name": "Kim" + }, + { + "first_name": "Joon", + "last_name": "Son Chung" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Diversified and Personalized Multi-rater Medical Image Segmentation", - "authors": "Yicheng Wu, Xiangde Luo, Zhe Xu, Xiaoqing Guo, Lie Ju, Zongyuan Ge, Wenjun Liao, Jianfei Cai", + "authors": [ + { + "first_name": "Yicheng", + "last_name": "Wu" + }, + { + "first_name": "Xiangde", + "last_name": "Luo" + }, + { + "first_name": "Zhe", + "last_name": "Xu" + }, + { + "first_name": "Xiaoqing", + "last_name": "Guo" + }, + { + "first_name": "Lie", + "last_name": "Ju" + }, + { + "first_name": "Zongyuan", + "last_name": "Ge" + }, + { + "first_name": "Wenjun", + "last_name": "Liao" + }, + { + "first_name": "Jianfei", + "last_name": "Cai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards Automatic Power Battery Detection: New Challenge Benchmark Dataset and Baseline", - "authors": "Xiaoqi Zhao, Youwei Pang, Zhenyu Chen, Qian Yu, Lihe Zhang, Hanqi Liu, Jiaming Zuo, Huchuan Lu", + "authors": [ + { + "first_name": "Xiaoqi", + "last_name": "Zhao" + }, + { + "first_name": "Youwei", + "last_name": "Pang" + }, + { + "first_name": "Zhenyu", + "last_name": "Chen" + }, + { + "first_name": "Qian", + "last_name": "Yu" + }, + { + "first_name": "Lihe", + "last_name": "Zhang" + }, + { + "first_name": "Hanqi", + "last_name": "Liu" + }, + { + "first_name": "Jiaming", + "last_name": "Zuo" + }, + { + "first_name": "Huchuan", + "last_name": "Lu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "AVFF: Audio-Visual Feature Fusion for Video Deepfake Detection", - "authors": "Trevine Oorloff, Surya Koppisetti, Nicolò Bonettini, Divyaraj Solanki, Ben Colman, Yaser Yacoob, Ali Shahriyari, Gaurav Bharaj", + "authors": [ + { + "first_name": "Trevine", + "last_name": "Oorloff" + }, + { + "first_name": "Surya", + "last_name": "Koppisetti" + }, + { + "first_name": "Nicolò", + "last_name": "Bonettini" + }, + { + "first_name": "Divyaraj", + "last_name": "Solanki" + }, + { + "first_name": "Ben", + "last_name": "Colman" + }, + { + "first_name": "Yaser", + "last_name": "Yacoob" + }, + { + "first_name": "Ali", + "last_name": "Shahriyari" + }, + { + "first_name": "Gaurav", + "last_name": "Bharaj" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Discover and Mitigate Multiple Biased Subgroups in Image Classifiers", - "authors": "Zeliang Zhang, Mingqian Feng, Zhiheng Li, Chenliang Xu", + "authors": [ + { + "first_name": "Zeliang", + "last_name": "Zhang" + }, + { + "first_name": "Mingqian", + "last_name": "Feng" + }, + { + "first_name": "Zhiheng", + "last_name": "Li" + }, + { + "first_name": "Chenliang", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DiffusionRegPose: Enhancing Multi-Person Pose Estimation using a Diffusion-Based End-to-End Regression Approach", - "authors": "Dayi Tan, Hansheng Chen, Wei Tian, Lu Xiong", + "authors": [ + { + "first_name": "Dayi", + "last_name": "Tan" + }, + { + "first_name": "Hansheng", + "last_name": "Chen" + }, + { + "first_name": "Wei", + "last_name": "Tian" + }, + { + "first_name": "Lu", + "last_name": "Xiong" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Memory-Scalable and Simplified Functional Map Learning", - "authors": "Robin Magnet, Maks Ovsjanikov", + "authors": [ + { + "first_name": "Robin", + "last_name": "Magnet" + }, + { + "first_name": "Maks", + "last_name": "Ovsjanikov" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "X-MIC: Cross-Modal Instance Conditioning for Egocentric Action Generalization", - "authors": "Anna Kukleva, Fadime Sener, Edoardo Remelli, Bugra Tekin, Eric Sauser, Bernt Schiele, Shugao Ma", + "authors": [ + { + "first_name": "Anna", + "last_name": "Kukleva" + }, + { + "first_name": "Fadime", + "last_name": "Sener" + }, + { + "first_name": "Edoardo", + "last_name": "Remelli" + }, + { + "first_name": "Bugra", + "last_name": "Tekin" + }, + { + "first_name": "Eric", + "last_name": "Sauser" + }, + { + "first_name": "Bernt", + "last_name": "Schiele" + }, + { + "first_name": "Shugao", + "last_name": "Ma" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ExMap: Leveraging Explainability Heatmaps for Unsupervised Group Robustness to Spurious Correlations", - "authors": "Rwiddhi Chakraborty, Adrian Sletten, Michael C. Kampffmeyer", + "authors": [ + { + "first_name": "Rwiddhi", + "last_name": "Chakraborty" + }, + { + "first_name": "Adrian", + "last_name": "Sletten" + }, + { + "first_name": "Michael", + "last_name": "C. Kampffmeyer" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Gaussian Head Avatar: Ultra High-fidelity Head Avatar via Dynamic Gaussians", - "authors": "Yuelang Xu, Benwang Chen, Zhe Li, Hongwen Zhang, Lizhen Wang, Zerong Zheng, Yebin Liu", + "authors": [ + { + "first_name": "Yuelang", + "last_name": "Xu" + }, + { + "first_name": "Benwang", + "last_name": "Chen" + }, + { + "first_name": "Zhe", + "last_name": "Li" + }, + { + "first_name": "Hongwen", + "last_name": "Zhang" + }, + { + "first_name": "Lizhen", + "last_name": "Wang" + }, + { + "first_name": "Zerong", + "last_name": "Zheng" + }, + { + "first_name": "Yebin", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Stratified Avatar Generation from Sparse Observations", - "authors": "Han Feng, Wenchao Ma, Quankai Gao, Xianwei Zheng, Nan Xue, Huijuan Xu", + "authors": [ + { + "first_name": "Han", + "last_name": "Feng" + }, + { + "first_name": "Wenchao", + "last_name": "Ma" + }, + { + "first_name": "Quankai", + "last_name": "Gao" + }, + { + "first_name": "Xianwei", + "last_name": "Zheng" + }, + { + "first_name": "Nan", + "last_name": "Xue" + }, + { + "first_name": "Huijuan", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning to Segment Referred Objects from Narrated Egocentric Videos", - "authors": "Yuhan Shen, Huiyu Wang, Xitong Yang, Matt Feiszli, Ehsan Elhamifar, Lorenzo Torresani, Effrosyni Mavroudi", + "authors": [ + { + "first_name": "Yuhan", + "last_name": "Shen" + }, + { + "first_name": "Huiyu", + "last_name": "Wang" + }, + { + "first_name": "Xitong", + "last_name": "Yang" + }, + { + "first_name": "Matt", + "last_name": "Feiszli" + }, + { + "first_name": "Ehsan", + "last_name": "Elhamifar" + }, + { + "first_name": "Lorenzo", + "last_name": "Torresani" + }, + { + "first_name": "Effrosyni", + "last_name": "Mavroudi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Rewrite the Stars", - "authors": "Xu Ma, Xiyang Dai, Yue Bai, Yizhou Wang, Yun Fu", + "authors": [ + { + "first_name": "Xu", + "last_name": "Ma" + }, + { + "first_name": "Xiyang", + "last_name": "Dai" + }, + { + "first_name": "Yue", + "last_name": "Bai" + }, + { + "first_name": "Yizhou", + "last_name": "Wang" + }, + { + "first_name": "Yun", + "last_name": "Fu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Images", - "authors": "Chaoqin Huang, Aofan Jiang, Jinghao Feng, Ya Zhang, Xinchao Wang, Yanfeng Wang", + "authors": [ + { + "first_name": "Chaoqin", + "last_name": "Huang" + }, + { + "first_name": "Aofan", + "last_name": "Jiang" + }, + { + "first_name": "Jinghao", + "last_name": "Feng" + }, + { + "first_name": "Ya", + "last_name": "Zhang" + }, + { + "first_name": "Xinchao", + "last_name": "Wang" + }, + { + "first_name": "Yanfeng", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "AV-RIR: Audio-Visual Room Impulse Response Estimation", - "authors": "Anton Ratnarajah, Sreyan Ghosh, Sonal Kumar, Purva Chiniya, Dinesh Manocha", + "authors": [ + { + "first_name": "Anton", + "last_name": "Ratnarajah" + }, + { + "first_name": "Sreyan", + "last_name": "Ghosh" + }, + { + "first_name": "Sonal", + "last_name": "Kumar" + }, + { + "first_name": "Purva", + "last_name": "Chiniya" + }, + { + "first_name": "Dinesh", + "last_name": "Manocha" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Depth-aware Test-Time Training for Zero-shot Video Object Segmentation", - "authors": "Weihuang Liu, Xi Shen, Haolun Li, Xiuli Bi, Bo Liu, Chi-Man Pun, Xiaodong Cun", + "authors": [ + { + "first_name": "Weihuang", + "last_name": "Liu" + }, + { + "first_name": "Xi", + "last_name": "Shen" + }, + { + "first_name": "Haolun", + "last_name": "Li" + }, + { + "first_name": "Xiuli", + "last_name": "Bi" + }, + { + "first_name": "Bo", + "last_name": "Liu" + }, + { + "first_name": "Chi-Man", + "last_name": "Pun" + }, + { + "first_name": "Xiaodong", + "last_name": "Cun" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Dual-Consistency Model Inversion for Non-Exemplar Class Incremental Learning", - "authors": "Zihuan Qiu, Yi Xu, Fanman Meng, Hongliang Li, Linfeng Xu, Qingbo Wu", + "authors": [ + { + "first_name": "Zihuan", + "last_name": "Qiu" + }, + { + "first_name": "Yi", + "last_name": "Xu" + }, + { + "first_name": "Fanman", + "last_name": "Meng" + }, + { + "first_name": "Hongliang", + "last_name": "Li" + }, + { + "first_name": "Linfeng", + "last_name": "Xu" + }, + { + "first_name": "Qingbo", + "last_name": "Wu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "RMem: Restricted Memory Banks Improve Video Object Segmentation", - "authors": "Junbao Zhou, Ziqi Pang, Yu-Xiong Wang", + "authors": [ + { + "first_name": "Junbao", + "last_name": "Zhou" + }, + { + "first_name": "Ziqi", + "last_name": "Pang" + }, + { + "first_name": "Yu-Xiong", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transfomers", - "authors": "Sheng Yang, Jiawang Bai, Kuofeng Gao, Yong Yang, Yiming Li, Shu-Tao Xia", + "authors": [ + { + "first_name": "Sheng", + "last_name": "Yang" + }, + { + "first_name": "Jiawang", + "last_name": "Bai" + }, + { + "first_name": "Kuofeng", + "last_name": "Gao" + }, + { + "first_name": "Yong", + "last_name": "Yang" + }, + { + "first_name": "Yiming", + "last_name": "Li" + }, + { + "first_name": "Shu-Tao", + "last_name": "Xia" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PairDETR : Joint Detection and Association of Human Bodies and Faces", - "authors": "Ammar Ali, Georgii Gaikov, Denis Rybalchenko, Alexander Chigorin, Ivan Laptev, Sergey Zagoruyko", + "authors": [ + { + "first_name": "Ammar", + "last_name": "Ali" + }, + { + "first_name": "Georgii", + "last_name": "Gaikov" + }, + { + "first_name": "Denis", + "last_name": "Rybalchenko" + }, + { + "first_name": "Alexander", + "last_name": "Chigorin" + }, + { + "first_name": "Ivan", + "last_name": "Laptev" + }, + { + "first_name": "Sergey", + "last_name": "Zagoruyko" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PortraitBooth: A Versatile Portrait Model for Fast Identity-preserved Personalization", - "authors": "Xu Peng, Junwei Zhu, Boyuan Jiang, Ying Tai, Donghao Luo, Jiangning Zhang, Wei Lin, Taisong Jin, Chengjie Wang, Rongrong Ji", + "authors": [ + { + "first_name": "Xu", + "last_name": "Peng" + }, + { + "first_name": "Junwei", + "last_name": "Zhu" + }, + { + "first_name": "Boyuan", + "last_name": "Jiang" + }, + { + "first_name": "Ying", + "last_name": "Tai" + }, + { + "first_name": "Donghao", + "last_name": "Luo" + }, + { + "first_name": "Jiangning", + "last_name": "Zhang" + }, + { + "first_name": "Wei", + "last_name": "Lin" + }, + { + "first_name": "Taisong", + "last_name": "Jin" + }, + { + "first_name": "Chengjie", + "last_name": "Wang" + }, + { + "first_name": "Rongrong", + "last_name": "Ji" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learn from View Correlation: An Anchor Enhancement Strategy for Multi-view Clustering", - "authors": "Suyuan Liu, Ke Liang, Zhibin Dong, Siwei Wang, Xihong Yang, Sihang Zhou, En Zhu, Xinwang Liu", + "authors": [ + { + "first_name": "Suyuan", + "last_name": "Liu" + }, + { + "first_name": "Ke", + "last_name": "Liang" + }, + { + "first_name": "Zhibin", + "last_name": "Dong" + }, + { + "first_name": "Siwei", + "last_name": "Wang" + }, + { + "first_name": "Xihong", + "last_name": "Yang" + }, + { + "first_name": "Sihang", + "last_name": "Zhou" + }, + { + "first_name": "En", + "last_name": "Zhu" + }, + { + "first_name": "Xinwang", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentation", - "authors": "Weizhao He, Yang Zhang, Wei Zhuo, Linlin Shen, Jiaqi Yang, Songhe Deng, Liang Sun", + "authors": [ + { + "first_name": "Weizhao", + "last_name": "He" + }, + { + "first_name": "Yang", + "last_name": "Zhang" + }, + { + "first_name": "Wei", + "last_name": "Zhuo" + }, + { + "first_name": "Linlin", + "last_name": "Shen" + }, + { + "first_name": "Jiaqi", + "last_name": "Yang" + }, + { + "first_name": "Songhe", + "last_name": "Deng" + }, + { + "first_name": "Liang", + "last_name": "Sun" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Text2HOI: Text-guided 3D Motion Generation for Hand-Object Interaction", - "authors": "Junuk Cha, Jihyeon Kim, Jae Shin Yoon, Seungryul Baek", + "authors": [ + { + "first_name": "Junuk", + "last_name": "Cha" + }, + { + "first_name": "Jihyeon", + "last_name": "Kim" + }, + { + "first_name": "Jae", + "last_name": "Shin Yoon" + }, + { + "first_name": "Seungryul", + "last_name": "Baek" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Zero-TPrune: Zero-Shot Token Pruning through Leveraging of the Attention Graph in Pre-Trained Transformers", - "authors": "Hongjie Wang, Bhishma Dedhia, Niraj K. Jha", + "authors": [ + { + "first_name": "Hongjie", + "last_name": "Wang" + }, + { + "first_name": "Bhishma", + "last_name": "Dedhia" + }, + { + "first_name": "Niraj", + "last_name": "K. Jha" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Enhancing Visual Continual Learning with Language-Guided Supervision", - "authors": "Bolin Ni, Hongbo Zhao, Chenghao Zhang, Ke Hu, Gaofeng Meng, Zhaoxiang Zhang, Shiming Xiang", + "authors": [ + { + "first_name": "Bolin", + "last_name": "Ni" + }, + { + "first_name": "Hongbo", + "last_name": "Zhao" + }, + { + "first_name": "Chenghao", + "last_name": "Zhang" + }, + { + "first_name": "Ke", + "last_name": "Hu" + }, + { + "first_name": "Gaofeng", + "last_name": "Meng" + }, + { + "first_name": "Zhaoxiang", + "last_name": "Zhang" + }, + { + "first_name": "Shiming", + "last_name": "Xiang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MACE: Mass Concept Erasure in Diffusion Models", - "authors": "Shilin Lu, Zilan Wang, Leyang Li, Yanzhu Liu, Adams Wai-Kin Kong", + "authors": [ + { + "first_name": "Shilin", + "last_name": "Lu" + }, + { + "first_name": "Zilan", + "last_name": "Wang" + }, + { + "first_name": "Leyang", + "last_name": "Li" + }, + { + "first_name": "Yanzhu", + "last_name": "Liu" + }, + { + "first_name": "Adams", + "last_name": "Wai-Kin Kong" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DIBS: Enhancing Dense Video Captioning with Unlabeled Videos via Pseudo Boundary Enrichment and Online Refinement", - "authors": "Hao Wu, Huabin Liu, Yu Qiao, Xiao Sun", + "authors": [ + { + "first_name": "Hao", + "last_name": "Wu" + }, + { + "first_name": "Huabin", + "last_name": "Liu" + }, + { + "first_name": "Yu", + "last_name": "Qiao" + }, + { + "first_name": "Xiao", + "last_name": "Sun" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PeLK: Parameter-efficient Large Kernel ConvNets with Peripheral Convolution", - "authors": "Honghao Chen, Xiangxiang Chu, Yongjian Ren, Xin Zhao, Kaiqi Huang", + "authors": [ + { + "first_name": "Honghao", + "last_name": "Chen" + }, + { + "first_name": "Xiangxiang", + "last_name": "Chu" + }, + { + "first_name": "Yongjian", + "last_name": "Ren" + }, + { + "first_name": "Xin", + "last_name": "Zhao" + }, + { + "first_name": "Kaiqi", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation", - "authors": "Qingping Sun, Yanjun Wang, Ailing Zeng, Wanqi Yin, Chen Wei, Wenjia Wang, Haiyi Mei, Chi-Sing Leung, Ziwei Liu, Lei Yang, Zhongang Cai", + "authors": [ + { + "first_name": "Qingping", + "last_name": "Sun" + }, + { + "first_name": "Yanjun", + "last_name": "Wang" + }, + { + "first_name": "Ailing", + "last_name": "Zeng" + }, + { + "first_name": "Wanqi", + "last_name": "Yin" + }, + { + "first_name": "Chen", + "last_name": "Wei" + }, + { + "first_name": "Wenjia", + "last_name": "Wang" + }, + { + "first_name": "Haiyi", + "last_name": "Mei" + }, + { + "first_name": "Chi-Sing", + "last_name": "Leung" + }, + { + "first_name": "Ziwei", + "last_name": "Liu" + }, + { + "first_name": "Lei", + "last_name": "Yang" + }, + { + "first_name": "Zhongang", + "last_name": "Cai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SOK-Bench: A Situated Video Reasoning Benchmark with Aligned Open-World Knowledge", - "authors": "Andong Wang, Bo Wu, Sunli Chen, Zhenfang Chen, Haotian Guan, Wei-Ning Lee, Li Erran Li, Chuang Gan", + "authors": [ + { + "first_name": "Andong", + "last_name": "Wang" + }, + { + "first_name": "Bo", + "last_name": "Wu" + }, + { + "first_name": "Sunli", + "last_name": "Chen" + }, + { + "first_name": "Zhenfang", + "last_name": "Chen" + }, + { + "first_name": "Haotian", + "last_name": "Guan" + }, + { + "first_name": "Wei-Ning", + "last_name": "Lee" + }, + { + "first_name": "Li", + "last_name": "Erran Li" + }, + { + "first_name": "Chuang", + "last_name": "Gan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LORS: Low-rank Residual Structure for Parameter-Efficient Network Stacking", - "authors": "Jialin Li, Qiang Nie, Weifu Fu, Yuhuan Lin, Guangpin Tao, Yong Liu, Chengjie Wang", + "authors": [ + { + "first_name": "Jialin", + "last_name": "Li" + }, + { + "first_name": "Qiang", + "last_name": "Nie" + }, + { + "first_name": "Weifu", + "last_name": "Fu" + }, + { + "first_name": "Yuhuan", + "last_name": "Lin" + }, + { + "first_name": "Guangpin", + "last_name": "Tao" + }, + { + "first_name": "Yong", + "last_name": "Liu" + }, + { + "first_name": "Chengjie", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Design2Cloth: 3D Cloth Generation from 2D Masks", - "authors": "Jiali Zheng, Rolandos Alexandros Potamias, Stefanos Zafeiriou", + "authors": [ + { + "first_name": "Jiali", + "last_name": "Zheng" + }, + { + "first_name": "Rolandos", + "last_name": "Alexandros Potamias" + }, + { + "first_name": "Stefanos", + "last_name": "Zafeiriou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Multi-modal In-Context Learning Makes an Ego-evolving Scene Text Recognizer", - "authors": "Zhen Zhao, Jingqun Tang, Chunhui Lin, Binghong Wu, Can Huang, Hao Liu, Xin Tan, Zhizhong Zhang, Yuan Xie", + "authors": [ + { + "first_name": "Zhen", + "last_name": "Zhao" + }, + { + "first_name": "Jingqun", + "last_name": "Tang" + }, + { + "first_name": "Chunhui", + "last_name": "Lin" + }, + { + "first_name": "Binghong", + "last_name": "Wu" + }, + { + "first_name": "Can", + "last_name": "Huang" + }, + { + "first_name": "Hao", + "last_name": "Liu" + }, + { + "first_name": "Xin", + "last_name": "Tan" + }, + { + "first_name": "Zhizhong", + "last_name": "Zhang" + }, + { + "first_name": "Yuan", + "last_name": "Xie" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Amodal Completion via Progressive Mixed Context Diffusion", - "authors": "Katherine Xu, Lingzhi Zhang, Jianbo Shi", + "authors": [ + { + "first_name": "Katherine", + "last_name": "Xu" + }, + { + "first_name": "Lingzhi", + "last_name": "Zhang" + }, + { + "first_name": "Jianbo", + "last_name": "Shi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Training Diffusion Models Towards Diverse Image Generation with Reinforcement Learning", - "authors": "Zichen Miao, Jiang Wang, Ze Wang, Zhengyuan Yang, Lijuan Wang, Qiang Qiu, Zicheng Liu", + "authors": [ + { + "first_name": "Zichen", + "last_name": "Miao" + }, + { + "first_name": "Jiang", + "last_name": "Wang" + }, + { + "first_name": "Ze", + "last_name": "Wang" + }, + { + "first_name": "Zhengyuan", + "last_name": "Yang" + }, + { + "first_name": "Lijuan", + "last_name": "Wang" + }, + { + "first_name": "Qiang", + "last_name": "Qiu" + }, + { + "first_name": "Zicheng", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Diffusion 3D Features (Diff3F): Decorating Untextured Shapes with Distilled Semantic Features", - "authors": "Niladri Shekhar Dutt, Sanjeev Muralikrishnan, Niloy J. Mitra", + "authors": [ + { + "first_name": "Niladri", + "last_name": "Shekhar Dutt" + }, + { + "first_name": "Sanjeev", + "last_name": "Muralikrishnan" + }, + { + "first_name": "Niloy", + "last_name": "J. Mitra" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LASIL: Learner-Aware Supervised Imitation Learning For Long-term Microscopic Traffic Simulation", - "authors": "Ke Guo, Zhenwei Miao, Wei Jing, Weiwei Liu, Weizi Li, Dayang Hao, Jia Pan", + "authors": [ + { + "first_name": "Ke", + "last_name": "Guo" + }, + { + "first_name": "Zhenwei", + "last_name": "Miao" + }, + { + "first_name": "Wei", + "last_name": "Jing" + }, + { + "first_name": "Weiwei", + "last_name": "Liu" + }, + { + "first_name": "Weizi", + "last_name": "Li" + }, + { + "first_name": "Dayang", + "last_name": "Hao" + }, + { + "first_name": "Jia", + "last_name": "Pan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Revamping Federated Learning Security from a Defender's Perspective: A Unified Defense with Homomorphic Encrypted Data Space", - "authors": "K Naveen Kumar, Reshmi Mitra, C Krishna Mohan", + "authors": [ + { + "first_name": "K", + "last_name": "Naveen Kumar" + }, + { + "first_name": "Reshmi", + "last_name": "Mitra" + }, + { + "first_name": "C", + "last_name": "Krishna Mohan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "A Dynamic Kernel Prior Model for Unsupervised Blind Image Super-Resolution", - "authors": "Zhixiong Yang, Jingyuan Xia, Shengxi Li, Xinghua Huang, Shuanghui Zhang, Zhen Liu, Yaowen Fu, Yongxiang Liu", + "authors": [ + { + "first_name": "Zhixiong", + "last_name": "Yang" + }, + { + "first_name": "Jingyuan", + "last_name": "Xia" + }, + { + "first_name": "Shengxi", + "last_name": "Li" + }, + { + "first_name": "Xinghua", + "last_name": "Huang" + }, + { + "first_name": "Shuanghui", + "last_name": "Zhang" + }, + { + "first_name": "Zhen", + "last_name": "Liu" + }, + { + "first_name": "Yaowen", + "last_name": "Fu" + }, + { + "first_name": "Yongxiang", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Cinematic Behavior Transfer via NeRF-based Differentiable Filming", - "authors": "Xuekun Jiang, Anyi Rao, Jingbo Wang, Dahua Lin, Bo Dai", + "authors": [ + { + "first_name": "Xuekun", + "last_name": "Jiang" + }, + { + "first_name": "Anyi", + "last_name": "Rao" + }, + { + "first_name": "Jingbo", + "last_name": "Wang" + }, + { + "first_name": "Dahua", + "last_name": "Lin" + }, + { + "first_name": "Bo", + "last_name": "Dai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objects", - "authors": "Abhinav Kumar, Yuliang Guo, Xinyu Huang, Liu Ren, Xiaoming Liu", + "authors": [ + { + "first_name": "Abhinav", + "last_name": "Kumar" + }, + { + "first_name": "Yuliang", + "last_name": "Guo" + }, + { + "first_name": "Xinyu", + "last_name": "Huang" + }, + { + "first_name": "Liu", + "last_name": "Ren" + }, + { + "first_name": "Xiaoming", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Text-Driven Image Editing via Learnable Regions", - "authors": "Yuanze Lin, Yi-Wen Chen, Yi-Hsuan Tsai, Lu Jiang, Ming-Hsuan Yang", + "authors": [ + { + "first_name": "Yuanze", + "last_name": "Lin" + }, + { + "first_name": "Yi-Wen", + "last_name": "Chen" + }, + { + "first_name": "Yi-Hsuan", + "last_name": "Tsai" + }, + { + "first_name": "Lu", + "last_name": "Jiang" + }, + { + "first_name": "Ming-Hsuan", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Relation Rectification in Diffusion Model", - "authors": "Yinwei Wu, Xingyi Yang, Xinchao Wang", + "authors": [ + { + "first_name": "Yinwei", + "last_name": "Wu" + }, + { + "first_name": "Xingyi", + "last_name": "Yang" + }, + { + "first_name": "Xinchao", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "NOPE: Novel Object Pose Estimation from a Single Image", - "authors": "Van Nguyen Nguyen, Thibault Groueix, Georgy Ponimatkin, Yinlin Hu, Renaud Marlet, Mathieu Salzmann, Vincent Lepetit", + "authors": [ + { + "first_name": "Van", + "last_name": "Nguyen Nguyen" + }, + { + "first_name": "Thibault", + "last_name": "Groueix" + }, + { + "first_name": "Georgy", + "last_name": "Ponimatkin" + }, + { + "first_name": "Yinlin", + "last_name": "Hu" + }, + { + "first_name": "Renaud", + "last_name": "Marlet" + }, + { + "first_name": "Mathieu", + "last_name": "Salzmann" + }, + { + "first_name": "Vincent", + "last_name": "Lepetit" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Mocap Everyone Everywhere: Lightweight Motion Capture With Smartwatches and a Head-Mounted Camera", - "authors": "Jiye Lee, Hanbyul Joo", + "authors": [ + { + "first_name": "Jiye", + "last_name": "Lee" + }, + { + "first_name": "Hanbyul", + "last_name": "Joo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Fast ODE-based Sampling for Diffusion Models in Around 5 Steps", - "authors": "Zhenyu Zhou, Defang Chen, Can Wang, Chun Chen", + "authors": [ + { + "first_name": "Zhenyu", + "last_name": "Zhou" + }, + { + "first_name": "Defang", + "last_name": "Chen" + }, + { + "first_name": "Can", + "last_name": "Wang" + }, + { + "first_name": "Chun", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Dual-View Visual Contextualization for Web Navigation", - "authors": "Jihyung Kil, Chan Hee Song, Boyuan Zheng, Xiang Deng, Yu Su, Wei-Lun Chao", + "authors": [ + { + "first_name": "Jihyung", + "last_name": "Kil" + }, + { + "first_name": "Chan", + "last_name": "Hee Song" + }, + { + "first_name": "Boyuan", + "last_name": "Zheng" + }, + { + "first_name": "Xiang", + "last_name": "Deng" + }, + { + "first_name": "Yu", + "last_name": "Su" + }, + { + "first_name": "Wei-Lun", + "last_name": "Chao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Language-driven Grasp Detection", - "authors": "An Dinh Vuong, Minh Nhat Vu, Baoru Huang, Nghia Nguyen, Hieu Le, Thieu Vo, Anh Nguyen", + "authors": [ + { + "first_name": "An", + "last_name": "Dinh Vuong" + }, + { + "first_name": "Minh", + "last_name": "Nhat Vu" + }, + { + "first_name": "Baoru", + "last_name": "Huang" + }, + { + "first_name": "Nghia", + "last_name": "Nguyen" + }, + { + "first_name": "Hieu", + "last_name": "Le" + }, + { + "first_name": "Thieu", + "last_name": "Vo" + }, + { + "first_name": "Anh", + "last_name": "Nguyen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards Modern Image Manipulation Localization: A Large-Scale Dataset and Novel Methods", - "authors": "Chenfan Qu, Yiwu Zhong, Chongyu Liu, Guitao Xu, Dezhi Peng, Fengjun Guo, Lianwen Jin", + "authors": [ + { + "first_name": "Chenfan", + "last_name": "Qu" + }, + { + "first_name": "Yiwu", + "last_name": "Zhong" + }, + { + "first_name": "Chongyu", + "last_name": "Liu" + }, + { + "first_name": "Guitao", + "last_name": "Xu" + }, + { + "first_name": "Dezhi", + "last_name": "Peng" + }, + { + "first_name": "Fengjun", + "last_name": "Guo" + }, + { + "first_name": "Lianwen", + "last_name": "Jin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Mitigating Noisy Correspondence by Geometrical Structure Consistency Learning", - "authors": "Zihua Zhao, Mengxi Chen, Tianjie Dai, Jiangchao Yao, Bo Han, Ya Zhang, Yanfeng Wang", + "authors": [ + { + "first_name": "Zihua", + "last_name": "Zhao" + }, + { + "first_name": "Mengxi", + "last_name": "Chen" + }, + { + "first_name": "Tianjie", + "last_name": "Dai" + }, + { + "first_name": "Jiangchao", + "last_name": "Yao" + }, + { + "first_name": "Bo", + "last_name": "Han" + }, + { + "first_name": "Ya", + "last_name": "Zhang" + }, + { + "first_name": "Yanfeng", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CLiC: Concept Learning in Context", - "authors": "Mehdi Safaee, Aryan Mikaeili, Or Patashnik, Daniel Cohen-Or, Ali Mahdavi-Amiri", + "authors": [ + { + "first_name": "Mehdi", + "last_name": "Safaee" + }, + { + "first_name": "Aryan", + "last_name": "Mikaeili" + }, + { + "first_name": "Or", + "last_name": "Patashnik" + }, + { + "first_name": "Daniel", + "last_name": "Cohen-Or" + }, + { + "first_name": "Ali", + "last_name": "Mahdavi-Amiri" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attention", - "authors": "Mohammad Sadil Khan, Elona Dupont, Sk Aziz Ali, Kseniya Cherenkova, Anis Kacem, Djamila Aouada", + "authors": [ + { + "first_name": "Mohammad", + "last_name": "Sadil Khan" + }, + { + "first_name": "Elona", + "last_name": "Dupont" + }, + { + "first_name": "Sk", + "last_name": "Aziz Ali" + }, + { + "first_name": "Kseniya", + "last_name": "Cherenkova" + }, + { + "first_name": "Anis", + "last_name": "Kacem" + }, + { + "first_name": "Djamila", + "last_name": "Aouada" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Object Recognition as Next Token Prediction", - "authors": "Kaiyu Yue, Bor-Chun Chen, Jonas Geiping, Hengduo Li, Tom Goldstein, Ser-Nam Lim", + "authors": [ + { + "first_name": "Kaiyu", + "last_name": "Yue" + }, + { + "first_name": "Bor-Chun", + "last_name": "Chen" + }, + { + "first_name": "Jonas", + "last_name": "Geiping" + }, + { + "first_name": "Hengduo", + "last_name": "Li" + }, + { + "first_name": "Tom", + "last_name": "Goldstein" + }, + { + "first_name": "Ser-Nam", + "last_name": "Lim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CLIB-FIQA: Face Image Quality Assessment with Confidence Calibration", - "authors": "Fu-Zhao Ou, Chongyi Li, Shiqi Wang, Sam Kwong", + "authors": [ + { + "first_name": "Fu-Zhao", + "last_name": "Ou" + }, + { + "first_name": "Chongyi", + "last_name": "Li" + }, + { + "first_name": "Shiqi", + "last_name": "Wang" + }, + { + "first_name": "Sam", + "last_name": "Kwong" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DVMNet: Computing Relative Pose for Unseen Objects Beyond Hypotheses", - "authors": "Chen Zhao, Tong Zhang, Zheng Dang, Mathieu Salzmann", + "authors": [ + { + "first_name": "Chen", + "last_name": "Zhao" + }, + { + "first_name": "Tong", + "last_name": "Zhang" + }, + { + "first_name": "Zheng", + "last_name": "Dang" + }, + { + "first_name": "Mathieu", + "last_name": "Salzmann" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Transcriptomics-guided Slide Representation Learning in Computational Pathology", - "authors": "Guillaume Jaume, Lukas Oldenburg, Anurag Vaidya, Richard J. Chen, Drew F.K. Williamson, Thomas Peeters, Andrew H. Song, Faisal Mahmood", + "authors": [ + { + "first_name": "Guillaume", + "last_name": "Jaume" + }, + { + "first_name": "Lukas", + "last_name": "Oldenburg" + }, + { + "first_name": "Anurag", + "last_name": "Vaidya" + }, + { + "first_name": "Richard", + "last_name": "J. Chen" + }, + { + "first_name": "Drew", + "last_name": "F.K. Williamson" + }, + { + "first_name": "Thomas", + "last_name": "Peeters" + }, + { + "first_name": "Andrew", + "last_name": "H. Song" + }, + { + "first_name": "Faisal", + "last_name": "Mahmood" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Predicated Diffusion: Predicate Logic-Based Attention Guidance for Text-to-Image Diffusion Models", - "authors": "Kota Sueyoshi, Takashi Matsubara", + "authors": [ + { + "first_name": "Kota", + "last_name": "Sueyoshi" + }, + { + "first_name": "Takashi", + "last_name": "Matsubara" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MuRF: Multi-Baseline Radiance Fields", - "authors": "Haofei Xu, Anpei Chen, Yuedong Chen, Christos Sakaridis, Yulun Zhang, Marc Pollefeys, Andreas Geiger, Fisher Yu", + "authors": [ + { + "first_name": "Haofei", + "last_name": "Xu" + }, + { + "first_name": "Anpei", + "last_name": "Chen" + }, + { + "first_name": "Yuedong", + "last_name": "Chen" + }, + { + "first_name": "Christos", + "last_name": "Sakaridis" + }, + { + "first_name": "Yulun", + "last_name": "Zhang" + }, + { + "first_name": "Marc", + "last_name": "Pollefeys" + }, + { + "first_name": "Andreas", + "last_name": "Geiger" + }, + { + "first_name": "Fisher", + "last_name": "Yu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CLIP-BEVFormer: Enhancing Multi-View Image-Based BEV Detector with Ground Truth Flow", - "authors": "Chenbin Pan, Burhaneddin Yaman, Senem Velipasalar, Liu Ren", + "authors": [ + { + "first_name": "Chenbin", + "last_name": "Pan" + }, + { + "first_name": "Burhaneddin", + "last_name": "Yaman" + }, + { + "first_name": "Senem", + "last_name": "Velipasalar" + }, + { + "first_name": "Liu", + "last_name": "Ren" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CLOVA: A Closed-LOop Visual Assistant with Tool Usage and Update", - "authors": "Zhi Gao, Yuntao Du, Xintong Zhang, Xiaojian Ma, Wenjuan Han, Song-Chun Zhu, Qing Li", + "authors": [ + { + "first_name": "Zhi", + "last_name": "Gao" + }, + { + "first_name": "Yuntao", + "last_name": "Du" + }, + { + "first_name": "Xintong", + "last_name": "Zhang" + }, + { + "first_name": "Xiaojian", + "last_name": "Ma" + }, + { + "first_name": "Wenjuan", + "last_name": "Han" + }, + { + "first_name": "Song-Chun", + "last_name": "Zhu" + }, + { + "first_name": "Qing", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Depth Prompting for Sensor-Agnostic Depth Estimation", - "authors": "Jin-Hwi Park, Chanhwi Jeong, Junoh Lee, Hae-Gon Jeon", + "authors": [ + { + "first_name": "Jin-Hwi", + "last_name": "Park" + }, + { + "first_name": "Chanhwi", + "last_name": "Jeong" + }, + { + "first_name": "Junoh", + "last_name": "Lee" + }, + { + "first_name": "Hae-Gon", + "last_name": "Jeon" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "G3DR: Generative 3D Reconstruction in ImageNet", - "authors": "Pradyumna Reddy, Ismail Elezi, Jiankang Deng", + "authors": [ + { + "first_name": "Pradyumna", + "last_name": "Reddy" + }, + { + "first_name": "Ismail", + "last_name": "Elezi" + }, + { + "first_name": "Jiankang", + "last_name": "Deng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MoML: Online Meta Adaptation for 3D Human Motion Prediction", - "authors": "Xiaoning Sun, Huaijiang Sun, Bin Li, Dong Wei, Weiqing Li, Jianfeng Lu", + "authors": [ + { + "first_name": "Xiaoning", + "last_name": "Sun" + }, + { + "first_name": "Huaijiang", + "last_name": "Sun" + }, + { + "first_name": "Bin", + "last_name": "Li" + }, + { + "first_name": "Dong", + "last_name": "Wei" + }, + { + "first_name": "Weiqing", + "last_name": "Li" + }, + { + "first_name": "Jianfeng", + "last_name": "Lu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CAT-DM: Controllable Accelerated Virtual Try-on with Diffusion Model", - "authors": "Jianhao Zeng, Dan Song, Weizhi Nie, Hongshuo Tian, Tongtong Wang, An-An Liu", + "authors": [ + { + "first_name": "Jianhao", + "last_name": "Zeng" + }, + { + "first_name": "Dan", + "last_name": "Song" + }, + { + "first_name": "Weizhi", + "last_name": "Nie" + }, + { + "first_name": "Hongshuo", + "last_name": "Tian" + }, + { + "first_name": "Tongtong", + "last_name": "Wang" + }, + { + "first_name": "An-An", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Hyperspherical Classification with Dynamic Label-to-Prototype Assignment", - "authors": "Mohammad Saeed Ebrahimi Saadabadi, Ali Dabouei, Sahar Rahimi Malakshan, Nasser M. Nasrabadi", + "authors": [ + { + "first_name": "Mohammad", + "last_name": "Saeed Ebrahimi Saadabadi" + }, + { + "first_name": "Ali", + "last_name": "Dabouei" + }, + { + "first_name": "Sahar", + "last_name": "Rahimi Malakshan" + }, + { + "first_name": "Nasser", + "last_name": "M. Nasrabadi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "VTimeLLM: Empower LLM to Grasp Video Moments", - "authors": "Bin Huang, Xin Wang, Hong Chen, Zihan Song, Wenwu Zhu", + "authors": [ + { + "first_name": "Bin", + "last_name": "Huang" + }, + { + "first_name": "Xin", + "last_name": "Wang" + }, + { + "first_name": "Hong", + "last_name": "Chen" + }, + { + "first_name": "Zihan", + "last_name": "Song" + }, + { + "first_name": "Wenwu", + "last_name": "Zhu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FLHetBench: Benchmarking Device and State Heterogeneity in Federated Learning", - "authors": "Junyuan Zhang, Shuang Zeng, Miao Zhang, Runxi Wang, Feifei Wang, Yuyin Zhou, Paul Pu Liang, Liangqiong Qu", + "authors": [ + { + "first_name": "Junyuan", + "last_name": "Zhang" + }, + { + "first_name": "Shuang", + "last_name": "Zeng" + }, + { + "first_name": "Miao", + "last_name": "Zhang" + }, + { + "first_name": "Runxi", + "last_name": "Wang" + }, + { + "first_name": "Feifei", + "last_name": "Wang" + }, + { + "first_name": "Yuyin", + "last_name": "Zhou" + }, + { + "first_name": "Paul", + "last_name": "Pu Liang" + }, + { + "first_name": "Liangqiong", + "last_name": "Qu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Flattening the Parent Bias: Hierarchical Semantic Segmentation in the Poincare Ball", - "authors": "Simon Weber, Bar?? Zöngür, Nikita Araslanov, Daniel Cremers", + "authors": [ + { + "first_name": "Simon", + "last_name": "Weber" + }, + { + "first_name": "Bar??", + "last_name": "Zöngür" + }, + { + "first_name": "Nikita", + "last_name": "Araslanov" + }, + { + "first_name": "Daniel", + "last_name": "Cremers" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Privacy-Preserving Optics for Enhancing Protection in Face De-Identification", - "authors": "Jhon Lopez, Carlos Hinojosa, Henry Arguello, Bernard Ghanem", + "authors": [ + { + "first_name": "Jhon", + "last_name": "Lopez" + }, + { + "first_name": "Carlos", + "last_name": "Hinojosa" + }, + { + "first_name": "Henry", + "last_name": "Arguello" + }, + { + "first_name": "Bernard", + "last_name": "Ghanem" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SmartRefine: A Scenario-Adaptive Refinement Framework for Efficient Motion Prediction", - "authors": "Yang Zhou, Hao Shao, Letian Wang, Steven L. Waslander, Hongsheng Li, Yu Liu", + "authors": [ + { + "first_name": "Yang", + "last_name": "Zhou" + }, + { + "first_name": "Hao", + "last_name": "Shao" + }, + { + "first_name": "Letian", + "last_name": "Wang" + }, + { + "first_name": "Steven", + "last_name": "L. Waslander" + }, + { + "first_name": "Hongsheng", + "last_name": "Li" + }, + { + "first_name": "Yu", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MVBench: A Comprehensive Multi-modal Video Understanding Benchmark", - "authors": "Kunchang Li, Yali Wang, Yinan He, Yizhuo Li, Yi Wang, Yi Liu, Zun Wang, Jilan Xu, Guo Chen, Ping Luo, Limin Wang, Yu Qiao", + "authors": [ + { + "first_name": "Kunchang", + "last_name": "Li" + }, + { + "first_name": "Yali", + "last_name": "Wang" + }, + { + "first_name": "Yinan", + "last_name": "He" + }, + { + "first_name": "Yizhuo", + "last_name": "Li" + }, + { + "first_name": "Yi", + "last_name": "Wang" + }, + { + "first_name": "Yi", + "last_name": "Liu" + }, + { + "first_name": "Zun", + "last_name": "Wang" + }, + { + "first_name": "Jilan", + "last_name": "Xu" + }, + { + "first_name": "Guo", + "last_name": "Chen" + }, + { + "first_name": "Ping", + "last_name": "Luo" + }, + { + "first_name": "Limin", + "last_name": "Wang" + }, + { + "first_name": "Yu", + "last_name": "Qiao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Multi-Scale Video Anomaly Detection by Multi-Grained Spatio-Temporal Representation Learning", - "authors": "Menghao Zhang, Jingyu Wang, Qi Qi, Haifeng Sun, Zirui Zhuang, Pengfei Ren, Ruilong Ma, Jianxin Liao", + "authors": [ + { + "first_name": "Menghao", + "last_name": "Zhang" + }, + { + "first_name": "Jingyu", + "last_name": "Wang" + }, + { + "first_name": "Qi", + "last_name": "Qi" + }, + { + "first_name": "Haifeng", + "last_name": "Sun" + }, + { + "first_name": "Zirui", + "last_name": "Zhuang" + }, + { + "first_name": "Pengfei", + "last_name": "Ren" + }, + { + "first_name": "Ruilong", + "last_name": "Ma" + }, + { + "first_name": "Jianxin", + "last_name": "Liao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "An Aggregation-Free Federated Learning for Tackling Data Heterogeneity", - "authors": "Yuan Wang, Huazhu Fu, Renuga Kanagavelu, Qingsong Wei, Yong Liu, Rick Siow Mong Goh", + "authors": [ + { + "first_name": "Yuan", + "last_name": "Wang" + }, + { + "first_name": "Huazhu", + "last_name": "Fu" + }, + { + "first_name": "Renuga", + "last_name": "Kanagavelu" + }, + { + "first_name": "Qingsong", + "last_name": "Wei" + }, + { + "first_name": "Yong", + "last_name": "Liu" + }, + { + "first_name": "Rick", + "last_name": "Siow Mong Goh" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Generative Multimodal Models are In-Context Learners", - "authors": "Quan Sun, Yufeng Cui, Xiaosong Zhang, Fan Zhang, Qiying Yu, Yueze Wang, Yongming Rao, Jingjing Liu, Tiejun Huang, Xinlong Wang", + "authors": [ + { + "first_name": "Quan", + "last_name": "Sun" + }, + { + "first_name": "Yufeng", + "last_name": "Cui" + }, + { + "first_name": "Xiaosong", + "last_name": "Zhang" + }, + { + "first_name": "Fan", + "last_name": "Zhang" + }, + { + "first_name": "Qiying", + "last_name": "Yu" + }, + { + "first_name": "Yueze", + "last_name": "Wang" + }, + { + "first_name": "Yongming", + "last_name": "Rao" + }, + { + "first_name": "Jingjing", + "last_name": "Liu" + }, + { + "first_name": "Tiejun", + "last_name": "Huang" + }, + { + "first_name": "Xinlong", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Synergistic Global-space Camera and Human Reconstruction from Videos", - "authors": "Yizhou Zhao, Tuanfeng Yang Wang, Bhiksha Raj, Min Xu, Jimei Yang, Chun-Hao Paul Huang", + "authors": [ + { + "first_name": "Yizhou", + "last_name": "Zhao" + }, + { + "first_name": "Tuanfeng", + "last_name": "Yang Wang" + }, + { + "first_name": "Bhiksha", + "last_name": "Raj" + }, + { + "first_name": "Min", + "last_name": "Xu" + }, + { + "first_name": "Jimei", + "last_name": "Yang" + }, + { + "first_name": "Chun-Hao", + "last_name": "Paul Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Hierarchical Intra-modal Correlation Learning for Label-free 3D Semantic Segmentation", - "authors": "Xin Kang, Lei Chu, Jiahao Li, Xuejin Chen, Yan Lu", + "authors": [ + { + "first_name": "Xin", + "last_name": "Kang" + }, + { + "first_name": "Lei", + "last_name": "Chu" + }, + { + "first_name": "Jiahao", + "last_name": "Li" + }, + { + "first_name": "Xuejin", + "last_name": "Chen" + }, + { + "first_name": "Yan", + "last_name": "Lu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Feature Re-Embedding: Towards Foundation Model-Level Performance in Computational Pathology", - "authors": "Wenhao Tang, Fengtao Zhou, Sheng Huang, Xiang Zhu, Yi Zhang, Bo Liu", + "authors": [ + { + "first_name": "Wenhao", + "last_name": "Tang" + }, + { + "first_name": "Fengtao", + "last_name": "Zhou" + }, + { + "first_name": "Sheng", + "last_name": "Huang" + }, + { + "first_name": "Xiang", + "last_name": "Zhu" + }, + { + "first_name": "Yi", + "last_name": "Zhang" + }, + { + "first_name": "Bo", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DiffSal: Joint Audio and Video Learning for Diffusion Saliency Prediction", - "authors": "Junwen Xiong, Peng Zhang, Tao You, Chuanyue Li, Wei Huang, Yufei Zha", + "authors": [ + { + "first_name": "Junwen", + "last_name": "Xiong" + }, + { + "first_name": "Peng", + "last_name": "Zhang" + }, + { + "first_name": "Tao", + "last_name": "You" + }, + { + "first_name": "Chuanyue", + "last_name": "Li" + }, + { + "first_name": "Wei", + "last_name": "Huang" + }, + { + "first_name": "Yufei", + "last_name": "Zha" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Revisiting Single Image Reflection Removal In the Wild", - "authors": "Yurui Zhu, Xueyang Fu, Peng-Tao Jiang, Hao Zhang, Qibin Sun, Jinwei Chen, Zheng-Jun Zha, Bo Li", + "authors": [ + { + "first_name": "Yurui", + "last_name": "Zhu" + }, + { + "first_name": "Xueyang", + "last_name": "Fu" + }, + { + "first_name": "Peng-Tao", + "last_name": "Jiang" + }, + { + "first_name": "Hao", + "last_name": "Zhang" + }, + { + "first_name": "Qibin", + "last_name": "Sun" + }, + { + "first_name": "Jinwei", + "last_name": "Chen" + }, + { + "first_name": "Zheng-Jun", + "last_name": "Zha" + }, + { + "first_name": "Bo", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "3D Face Reconstruction with the Geometric Guidance of Facial Part Segmentation", - "authors": "Zidu Wang, Xiangyu Zhu, Tianshuo Zhang, Baiqin Wang, Zhen Lei", + "authors": [ + { + "first_name": "Zidu", + "last_name": "Wang" + }, + { + "first_name": "Xiangyu", + "last_name": "Zhu" + }, + { + "first_name": "Tianshuo", + "last_name": "Zhang" + }, + { + "first_name": "Baiqin", + "last_name": "Wang" + }, + { + "first_name": "Zhen", + "last_name": "Lei" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FreeU: Free Lunch in Diffusion U-Net", - "authors": "Chenyang Si, Ziqi Huang, Yuming Jiang, Ziwei Liu", + "authors": [ + { + "first_name": "Chenyang", + "last_name": "Si" + }, + { + "first_name": "Ziqi", + "last_name": "Huang" + }, + { + "first_name": "Yuming", + "last_name": "Jiang" + }, + { + "first_name": "Ziwei", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Text Prompt with Normality Guidance for Weakly Supervised Video Anomaly Detection", - "authors": "Zhiwei Yang, Jing Liu, Peng Wu", + "authors": [ + { + "first_name": "Zhiwei", + "last_name": "Yang" + }, + { + "first_name": "Jing", + "last_name": "Liu" + }, + { + "first_name": "Peng", + "last_name": "Wu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SparseOcc: Rethinking Sparse Latent Representation for Vision-Based Semantic Occupancy Prediction", - "authors": "Pin Tang, Zhongdao Wang, Guoqing Wang, Jilai Zheng, Xiangxuan Ren, Bailan Feng, Chao Ma", + "authors": [ + { + "first_name": "Pin", + "last_name": "Tang" + }, + { + "first_name": "Zhongdao", + "last_name": "Wang" + }, + { + "first_name": "Guoqing", + "last_name": "Wang" + }, + { + "first_name": "Jilai", + "last_name": "Zheng" + }, + { + "first_name": "Xiangxuan", + "last_name": "Ren" + }, + { + "first_name": "Bailan", + "last_name": "Feng" + }, + { + "first_name": "Chao", + "last_name": "Ma" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SinSR: Diffusion-Based Image Super-Resolution in a Single Step", - "authors": "Yufei Wang, Wenhan Yang, Xinyuan Chen, Yaohui Wang, Lanqing Guo, Lap-Pui Chau, Ziwei Liu, Yu Qiao, Alex C. Kot, Bihan Wen", + "authors": [ + { + "first_name": "Yufei", + "last_name": "Wang" + }, + { + "first_name": "Wenhan", + "last_name": "Yang" + }, + { + "first_name": "Xinyuan", + "last_name": "Chen" + }, + { + "first_name": "Yaohui", + "last_name": "Wang" + }, + { + "first_name": "Lanqing", + "last_name": "Guo" + }, + { + "first_name": "Lap-Pui", + "last_name": "Chau" + }, + { + "first_name": "Ziwei", + "last_name": "Liu" + }, + { + "first_name": "Yu", + "last_name": "Qiao" + }, + { + "first_name": "Alex", + "last_name": "C. Kot" + }, + { + "first_name": "Bihan", + "last_name": "Wen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Frequency Decoupling for Motion Magnification via Multi-Level Isomorphic Architecture", - "authors": "Fei Wang, Dan Guo, Kun Li, Zhun Zhong, Meng Wang", + "authors": [ + { + "first_name": "Fei", + "last_name": "Wang" + }, + { + "first_name": "Dan", + "last_name": "Guo" + }, + { + "first_name": "Kun", + "last_name": "Li" + }, + { + "first_name": "Zhun", + "last_name": "Zhong" + }, + { + "first_name": "Meng", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Systematic Comparison of Semi-supervised and Self-supervised Learning for Medical Image Classification", - "authors": "Zhe Huang, Ruijie Jiang, Shuchin Aeron, Michael C. Hughes", + "authors": [ + { + "first_name": "Zhe", + "last_name": "Huang" + }, + { + "first_name": "Ruijie", + "last_name": "Jiang" + }, + { + "first_name": "Shuchin", + "last_name": "Aeron" + }, + { + "first_name": "Michael", + "last_name": "C. Hughes" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ViewDiff: 3D-Consistent Image Generation with Text-to-Image Models", - "authors": "Lukas Höllein, Aljaž Božič, Norman Müller, David Novotny, Hung-Yu Tseng, Christian Richardt, Michael Zollhöfer, Matthias Nießner", + "authors": [ + { + "first_name": "Lukas", + "last_name": "Höllein" + }, + { + "first_name": "Aljaž", + "last_name": "Božič" + }, + { + "first_name": "Norman", + "last_name": "Müller" + }, + { + "first_name": "David", + "last_name": "Novotny" + }, + { + "first_name": "Hung-Yu", + "last_name": "Tseng" + }, + { + "first_name": "Christian", + "last_name": "Richardt" + }, + { + "first_name": "Michael", + "last_name": "Zollhöfer" + }, + { + "first_name": "Matthias", + "last_name": "Nießner" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Hyperbolic Learning with Synthetic Captions for Open-World Detection", - "authors": "Fanjie Kong, Yanbei Chen, Jiarui Cai, Davide Modolo", + "authors": [ + { + "first_name": "Fanjie", + "last_name": "Kong" + }, + { + "first_name": "Yanbei", + "last_name": "Chen" + }, + { + "first_name": "Jiarui", + "last_name": "Cai" + }, + { + "first_name": "Davide", + "last_name": "Modolo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Diffusion Models Without Attention", - "authors": "Jing Nathan Yan, Jiatao Gu, Alexander M. Rush", + "authors": [ + { + "first_name": "Jing", + "last_name": "Nathan Yan" + }, + { + "first_name": "Jiatao", + "last_name": "Gu" + }, + { + "first_name": "Alexander", + "last_name": "M. Rush" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Interpretable Measures of Conceptual Similarity by Complexity-Constrained Descriptive Auto-Encoding", - "authors": "Alessandro Achille, Greg Ver Steeg, Tian Yu Liu, Matthew Trager, Carson Klingenberg, Stefano Soatto", + "authors": [ + { + "first_name": "Alessandro", + "last_name": "Achille" + }, + { + "first_name": "Greg", + "last_name": "Ver Steeg" + }, + { + "first_name": "Tian", + "last_name": "Yu Liu" + }, + { + "first_name": "Matthew", + "last_name": "Trager" + }, + { + "first_name": "Carson", + "last_name": "Klingenberg" + }, + { + "first_name": "Stefano", + "last_name": "Soatto" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Emotional Speech-driven 3D Body Animation via Disentangled Latent Diffusion", - "authors": "Kiran Chhatre, Radek Dan??ek, Nikos Athanasiou, Giorgio Becherini, Christopher Peters, Michael J. Black, Timo Bolkart", + "authors": [ + { + "first_name": "Kiran", + "last_name": "Chhatre" + }, + { + "first_name": "Radek", + "last_name": "Dan??ek" + }, + { + "first_name": "Nikos", + "last_name": "Athanasiou" + }, + { + "first_name": "Giorgio", + "last_name": "Becherini" + }, + { + "first_name": "Christopher", + "last_name": "Peters" + }, + { + "first_name": "Michael", + "last_name": "J. Black" + }, + { + "first_name": "Timo", + "last_name": "Bolkart" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "3D Feature Tracking via Event Camera", - "authors": "Siqi Li, Zhikuan Zhou, Zhou Xue, Yipeng Li, Shaoyi Du, Yue Gao", + "authors": [ + { + "first_name": "Siqi", + "last_name": "Li" + }, + { + "first_name": "Zhikuan", + "last_name": "Zhou" + }, + { + "first_name": "Zhou", + "last_name": "Xue" + }, + { + "first_name": "Yipeng", + "last_name": "Li" + }, + { + "first_name": "Shaoyi", + "last_name": "Du" + }, + { + "first_name": "Yue", + "last_name": "Gao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Retrieval-Augmented Layout Transformer for Content-Aware Layout Generation", - "authors": "Daichi Horita, Naoto Inoue, Kotaro Kikuchi, Kota Yamaguchi, Kiyoharu Aizawa", + "authors": [ + { + "first_name": "Daichi", + "last_name": "Horita" + }, + { + "first_name": "Naoto", + "last_name": "Inoue" + }, + { + "first_name": "Kotaro", + "last_name": "Kikuchi" + }, + { + "first_name": "Kota", + "last_name": "Yamaguchi" + }, + { + "first_name": "Kiyoharu", + "last_name": "Aizawa" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MSU-4S - The Michigan State University Four Seasons Dataset", - "authors": "Daniel Kent, Mohammed Alyaqoub, Xiaohu Lu, Hamed Khatounabadi, Kookjin Sung, Cole Scheller, Alexander Dalat, Asma bin Thabit, Roberto Whitley, Hayder Radha", + "authors": [ + { + "first_name": "Daniel", + "last_name": "Kent" + }, + { + "first_name": "Mohammed", + "last_name": "Alyaqoub" + }, + { + "first_name": "Xiaohu", + "last_name": "Lu" + }, + { + "first_name": "Hamed", + "last_name": "Khatounabadi" + }, + { + "first_name": "Kookjin", + "last_name": "Sung" + }, + { + "first_name": "Cole", + "last_name": "Scheller" + }, + { + "first_name": "Alexander", + "last_name": "Dalat" + }, + { + "first_name": "Asma", + "last_name": "bin Thabit" + }, + { + "first_name": "Roberto", + "last_name": "Whitley" + }, + { + "first_name": "Hayder", + "last_name": "Radha" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Improving Plasticity in Online Continual Learning via Collaborative Learning", - "authors": "Maorong Wang, Nicolas Michel, Ling Xiao, Toshihiko Yamasaki", + "authors": [ + { + "first_name": "Maorong", + "last_name": "Wang" + }, + { + "first_name": "Nicolas", + "last_name": "Michel" + }, + { + "first_name": "Ling", + "last_name": "Xiao" + }, + { + "first_name": "Toshihiko", + "last_name": "Yamasaki" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuning", - "authors": "Jing Shi, Wei Xiong, Zhe Lin, Hyun Joon Jung", + "authors": [ + { + "first_name": "Jing", + "last_name": "Shi" + }, + { + "first_name": "Wei", + "last_name": "Xiong" + }, + { + "first_name": "Zhe", + "last_name": "Lin" + }, + { + "first_name": "Hyun", + "last_name": "Joon Jung" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MaxQ: Multi-Axis Query for N:M Sparsity Network", - "authors": "Jingyang Xiang, Siqi Li, Junhao Chen, Zhuangzhi Chen, Tianxin Huang, Linpeng Peng, Yong Liu", + "authors": [ + { + "first_name": "Jingyang", + "last_name": "Xiang" + }, + { + "first_name": "Siqi", + "last_name": "Li" + }, + { + "first_name": "Junhao", + "last_name": "Chen" + }, + { + "first_name": "Zhuangzhi", + "last_name": "Chen" + }, + { + "first_name": "Tianxin", + "last_name": "Huang" + }, + { + "first_name": "Linpeng", + "last_name": "Peng" + }, + { + "first_name": "Yong", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognition", - "authors": "Anqi Zhu, Qiuhong Ke, Mingming Gong, James Bailey", + "authors": [ + { + "first_name": "Anqi", + "last_name": "Zhu" + }, + { + "first_name": "Qiuhong", + "last_name": "Ke" + }, + { + "first_name": "Mingming", + "last_name": "Gong" + }, + { + "first_name": "James", + "last_name": "Bailey" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SD2Event:Self-supervised Learning of Dynamic Detectors and Contextual Descriptors for Event Cameras", - "authors": "Yuan Gao, Yuqing Zhu, Xinjun Li, Yimin Du, Tianzhu Zhang", + "authors": [ + { + "first_name": "Yuan", + "last_name": "Gao" + }, + { + "first_name": "Yuqing", + "last_name": "Zhu" + }, + { + "first_name": "Xinjun", + "last_name": "Li" + }, + { + "first_name": "Yimin", + "last_name": "Du" + }, + { + "first_name": "Tianzhu", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Composing Object Relations and Attributes for Image-Text Matching", - "authors": "Khoi Pham, Chuong Huynh, Ser-Nam Lim, Abhinav Shrivastava", + "authors": [ + { + "first_name": "Khoi", + "last_name": "Pham" + }, + { + "first_name": "Chuong", + "last_name": "Huynh" + }, + { + "first_name": "Ser-Nam", + "last_name": "Lim" + }, + { + "first_name": "Abhinav", + "last_name": "Shrivastava" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Previously on ... From Recaps to Story Summarization", - "authors": "Aditya Kumar Singh, Dhruv Srivastava, Makarand Tapaswi", + "authors": [ + { + "first_name": "Aditya", + "last_name": "Kumar Singh" + }, + { + "first_name": "Dhruv", + "last_name": "Srivastava" + }, + { + "first_name": "Makarand", + "last_name": "Tapaswi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PaReNeRF: Toward Fast Large-scale Dynamic NeRF with Patch-based Reference", - "authors": "Xiao Tang, Min Yang, Penghui Sun, Hui Li, Yuchao Dai, Feng Zhu, Hojae Lee", + "authors": [ + { + "first_name": "Xiao", + "last_name": "Tang" + }, + { + "first_name": "Min", + "last_name": "Yang" + }, + { + "first_name": "Penghui", + "last_name": "Sun" + }, + { + "first_name": "Hui", + "last_name": "Li" + }, + { + "first_name": "Yuchao", + "last_name": "Dai" + }, + { + "first_name": "Feng", + "last_name": "Zhu" + }, + { + "first_name": "Hojae", + "last_name": "Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration", - "authors": "Qinghao Ye, Haiyang Xu, Jiabo Ye, Ming Yan, Anwen Hu, Haowei Liu, Qi Qian, Ji Zhang, Fei Huang", + "authors": [ + { + "first_name": "Qinghao", + "last_name": "Ye" + }, + { + "first_name": "Haiyang", + "last_name": "Xu" + }, + { + "first_name": "Jiabo", + "last_name": "Ye" + }, + { + "first_name": "Ming", + "last_name": "Yan" + }, + { + "first_name": "Anwen", + "last_name": "Hu" + }, + { + "first_name": "Haowei", + "last_name": "Liu" + }, + { + "first_name": "Qi", + "last_name": "Qian" + }, + { + "first_name": "Ji", + "last_name": "Zhang" + }, + { + "first_name": "Fei", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Spectral and Polarization Vision: Spectro-polarimetric Real-world Dataset", - "authors": "Yujin Jeon, Eunsue Choi, Youngchan Kim, Yunseong Moon, Khalid Omer, Felix Heide, Seung-Hwan Baek", + "authors": [ + { + "first_name": "Yujin", + "last_name": "Jeon" + }, + { + "first_name": "Eunsue", + "last_name": "Choi" + }, + { + "first_name": "Youngchan", + "last_name": "Kim" + }, + { + "first_name": "Yunseong", + "last_name": "Moon" + }, + { + "first_name": "Khalid", + "last_name": "Omer" + }, + { + "first_name": "Felix", + "last_name": "Heide" + }, + { + "first_name": "Seung-Hwan", + "last_name": "Baek" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning by Correction: Efficient Tuning Task for Zero-Shot Generative Vision-Language Reasoning", - "authors": "Rongjie Li, Yu Wu, Xuming He", + "authors": [ + { + "first_name": "Rongjie", + "last_name": "Li" + }, + { + "first_name": "Yu", + "last_name": "Wu" + }, + { + "first_name": "Xuming", + "last_name": "He" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Supervised Anomaly Detection for Complex Industrial Images", - "authors": "Aimira Baitieva, David Hurych, Victor Besnier, Olivier Bernard", + "authors": [ + { + "first_name": "Aimira", + "last_name": "Baitieva" + }, + { + "first_name": "David", + "last_name": "Hurych" + }, + { + "first_name": "Victor", + "last_name": "Besnier" + }, + { + "first_name": "Olivier", + "last_name": "Bernard" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships", - "authors": "Sebastian Koch, Narunas Vaskevicius, Mirco Colosi, Pedro Hermosilla, Timo Ropinski", + "authors": [ + { + "first_name": "Sebastian", + "last_name": "Koch" + }, + { + "first_name": "Narunas", + "last_name": "Vaskevicius" + }, + { + "first_name": "Mirco", + "last_name": "Colosi" + }, + { + "first_name": "Pedro", + "last_name": "Hermosilla" + }, + { + "first_name": "Timo", + "last_name": "Ropinski" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SURE: SUrvey REcipes for building reliable and robust deep networks", - "authors": "Yuting Li, Yingyi Chen, Xuanlong Yu, Dexiong Chen, Xi Shen", + "authors": [ + { + "first_name": "Yuting", + "last_name": "Li" + }, + { + "first_name": "Yingyi", + "last_name": "Chen" + }, + { + "first_name": "Xuanlong", + "last_name": "Yu" + }, + { + "first_name": "Dexiong", + "last_name": "Chen" + }, + { + "first_name": "Xi", + "last_name": "Shen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PolarRec: Improving Radio Interferometric Data Reconstruction Using Polar Coordinates", - "authors": "Ruoqi Wang, Zhuoyang Chen, Jiayi Zhu, Qiong Luo, Feng Wang", + "authors": [ + { + "first_name": "Ruoqi", + "last_name": "Wang" + }, + { + "first_name": "Zhuoyang", + "last_name": "Chen" + }, + { + "first_name": "Jiayi", + "last_name": "Zhu" + }, + { + "first_name": "Qiong", + "last_name": "Luo" + }, + { + "first_name": "Feng", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Affine Equivariant Networks Based on Differential Invariants", - "authors": "Yikang Li, Yeqing Qiu, Yuxuan Chen, Lingshen He, Zhouchen Lin", + "authors": [ + { + "first_name": "Yikang", + "last_name": "Li" + }, + { + "first_name": "Yeqing", + "last_name": "Qiu" + }, + { + "first_name": "Yuxuan", + "last_name": "Chen" + }, + { + "first_name": "Lingshen", + "last_name": "He" + }, + { + "first_name": "Zhouchen", + "last_name": "Lin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Selectively Informative Description can Reduce Undesired Embedding Entanglements in Text-to-Image Personalization", - "authors": "Jimyeong Kim, Jungwon Park, Wonjong Rhee", + "authors": [ + { + "first_name": "Jimyeong", + "last_name": "Kim" + }, + { + "first_name": "Jungwon", + "last_name": "Park" + }, + { + "first_name": "Wonjong", + "last_name": "Rhee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Summarize the Past to Predict the Future: Natural Language Descriptions of Context Boost Multimodal Object Interaction Anticipation", - "authors": "Razvan-George Pasca, Alexey Gavryushin, Muhammad Hamza, Yen-Ling Kuo, Kaichun Mo, Luc Van Gool, Otmar Hilliges, Xi Wang", + "authors": [ + { + "first_name": "Razvan-George", + "last_name": "Pasca" + }, + { + "first_name": "Alexey", + "last_name": "Gavryushin" + }, + { + "first_name": "Muhammad", + "last_name": "Hamza" + }, + { + "first_name": "Yen-Ling", + "last_name": "Kuo" + }, + { + "first_name": "Kaichun", + "last_name": "Mo" + }, + { + "first_name": "Luc", + "last_name": "Van Gool" + }, + { + "first_name": "Otmar", + "last_name": "Hilliges" + }, + { + "first_name": "Xi", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Transfer CLIP for Generalizable Image Denoising", - "authors": "Jun Cheng, Dong Liang, Shan Tan", + "authors": [ + { + "first_name": "Jun", + "last_name": "Cheng" + }, + { + "first_name": "Dong", + "last_name": "Liang" + }, + { + "first_name": "Shan", + "last_name": "Tan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models", - "authors": "Jiayi Guo, Xingqian Xu, Yifan Pu, Zanlin Ni, Chaofei Wang, Manushree Vasu, Shiji Song, Gao Huang, Humphrey Shi", + "authors": [ + { + "first_name": "Jiayi", + "last_name": "Guo" + }, + { + "first_name": "Xingqian", + "last_name": "Xu" + }, + { + "first_name": "Yifan", + "last_name": "Pu" + }, + { + "first_name": "Zanlin", + "last_name": "Ni" + }, + { + "first_name": "Chaofei", + "last_name": "Wang" + }, + { + "first_name": "Manushree", + "last_name": "Vasu" + }, + { + "first_name": "Shiji", + "last_name": "Song" + }, + { + "first_name": "Gao", + "last_name": "Huang" + }, + { + "first_name": "Humphrey", + "last_name": "Shi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards CLIP-driven Language-free 3D Visual Grounding via 2D-3D Relational Enhancement and Consistency", - "authors": "Yuqi Zhang, Han Luo, Yinjie Lei", + "authors": [ + { + "first_name": "Yuqi", + "last_name": "Zhang" + }, + { + "first_name": "Han", + "last_name": "Luo" + }, + { + "first_name": "Yinjie", + "last_name": "Lei" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Optimal Transport Aggregation for Visual Place Recognition", - "authors": "Sergio Izquierdo, Javier Civera", + "authors": [ + { + "first_name": "Sergio", + "last_name": "Izquierdo" + }, + { + "first_name": "Javier", + "last_name": "Civera" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FlowIE: Efficient Image Enhancement via Rectified Flow", - "authors": "Yixuan Zhu, Wenliang Zhao, Ao Li, Yansong Tang, Jie Zhou, Jiwen Lu", + "authors": [ + { + "first_name": "Yixuan", + "last_name": "Zhu" + }, + { + "first_name": "Wenliang", + "last_name": "Zhao" + }, + { + "first_name": "Ao", + "last_name": "Li" + }, + { + "first_name": "Yansong", + "last_name": "Tang" + }, + { + "first_name": "Jie", + "last_name": "Zhou" + }, + { + "first_name": "Jiwen", + "last_name": "Lu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Aligning and Prompting Everything All at Once for Universal Visual Perception", - "authors": "Yunhang Shen, Chaoyou Fu, Peixian Chen, Mengdan Zhang, Ke Li, Xing Sun, Yunsheng Wu, Shaohui Lin, Rongrong Ji", + "authors": [ + { + "first_name": "Yunhang", + "last_name": "Shen" + }, + { + "first_name": "Chaoyou", + "last_name": "Fu" + }, + { + "first_name": "Peixian", + "last_name": "Chen" + }, + { + "first_name": "Mengdan", + "last_name": "Zhang" + }, + { + "first_name": "Ke", + "last_name": "Li" + }, + { + "first_name": "Xing", + "last_name": "Sun" + }, + { + "first_name": "Yunsheng", + "last_name": "Wu" + }, + { + "first_name": "Shaohui", + "last_name": "Lin" + }, + { + "first_name": "Rongrong", + "last_name": "Ji" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Correlation-Decoupled Knowledge Distillation for Multimodal Sentiment Analysis with Incomplete Modalities", - "authors": "Mingcheng Li, Dingkang Yang, Xiao Zhao, Shuaibing Wang, Yan Wang, Kun Yang, Mingyang Sun, Dongliang Kou, Ziyun Qian, Lihua Zhang", + "authors": [ + { + "first_name": "Mingcheng", + "last_name": "Li" + }, + { + "first_name": "Dingkang", + "last_name": "Yang" + }, + { + "first_name": "Xiao", + "last_name": "Zhao" + }, + { + "first_name": "Shuaibing", + "last_name": "Wang" + }, + { + "first_name": "Yan", + "last_name": "Wang" + }, + { + "first_name": "Kun", + "last_name": "Yang" + }, + { + "first_name": "Mingyang", + "last_name": "Sun" + }, + { + "first_name": "Dongliang", + "last_name": "Kou" + }, + { + "first_name": "Ziyun", + "last_name": "Qian" + }, + { + "first_name": "Lihua", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Revisiting Adversarial Training at Scale", - "authors": "Zeyu Wang, Xianhang Li, Hongru Zhu, Cihang Xie", + "authors": [ + { + "first_name": "Zeyu", + "last_name": "Wang" + }, + { + "first_name": "Xianhang", + "last_name": "Li" + }, + { + "first_name": "Hongru", + "last_name": "Zhu" + }, + { + "first_name": "Cihang", + "last_name": "Xie" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards Fairness-Aware Adversarial Learning", - "authors": "Yanghao Zhang, Tianle Zhang, Ronghui Mu, Xiaowei Huang, Wenjie Ruan", + "authors": [ + { + "first_name": "Yanghao", + "last_name": "Zhang" + }, + { + "first_name": "Tianle", + "last_name": "Zhang" + }, + { + "first_name": "Ronghui", + "last_name": "Mu" + }, + { + "first_name": "Xiaowei", + "last_name": "Huang" + }, + { + "first_name": "Wenjie", + "last_name": "Ruan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LoSh: Long-Short Text Joint Prediction Network for Referring Video Object Segmentation", - "authors": "Linfeng Yuan, Miaojing Shi, Zijie Yue, Qijun Chen", + "authors": [ + { + "first_name": "Linfeng", + "last_name": "Yuan" + }, + { + "first_name": "Miaojing", + "last_name": "Shi" + }, + { + "first_name": "Zijie", + "last_name": "Yue" + }, + { + "first_name": "Qijun", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MirageRoom: 3D Scene Segmentation with 2D Pre-trained Models by Mirage Projection", - "authors": "Haowen Sun, Yueqi Duan, Juncheng Yan, Yifan Liu, Jiwen Lu", + "authors": [ + { + "first_name": "Haowen", + "last_name": "Sun" + }, + { + "first_name": "Yueqi", + "last_name": "Duan" + }, + { + "first_name": "Juncheng", + "last_name": "Yan" + }, + { + "first_name": "Yifan", + "last_name": "Liu" + }, + { + "first_name": "Jiwen", + "last_name": "Lu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "In2SET: Intra-Inter Similarity Exploiting Transformer for Dual-Camera Compressive Hyperspectral Imaging", - "authors": "Xin Wang, Lizhi Wang, Xiangtian Ma, Maoqing Zhang, Lin Zhu, Hua Huang", + "authors": [ + { + "first_name": "Xin", + "last_name": "Wang" + }, + { + "first_name": "Lizhi", + "last_name": "Wang" + }, + { + "first_name": "Xiangtian", + "last_name": "Ma" + }, + { + "first_name": "Maoqing", + "last_name": "Zhang" + }, + { + "first_name": "Lin", + "last_name": "Zhu" + }, + { + "first_name": "Hua", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Dual Prototype Attention for Unsupervised Video Object Segmentation", - "authors": "Suhwan Cho, Minhyeok Lee, Seunghoon Lee, Dogyoon Lee, Heeseung Choi, Ig-Jae Kim, Sangyoun Lee", + "authors": [ + { + "first_name": "Suhwan", + "last_name": "Cho" + }, + { + "first_name": "Minhyeok", + "last_name": "Lee" + }, + { + "first_name": "Seunghoon", + "last_name": "Lee" + }, + { + "first_name": "Dogyoon", + "last_name": "Lee" + }, + { + "first_name": "Heeseung", + "last_name": "Choi" + }, + { + "first_name": "Ig-Jae", + "last_name": "Kim" + }, + { + "first_name": "Sangyoun", + "last_name": "Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Look-Up Table Compression for Efficient Image Restoration", - "authors": "Yinglong Li, Jiacheng Li, Zhiwei Xiong", + "authors": [ + { + "first_name": "Yinglong", + "last_name": "Li" + }, + { + "first_name": "Jiacheng", + "last_name": "Li" + }, + { + "first_name": "Zhiwei", + "last_name": "Xiong" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "TextNeRF: A Novel Scene-Text Image Synthesis Method based on Neural Radiance Fields", - "authors": "Jialei Cui, Jianwei Du, Wenzhuo Liu, Zhouhui Lian", + "authors": [ + { + "first_name": "Jialei", + "last_name": "Cui" + }, + { + "first_name": "Jianwei", + "last_name": "Du" + }, + { + "first_name": "Wenzhuo", + "last_name": "Liu" + }, + { + "first_name": "Zhouhui", + "last_name": "Lian" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Dr.Hair: Reconstructing Scalp-Connected Hair Strands without Pre-Training via Differentiable Rendering of Line Segments", - "authors": "Yusuke Takimoto, Hikari Takehara, Hiroyuki Sato, Zihao Zhu, Bo Zheng", + "authors": [ + { + "first_name": "Yusuke", + "last_name": "Takimoto" + }, + { + "first_name": "Hikari", + "last_name": "Takehara" + }, + { + "first_name": "Hiroyuki", + "last_name": "Sato" + }, + { + "first_name": "Zihao", + "last_name": "Zhu" + }, + { + "first_name": "Bo", + "last_name": "Zheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Improving Training Efficiency of Diffusion Models via Multi-Stage Framework and Tailored Multi-Decoder Architecture", - "authors": "Huijie Zhang, Yifu Lu, Ismail Alkhouri, Saiprasad Ravishankar, Dogyoon Song, Qing Qu", + "authors": [ + { + "first_name": "Huijie", + "last_name": "Zhang" + }, + { + "first_name": "Yifu", + "last_name": "Lu" + }, + { + "first_name": "Ismail", + "last_name": "Alkhouri" + }, + { + "first_name": "Saiprasad", + "last_name": "Ravishankar" + }, + { + "first_name": "Dogyoon", + "last_name": "Song" + }, + { + "first_name": "Qing", + "last_name": "Qu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "In-Context Matting", - "authors": "He Guo, Zixuan Ye, Zhiguo Cao, Hao Lu", + "authors": [ + { + "first_name": "He", + "last_name": "Guo" + }, + { + "first_name": "Zixuan", + "last_name": "Ye" + }, + { + "first_name": "Zhiguo", + "last_name": "Cao" + }, + { + "first_name": "Hao", + "last_name": "Lu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Navigate Beyond Shortcuts: Debiased Learning Through the Lens of Neural Collapse", - "authors": "Yining Wang, Junjie Sun, Chenyue Wang, Mi Zhang, Min Yang", + "authors": [ + { + "first_name": "Yining", + "last_name": "Wang" + }, + { + "first_name": "Junjie", + "last_name": "Sun" + }, + { + "first_name": "Chenyue", + "last_name": "Wang" + }, + { + "first_name": "Mi", + "last_name": "Zhang" + }, + { + "first_name": "Min", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DiVa-360: The Dynamic Visual Dataset for Immersive Neural Fields", - "authors": "Cheng-You Lu, Peisen Zhou, Angela Xing, Chandradeep Pokhariya, Arnab Dey, Ishaan Nikhil Shah, Rugved Mavidipalli, Dylan Hu, Andrew I. Comport, Kefan Chen, Srinath Sridhar", + "authors": [ + { + "first_name": "Cheng-You", + "last_name": "Lu" + }, + { + "first_name": "Peisen", + "last_name": "Zhou" + }, + { + "first_name": "Angela", + "last_name": "Xing" + }, + { + "first_name": "Chandradeep", + "last_name": "Pokhariya" + }, + { + "first_name": "Arnab", + "last_name": "Dey" + }, + { + "first_name": "Ishaan", + "last_name": "Nikhil Shah" + }, + { + "first_name": "Rugved", + "last_name": "Mavidipalli" + }, + { + "first_name": "Dylan", + "last_name": "Hu" + }, + { + "first_name": "Andrew", + "last_name": "I. Comport" + }, + { + "first_name": "Kefan", + "last_name": "Chen" + }, + { + "first_name": "Srinath", + "last_name": "Sridhar" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "A Subspace-Constrained Tyler's Estimator and its Applications to Structure from Motion", - "authors": "Feng Yu, Teng Zhang, Gilad Lerman", + "authors": [ + { + "first_name": "Feng", + "last_name": "Yu" + }, + { + "first_name": "Teng", + "last_name": "Zhang" + }, + { + "first_name": "Gilad", + "last_name": "Lerman" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FSC: Few-point Shape Completion", - "authors": "Xianzu Wu, Xianfeng Wu, Tianyu Luan, Yajing Bai, Zhongyuan Lai, Junsong Yuan", + "authors": [ + { + "first_name": "Xianzu", + "last_name": "Wu" + }, + { + "first_name": "Xianfeng", + "last_name": "Wu" + }, + { + "first_name": "Tianyu", + "last_name": "Luan" + }, + { + "first_name": "Yajing", + "last_name": "Bai" + }, + { + "first_name": "Zhongyuan", + "last_name": "Lai" + }, + { + "first_name": "Junsong", + "last_name": "Yuan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CAD: Photorealistic 3D Generation via Adversarial Distillation", - "authors": "Ziyu Wan, Despoina Paschalidou, Ian Huang, Hongyu Liu, Bokui Shen, Xiaoyu Xiang, Jing Liao, Leonidas Guibas", + "authors": [ + { + "first_name": "Ziyu", + "last_name": "Wan" + }, + { + "first_name": "Despoina", + "last_name": "Paschalidou" + }, + { + "first_name": "Ian", + "last_name": "Huang" + }, + { + "first_name": "Hongyu", + "last_name": "Liu" + }, + { + "first_name": "Bokui", + "last_name": "Shen" + }, + { + "first_name": "Xiaoyu", + "last_name": "Xiang" + }, + { + "first_name": "Jing", + "last_name": "Liao" + }, + { + "first_name": "Leonidas", + "last_name": "Guibas" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Enhancing Vision-Language Pre-training with Rich Supervisions", - "authors": "Yuan Gao, Kunyu Shi, Pengkai Zhu, Edouard Belval, Oren Nuriel, Srikar Appalaraju, Shabnam Ghadar, Zhuowen Tu, Vijay Mahadevan, Stefano Soatto", + "authors": [ + { + "first_name": "Yuan", + "last_name": "Gao" + }, + { + "first_name": "Kunyu", + "last_name": "Shi" + }, + { + "first_name": "Pengkai", + "last_name": "Zhu" + }, + { + "first_name": "Edouard", + "last_name": "Belval" + }, + { + "first_name": "Oren", + "last_name": "Nuriel" + }, + { + "first_name": "Srikar", + "last_name": "Appalaraju" + }, + { + "first_name": "Shabnam", + "last_name": "Ghadar" + }, + { + "first_name": "Zhuowen", + "last_name": "Tu" + }, + { + "first_name": "Vijay", + "last_name": "Mahadevan" + }, + { + "first_name": "Stefano", + "last_name": "Soatto" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "T-VSL: Text-Guided Visual Sound Source Localization in Mixtures", - "authors": "Tanvir Mahmud, Yapeng Tian, Diana Marculescu", + "authors": [ + { + "first_name": "Tanvir", + "last_name": "Mahmud" + }, + { + "first_name": "Yapeng", + "last_name": "Tian" + }, + { + "first_name": "Diana", + "last_name": "Marculescu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DemoCaricature: Democratising Caricature Generation with a Rough Sketch", - "authors": "Dar-Yen Chen, Ayan Kumar Bhunia, Subhadeep Koley, Aneeshan Sain, Pinaki Nath Chowdhury, Yi-Zhe Song", + "authors": [ + { + "first_name": "Dar-Yen", + "last_name": "Chen" + }, + { + "first_name": "Ayan", + "last_name": "Kumar Bhunia" + }, + { + "first_name": "Subhadeep", + "last_name": "Koley" + }, + { + "first_name": "Aneeshan", + "last_name": "Sain" + }, + { + "first_name": "Pinaki", + "last_name": "Nath Chowdhury" + }, + { + "first_name": "Yi-Zhe", + "last_name": "Song" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CapHuman: Capture Your Moments in Parallel Universes", - "authors": "Chao Liang, Fan Ma, Linchao Zhu, Yingying Deng, Yi Yang", + "authors": [ + { + "first_name": "Chao", + "last_name": "Liang" + }, + { + "first_name": "Fan", + "last_name": "Ma" + }, + { + "first_name": "Linchao", + "last_name": "Zhu" + }, + { + "first_name": "Yingying", + "last_name": "Deng" + }, + { + "first_name": "Yi", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SDPose: Tokenized Pose Estimation via Circulation-Guide Self-Distillation", - "authors": "Sichen Chen, Yingyi Zhang, Siming Huang, Ran Yi, Ke Fan, Ruixin Zhang, Peixian Chen, Jun Wang, Shouhong Ding, Lizhuang Ma", + "authors": [ + { + "first_name": "Sichen", + "last_name": "Chen" + }, + { + "first_name": "Yingyi", + "last_name": "Zhang" + }, + { + "first_name": "Siming", + "last_name": "Huang" + }, + { + "first_name": "Ran", + "last_name": "Yi" + }, + { + "first_name": "Ke", + "last_name": "Fan" + }, + { + "first_name": "Ruixin", + "last_name": "Zhang" + }, + { + "first_name": "Peixian", + "last_name": "Chen" + }, + { + "first_name": "Jun", + "last_name": "Wang" + }, + { + "first_name": "Shouhong", + "last_name": "Ding" + }, + { + "first_name": "Lizhuang", + "last_name": "Ma" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Authentic Hand Avatar from a Phone Scan via Universal Hand Model", - "authors": "Gyeongsik Moon, Weipeng Xu, Rohan Joshi, Chenglei Wu, Takaaki Shiratori", + "authors": [ + { + "first_name": "Gyeongsik", + "last_name": "Moon" + }, + { + "first_name": "Weipeng", + "last_name": "Xu" + }, + { + "first_name": "Rohan", + "last_name": "Joshi" + }, + { + "first_name": "Chenglei", + "last_name": "Wu" + }, + { + "first_name": "Takaaki", + "last_name": "Shiratori" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "VCoder: Versatile Vision Encoders for Multimodal Large Language Models", - "authors": "Jitesh Jain, Jianwei Yang, Humphrey Shi", + "authors": [ + { + "first_name": "Jitesh", + "last_name": "Jain" + }, + { + "first_name": "Jianwei", + "last_name": "Yang" + }, + { + "first_name": "Humphrey", + "last_name": "Shi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Event-based Visible and Infrared Fusion via Multi-task Collaboration", - "authors": "Mengyue Geng, Lin Zhu, Lizhi Wang, Wei Zhang, Ruiqin Xiong, Yonghong Tian", + "authors": [ + { + "first_name": "Mengyue", + "last_name": "Geng" + }, + { + "first_name": "Lin", + "last_name": "Zhu" + }, + { + "first_name": "Lizhi", + "last_name": "Wang" + }, + { + "first_name": "Wei", + "last_name": "Zhang" + }, + { + "first_name": "Ruiqin", + "last_name": "Xiong" + }, + { + "first_name": "Yonghong", + "last_name": "Tian" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Open-World Semantic Segmentation Including Class Similarity", - "authors": "Matteo Sodano, Federico Magistri, Lucas Nunes, Jens Behley, Cyrill Stachniss", + "authors": [ + { + "first_name": "Matteo", + "last_name": "Sodano" + }, + { + "first_name": "Federico", + "last_name": "Magistri" + }, + { + "first_name": "Lucas", + "last_name": "Nunes" + }, + { + "first_name": "Jens", + "last_name": "Behley" + }, + { + "first_name": "Cyrill", + "last_name": "Stachniss" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene Understanding", - "authors": "Jihan Yang, Runyu Ding, Weipeng Deng, Zhe Wang, Xiaojuan Qi", + "authors": [ + { + "first_name": "Jihan", + "last_name": "Yang" + }, + { + "first_name": "Runyu", + "last_name": "Ding" + }, + { + "first_name": "Weipeng", + "last_name": "Deng" + }, + { + "first_name": "Zhe", + "last_name": "Wang" + }, + { + "first_name": "Xiaojuan", + "last_name": "Qi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Adaptive VIO: Deep Visual-Inertial Odometry with Online Continual Learning", - "authors": "Youqi Pan, Wugen Zhou, Yingdian Cao, Hongbin Zha", + "authors": [ + { + "first_name": "Youqi", + "last_name": "Pan" + }, + { + "first_name": "Wugen", + "last_name": "Zhou" + }, + { + "first_name": "Yingdian", + "last_name": "Cao" + }, + { + "first_name": "Hongbin", + "last_name": "Zha" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards Memorization-Free Diffusion Models", - "authors": "Chen Chen, Daochang Liu, Chang Xu", + "authors": [ + { + "first_name": "Chen", + "last_name": "Chen" + }, + { + "first_name": "Daochang", + "last_name": "Liu" + }, + { + "first_name": "Chang", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Generalized Large-Scale Data Condensation via Various Backbone and Statistical Matching", - "authors": "Shitong Shao, Zeyuan Yin, Muxin Zhou, Xindong Zhang, Zhiqiang Shen", + "authors": [ + { + "first_name": "Shitong", + "last_name": "Shao" + }, + { + "first_name": "Zeyuan", + "last_name": "Yin" + }, + { + "first_name": "Muxin", + "last_name": "Zhou" + }, + { + "first_name": "Xindong", + "last_name": "Zhang" + }, + { + "first_name": "Zhiqiang", + "last_name": "Shen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Three Pillars Improving Vision Foundation Model Distillation for Lidar", - "authors": "Gilles Puy, Spyros Gidaris, Alexandre Boulch, Oriane Siméoni, Corentin Sautier, Patrick Pérez, Andrei Bursuc, Renaud Marlet", + "authors": [ + { + "first_name": "Gilles", + "last_name": "Puy" + }, + { + "first_name": "Spyros", + "last_name": "Gidaris" + }, + { + "first_name": "Alexandre", + "last_name": "Boulch" + }, + { + "first_name": "Oriane", + "last_name": "Siméoni" + }, + { + "first_name": "Corentin", + "last_name": "Sautier" + }, + { + "first_name": "Patrick", + "last_name": "Pérez" + }, + { + "first_name": "Andrei", + "last_name": "Bursuc" + }, + { + "first_name": "Renaud", + "last_name": "Marlet" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "On Train-Test Class Overlap and Detection for Image Retrieval", - "authors": "Chull Hwan Song, Jooyoung Yoon, Taebaek Hwang, Shunghyun Choi, Yeong Hyeon Gu, Yannis Avrithis", + "authors": [ + { + "first_name": "Chull", + "last_name": "Hwan Song" + }, + { + "first_name": "Jooyoung", + "last_name": "Yoon" + }, + { + "first_name": "Taebaek", + "last_name": "Hwang" + }, + { + "first_name": "Shunghyun", + "last_name": "Choi" + }, + { + "first_name": "Yeong", + "last_name": "Hyeon Gu" + }, + { + "first_name": "Yannis", + "last_name": "Avrithis" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "AttriHuman-3D: Editable 3D Human Avatar Generation with Attribute Decomposition and Indexing", - "authors": "Fan Yang, Tianyi Chen, Xiaosheng He, Zhongang Cai, Lei Yang, Si Wu, Guosheng Lin", + "authors": [ + { + "first_name": "Fan", + "last_name": "Yang" + }, + { + "first_name": "Tianyi", + "last_name": "Chen" + }, + { + "first_name": "Xiaosheng", + "last_name": "He" + }, + { + "first_name": "Zhongang", + "last_name": "Cai" + }, + { + "first_name": "Lei", + "last_name": "Yang" + }, + { + "first_name": "Si", + "last_name": "Wu" + }, + { + "first_name": "Guosheng", + "last_name": "Lin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "IQ-VFI: Implicit Quadratic Motion Estimation for Video Frame Interpolation", - "authors": "Mengshun Hu, Kui Jiang, Zhihang Zhong, Zheng Wang, Yinqiang Zheng", + "authors": [ + { + "first_name": "Mengshun", + "last_name": "Hu" + }, + { + "first_name": "Kui", + "last_name": "Jiang" + }, + { + "first_name": "Zhihang", + "last_name": "Zhong" + }, + { + "first_name": "Zheng", + "last_name": "Wang" + }, + { + "first_name": "Yinqiang", + "last_name": "Zheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "KeyPoint Relative Position Encoding for Face Recognition", - "authors": "Minchul Kim, Yiyang Su, Feng Liu, Anil Jain, Xiaoming Liu", + "authors": [ + { + "first_name": "Minchul", + "last_name": "Kim" + }, + { + "first_name": "Yiyang", + "last_name": "Su" + }, + { + "first_name": "Feng", + "last_name": "Liu" + }, + { + "first_name": "Anil", + "last_name": "Jain" + }, + { + "first_name": "Xiaoming", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Hyper-MD: Mesh Denoising with Customized Parameters Aware of Noise Intensity and Geometric Characteristics", - "authors": "Xingtao Wang, Hongliang Wei, Xiaopeng Fan, Debin Zhao", + "authors": [ + { + "first_name": "Xingtao", + "last_name": "Wang" + }, + { + "first_name": "Hongliang", + "last_name": "Wei" + }, + { + "first_name": "Xiaopeng", + "last_name": "Fan" + }, + { + "first_name": "Debin", + "last_name": "Zhao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning Object State Changes in Videos: An Open-World Perspective", - "authors": "Zihui Xue, Kumar Ashutosh, Kristen Grauman", + "authors": [ + { + "first_name": "Zihui", + "last_name": "Xue" + }, + { + "first_name": "Kumar", + "last_name": "Ashutosh" + }, + { + "first_name": "Kristen", + "last_name": "Grauman" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Beyond First-Order Tweedie: Solving Inverse Problems using Latent Diffusion", - "authors": "Litu Rout, Yujia Chen, Abhishek Kumar, Constantine Caramanis, Sanjay Shakkottai, Wen-Sheng Chu", + "authors": [ + { + "first_name": "Litu", + "last_name": "Rout" + }, + { + "first_name": "Yujia", + "last_name": "Chen" + }, + { + "first_name": "Abhishek", + "last_name": "Kumar" + }, + { + "first_name": "Constantine", + "last_name": "Caramanis" + }, + { + "first_name": "Sanjay", + "last_name": "Shakkottai" + }, + { + "first_name": "Wen-Sheng", + "last_name": "Chu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Rethinking the Objectives of Vector-Quantized Tokenizers for Image Synthesis", - "authors": "Yuchao Gu, Xintao Wang, Yixiao Ge, Ying Shan, Mike Zheng Shou", + "authors": [ + { + "first_name": "Yuchao", + "last_name": "Gu" + }, + { + "first_name": "Xintao", + "last_name": "Wang" + }, + { + "first_name": "Yixiao", + "last_name": "Ge" + }, + { + "first_name": "Ying", + "last_name": "Shan" + }, + { + "first_name": "Mike", + "last_name": "Zheng Shou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ShapeWalk: Compositional Shape Editing Through Language-Guided Chains", - "authors": "Habib Slim, Mohamed Elhoseiny", + "authors": [ + { + "first_name": "Habib", + "last_name": "Slim" + }, + { + "first_name": "Mohamed", + "last_name": "Elhoseiny" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MESA: Matching Everything by Segmenting Anything", - "authors": "Yesheng Zhang, Xu Zhao", + "authors": [ + { + "first_name": "Yesheng", + "last_name": "Zhang" + }, + { + "first_name": "Xu", + "last_name": "Zhao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning Degradation-Independent Representations for Camera ISP Pipelines", - "authors": "Yanhui Guo, Fangzhou Luo, Xiaolin Wu", + "authors": [ + { + "first_name": "Yanhui", + "last_name": "Guo" + }, + { + "first_name": "Fangzhou", + "last_name": "Luo" + }, + { + "first_name": "Xiaolin", + "last_name": "Wu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SCoFT: Self-Contrastive Fine-Tuning for Equitable Image Generation", - "authors": "Zhixuan Liu, Peter Schaldenbrand, Beverley-Claire Okogwu, Wenxuan Peng, Youngsik Yun, Andrew Hundt, Jihie Kim, Jean Oh", + "authors": [ + { + "first_name": "Zhixuan", + "last_name": "Liu" + }, + { + "first_name": "Peter", + "last_name": "Schaldenbrand" + }, + { + "first_name": "Beverley-Claire", + "last_name": "Okogwu" + }, + { + "first_name": "Wenxuan", + "last_name": "Peng" + }, + { + "first_name": "Youngsik", + "last_name": "Yun" + }, + { + "first_name": "Andrew", + "last_name": "Hundt" + }, + { + "first_name": "Jihie", + "last_name": "Kim" + }, + { + "first_name": "Jean", + "last_name": "Oh" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Continuous Pose for Monocular Cameras in Neural Implicit Representation", - "authors": "Qi Ma, Danda Pani Paudel, Ajad Chhatkuli, Luc Van Gool", + "authors": [ + { + "first_name": "Qi", + "last_name": "Ma" + }, + { + "first_name": "Danda", + "last_name": "Pani Paudel" + }, + { + "first_name": "Ajad", + "last_name": "Chhatkuli" + }, + { + "first_name": "Luc", + "last_name": "Van Gool" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "OmniGlue: Generalizable Feature Matching with Foundation Model Guidance", - "authors": "Hanwen Jiang, Arjun Karpur, Bingyi Cao, Qixing Huang, André Araujo", + "authors": [ + { + "first_name": "Hanwen", + "last_name": "Jiang" + }, + { + "first_name": "Arjun", + "last_name": "Karpur" + }, + { + "first_name": "Bingyi", + "last_name": "Cao" + }, + { + "first_name": "Qixing", + "last_name": "Huang" + }, + { + "first_name": "André", + "last_name": "Araujo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "D^4: Dataset Distillation via Disentangled Diffusion Model", - "authors": "Duo Su, Junjie Hou, Weizhi Gao, Yingjie Tian, Bowen Tang", + "authors": [ + { + "first_name": "Duo", + "last_name": "Su" + }, + { + "first_name": "Junjie", + "last_name": "Hou" + }, + { + "first_name": "Weizhi", + "last_name": "Gao" + }, + { + "first_name": "Yingjie", + "last_name": "Tian" + }, + { + "first_name": "Bowen", + "last_name": "Tang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "OmniSDF: Scene Reconstruction using Omnidirectional Signed Distance Functions and Adaptive Binoctrees", - "authors": "Hakyeong Kim, Andreas Meuleman, Hyeonjoong Jang, James Tompkin, Min H. Kim", + "authors": [ + { + "first_name": "Hakyeong", + "last_name": "Kim" + }, + { + "first_name": "Andreas", + "last_name": "Meuleman" + }, + { + "first_name": "Hyeonjoong", + "last_name": "Jang" + }, + { + "first_name": "James", + "last_name": "Tompkin" + }, + { + "first_name": "Min", + "last_name": "H. Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Generating Content for HDR Deghosting from Frequency View", - "authors": "Tao Hu, Qingsen Yan, Yuankai Qi, Yanning Zhang", + "authors": [ + { + "first_name": "Tao", + "last_name": "Hu" + }, + { + "first_name": "Qingsen", + "last_name": "Yan" + }, + { + "first_name": "Yuankai", + "last_name": "Qi" + }, + { + "first_name": "Yanning", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Iterated Learning Improves Compositionality in Large Vision-Language Models", - "authors": "Chenhao Zheng, Jieyu Zhang, Aniruddha Kembhavi, Ranjay Krishna", + "authors": [ + { + "first_name": "Chenhao", + "last_name": "Zheng" + }, + { + "first_name": "Jieyu", + "last_name": "Zhang" + }, + { + "first_name": "Aniruddha", + "last_name": "Kembhavi" + }, + { + "first_name": "Ranjay", + "last_name": "Krishna" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Event Stream-based Visual Object Tracking: A High-Resolution Benchmark Dataset and A Novel Baseline", - "authors": "Xiao Wang, Shiao Wang, Chuanming Tang, Lin Zhu, Bo Jiang, Yonghong Tian, Jin Tang", + "authors": [ + { + "first_name": "Xiao", + "last_name": "Wang" + }, + { + "first_name": "Shiao", + "last_name": "Wang" + }, + { + "first_name": "Chuanming", + "last_name": "Tang" + }, + { + "first_name": "Lin", + "last_name": "Zhu" + }, + { + "first_name": "Bo", + "last_name": "Jiang" + }, + { + "first_name": "Yonghong", + "last_name": "Tian" + }, + { + "first_name": "Jin", + "last_name": "Tang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LiDAR-Net: A Real-scanned 3D Point Cloud Dataset for Indoor Scenes", - "authors": "Yanwen Guo, Yuanqi Li, Dayong Ren, Xiaohong Zhang, Jiawei Li, Liang Pu, Changfeng Ma, Xiaoyu Zhan, Jie Guo, Mingqiang Wei, Yan Zhang, Piaopiao Yu, Shuangyu Yang, Donghao Ji, Huisheng Ye, Hao Sun, Yansong Liu, Yinuo Chen, Jiaqi Zhu, Hongyu Liu", + "authors": [ + { + "first_name": "Yanwen", + "last_name": "Guo" + }, + { + "first_name": "Yuanqi", + "last_name": "Li" + }, + { + "first_name": "Dayong", + "last_name": "Ren" + }, + { + "first_name": "Xiaohong", + "last_name": "Zhang" + }, + { + "first_name": "Jiawei", + "last_name": "Li" + }, + { + "first_name": "Liang", + "last_name": "Pu" + }, + { + "first_name": "Changfeng", + "last_name": "Ma" + }, + { + "first_name": "Xiaoyu", + "last_name": "Zhan" + }, + { + "first_name": "Jie", + "last_name": "Guo" + }, + { + "first_name": "Mingqiang", + "last_name": "Wei" + }, + { + "first_name": "Yan", + "last_name": "Zhang" + }, + { + "first_name": "Piaopiao", + "last_name": "Yu" + }, + { + "first_name": "Shuangyu", + "last_name": "Yang" + }, + { + "first_name": "Donghao", + "last_name": "Ji" + }, + { + "first_name": "Huisheng", + "last_name": "Ye" + }, + { + "first_name": "Hao", + "last_name": "Sun" + }, + { + "first_name": "Yansong", + "last_name": "Liu" + }, + { + "first_name": "Yinuo", + "last_name": "Chen" + }, + { + "first_name": "Jiaqi", + "last_name": "Zhu" + }, + { + "first_name": "Hongyu", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Dual DETRs for Multi-Label Temporal Action Detection", - "authors": "Yuhan Zhu, Guozhen Zhang, Jing Tan, Gangshan Wu, Limin Wang", + "authors": [ + { + "first_name": "Yuhan", + "last_name": "Zhu" + }, + { + "first_name": "Guozhen", + "last_name": "Zhang" + }, + { + "first_name": "Jing", + "last_name": "Tan" + }, + { + "first_name": "Gangshan", + "last_name": "Wu" + }, + { + "first_name": "Limin", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Rich Human Feedback for Text-to-Image Generation", - "authors": "Youwei Liang, Junfeng He, Gang Li, Peizhao Li, Arseniy Klimovskiy, Nicholas Carolan, Jiao Sun, Jordi Pont-Tuset, Sarah Young, Feng Yang, Junjie Ke, Krishnamurthy Dj Dvijotham, Katherine M. Collins, Yiwen Luo, Yang Li, Kai J Kohlhoff, Deepak Ramachandran, Vidhya Navalpakkam", + "authors": [ + { + "first_name": "Youwei", + "last_name": "Liang" + }, + { + "first_name": "Junfeng", + "last_name": "He" + }, + { + "first_name": "Gang", + "last_name": "Li" + }, + { + "first_name": "Peizhao", + "last_name": "Li" + }, + { + "first_name": "Arseniy", + "last_name": "Klimovskiy" + }, + { + "first_name": "Nicholas", + "last_name": "Carolan" + }, + { + "first_name": "Jiao", + "last_name": "Sun" + }, + { + "first_name": "Jordi", + "last_name": "Pont-Tuset" + }, + { + "first_name": "Sarah", + "last_name": "Young" + }, + { + "first_name": "Feng", + "last_name": "Yang" + }, + { + "first_name": "Junjie", + "last_name": "Ke" + }, + { + "first_name": "Krishnamurthy", + "last_name": "Dj Dvijotham" + }, + { + "first_name": "Katherine", + "last_name": "M. Collins" + }, + { + "first_name": "Yiwen", + "last_name": "Luo" + }, + { + "first_name": "Yang", + "last_name": "Li" + }, + { + "first_name": "Kai", + "last_name": "J Kohlhoff" + }, + { + "first_name": "Deepak", + "last_name": "Ramachandran" + }, + { + "first_name": "Vidhya", + "last_name": "Navalpakkam" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "360DVD: Controllable Panorama Video Generation with 360-Degree Video Diffusion Model", - "authors": "Qian Wang, Weiqi Li, Chong Mou, Xinhua Cheng, Jian Zhang", + "authors": [ + { + "first_name": "Qian", + "last_name": "Wang" + }, + { + "first_name": "Weiqi", + "last_name": "Li" + }, + { + "first_name": "Chong", + "last_name": "Mou" + }, + { + "first_name": "Xinhua", + "last_name": "Cheng" + }, + { + "first_name": "Jian", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Map-Relative Pose Regression for Visual Re-Localization", - "authors": "Shuai Chen, Tommaso Cavallari, Victor Adrian Prisacariu, Eric Brachmann", + "authors": [ + { + "first_name": "Shuai", + "last_name": "Chen" + }, + { + "first_name": "Tommaso", + "last_name": "Cavallari" + }, + { + "first_name": "Victor", + "last_name": "Adrian Prisacariu" + }, + { + "first_name": "Eric", + "last_name": "Brachmann" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Implicit Event-RGBD Neural SLAM", - "authors": "Delin Qu, Chi Yan, Dong Wang, Jie Yin, Qizhi Chen, Dan Xu, Yiting Zhang, Bin Zhao, Xuelong Li", + "authors": [ + { + "first_name": "Delin", + "last_name": "Qu" + }, + { + "first_name": "Chi", + "last_name": "Yan" + }, + { + "first_name": "Dong", + "last_name": "Wang" + }, + { + "first_name": "Jie", + "last_name": "Yin" + }, + { + "first_name": "Qizhi", + "last_name": "Chen" + }, + { + "first_name": "Dan", + "last_name": "Xu" + }, + { + "first_name": "Yiting", + "last_name": "Zhang" + }, + { + "first_name": "Bin", + "last_name": "Zhao" + }, + { + "first_name": "Xuelong", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Virtual Immunohistochemistry Staining for Histological Images Assisted by Weakly-supervised Learning", - "authors": "Jiahan Li, Jiuyang Dong, Shenjin Huang, Xi Li, Junjun Jiang, Xiaopeng Fan, Yongbing Zhang", + "authors": [ + { + "first_name": "Jiahan", + "last_name": "Li" + }, + { + "first_name": "Jiuyang", + "last_name": "Dong" + }, + { + "first_name": "Shenjin", + "last_name": "Huang" + }, + { + "first_name": "Xi", + "last_name": "Li" + }, + { + "first_name": "Junjun", + "last_name": "Jiang" + }, + { + "first_name": "Xiaopeng", + "last_name": "Fan" + }, + { + "first_name": "Yongbing", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DeCoTR: Enhancing Depth Completion with 2D and 3D Attentions", - "authors": "Yunxiao Shi, Manish Kumar Singh, Hong Cai, Fatih Porikli", + "authors": [ + { + "first_name": "Yunxiao", + "last_name": "Shi" + }, + { + "first_name": "Manish", + "last_name": "Kumar Singh" + }, + { + "first_name": "Hong", + "last_name": "Cai" + }, + { + "first_name": "Fatih", + "last_name": "Porikli" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Utility-Fairness Trade-Offs and How to Find Them", - "authors": "Sepehr Dehdashtian, Bashir Sadeghi, Vishnu Naresh Boddeti", + "authors": [ + { + "first_name": "Sepehr", + "last_name": "Dehdashtian" + }, + { + "first_name": "Bashir", + "last_name": "Sadeghi" + }, + { + "first_name": "Vishnu", + "last_name": "Naresh Boddeti" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Domain-Specific Block Selection and Paired-View Pseudo-Labeling for Online Test-Time Adaptation", - "authors": "Yeonguk Yu, Sungho Shin, Seunghyeok Back, Mihwan Ko, Sangjun Noh, Kyoobin Lee", + "authors": [ + { + "first_name": "Yeonguk", + "last_name": "Yu" + }, + { + "first_name": "Sungho", + "last_name": "Shin" + }, + { + "first_name": "Seunghyeok", + "last_name": "Back" + }, + { + "first_name": "Mihwan", + "last_name": "Ko" + }, + { + "first_name": "Sangjun", + "last_name": "Noh" + }, + { + "first_name": "Kyoobin", + "last_name": "Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Aerial Lifting: Neural Urban Semantic and Building Instance Lifting from Aerial Imagery", - "authors": "Yuqi Zhang, Guanying Chen, Jiaxing Chen, Shuguang Cui", + "authors": [ + { + "first_name": "Yuqi", + "last_name": "Zhang" + }, + { + "first_name": "Guanying", + "last_name": "Chen" + }, + { + "first_name": "Jiaxing", + "last_name": "Chen" + }, + { + "first_name": "Shuguang", + "last_name": "Cui" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SAOR: Single-View Articulated Object Reconstruction", - "authors": "Mehmet Aygun, Oisin Mac Aodha", + "authors": [ + { + "first_name": "Mehmet", + "last_name": "Aygun" + }, + { + "first_name": "Oisin", + "last_name": "Mac Aodha" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "A Theory of Joint Light and Heat Transport for Lambertian Scenes", - "authors": "Mani Ramanagopal, Sriram Narayanan, Aswin C. Sankaranarayanan, Srinivasa G. Narasimhan", + "authors": [ + { + "first_name": "Mani", + "last_name": "Ramanagopal" + }, + { + "first_name": "Sriram", + "last_name": "Narayanan" + }, + { + "first_name": "Aswin", + "last_name": "C. Sankaranarayanan" + }, + { + "first_name": "Srinivasa", + "last_name": "G. Narasimhan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "iKUN: Speak to Trackers without Retraining", - "authors": "Yunhao Du, Cheng Lei, Zhicheng Zhao, Fei Su", + "authors": [ + { + "first_name": "Yunhao", + "last_name": "Du" + }, + { + "first_name": "Cheng", + "last_name": "Lei" + }, + { + "first_name": "Zhicheng", + "last_name": "Zhao" + }, + { + "first_name": "Fei", + "last_name": "Su" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "RankMatch: Exploring the Better Consistency Regularization for Semi-supervised Semantic Segmentation", - "authors": "Huayu Mai, Rui Sun, Tianzhu Zhang, Feng Wu", + "authors": [ + { + "first_name": "Huayu", + "last_name": "Mai" + }, + { + "first_name": "Rui", + "last_name": "Sun" + }, + { + "first_name": "Tianzhu", + "last_name": "Zhang" + }, + { + "first_name": "Feng", + "last_name": "Wu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Facial Identity Anonymization via Intrinsic and Extrinsic Attention Distraction", - "authors": "Zhenzhong Kuang, Xiaochen Yang, Yingjie Shen, Chao Hu, Jun Yu", + "authors": [ + { + "first_name": "Zhenzhong", + "last_name": "Kuang" + }, + { + "first_name": "Xiaochen", + "last_name": "Yang" + }, + { + "first_name": "Yingjie", + "last_name": "Shen" + }, + { + "first_name": "Chao", + "last_name": "Hu" + }, + { + "first_name": "Jun", + "last_name": "Yu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "3D-SceneDreamer: Text-Driven 3D-Consistent Scene Generation", - "authors": "Songchun Zhang, Yibo Zhang, Quan Zheng, Rui Ma, Wei Hua, Hujun Bao, Weiwei Xu, Changqing Zou", + "authors": [ + { + "first_name": "Songchun", + "last_name": "Zhang" + }, + { + "first_name": "Yibo", + "last_name": "Zhang" + }, + { + "first_name": "Quan", + "last_name": "Zheng" + }, + { + "first_name": "Rui", + "last_name": "Ma" + }, + { + "first_name": "Wei", + "last_name": "Hua" + }, + { + "first_name": "Hujun", + "last_name": "Bao" + }, + { + "first_name": "Weiwei", + "last_name": "Xu" + }, + { + "first_name": "Changqing", + "last_name": "Zou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "VMINer: Versatile Multi-view Inverse Rendering with Near- and Far-field Light Sources", - "authors": "Fan Fei, Jiajun Tang, Ping Tan, Boxin Shi", + "authors": [ + { + "first_name": "Fan", + "last_name": "Fei" + }, + { + "first_name": "Jiajun", + "last_name": "Tang" + }, + { + "first_name": "Ping", + "last_name": "Tan" + }, + { + "first_name": "Boxin", + "last_name": "Shi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "RoHM: Robust Human Motion Reconstruction via Diffusion", - "authors": "Siwei Zhang, Bharat Lal Bhatnagar, Yuanlu Xu, Alexander Winkler, Petr Kadlecek, Siyu Tang, Federica Bogo", + "authors": [ + { + "first_name": "Siwei", + "last_name": "Zhang" + }, + { + "first_name": "Bharat", + "last_name": "Lal Bhatnagar" + }, + { + "first_name": "Yuanlu", + "last_name": "Xu" + }, + { + "first_name": "Alexander", + "last_name": "Winkler" + }, + { + "first_name": "Petr", + "last_name": "Kadlecek" + }, + { + "first_name": "Siyu", + "last_name": "Tang" + }, + { + "first_name": "Federica", + "last_name": "Bogo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Do You Remember? Dense Video Captioning with Cross-Modal Memory Retrieval", - "authors": "Minkuk Kim, Hyeon Bae Kim, Jinyoung Moon, Jinwoo Choi, Seong Tae Kim", + "authors": [ + { + "first_name": "Minkuk", + "last_name": "Kim" + }, + { + "first_name": "Hyeon", + "last_name": "Bae Kim" + }, + { + "first_name": "Jinyoung", + "last_name": "Moon" + }, + { + "first_name": "Jinwoo", + "last_name": "Choi" + }, + { + "first_name": "Seong", + "last_name": "Tae Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DuPL: Dual Student with Trustworthy Progressive Learning for Robust Weakly Supervised Semantic Segmentation", - "authors": "Yuanchen Wu, Xichen Ye, Kequan Yang, Jide Li, Xiaoqiang Li", + "authors": [ + { + "first_name": "Yuanchen", + "last_name": "Wu" + }, + { + "first_name": "Xichen", + "last_name": "Ye" + }, + { + "first_name": "Kequan", + "last_name": "Yang" + }, + { + "first_name": "Jide", + "last_name": "Li" + }, + { + "first_name": "Xiaoqiang", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning with Structural Labels for Learning with Noisy Labels", - "authors": "Noo-ri Kim, Jin-Seop Lee, Jee-Hyong Lee", + "authors": [ + { + "first_name": "Noo-ri", + "last_name": "Kim" + }, + { + "first_name": "Jin-Seop", + "last_name": "Lee" + }, + { + "first_name": "Jee-Hyong", + "last_name": "Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SurMo: Surface-based 4D Motion Modeling for Dynamic Human Rendering", - "authors": "Tao Hu, Fangzhou Hong, Ziwei Liu", + "authors": [ + { + "first_name": "Tao", + "last_name": "Hu" + }, + { + "first_name": "Fangzhou", + "last_name": "Hong" + }, + { + "first_name": "Ziwei", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SPAD: Spatially Aware Multi-View Diffusers", - "authors": "Yash Kant, Aliaksandr Siarohin, Ziyi Wu, Michael Vasilkovsky, Guocheng Qian, Jian Ren, Riza Alp Guler, Bernard Ghanem, Sergey Tulyakov, Igor Gilitschenski", + "authors": [ + { + "first_name": "Yash", + "last_name": "Kant" + }, + { + "first_name": "Aliaksandr", + "last_name": "Siarohin" + }, + { + "first_name": "Ziyi", + "last_name": "Wu" + }, + { + "first_name": "Michael", + "last_name": "Vasilkovsky" + }, + { + "first_name": "Guocheng", + "last_name": "Qian" + }, + { + "first_name": "Jian", + "last_name": "Ren" + }, + { + "first_name": "Riza", + "last_name": "Alp Guler" + }, + { + "first_name": "Bernard", + "last_name": "Ghanem" + }, + { + "first_name": "Sergey", + "last_name": "Tulyakov" + }, + { + "first_name": "Igor", + "last_name": "Gilitschenski" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Gradient Reweighting: Towards Imbalanced Class-Incremental Learning", - "authors": "Jiangpeng He", + "authors": [ + { + "first_name": "Jiangpeng", + "last_name": "He" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Hierarchical Spatio-temporal Decoupling for Text-to-Video Generation", - "authors": "Zhiwu Qing, Shiwei Zhang, Jiayu Wang, Xiang Wang, Yujie Wei, Yingya Zhang, Changxin Gao, Nong Sang", + "authors": [ + { + "first_name": "Zhiwu", + "last_name": "Qing" + }, + { + "first_name": "Shiwei", + "last_name": "Zhang" + }, + { + "first_name": "Jiayu", + "last_name": "Wang" + }, + { + "first_name": "Xiang", + "last_name": "Wang" + }, + { + "first_name": "Yujie", + "last_name": "Wei" + }, + { + "first_name": "Yingya", + "last_name": "Zhang" + }, + { + "first_name": "Changxin", + "last_name": "Gao" + }, + { + "first_name": "Nong", + "last_name": "Sang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PLACE: Adaptive Layout-Semantic Fusion for Semantic Image Synthesis", - "authors": "Zhengyao Lv, Yuxiang Wei, Wangmeng Zuo, Kwan-Yee K. Wong", + "authors": [ + { + "first_name": "Zhengyao", + "last_name": "Lv" + }, + { + "first_name": "Yuxiang", + "last_name": "Wei" + }, + { + "first_name": "Wangmeng", + "last_name": "Zuo" + }, + { + "first_name": "Kwan-Yee", + "last_name": "K. Wong" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Exploring Efficient Asymmetric Blind-Spots for Self-Supervised Denoising in Real-World Scenarios", - "authors": "Shiyan Chen, Jiyuan Zhang, Zhaofei Yu, Tiejun Huang", + "authors": [ + { + "first_name": "Shiyan", + "last_name": "Chen" + }, + { + "first_name": "Jiyuan", + "last_name": "Zhang" + }, + { + "first_name": "Zhaofei", + "last_name": "Yu" + }, + { + "first_name": "Tiejun", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Gaussian Splatting SLAM", - "authors": "Hidenobu Matsuki, Riku Murai, Paul H.J. Kelly, Andrew J. Davison", + "authors": [ + { + "first_name": "Hidenobu", + "last_name": "Matsuki" + }, + { + "first_name": "Riku", + "last_name": "Murai" + }, + { + "first_name": "Paul", + "last_name": "H.J. Kelly" + }, + { + "first_name": "Andrew", + "last_name": "J. Davison" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Not All Classes Stand on Same Embeddings: Calibrating a Semantic Distance with Metric Tensor", - "authors": "Jae Hyeon Park, Gyoomin Lee, Seunggi Park, Sung In Cho", + "authors": [ + { + "first_name": "Jae", + "last_name": "Hyeon Park" + }, + { + "first_name": "Gyoomin", + "last_name": "Lee" + }, + { + "first_name": "Seunggi", + "last_name": "Park" + }, + { + "first_name": "Sung", + "last_name": "In Cho" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "A Simple Recipe for Contrastively Pre-training Video-First Encoders Beyond 16 Frames", - "authors": "Pinelopi Papalampidi, Skanda Koppula, Shreya Pathak, Justin Chiu, Joe Heyward, Viorica Patraucean, Jiajun Shen, Antoine Miech, Andrew Zisserman, Aida Nematzdeh", + "authors": [ + { + "first_name": "Pinelopi", + "last_name": "Papalampidi" + }, + { + "first_name": "Skanda", + "last_name": "Koppula" + }, + { + "first_name": "Shreya", + "last_name": "Pathak" + }, + { + "first_name": "Justin", + "last_name": "Chiu" + }, + { + "first_name": "Joe", + "last_name": "Heyward" + }, + { + "first_name": "Viorica", + "last_name": "Patraucean" + }, + { + "first_name": "Jiajun", + "last_name": "Shen" + }, + { + "first_name": "Antoine", + "last_name": "Miech" + }, + { + "first_name": "Andrew", + "last_name": "Zisserman" + }, + { + "first_name": "Aida", + "last_name": "Nematzdeh" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DeMatch: Deep Decomposition of Motion Field for Two-View Correspondence Learning", - "authors": "Shihua Zhang, Zizhuo Li, Yuan Gao, Jiayi Ma", + "authors": [ + { + "first_name": "Shihua", + "last_name": "Zhang" + }, + { + "first_name": "Zizhuo", + "last_name": "Li" + }, + { + "first_name": "Yuan", + "last_name": "Gao" + }, + { + "first_name": "Jiayi", + "last_name": "Ma" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Hierarchical Diffusion Policy for Kinematics-Aware Multi-Task Robotic Manipulation", - "authors": "Xiao Ma, Sumit Patidar, Iain Haughton, Stephen James", + "authors": [ + { + "first_name": "Xiao", + "last_name": "Ma" + }, + { + "first_name": "Sumit", + "last_name": "Patidar" + }, + { + "first_name": "Iain", + "last_name": "Haughton" + }, + { + "first_name": "Stephen", + "last_name": "James" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Efficient Multi-scale Network with Learnable Discrete Wavelet Transform for Blind Motion Deblurring", - "authors": "Xin Gao, Tianheng Qiu, Xinyu Zhang, Hanlin Bai, Kang Liu, Xuan Huang, Hu Wei, Guoying Zhang, Huaping Liu", + "authors": [ + { + "first_name": "Xin", + "last_name": "Gao" + }, + { + "first_name": "Tianheng", + "last_name": "Qiu" + }, + { + "first_name": "Xinyu", + "last_name": "Zhang" + }, + { + "first_name": "Hanlin", + "last_name": "Bai" + }, + { + "first_name": "Kang", + "last_name": "Liu" + }, + { + "first_name": "Xuan", + "last_name": "Huang" + }, + { + "first_name": "Hu", + "last_name": "Wei" + }, + { + "first_name": "Guoying", + "last_name": "Zhang" + }, + { + "first_name": "Huaping", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MaskPLAN: Masked Generative Layout Planning from Partial Input", - "authors": "Hang Zhang, Anton Savov, Benjamin Dillenburger", + "authors": [ + { + "first_name": "Hang", + "last_name": "Zhang" + }, + { + "first_name": "Anton", + "last_name": "Savov" + }, + { + "first_name": "Benjamin", + "last_name": "Dillenburger" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Benchmarking the Robustness of Temporal Action Detection Models Against Temporal Corruptions", - "authors": "Runhao Zeng, Xiaoyong Chen, Jiaming Liang, Huisi Wu, Guangzhong Cao, Yong Guo", + "authors": [ + { + "first_name": "Runhao", + "last_name": "Zeng" + }, + { + "first_name": "Xiaoyong", + "last_name": "Chen" + }, + { + "first_name": "Jiaming", + "last_name": "Liang" + }, + { + "first_name": "Huisi", + "last_name": "Wu" + }, + { + "first_name": "Guangzhong", + "last_name": "Cao" + }, + { + "first_name": "Yong", + "last_name": "Guo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Open-World Human-Object Interaction Detection via Multi-modal Prompts", - "authors": "Jie Yang, Bingliang Li, Ailing Zeng, Lei Zhang, Ruimao Zhang", + "authors": [ + { + "first_name": "Jie", + "last_name": "Yang" + }, + { + "first_name": "Bingliang", + "last_name": "Li" + }, + { + "first_name": "Ailing", + "last_name": "Zeng" + }, + { + "first_name": "Lei", + "last_name": "Zhang" + }, + { + "first_name": "Ruimao", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HMD-Poser: On-Device Real-time Human Motion Tracking from Scalable Sparse Observations", - "authors": "Peng Dai, Yang Zhang, Tao Liu, Zhen Fan, Tianyuan Du, Zhuo Su, Xiaozheng Zheng, Zeming Li", + "authors": [ + { + "first_name": "Peng", + "last_name": "Dai" + }, + { + "first_name": "Yang", + "last_name": "Zhang" + }, + { + "first_name": "Tao", + "last_name": "Liu" + }, + { + "first_name": "Zhen", + "last_name": "Fan" + }, + { + "first_name": "Tianyuan", + "last_name": "Du" + }, + { + "first_name": "Zhuo", + "last_name": "Su" + }, + { + "first_name": "Xiaozheng", + "last_name": "Zheng" + }, + { + "first_name": "Zeming", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "UniMODE: Unified Monocular 3D Object Detection", - "authors": "Zhuoling Li, Xiaogang Xu, SerNam Lim, Hengshuang Zhao", + "authors": [ + { + "first_name": "Zhuoling", + "last_name": "Li" + }, + { + "first_name": "Xiaogang", + "last_name": "Xu" + }, + { + "first_name": "SerNam", + "last_name": "Lim" + }, + { + "first_name": "Hengshuang", + "last_name": "Zhao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Sherpa3D: Boosting High-Fidelity Text-to-3D Generation via Coarse 3D Prior", - "authors": "Fangfu Liu, Diankun Wu, Yi Wei, Yongming Rao, Yueqi Duan", + "authors": [ + { + "first_name": "Fangfu", + "last_name": "Liu" + }, + { + "first_name": "Diankun", + "last_name": "Wu" + }, + { + "first_name": "Yi", + "last_name": "Wei" + }, + { + "first_name": "Yongming", + "last_name": "Rao" + }, + { + "first_name": "Yueqi", + "last_name": "Duan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Flexible Biometrics Recognition: Bridging the Multimodality Gap through Attention Alignment and Prompt Tuning", - "authors": "Leslie Ching Ow Tiong, Dick Sigmund, Chen-Hui Chan, Andrew Beng Jin Teoh", + "authors": [ + { + "first_name": "Leslie", + "last_name": "Ching Ow Tiong" + }, + { + "first_name": "Dick", + "last_name": "Sigmund" + }, + { + "first_name": "Chen-Hui", + "last_name": "Chan" + }, + { + "first_name": "Andrew", + "last_name": "Beng Jin Teoh" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Multi-agent Collaborative Perception via Motion-aware Robust Communication Network", - "authors": "Shixin Hong, Yu Liu, Zhi Li, Shaohui Li, You He", + "authors": [ + { + "first_name": "Shixin", + "last_name": "Hong" + }, + { + "first_name": "Yu", + "last_name": "Liu" + }, + { + "first_name": "Zhi", + "last_name": "Li" + }, + { + "first_name": "Shaohui", + "last_name": "Li" + }, + { + "first_name": "You", + "last_name": "He" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "The Manga Whisperer: Automatically Generating Transcriptions for Comics", - "authors": "Ragav Sachdeva, Andrew Zisserman", + "authors": [ + { + "first_name": "Ragav", + "last_name": "Sachdeva" + }, + { + "first_name": "Andrew", + "last_name": "Zisserman" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Exploring Region-Word Alignment in Built-in Detector for Open-Vocabulary Object Detection", - "authors": "Heng Zhang, Qiuyu Zhao, Linyu Zheng, Hao Zeng, Zhiwei Ge, Tianhao Li, Sulong Xu", + "authors": [ + { + "first_name": "Heng", + "last_name": "Zhang" + }, + { + "first_name": "Qiuyu", + "last_name": "Zhao" + }, + { + "first_name": "Linyu", + "last_name": "Zheng" + }, + { + "first_name": "Hao", + "last_name": "Zeng" + }, + { + "first_name": "Zhiwei", + "last_name": "Ge" + }, + { + "first_name": "Tianhao", + "last_name": "Li" + }, + { + "first_name": "Sulong", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MovieChat: From Dense Token to Sparse Memory for Long Video Understanding", - "authors": "Enxin Song, Wenhao Chai, Guanhong Wang, Yucheng Zhang, Haoyang Zhou, Feiyang Wu, Haozhe Chi, Xun Guo, Tian Ye, Yanting Zhang, Yan Lu, Jenq-Neng Hwang, Gaoang Wang", + "authors": [ + { + "first_name": "Enxin", + "last_name": "Song" + }, + { + "first_name": "Wenhao", + "last_name": "Chai" + }, + { + "first_name": "Guanhong", + "last_name": "Wang" + }, + { + "first_name": "Yucheng", + "last_name": "Zhang" + }, + { + "first_name": "Haoyang", + "last_name": "Zhou" + }, + { + "first_name": "Feiyang", + "last_name": "Wu" + }, + { + "first_name": "Haozhe", + "last_name": "Chi" + }, + { + "first_name": "Xun", + "last_name": "Guo" + }, + { + "first_name": "Tian", + "last_name": "Ye" + }, + { + "first_name": "Yanting", + "last_name": "Zhang" + }, + { + "first_name": "Yan", + "last_name": "Lu" + }, + { + "first_name": "Jenq-Neng", + "last_name": "Hwang" + }, + { + "first_name": "Gaoang", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Comparing the Decision-Making Mechanisms by Transformers and CNNs via Explanation Methods", - "authors": "Mingqi Jiang, Saeed Khorram, Li Fuxin", + "authors": [ + { + "first_name": "Mingqi", + "last_name": "Jiang" + }, + { + "first_name": "Saeed", + "last_name": "Khorram" + }, + { + "first_name": "Li", + "last_name": "Fuxin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "A Unified Diffusion Framework for Scene-aware Human Motion Estimation from Sparse Signals", - "authors": "Jiangnan Tang, Jingya Wang, Kaiyang Ji, Lan Xu, Jingyi Yu, Ye Shi", + "authors": [ + { + "first_name": "Jiangnan", + "last_name": "Tang" + }, + { + "first_name": "Jingya", + "last_name": "Wang" + }, + { + "first_name": "Kaiyang", + "last_name": "Ji" + }, + { + "first_name": "Lan", + "last_name": "Xu" + }, + { + "first_name": "Jingyi", + "last_name": "Yu" + }, + { + "first_name": "Ye", + "last_name": "Shi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Single Domain Generalization for Crowd Counting", - "authors": "Zhuoxuan Peng, S.-H. Gary Chan", + "authors": [ + { + "first_name": "Zhuoxuan", + "last_name": "Peng" + }, + { + "first_name": "S.-H.", + "last_name": "Gary Chan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Atlantis: Enabling Underwater Depth Estimation with Stable Diffusion", - "authors": "Fan Zhang, Shaodi You, Yu Li, Ying Fu", + "authors": [ + { + "first_name": "Fan", + "last_name": "Zhang" + }, + { + "first_name": "Shaodi", + "last_name": "You" + }, + { + "first_name": "Yu", + "last_name": "Li" + }, + { + "first_name": "Ying", + "last_name": "Fu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Matching Anything by Segmenting Anything", - "authors": "Siyuan Li, Lei Ke, Martin Danelljan, Luigi Piccinelli, Mattia Segu, Luc Van Gool, Fisher Yu", + "authors": [ + { + "first_name": "Siyuan", + "last_name": "Li" + }, + { + "first_name": "Lei", + "last_name": "Ke" + }, + { + "first_name": "Martin", + "last_name": "Danelljan" + }, + { + "first_name": "Luigi", + "last_name": "Piccinelli" + }, + { + "first_name": "Mattia", + "last_name": "Segu" + }, + { + "first_name": "Luc", + "last_name": "Van Gool" + }, + { + "first_name": "Fisher", + "last_name": "Yu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Task-Aware Encoder Control for Deep Video Compression", - "authors": "Xingtong Ge, Jixiang Luo, Xinjie Zhang, Tongda Xu, Guo Lu, Dailan He, Jing Geng, Yan Wang, Jun Zhang, Hongwei Qin", + "authors": [ + { + "first_name": "Xingtong", + "last_name": "Ge" + }, + { + "first_name": "Jixiang", + "last_name": "Luo" + }, + { + "first_name": "Xinjie", + "last_name": "Zhang" + }, + { + "first_name": "Tongda", + "last_name": "Xu" + }, + { + "first_name": "Guo", + "last_name": "Lu" + }, + { + "first_name": "Dailan", + "last_name": "He" + }, + { + "first_name": "Jing", + "last_name": "Geng" + }, + { + "first_name": "Yan", + "last_name": "Wang" + }, + { + "first_name": "Jun", + "last_name": "Zhang" + }, + { + "first_name": "Hongwei", + "last_name": "Qin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Multi-scale Dynamic and Hierarchical Relationship Modeling for Facial Action Units Recognition", - "authors": "Zihan Wang, Siyang Song, Cheng Luo, Songhe Deng, Weicheng Xie, Linlin Shen", + "authors": [ + { + "first_name": "Zihan", + "last_name": "Wang" + }, + { + "first_name": "Siyang", + "last_name": "Song" + }, + { + "first_name": "Cheng", + "last_name": "Luo" + }, + { + "first_name": "Songhe", + "last_name": "Deng" + }, + { + "first_name": "Weicheng", + "last_name": "Xie" + }, + { + "first_name": "Linlin", + "last_name": "Shen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Decoupled Pseudo-labeling for Semi-Supervised Monocular 3D Object Detection", - "authors": "Jiacheng Zhang, Jiaming Li, Xiangru Lin, Wei Zhang, Xiao Tan, Junyu Han, Errui Ding, Jingdong Wang, Guanbin Li", + "authors": [ + { + "first_name": "Jiacheng", + "last_name": "Zhang" + }, + { + "first_name": "Jiaming", + "last_name": "Li" + }, + { + "first_name": "Xiangru", + "last_name": "Lin" + }, + { + "first_name": "Wei", + "last_name": "Zhang" + }, + { + "first_name": "Xiao", + "last_name": "Tan" + }, + { + "first_name": "Junyu", + "last_name": "Han" + }, + { + "first_name": "Errui", + "last_name": "Ding" + }, + { + "first_name": "Jingdong", + "last_name": "Wang" + }, + { + "first_name": "Guanbin", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Temporally Consistent Unbalanced Optimal Transport for Unsupervised Action Segmentation", - "authors": "Ming Xu, Stephen Gould", + "authors": [ + { + "first_name": "Ming", + "last_name": "Xu" + }, + { + "first_name": "Stephen", + "last_name": "Gould" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning Transferable Negative Prompts for Out-of-Distribution Detection", - "authors": "Tianqi Li, Guansong Pang, Xiao Bai, Wenjun Miao, Jin Zheng", + "authors": [ + { + "first_name": "Tianqi", + "last_name": "Li" + }, + { + "first_name": "Guansong", + "last_name": "Pang" + }, + { + "first_name": "Xiao", + "last_name": "Bai" + }, + { + "first_name": "Wenjun", + "last_name": "Miao" + }, + { + "first_name": "Jin", + "last_name": "Zheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Long-Tail Class Incremental Learning via Independent Sub-prototype Construction", - "authors": "Xi Wang, Xu Yang, Jie Yin, Kun Wei, Cheng Deng", + "authors": [ + { + "first_name": "Xi", + "last_name": "Wang" + }, + { + "first_name": "Xu", + "last_name": "Yang" + }, + { + "first_name": "Jie", + "last_name": "Yin" + }, + { + "first_name": "Kun", + "last_name": "Wei" + }, + { + "first_name": "Cheng", + "last_name": "Deng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning with Unreliability: Fast Few-shot Voxel Radiance Fields with Relative Geometric Consistency", - "authors": "Yingjie Xu, Bangzhen Liu, Hao Tang, Bailin Deng, Shengfeng He", + "authors": [ + { + "first_name": "Yingjie", + "last_name": "Xu" + }, + { + "first_name": "Bangzhen", + "last_name": "Liu" + }, + { + "first_name": "Hao", + "last_name": "Tang" + }, + { + "first_name": "Bailin", + "last_name": "Deng" + }, + { + "first_name": "Shengfeng", + "last_name": "He" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards Understanding and Improving Adversarial Robustness of Vision Transformers", - "authors": "Samyak Jain, Tanima Dutta", + "authors": [ + { + "first_name": "Samyak", + "last_name": "Jain" + }, + { + "first_name": "Tanima", + "last_name": "Dutta" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "EventEgo3D: 3D Human Motion Capture from Egocentric Event Streams", - "authors": "Christen Millerdurai, Hiroyasu Akada, Jian Wang, Diogo Luvizon, Christian Theobalt, Vladislav Golyanik", + "authors": [ + { + "first_name": "Christen", + "last_name": "Millerdurai" + }, + { + "first_name": "Hiroyasu", + "last_name": "Akada" + }, + { + "first_name": "Jian", + "last_name": "Wang" + }, + { + "first_name": "Diogo", + "last_name": "Luvizon" + }, + { + "first_name": "Christian", + "last_name": "Theobalt" + }, + { + "first_name": "Vladislav", + "last_name": "Golyanik" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Holistic Features are almost Sufficient for Text-to-Video Retrieval", - "authors": "Kaibin Tian, Ruixiang Zhao, Zijie Xin, Bangxiang Lan, Xirong Li", + "authors": [ + { + "first_name": "Kaibin", + "last_name": "Tian" + }, + { + "first_name": "Ruixiang", + "last_name": "Zhao" + }, + { + "first_name": "Zijie", + "last_name": "Xin" + }, + { + "first_name": "Bangxiang", + "last_name": "Lan" + }, + { + "first_name": "Xirong", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "A Call to Reflect on Evaluation Practices for Age Estimation: Comparative Analysis of the State-of-the-Art and a Unified Benchmark", - "authors": "Jakub Paplhám, Vojt?ch Franc", + "authors": [ + { + "first_name": "Jakub", + "last_name": "Paplhám" + }, + { + "first_name": "Vojt?ch", + "last_name": "Franc" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CosalPure: Learning Concept from Group Images for Robust Co-Saliency Detection", - "authors": "Jiayi Zhu, Qing Guo, Felix Juefei-Xu, Yihao Huang, Yang Liu, Geguang Pu", + "authors": [ + { + "first_name": "Jiayi", + "last_name": "Zhu" + }, + { + "first_name": "Qing", + "last_name": "Guo" + }, + { + "first_name": "Felix", + "last_name": "Juefei-Xu" + }, + { + "first_name": "Yihao", + "last_name": "Huang" + }, + { + "first_name": "Yang", + "last_name": "Liu" + }, + { + "first_name": "Geguang", + "last_name": "Pu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Uncertainty-aware Action Decoupling Transformer for Action Anticipation", - "authors": "Hongji Guo, Nakul Agarwal, Shao-Yuan Lo, Kwonjoon Lee, Qiang Ji", + "authors": [ + { + "first_name": "Hongji", + "last_name": "Guo" + }, + { + "first_name": "Nakul", + "last_name": "Agarwal" + }, + { + "first_name": "Shao-Yuan", + "last_name": "Lo" + }, + { + "first_name": "Kwonjoon", + "last_name": "Lee" + }, + { + "first_name": "Qiang", + "last_name": "Ji" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MRFP: Learning Generalizable Semantic Segmentation from Sim-2-Real with Multi-Resolution Feature Perturbation", - "authors": "Sumanth Udupa, Prajwal Gurunath, Aniruddh Sikdar, Suresh Sundaram", + "authors": [ + { + "first_name": "Sumanth", + "last_name": "Udupa" + }, + { + "first_name": "Prajwal", + "last_name": "Gurunath" + }, + { + "first_name": "Aniruddh", + "last_name": "Sikdar" + }, + { + "first_name": "Suresh", + "last_name": "Sundaram" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "S-DyRF: Reference-Based Stylized Radiance Fields for Dynamic Scenes", - "authors": "Xingyi Li, Zhiguo Cao, Yizheng Wu, Kewei Wang, Ke Xian, Zhe Wang, Guosheng Lin", + "authors": [ + { + "first_name": "Xingyi", + "last_name": "Li" + }, + { + "first_name": "Zhiguo", + "last_name": "Cao" + }, + { + "first_name": "Yizheng", + "last_name": "Wu" + }, + { + "first_name": "Kewei", + "last_name": "Wang" + }, + { + "first_name": "Ke", + "last_name": "Xian" + }, + { + "first_name": "Zhe", + "last_name": "Wang" + }, + { + "first_name": "Guosheng", + "last_name": "Lin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MotionEditor: Editing Video Motion via Content-Aware Diffusion", - "authors": "Shuyuan Tu, Qi Dai, Zhi-Qi Cheng, Han Hu, Xintong Han, Zuxuan Wu, Yu-Gang Jiang", + "authors": [ + { + "first_name": "Shuyuan", + "last_name": "Tu" + }, + { + "first_name": "Qi", + "last_name": "Dai" + }, + { + "first_name": "Zhi-Qi", + "last_name": "Cheng" + }, + { + "first_name": "Han", + "last_name": "Hu" + }, + { + "first_name": "Xintong", + "last_name": "Han" + }, + { + "first_name": "Zuxuan", + "last_name": "Wu" + }, + { + "first_name": "Yu-Gang", + "last_name": "Jiang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "What How and When Should Object Detectors Update in Continually Changing Test Domains?", - "authors": "Jayeon Yoo, Dongkwan Lee, Inseop Chung, Donghyun Kim, Nojun Kwak", + "authors": [ + { + "first_name": "Jayeon", + "last_name": "Yoo" + }, + { + "first_name": "Dongkwan", + "last_name": "Lee" + }, + { + "first_name": "Inseop", + "last_name": "Chung" + }, + { + "first_name": "Donghyun", + "last_name": "Kim" + }, + { + "first_name": "Nojun", + "last_name": "Kwak" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "One-Prompt to Segment All Medical Images", - "authors": "Junde Wu, Min Xu", + "authors": [ + { + "first_name": "Junde", + "last_name": "Wu" + }, + { + "first_name": "Min", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Bayesian Exploration of Pre-trained Models for Low-shot Image Classification", - "authors": "Yibo Miao, Yu Lei, Feng Zhou, Zhijie Deng", + "authors": [ + { + "first_name": "Yibo", + "last_name": "Miao" + }, + { + "first_name": "Yu", + "last_name": "Lei" + }, + { + "first_name": "Feng", + "last_name": "Zhou" + }, + { + "first_name": "Zhijie", + "last_name": "Deng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GROUNDHOG: Grounding Large Language Models to Holistic Segmentation", - "authors": "Yichi Zhang, Ziqiao Ma, Xiaofeng Gao, Suhaila Shakiah, Qiaozi Gao, Joyce Chai", + "authors": [ + { + "first_name": "Yichi", + "last_name": "Zhang" + }, + { + "first_name": "Ziqiao", + "last_name": "Ma" + }, + { + "first_name": "Xiaofeng", + "last_name": "Gao" + }, + { + "first_name": "Suhaila", + "last_name": "Shakiah" + }, + { + "first_name": "Qiaozi", + "last_name": "Gao" + }, + { + "first_name": "Joyce", + "last_name": "Chai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Doubly Abductive Counterfactual Inference for Text-based Image Editing", - "authors": "Xue Song, Jiequan Cui, Hanwang Zhang, Jingjing Chen, Richang Hong, Yu-Gang Jiang", + "authors": [ + { + "first_name": "Xue", + "last_name": "Song" + }, + { + "first_name": "Jiequan", + "last_name": "Cui" + }, + { + "first_name": "Hanwang", + "last_name": "Zhang" + }, + { + "first_name": "Jingjing", + "last_name": "Chen" + }, + { + "first_name": "Richang", + "last_name": "Hong" + }, + { + "first_name": "Yu-Gang", + "last_name": "Jiang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "RoMa: Robust Dense Feature Matching", - "authors": "Johan Edstedt, Qiyu Sun, Georg Bökman, Mårten Wadenbäck, Michael Felsberg", + "authors": [ + { + "first_name": "Johan", + "last_name": "Edstedt" + }, + { + "first_name": "Qiyu", + "last_name": "Sun" + }, + { + "first_name": "Georg", + "last_name": "Bökman" + }, + { + "first_name": "Mårten", + "last_name": "Wadenbäck" + }, + { + "first_name": "Michael", + "last_name": "Felsberg" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts", - "authors": "Jialin Wu, Xia Hu, Yaqing Wang, Bo Pang, Radu Soricut", + "authors": [ + { + "first_name": "Jialin", + "last_name": "Wu" + }, + { + "first_name": "Xia", + "last_name": "Hu" + }, + { + "first_name": "Yaqing", + "last_name": "Wang" + }, + { + "first_name": "Bo", + "last_name": "Pang" + }, + { + "first_name": "Radu", + "last_name": "Soricut" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SeMoLi: What Moves Together Belongs Together", - "authors": "Jenny Seidenschwarz, Aljosa Osep, Francesco Ferroni, Simon Lucey, Laura Leal-Taixe", + "authors": [ + { + "first_name": "Jenny", + "last_name": "Seidenschwarz" + }, + { + "first_name": "Aljosa", + "last_name": "Osep" + }, + { + "first_name": "Francesco", + "last_name": "Ferroni" + }, + { + "first_name": "Simon", + "last_name": "Lucey" + }, + { + "first_name": "Laura", + "last_name": "Leal-Taixe" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Insights from the Use of Previously Unseen Neural Architecture Search Datasets", - "authors": "Rob Geada, David Towers, Matthew Forshaw, Amir Atapour-Abarghouei, A. Stephen McGough", + "authors": [ + { + "first_name": "Rob", + "last_name": "Geada" + }, + { + "first_name": "David", + "last_name": "Towers" + }, + { + "first_name": "Matthew", + "last_name": "Forshaw" + }, + { + "first_name": "Amir", + "last_name": "Atapour-Abarghouei" + }, + { + "first_name": "A.", + "last_name": "Stephen McGough" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Adversarially Robust Few-shot Learning via Parameter Co-distillation of Similarity and Class Concept Learners", - "authors": "Junhao Dong, Piotr Koniusz, Junxi Chen, Xiaohua Xie, Yew-Soon Ong", + "authors": [ + { + "first_name": "Junhao", + "last_name": "Dong" + }, + { + "first_name": "Piotr", + "last_name": "Koniusz" + }, + { + "first_name": "Junxi", + "last_name": "Chen" + }, + { + "first_name": "Xiaohua", + "last_name": "Xie" + }, + { + "first_name": "Yew-Soon", + "last_name": "Ong" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Context-Guided Spatio-Temporal Video Grounding", - "authors": "Xin Gu, Heng Fan, Yan Huang, Tiejian Luo, Libo Zhang", + "authors": [ + { + "first_name": "Xin", + "last_name": "Gu" + }, + { + "first_name": "Heng", + "last_name": "Fan" + }, + { + "first_name": "Yan", + "last_name": "Huang" + }, + { + "first_name": "Tiejian", + "last_name": "Luo" + }, + { + "first_name": "Libo", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Explaining the Implicit Neural Canvas: Connecting Pixels to Neurons by Tracing their Contributions", - "authors": "Namitha Padmanabhan, Matthew Gwilliam, Pulkit Kumar, Shishira R Maiya, Max Ehrlich, Abhinav Shrivastava", + "authors": [ + { + "first_name": "Namitha", + "last_name": "Padmanabhan" + }, + { + "first_name": "Matthew", + "last_name": "Gwilliam" + }, + { + "first_name": "Pulkit", + "last_name": "Kumar" + }, + { + "first_name": "Shishira", + "last_name": "R Maiya" + }, + { + "first_name": "Max", + "last_name": "Ehrlich" + }, + { + "first_name": "Abhinav", + "last_name": "Shrivastava" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "APISR: Anime Production Inspired Real-World Anime Super-Resolution", - "authors": "Boyang Wang, Fengyu Yang, Xihang Yu, Chao Zhang, Hanbin Zhao", + "authors": [ + { + "first_name": "Boyang", + "last_name": "Wang" + }, + { + "first_name": "Fengyu", + "last_name": "Yang" + }, + { + "first_name": "Xihang", + "last_name": "Yu" + }, + { + "first_name": "Chao", + "last_name": "Zhang" + }, + { + "first_name": "Hanbin", + "last_name": "Zhao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MVCPS-NeuS: Multi-view Constrained Photometric Stereo for Neural Surface Reconstruction", - "authors": "Hiroaki Santo, Fumio Okura, Yasuyuki Matsushita", + "authors": [ + { + "first_name": "Hiroaki", + "last_name": "Santo" + }, + { + "first_name": "Fumio", + "last_name": "Okura" + }, + { + "first_name": "Yasuyuki", + "last_name": "Matsushita" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding", - "authors": "Le Xue, Ning Yu, Shu Zhang, Artemis Panagopoulou, Junnan Li, Roberto Martín-Martín, Jiajun Wu, Caiming Xiong, Ran Xu, Juan Carlos Niebles, Silvio Savarese", + "authors": [ + { + "first_name": "Le", + "last_name": "Xue" + }, + { + "first_name": "Ning", + "last_name": "Yu" + }, + { + "first_name": "Shu", + "last_name": "Zhang" + }, + { + "first_name": "Artemis", + "last_name": "Panagopoulou" + }, + { + "first_name": "Junnan", + "last_name": "Li" + }, + { + "first_name": "Roberto", + "last_name": "Martín-Martín" + }, + { + "first_name": "Jiajun", + "last_name": "Wu" + }, + { + "first_name": "Caiming", + "last_name": "Xiong" + }, + { + "first_name": "Ran", + "last_name": "Xu" + }, + { + "first_name": "Juan", + "last_name": "Carlos Niebles" + }, + { + "first_name": "Silvio", + "last_name": "Savarese" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Normalizing Flows on the Product Space of SO(3) Manifolds for Probabilistic Human Pose Modeling", - "authors": "Olaf Dünkel, Tim Salzmann, Florian Pfaff", + "authors": [ + { + "first_name": "Olaf", + "last_name": "Dünkel" + }, + { + "first_name": "Tim", + "last_name": "Salzmann" + }, + { + "first_name": "Florian", + "last_name": "Pfaff" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Adapting to Length Shift: FlexiLength Network for Trajectory Prediction", - "authors": "Yi Xu, Yun Fu", + "authors": [ + { + "first_name": "Yi", + "last_name": "Xu" + }, + { + "first_name": "Yun", + "last_name": "Fu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "WorDepth: Variational Language Prior for Monocular Depth Estimation", - "authors": "Ziyao Zeng, Daniel Wang, Fengyu Yang, Hyoungseob Park, Stefano Soatto, Dong Lao, Alex Wong", + "authors": [ + { + "first_name": "Ziyao", + "last_name": "Zeng" + }, + { + "first_name": "Daniel", + "last_name": "Wang" + }, + { + "first_name": "Fengyu", + "last_name": "Yang" + }, + { + "first_name": "Hyoungseob", + "last_name": "Park" + }, + { + "first_name": "Stefano", + "last_name": "Soatto" + }, + { + "first_name": "Dong", + "last_name": "Lao" + }, + { + "first_name": "Alex", + "last_name": "Wong" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "WaveMo: Learning Wavefront Modulations to See Through Scattering", - "authors": "Mingyang Xie, Haiyun Guo, Brandon Y. Feng, Lingbo Jin, Ashok Veeraraghavan, Christopher A. Metzler", + "authors": [ + { + "first_name": "Mingyang", + "last_name": "Xie" + }, + { + "first_name": "Haiyun", + "last_name": "Guo" + }, + { + "first_name": "Brandon", + "last_name": "Y. Feng" + }, + { + "first_name": "Lingbo", + "last_name": "Jin" + }, + { + "first_name": "Ashok", + "last_name": "Veeraraghavan" + }, + { + "first_name": "Christopher", + "last_name": "A. Metzler" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ReGenNet: Towards Human Action-Reaction Synthesis", - "authors": "Liang Xu, Yizhou Zhou, Yichao Yan, Xin Jin, Wenhan Zhu, Fengyun Rao, Xiaokang Yang, Wenjun Zeng", + "authors": [ + { + "first_name": "Liang", + "last_name": "Xu" + }, + { + "first_name": "Yizhou", + "last_name": "Zhou" + }, + { + "first_name": "Yichao", + "last_name": "Yan" + }, + { + "first_name": "Xin", + "last_name": "Jin" + }, + { + "first_name": "Wenhan", + "last_name": "Zhu" + }, + { + "first_name": "Fengyun", + "last_name": "Rao" + }, + { + "first_name": "Xiaokang", + "last_name": "Yang" + }, + { + "first_name": "Wenjun", + "last_name": "Zeng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "A Simple Baseline for Efficient Hand Mesh Reconstruction", - "authors": "Zhishan Zhou, Shihao Zhou, Zhi Lv, Minqiang Zou, Yao Tang, Jiajun Liang", + "authors": [ + { + "first_name": "Zhishan", + "last_name": "Zhou" + }, + { + "first_name": "Shihao", + "last_name": "Zhou" + }, + { + "first_name": "Zhi", + "last_name": "Lv" + }, + { + "first_name": "Minqiang", + "last_name": "Zou" + }, + { + "first_name": "Yao", + "last_name": "Tang" + }, + { + "first_name": "Jiajun", + "last_name": "Liang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Integrating Efficient Optimal Transport and Functional Maps For Unsupervised Shape Correspondence Learning", - "authors": "Tung Le, Khai Nguyen, Shanlin Sun, Nhat Ho, Xiaohui Xie", + "authors": [ + { + "first_name": "Tung", + "last_name": "Le" + }, + { + "first_name": "Khai", + "last_name": "Nguyen" + }, + { + "first_name": "Shanlin", + "last_name": "Sun" + }, + { + "first_name": "Nhat", + "last_name": "Ho" + }, + { + "first_name": "Xiaohui", + "last_name": "Xie" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding", - "authors": "Zhen Li, Mingdeng Cao, Xintao Wang, Zhongang Qi, Ming-Ming Cheng, Ying Shan", + "authors": [ + { + "first_name": "Zhen", + "last_name": "Li" + }, + { + "first_name": "Mingdeng", + "last_name": "Cao" + }, + { + "first_name": "Xintao", + "last_name": "Wang" + }, + { + "first_name": "Zhongang", + "last_name": "Qi" + }, + { + "first_name": "Ming-Ming", + "last_name": "Cheng" + }, + { + "first_name": "Ying", + "last_name": "Shan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Score-Guided Diffusion for 3D Human Recovery", - "authors": "Anastasis Stathopoulos, Ligong Han, Dimitris Metaxas", + "authors": [ + { + "first_name": "Anastasis", + "last_name": "Stathopoulos" + }, + { + "first_name": "Ligong", + "last_name": "Han" + }, + { + "first_name": "Dimitris", + "last_name": "Metaxas" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Check Locate Rectify: A Training-Free Layout Calibration System for Text-to-Image Generation", - "authors": "Biao Gong, Siteng Huang, Yutong Feng, Shiwei Zhang, Yuyuan Li, Yu Liu", + "authors": [ + { + "first_name": "Biao", + "last_name": "Gong" + }, + { + "first_name": "Siteng", + "last_name": "Huang" + }, + { + "first_name": "Yutong", + "last_name": "Feng" + }, + { + "first_name": "Shiwei", + "last_name": "Zhang" + }, + { + "first_name": "Yuyuan", + "last_name": "Li" + }, + { + "first_name": "Yu", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ODCR: Orthogonal Decoupling Contrastive Regularization for Unpaired Image Dehazing", - "authors": "Zhongze Wang, Haitao Zhao, Jingchao Peng, Lujian Yao, Kaijie Zhao", + "authors": [ + { + "first_name": "Zhongze", + "last_name": "Wang" + }, + { + "first_name": "Haitao", + "last_name": "Zhao" + }, + { + "first_name": "Jingchao", + "last_name": "Peng" + }, + { + "first_name": "Lujian", + "last_name": "Yao" + }, + { + "first_name": "Kaijie", + "last_name": "Zhao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Pose-Transformed Equivariant Network for 3D Point Trajectory Prediction", - "authors": "Ruixuan Yu, Jian Sun", + "authors": [ + { + "first_name": "Ruixuan", + "last_name": "Yu" + }, + { + "first_name": "Jian", + "last_name": "Sun" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "OmniSeg3D: Omniversal 3D Segmentation via Hierarchical Contrastive Learning", - "authors": "Haiyang Ying, Yixuan Yin, Jinzhi Zhang, Fan Wang, Tao Yu, Ruqi Huang, Lu Fang", + "authors": [ + { + "first_name": "Haiyang", + "last_name": "Ying" + }, + { + "first_name": "Yixuan", + "last_name": "Yin" + }, + { + "first_name": "Jinzhi", + "last_name": "Zhang" + }, + { + "first_name": "Fan", + "last_name": "Wang" + }, + { + "first_name": "Tao", + "last_name": "Yu" + }, + { + "first_name": "Ruqi", + "last_name": "Huang" + }, + { + "first_name": "Lu", + "last_name": "Fang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Revisiting Sampson Approximations for Geometric Estimation Problems", - "authors": "Felix Rydell, Angélica Torres, Viktor Larsson", + "authors": [ + { + "first_name": "Felix", + "last_name": "Rydell" + }, + { + "first_name": "Angélica", + "last_name": "Torres" + }, + { + "first_name": "Viktor", + "last_name": "Larsson" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Fixed Point Diffusion Models", - "authors": "Xingjian Bai, Luke Melas-Kyriazi", + "authors": [ + { + "first_name": "Xingjian", + "last_name": "Bai" + }, + { + "first_name": "Luke", + "last_name": "Melas-Kyriazi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Simple Semantic-Aided Few-Shot Learning", - "authors": "Hai Zhang, Junzhe Xu, Shanlin Jiang, Zhenan He", + "authors": [ + { + "first_name": "Hai", + "last_name": "Zhang" + }, + { + "first_name": "Junzhe", + "last_name": "Xu" + }, + { + "first_name": "Shanlin", + "last_name": "Jiang" + }, + { + "first_name": "Zhenan", + "last_name": "He" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "A Unified Framework for Microscopy Defocus Deblur with Multi-Pyramid Transformer and Contrastive Learning", - "authors": "Yuelin Zhang, Pengyu Zheng, Wanquan Yan, Chengyu Fang, Shing Shin Cheng", + "authors": [ + { + "first_name": "Yuelin", + "last_name": "Zhang" + }, + { + "first_name": "Pengyu", + "last_name": "Zheng" + }, + { + "first_name": "Wanquan", + "last_name": "Yan" + }, + { + "first_name": "Chengyu", + "last_name": "Fang" + }, + { + "first_name": "Shing", + "last_name": "Shin Cheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Frozen Feature Augmentation for Few-Shot Image Classification", - "authors": "Andreas Bär, Neil Houlsby, Mostafa Dehghani, Manoj Kumar", + "authors": [ + { + "first_name": "Andreas", + "last_name": "Bär" + }, + { + "first_name": "Neil", + "last_name": "Houlsby" + }, + { + "first_name": "Mostafa", + "last_name": "Dehghani" + }, + { + "first_name": "Manoj", + "last_name": "Kumar" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Residual Learning in Diffusion Models", - "authors": "Junyu Zhang, Daochang Liu, Eunbyung Park, Shichao Zhang, Chang Xu", + "authors": [ + { + "first_name": "Junyu", + "last_name": "Zhang" + }, + { + "first_name": "Daochang", + "last_name": "Liu" + }, + { + "first_name": "Eunbyung", + "last_name": "Park" + }, + { + "first_name": "Shichao", + "last_name": "Zhang" + }, + { + "first_name": "Chang", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Leveraging Cross-Modal Neighbor Representation for Improved CLIP Classification", - "authors": "Chao Yi, Lu Ren, De-Chuan Zhan, Han-Jia Ye", + "authors": [ + { + "first_name": "Chao", + "last_name": "Yi" + }, + { + "first_name": "Lu", + "last_name": "Ren" + }, + { + "first_name": "De-Chuan", + "last_name": "Zhan" + }, + { + "first_name": "Han-Jia", + "last_name": "Ye" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Beyond Textual Constraints: Learning Novel Diffusion Conditions with Fewer Examples", - "authors": "Yuyang Yu, Bangzhen Liu, Chenxi Zheng, Xuemiao Xu, Huaidong Zhang, Shengfeng He", + "authors": [ + { + "first_name": "Yuyang", + "last_name": "Yu" + }, + { + "first_name": "Bangzhen", + "last_name": "Liu" + }, + { + "first_name": "Chenxi", + "last_name": "Zheng" + }, + { + "first_name": "Xuemiao", + "last_name": "Xu" + }, + { + "first_name": "Huaidong", + "last_name": "Zhang" + }, + { + "first_name": "Shengfeng", + "last_name": "He" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Incorporating Geo-Diverse Knowledge into Prompting for Increased Geographical Robustness in Object Recognition", - "authors": "Kyle Buettner, Sina Malakouti, Xiang Lorraine Li, Adriana Kovashka", + "authors": [ + { + "first_name": "Kyle", + "last_name": "Buettner" + }, + { + "first_name": "Sina", + "last_name": "Malakouti" + }, + { + "first_name": "Xiang", + "last_name": "Lorraine Li" + }, + { + "first_name": "Adriana", + "last_name": "Kovashka" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Revisiting Adversarial Training Under Long-Tailed Distributions", - "authors": "Xinli Yue, Ningping Mou, Qian Wang, Lingchen Zhao", + "authors": [ + { + "first_name": "Xinli", + "last_name": "Yue" + }, + { + "first_name": "Ningping", + "last_name": "Mou" + }, + { + "first_name": "Qian", + "last_name": "Wang" + }, + { + "first_name": "Lingchen", + "last_name": "Zhao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Exploiting Style Latent Flows for Generalizing Deepfake Video Detection", - "authors": "Jongwook Choi, Taehoon Kim, Yonghyun Jeong, Seungryul Baek, Jongwon Choi", + "authors": [ + { + "first_name": "Jongwook", + "last_name": "Choi" + }, + { + "first_name": "Taehoon", + "last_name": "Kim" + }, + { + "first_name": "Yonghyun", + "last_name": "Jeong" + }, + { + "first_name": "Seungryul", + "last_name": "Baek" + }, + { + "first_name": "Jongwon", + "last_name": "Choi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PIN: Positional Insert Unlocks Object Localisation Abilities in VLMs", - "authors": "Michael Dorkenwald, Nimrod Barazani, Cees G. M. Snoek, Yuki M. Asano", + "authors": [ + { + "first_name": "Michael", + "last_name": "Dorkenwald" + }, + { + "first_name": "Nimrod", + "last_name": "Barazani" + }, + { + "first_name": "Cees", + "last_name": "G. M. Snoek" + }, + { + "first_name": "Yuki", + "last_name": "M. Asano" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "UniGarmentManip: A Unified Framework for Category-Level Garment Manipulation via Dense Visual Correspondence", - "authors": "Ruihai Wu, Haoran Lu, Yiyan Wang, Yubo Wang, Hao Dong", + "authors": [ + { + "first_name": "Ruihai", + "last_name": "Wu" + }, + { + "first_name": "Haoran", + "last_name": "Lu" + }, + { + "first_name": "Yiyan", + "last_name": "Wang" + }, + { + "first_name": "Yubo", + "last_name": "Wang" + }, + { + "first_name": "Hao", + "last_name": "Dong" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Multi-Attribute Interactions Matter for 3D Visual Grounding", - "authors": "Can Xu, Yuehui Han, Rui Xu, Le Hui, Jin Xie, Jian Yang", + "authors": [ + { + "first_name": "Can", + "last_name": "Xu" + }, + { + "first_name": "Yuehui", + "last_name": "Han" + }, + { + "first_name": "Rui", + "last_name": "Xu" + }, + { + "first_name": "Le", + "last_name": "Hui" + }, + { + "first_name": "Jin", + "last_name": "Xie" + }, + { + "first_name": "Jian", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Video-P2P: Video Editing with Cross-attention Control", - "authors": "Shaoteng Liu, Yuechen Zhang, Wenbo Li, Zhe Lin, Jiaya Jia", + "authors": [ + { + "first_name": "Shaoteng", + "last_name": "Liu" + }, + { + "first_name": "Yuechen", + "last_name": "Zhang" + }, + { + "first_name": "Wenbo", + "last_name": "Li" + }, + { + "first_name": "Zhe", + "last_name": "Lin" + }, + { + "first_name": "Jiaya", + "last_name": "Jia" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Hunting Attributes: Context Prototype-Aware Learning for Weakly Supervised Semantic Segmentation", - "authors": "Feilong Tang, Zhongxing Xu, Zhaojun Qu, Wei Feng, Xingjian Jiang, Zongyuan Ge", + "authors": [ + { + "first_name": "Feilong", + "last_name": "Tang" + }, + { + "first_name": "Zhongxing", + "last_name": "Xu" + }, + { + "first_name": "Zhaojun", + "last_name": "Qu" + }, + { + "first_name": "Wei", + "last_name": "Feng" + }, + { + "first_name": "Xingjian", + "last_name": "Jiang" + }, + { + "first_name": "Zongyuan", + "last_name": "Ge" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SCINeRF: Neural Radiance Fields from a Snapshot Compressive Image", - "authors": "Yunhao Li, Xiaodong Wang, Ping Wang, Xin Yuan, Peidong Liu", + "authors": [ + { + "first_name": "Yunhao", + "last_name": "Li" + }, + { + "first_name": "Xiaodong", + "last_name": "Wang" + }, + { + "first_name": "Ping", + "last_name": "Wang" + }, + { + "first_name": "Xin", + "last_name": "Yuan" + }, + { + "first_name": "Peidong", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PIE-NeRF: Physics-based Interactive Elastodynamics with NeRF", - "authors": "Yutao Feng, Yintong Shang, Xuan Li, Tianjia Shao, Chenfanfu Jiang, Yin Yang", + "authors": [ + { + "first_name": "Yutao", + "last_name": "Feng" + }, + { + "first_name": "Yintong", + "last_name": "Shang" + }, + { + "first_name": "Xuan", + "last_name": "Li" + }, + { + "first_name": "Tianjia", + "last_name": "Shao" + }, + { + "first_name": "Chenfanfu", + "last_name": "Jiang" + }, + { + "first_name": "Yin", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Improved Visual Grounding through Self-Consistent Explanations", - "authors": "Ruozhen He, Paola Cascante-Bonilla, Ziyan Yang, Alexander C. Berg, Vicente Ordonez", + "authors": [ + { + "first_name": "Ruozhen", + "last_name": "He" + }, + { + "first_name": "Paola", + "last_name": "Cascante-Bonilla" + }, + { + "first_name": "Ziyan", + "last_name": "Yang" + }, + { + "first_name": "Alexander", + "last_name": "C. Berg" + }, + { + "first_name": "Vicente", + "last_name": "Ordonez" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models", - "authors": "Zhang Li, Biao Yang, Qiang Liu, Zhiyin Ma, Shuo Zhang, Jingxu Yang, Yabo Sun, Yuliang Liu, Xiang Bai", + "authors": [ + { + "first_name": "Zhang", + "last_name": "Li" + }, + { + "first_name": "Biao", + "last_name": "Yang" + }, + { + "first_name": "Qiang", + "last_name": "Liu" + }, + { + "first_name": "Zhiyin", + "last_name": "Ma" + }, + { + "first_name": "Shuo", + "last_name": "Zhang" + }, + { + "first_name": "Jingxu", + "last_name": "Yang" + }, + { + "first_name": "Yabo", + "last_name": "Sun" + }, + { + "first_name": "Yuliang", + "last_name": "Liu" + }, + { + "first_name": "Xiang", + "last_name": "Bai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FlashAvatar: High-fidelity Head Avatar with Efficient Gaussian Embedding", - "authors": "Jun Xiang, Xuan Gao, Yudong Guo, Juyong Zhang", + "authors": [ + { + "first_name": "Jun", + "last_name": "Xiang" + }, + { + "first_name": "Xuan", + "last_name": "Gao" + }, + { + "first_name": "Yudong", + "last_name": "Guo" + }, + { + "first_name": "Juyong", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DifFlow3D: Toward Robust Uncertainty-Aware Scene Flow Estimation with Iterative Diffusion-Based Refinement", - "authors": "Jiuming Liu, Guangming Wang, Weicai Ye, Chaokang Jiang, Jinru Han, Zhe Liu, Guofeng Zhang, Dalong Du, Hesheng Wang", + "authors": [ + { + "first_name": "Jiuming", + "last_name": "Liu" + }, + { + "first_name": "Guangming", + "last_name": "Wang" + }, + { + "first_name": "Weicai", + "last_name": "Ye" + }, + { + "first_name": "Chaokang", + "last_name": "Jiang" + }, + { + "first_name": "Jinru", + "last_name": "Han" + }, + { + "first_name": "Zhe", + "last_name": "Liu" + }, + { + "first_name": "Guofeng", + "last_name": "Zhang" + }, + { + "first_name": "Dalong", + "last_name": "Du" + }, + { + "first_name": "Hesheng", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Decompose-and-Compose: A Compositional Approach to Mitigating Spurious Correlation", - "authors": "Fahimeh Hosseini Noohdani, Parsa Hosseini, Aryan Yazdan Parast, Hamidreza Yaghoubi Araghi, Mahdieh Soleymani Baghshah", + "authors": [ + { + "first_name": "Fahimeh", + "last_name": "Hosseini Noohdani" + }, + { + "first_name": "Parsa", + "last_name": "Hosseini" + }, + { + "first_name": "Aryan", + "last_name": "Yazdan Parast" + }, + { + "first_name": "Hamidreza", + "last_name": "Yaghoubi Araghi" + }, + { + "first_name": "Mahdieh", + "last_name": "Soleymani Baghshah" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FlashEval: Towards Fast and Accurate Evaluation of Text-to-image Diffusion Generative Models", - "authors": "Lin Zhao, Tianchen Zhao, Zinan Lin, Xuefei Ning, Guohao Dai, Huazhong Yang, Yu Wang", + "authors": [ + { + "first_name": "Lin", + "last_name": "Zhao" + }, + { + "first_name": "Tianchen", + "last_name": "Zhao" + }, + { + "first_name": "Zinan", + "last_name": "Lin" + }, + { + "first_name": "Xuefei", + "last_name": "Ning" + }, + { + "first_name": "Guohao", + "last_name": "Dai" + }, + { + "first_name": "Huazhong", + "last_name": "Yang" + }, + { + "first_name": "Yu", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ZERO-IG: Zero-Shot Illumination-Guided Joint Denoising and Adaptive Enhancement for Low-Light Images", - "authors": "Yiqi Shi, Duo Liu, Liguo Zhang, Ye Tian, Xuezhi Xia, Xiaojing Fu", + "authors": [ + { + "first_name": "Yiqi", + "last_name": "Shi" + }, + { + "first_name": "Duo", + "last_name": "Liu" + }, + { + "first_name": "Liguo", + "last_name": "Zhang" + }, + { + "first_name": "Ye", + "last_name": "Tian" + }, + { + "first_name": "Xuezhi", + "last_name": "Xia" + }, + { + "first_name": "Xiaojing", + "last_name": "Fu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "View From Above: Orthogonal-View aware Cross-view Localization", - "authors": "Shan Wang, Chuong Nguyen, Jiawei Liu, Yanhao Zhang, Sundaram Muthu, Fahira Afzal Maken, Kaihao Zhang, Hongdong Li", + "authors": [ + { + "first_name": "Shan", + "last_name": "Wang" + }, + { + "first_name": "Chuong", + "last_name": "Nguyen" + }, + { + "first_name": "Jiawei", + "last_name": "Liu" + }, + { + "first_name": "Yanhao", + "last_name": "Zhang" + }, + { + "first_name": "Sundaram", + "last_name": "Muthu" + }, + { + "first_name": "Fahira", + "last_name": "Afzal Maken" + }, + { + "first_name": "Kaihao", + "last_name": "Zhang" + }, + { + "first_name": "Hongdong", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FinePOSE: Fine-Grained Prompt-Driven 3D Human Pose Estimation via Diffusion Models", - "authors": "Jinglin Xu, Yijie Guo, Yuxin Peng", + "authors": [ + { + "first_name": "Jinglin", + "last_name": "Xu" + }, + { + "first_name": "Yijie", + "last_name": "Guo" + }, + { + "first_name": "Yuxin", + "last_name": "Peng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "BEM: Balanced and Entropy-based Mix for Long-Tailed Semi-Supervised Learning", - "authors": "Hongwei Zheng, Linyuan Zhou, Han Li, Jinming Su, Xiaoming Wei, Xiaoming Xu", + "authors": [ + { + "first_name": "Hongwei", + "last_name": "Zheng" + }, + { + "first_name": "Linyuan", + "last_name": "Zhou" + }, + { + "first_name": "Han", + "last_name": "Li" + }, + { + "first_name": "Jinming", + "last_name": "Su" + }, + { + "first_name": "Xiaoming", + "last_name": "Wei" + }, + { + "first_name": "Xiaoming", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting", - "authors": "Hongyu Zhou, Jiahao Shao, Lu Xu, Dongfeng Bai, Weichao Qiu, Bingbing Liu, Yue Wang, Andreas Geiger, Yiyi Liao", + "authors": [ + { + "first_name": "Hongyu", + "last_name": "Zhou" + }, + { + "first_name": "Jiahao", + "last_name": "Shao" + }, + { + "first_name": "Lu", + "last_name": "Xu" + }, + { + "first_name": "Dongfeng", + "last_name": "Bai" + }, + { + "first_name": "Weichao", + "last_name": "Qiu" + }, + { + "first_name": "Bingbing", + "last_name": "Liu" + }, + { + "first_name": "Yue", + "last_name": "Wang" + }, + { + "first_name": "Andreas", + "last_name": "Geiger" + }, + { + "first_name": "Yiyi", + "last_name": "Liao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DreamPropeller: Supercharge Text-to-3D Generation with Parallel Sampling", - "authors": "Linqi Zhou, Andy Shih, Chenlin Meng, Stefano Ermon", + "authors": [ + { + "first_name": "Linqi", + "last_name": "Zhou" + }, + { + "first_name": "Andy", + "last_name": "Shih" + }, + { + "first_name": "Chenlin", + "last_name": "Meng" + }, + { + "first_name": "Stefano", + "last_name": "Ermon" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PeVL: Pose-Enhanced Vision-Language Model for Fine-Grained Human Action Recognition", - "authors": "Haosong Zhang, Mei Chee Leong, Liyuan Li, Weisi Lin", + "authors": [ + { + "first_name": "Haosong", + "last_name": "Zhang" + }, + { + "first_name": "Mei", + "last_name": "Chee Leong" + }, + { + "first_name": "Liyuan", + "last_name": "Li" + }, + { + "first_name": "Weisi", + "last_name": "Lin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DeepCache: Accelerating Diffusion Models for Free", - "authors": "Xinyin Ma, Gongfan Fang, Xinchao Wang", + "authors": [ + { + "first_name": "Xinyin", + "last_name": "Ma" + }, + { + "first_name": "Gongfan", + "last_name": "Fang" + }, + { + "first_name": "Xinchao", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GeoAuxNet: Towards Universal 3D Representation Learning for Multi-sensor Point Clouds", - "authors": "Shengjun Zhang, Xin Fei, Yueqi Duan", + "authors": [ + { + "first_name": "Shengjun", + "last_name": "Zhang" + }, + { + "first_name": "Xin", + "last_name": "Fei" + }, + { + "first_name": "Yueqi", + "last_name": "Duan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Unveiling the Power of Audio-Visual Early Fusion Transformers with Dense Interactions through Masked Modeling", - "authors": "Shentong Mo, Pedro Morgado", + "authors": [ + { + "first_name": "Shentong", + "last_name": "Mo" + }, + { + "first_name": "Pedro", + "last_name": "Morgado" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning Correlation Structures for Vision Transformers", - "authors": "Manjin Kim, Paul Hongsuck Seo, Cordelia Schmid, Minsu Cho", + "authors": [ + { + "first_name": "Manjin", + "last_name": "Kim" + }, + { + "first_name": "Paul", + "last_name": "Hongsuck Seo" + }, + { + "first_name": "Cordelia", + "last_name": "Schmid" + }, + { + "first_name": "Minsu", + "last_name": "Cho" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Dysen-VDM: Empowering Dynamics-aware Text-to-Video Diffusion with LLMs", - "authors": "Hao Fei, Shengqiong Wu, Wei Ji, Hanwang Zhang, Tat-Seng Chua", + "authors": [ + { + "first_name": "Hao", + "last_name": "Fei" + }, + { + "first_name": "Shengqiong", + "last_name": "Wu" + }, + { + "first_name": "Wei", + "last_name": "Ji" + }, + { + "first_name": "Hanwang", + "last_name": "Zhang" + }, + { + "first_name": "Tat-Seng", + "last_name": "Chua" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PrPSeg: Universal Proposition Learning for Panoramic Renal Pathology Segmentation", - "authors": "Ruining Deng, Quan Liu, Can Cui, Tianyuan Yao, Jialin Yue, Juming Xiong, Lining Yu, Yifei Wu, Mengmeng Yin, Yu Wang, Shilin Zhao, Yucheng Tang, Haichun Yang, Yuankai Huo", + "authors": [ + { + "first_name": "Ruining", + "last_name": "Deng" + }, + { + "first_name": "Quan", + "last_name": "Liu" + }, + { + "first_name": "Can", + "last_name": "Cui" + }, + { + "first_name": "Tianyuan", + "last_name": "Yao" + }, + { + "first_name": "Jialin", + "last_name": "Yue" + }, + { + "first_name": "Juming", + "last_name": "Xiong" + }, + { + "first_name": "Lining", + "last_name": "Yu" + }, + { + "first_name": "Yifei", + "last_name": "Wu" + }, + { + "first_name": "Mengmeng", + "last_name": "Yin" + }, + { + "first_name": "Yu", + "last_name": "Wang" + }, + { + "first_name": "Shilin", + "last_name": "Zhao" + }, + { + "first_name": "Yucheng", + "last_name": "Tang" + }, + { + "first_name": "Haichun", + "last_name": "Yang" + }, + { + "first_name": "Yuankai", + "last_name": "Huo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "RepKPU: Point Cloud Upsampling with Kernel Point Representation and Deformation", - "authors": "Yi Rong, Haoran Zhou, Kang Xia, Cheng Mei, Jiahao Wang, Tong Lu", + "authors": [ + { + "first_name": "Yi", + "last_name": "Rong" + }, + { + "first_name": "Haoran", + "last_name": "Zhou" + }, + { + "first_name": "Kang", + "last_name": "Xia" + }, + { + "first_name": "Cheng", + "last_name": "Mei" + }, + { + "first_name": "Jiahao", + "last_name": "Wang" + }, + { + "first_name": "Tong", + "last_name": "Lu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ConCon-Chi: Concept-Context Chimera Benchmark for Personalized Vision-Language Tasks", - "authors": "Andrea Rosasco, Stefano Berti, Giulia Pasquale, Damiano Malafronte, Shogo Sato, Hiroyuki Segawa, Tetsugo Inada, Lorenzo Natale", + "authors": [ + { + "first_name": "Andrea", + "last_name": "Rosasco" + }, + { + "first_name": "Stefano", + "last_name": "Berti" + }, + { + "first_name": "Giulia", + "last_name": "Pasquale" + }, + { + "first_name": "Damiano", + "last_name": "Malafronte" + }, + { + "first_name": "Shogo", + "last_name": "Sato" + }, + { + "first_name": "Hiroyuki", + "last_name": "Segawa" + }, + { + "first_name": "Tetsugo", + "last_name": "Inada" + }, + { + "first_name": "Lorenzo", + "last_name": "Natale" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Weakly-Supervised Audio-Visual Video Parsing with Prototype-based Pseudo-Labeling", - "authors": "Kranthi Kumar Rachavarapu, Kalyan Ramakrishnan, Rajagopalan A. N.", + "authors": [ + { + "first_name": "Kranthi", + "last_name": "Kumar Rachavarapu" + }, + { + "first_name": "Kalyan", + "last_name": "Ramakrishnan" + }, + { + "first_name": "Rajagopalan", + "last_name": "A. N." + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Intraoperative 2D/3D Image Registration via Differentiable X-ray Rendering", - "authors": "Vivek Gopalakrishnan, Neel Dey, Polina Golland", + "authors": [ + { + "first_name": "Vivek", + "last_name": "Gopalakrishnan" + }, + { + "first_name": "Neel", + "last_name": "Dey" + }, + { + "first_name": "Polina", + "last_name": "Golland" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MICap: A Unified Model for Identity-Aware Movie Descriptions", - "authors": "Haran Raajesh, Naveen Reddy Desanur, Zeeshan Khan, Makarand Tapaswi", + "authors": [ + { + "first_name": "Haran", + "last_name": "Raajesh" + }, + { + "first_name": "Naveen", + "last_name": "Reddy Desanur" + }, + { + "first_name": "Zeeshan", + "last_name": "Khan" + }, + { + "first_name": "Makarand", + "last_name": "Tapaswi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MonoDiff: Monocular 3D Object Detection and Pose Estimation with Diffusion Models", - "authors": "Yasiru Ranasinghe, Deepti Hegde, Vishal M. Patel", + "authors": [ + { + "first_name": "Yasiru", + "last_name": "Ranasinghe" + }, + { + "first_name": "Deepti", + "last_name": "Hegde" + }, + { + "first_name": "Vishal", + "last_name": "M. Patel" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "General Object Foundation Model for Images and Videos at Scale", - "authors": "Junfeng Wu, Yi Jiang, Qihao Liu, Zehuan Yuan, Xiang Bai, Song Bai", + "authors": [ + { + "first_name": "Junfeng", + "last_name": "Wu" + }, + { + "first_name": "Yi", + "last_name": "Jiang" + }, + { + "first_name": "Qihao", + "last_name": "Liu" + }, + { + "first_name": "Zehuan", + "last_name": "Yuan" + }, + { + "first_name": "Xiang", + "last_name": "Bai" + }, + { + "first_name": "Song", + "last_name": "Bai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "An Upload-Efficient Scheme for Transferring Knowledge From a Server-Side Pre-trained Generator to Clients in Heterogeneous Federated Learning", - "authors": "Jianqing Zhang, Yang Liu, Yang Hua, Jian Cao", + "authors": [ + { + "first_name": "Jianqing", + "last_name": "Zhang" + }, + { + "first_name": "Yang", + "last_name": "Liu" + }, + { + "first_name": "Yang", + "last_name": "Hua" + }, + { + "first_name": "Jian", + "last_name": "Cao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers", - "authors": "Yawar Siddiqui, Antonio Alliegro, Alexey Artemov, Tatiana Tommasi, Daniele Sirigatti, Vladislav Rosov, Angela Dai, Matthias Nießner", + "authors": [ + { + "first_name": "Yawar", + "last_name": "Siddiqui" + }, + { + "first_name": "Antonio", + "last_name": "Alliegro" + }, + { + "first_name": "Alexey", + "last_name": "Artemov" + }, + { + "first_name": "Tatiana", + "last_name": "Tommasi" + }, + { + "first_name": "Daniele", + "last_name": "Sirigatti" + }, + { + "first_name": "Vladislav", + "last_name": "Rosov" + }, + { + "first_name": "Angela", + "last_name": "Dai" + }, + { + "first_name": "Matthias", + "last_name": "Nießner" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Inlier Confidence Calibration for Point Cloud Registration", - "authors": "Yongzhe Yuan, Yue Wu, Xiaolong Fan, Maoguo Gong, Qiguang Miao, Wenping Ma", + "authors": [ + { + "first_name": "Yongzhe", + "last_name": "Yuan" + }, + { + "first_name": "Yue", + "last_name": "Wu" + }, + { + "first_name": "Xiaolong", + "last_name": "Fan" + }, + { + "first_name": "Maoguo", + "last_name": "Gong" + }, + { + "first_name": "Qiguang", + "last_name": "Miao" + }, + { + "first_name": "Wenping", + "last_name": "Ma" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Instance-aware Exploration-Verification-Exploitation for Instance ImageGoal Navigation", - "authors": "Xiaohan Lei, Min Wang, Wengang Zhou, Li Li, Houqiang Li", + "authors": [ + { + "first_name": "Xiaohan", + "last_name": "Lei" + }, + { + "first_name": "Min", + "last_name": "Wang" + }, + { + "first_name": "Wengang", + "last_name": "Zhou" + }, + { + "first_name": "Li", + "last_name": "Li" + }, + { + "first_name": "Houqiang", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion", - "authors": "Minghua Liu, Ruoxi Shi, Linghao Chen, Zhuoyang Zhang, Chao Xu, Xinyue Wei, Hansheng Chen, Chong Zeng, Jiayuan Gu, Hao Su", + "authors": [ + { + "first_name": "Minghua", + "last_name": "Liu" + }, + { + "first_name": "Ruoxi", + "last_name": "Shi" + }, + { + "first_name": "Linghao", + "last_name": "Chen" + }, + { + "first_name": "Zhuoyang", + "last_name": "Zhang" + }, + { + "first_name": "Chao", + "last_name": "Xu" + }, + { + "first_name": "Xinyue", + "last_name": "Wei" + }, + { + "first_name": "Hansheng", + "last_name": "Chen" + }, + { + "first_name": "Chong", + "last_name": "Zeng" + }, + { + "first_name": "Jiayuan", + "last_name": "Gu" + }, + { + "first_name": "Hao", + "last_name": "Su" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Image Restoration by Denoising Diffusion Models with Iteratively Preconditioned Guidance", - "authors": "Tomer Garber, Tom Tirer", + "authors": [ + { + "first_name": "Tomer", + "last_name": "Garber" + }, + { + "first_name": "Tom", + "last_name": "Tirer" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Let's Think Outside the Box: Exploring Leap-of-Thought in Large Language Models with Creative Humor Generation", - "authors": "Shanshan Zhong, Zhongzhan Huang, Shanghua Gao, Wushao Wen, Liang Lin, Marinka Zitnik, Pan Zhou", + "authors": [ + { + "first_name": "Shanshan", + "last_name": "Zhong" + }, + { + "first_name": "Zhongzhan", + "last_name": "Huang" + }, + { + "first_name": "Shanghua", + "last_name": "Gao" + }, + { + "first_name": "Wushao", + "last_name": "Wen" + }, + { + "first_name": "Liang", + "last_name": "Lin" + }, + { + "first_name": "Marinka", + "last_name": "Zitnik" + }, + { + "first_name": "Pan", + "last_name": "Zhou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SceneFun3D: Fine-Grained Functionality and Affordance Understanding in 3D Scenes", - "authors": "Alexandros Delitzas, Ayca Takmaz, Federico Tombari, Robert Sumner, Marc Pollefeys, Francis Engelmann", + "authors": [ + { + "first_name": "Alexandros", + "last_name": "Delitzas" + }, + { + "first_name": "Ayca", + "last_name": "Takmaz" + }, + { + "first_name": "Federico", + "last_name": "Tombari" + }, + { + "first_name": "Robert", + "last_name": "Sumner" + }, + { + "first_name": "Marc", + "last_name": "Pollefeys" + }, + { + "first_name": "Francis", + "last_name": "Engelmann" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Readout Guidance: Learning Control from Diffusion Features", - "authors": "Grace Luo, Trevor Darrell, Oliver Wang, Dan B Goldman, Aleksander Holynski", + "authors": [ + { + "first_name": "Grace", + "last_name": "Luo" + }, + { + "first_name": "Trevor", + "last_name": "Darrell" + }, + { + "first_name": "Oliver", + "last_name": "Wang" + }, + { + "first_name": "Dan", + "last_name": "B Goldman" + }, + { + "first_name": "Aleksander", + "last_name": "Holynski" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "A Unified Approach for Text- and Image-guided 4D Scene Generation", - "authors": "Yufeng Zheng, Xueting Li, Koki Nagano, Sifei Liu, Otmar Hilliges, Shalini De Mello", + "authors": [ + { + "first_name": "Yufeng", + "last_name": "Zheng" + }, + { + "first_name": "Xueting", + "last_name": "Li" + }, + { + "first_name": "Koki", + "last_name": "Nagano" + }, + { + "first_name": "Sifei", + "last_name": "Liu" + }, + { + "first_name": "Otmar", + "last_name": "Hilliges" + }, + { + "first_name": "Shalini", + "last_name": "De Mello" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians", - "authors": "Liangxiao Hu, Hongwen Zhang, Yuxiang Zhang, Boyao Zhou, Boning Liu, Shengping Zhang, Liqiang Nie", + "authors": [ + { + "first_name": "Liangxiao", + "last_name": "Hu" + }, + { + "first_name": "Hongwen", + "last_name": "Zhang" + }, + { + "first_name": "Yuxiang", + "last_name": "Zhang" + }, + { + "first_name": "Boyao", + "last_name": "Zhou" + }, + { + "first_name": "Boning", + "last_name": "Liu" + }, + { + "first_name": "Shengping", + "last_name": "Zhang" + }, + { + "first_name": "Liqiang", + "last_name": "Nie" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MTMMC: A Large-Scale Real-World Multi-Modal Camera Tracking Benchmark", - "authors": "Sanghyun Woo, Kwanyong Park, Inkyu Shin, Myungchul Kim, In So Kweon", + "authors": [ + { + "first_name": "Sanghyun", + "last_name": "Woo" + }, + { + "first_name": "Kwanyong", + "last_name": "Park" + }, + { + "first_name": "Inkyu", + "last_name": "Shin" + }, + { + "first_name": "Myungchul", + "last_name": "Kim" + }, + { + "first_name": "In", + "last_name": "So Kweon" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Enhanced Motion-Text Alignment for Image-to-Video Transfer Learning", - "authors": "Wei Zhang, Chaoqun Wan, Tongliang Liu, Xinmei Tian, Xu Shen, Jieping Ye", + "authors": [ + { + "first_name": "Wei", + "last_name": "Zhang" + }, + { + "first_name": "Chaoqun", + "last_name": "Wan" + }, + { + "first_name": "Tongliang", + "last_name": "Liu" + }, + { + "first_name": "Xinmei", + "last_name": "Tian" + }, + { + "first_name": "Xu", + "last_name": "Shen" + }, + { + "first_name": "Jieping", + "last_name": "Ye" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DAP: A Dynamic Adversarial Patch for Evading Person Detectors", - "authors": "Amira Guesmi, Ruitian Ding, Muhammad Abdullah Hanif, Ihsen Alouani, Muhammad Shafique", + "authors": [ + { + "first_name": "Amira", + "last_name": "Guesmi" + }, + { + "first_name": "Ruitian", + "last_name": "Ding" + }, + { + "first_name": "Muhammad", + "last_name": "Abdullah Hanif" + }, + { + "first_name": "Ihsen", + "last_name": "Alouani" + }, + { + "first_name": "Muhammad", + "last_name": "Shafique" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learned Lossless Image Compression based on Bit Plane Slicing", - "authors": "Zhe Zhang, Huairui Wang, Zhenzhong Chen, Shan Liu", + "authors": [ + { + "first_name": "Zhe", + "last_name": "Zhang" + }, + { + "first_name": "Huairui", + "last_name": "Wang" + }, + { + "first_name": "Zhenzhong", + "last_name": "Chen" + }, + { + "first_name": "Shan", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "UV-IDM: Identity-Conditioned Latent Diffusion Model for Face UV-Texture Generation", - "authors": "Hong Li, Yutang Feng, Song Xue, Xuhui Liu, Bohan Zeng, Shanglin Li, Boyu Liu, Jianzhuang Liu, Shumin Han, Baochang Zhang", + "authors": [ + { + "first_name": "Hong", + "last_name": "Li" + }, + { + "first_name": "Yutang", + "last_name": "Feng" + }, + { + "first_name": "Song", + "last_name": "Xue" + }, + { + "first_name": "Xuhui", + "last_name": "Liu" + }, + { + "first_name": "Bohan", + "last_name": "Zeng" + }, + { + "first_name": "Shanglin", + "last_name": "Li" + }, + { + "first_name": "Boyu", + "last_name": "Liu" + }, + { + "first_name": "Jianzhuang", + "last_name": "Liu" + }, + { + "first_name": "Shumin", + "last_name": "Han" + }, + { + "first_name": "Baochang", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Mosaic-SDF for 3D Generative Models", - "authors": "Lior Yariv, Omri Puny, Oran Gafni, Yaron Lipman", + "authors": [ + { + "first_name": "Lior", + "last_name": "Yariv" + }, + { + "first_name": "Omri", + "last_name": "Puny" + }, + { + "first_name": "Oran", + "last_name": "Gafni" + }, + { + "first_name": "Yaron", + "last_name": "Lipman" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Diffusion Handles Enabling 3D Edits for Diffusion Models by Lifting Activations to 3D", - "authors": "Karran Pandey, Paul Guerrero, Matheus Gadelha, Yannick Hold-Geoffroy, Karan Singh, Niloy J. Mitra", + "authors": [ + { + "first_name": "Karran", + "last_name": "Pandey" + }, + { + "first_name": "Paul", + "last_name": "Guerrero" + }, + { + "first_name": "Matheus", + "last_name": "Gadelha" + }, + { + "first_name": "Yannick", + "last_name": "Hold-Geoffroy" + }, + { + "first_name": "Karan", + "last_name": "Singh" + }, + { + "first_name": "Niloy", + "last_name": "J. Mitra" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "A Pedestrian is Worth One Prompt: Towards Language Guidance Person Re-Identification", - "authors": "Zexian Yang, Dayan Wu, Chenming Wu, Zheng Lin, Jingzi Gu, Weiping Wang", + "authors": [ + { + "first_name": "Zexian", + "last_name": "Yang" + }, + { + "first_name": "Dayan", + "last_name": "Wu" + }, + { + "first_name": "Chenming", + "last_name": "Wu" + }, + { + "first_name": "Zheng", + "last_name": "Lin" + }, + { + "first_name": "Jingzi", + "last_name": "Gu" + }, + { + "first_name": "Weiping", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Friendly Sharpness-Aware Minimization", - "authors": "Tao Li, Pan Zhou, Zhengbao He, Xinwen Cheng, Xiaolin Huang", + "authors": [ + { + "first_name": "Tao", + "last_name": "Li" + }, + { + "first_name": "Pan", + "last_name": "Zhou" + }, + { + "first_name": "Zhengbao", + "last_name": "He" + }, + { + "first_name": "Xinwen", + "last_name": "Cheng" + }, + { + "first_name": "Xiaolin", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "BIVDiff: A Training-Free Framework for General-Purpose Video Synthesis via Bridging Image and Video Diffusion Models", - "authors": "Fengyuan Shi, Jiaxi Gu, Hang Xu, Songcen Xu, Wei Zhang, Limin Wang", + "authors": [ + { + "first_name": "Fengyuan", + "last_name": "Shi" + }, + { + "first_name": "Jiaxi", + "last_name": "Gu" + }, + { + "first_name": "Hang", + "last_name": "Xu" + }, + { + "first_name": "Songcen", + "last_name": "Xu" + }, + { + "first_name": "Wei", + "last_name": "Zhang" + }, + { + "first_name": "Limin", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "NC-TTT: A Noise Constrastive Approach for Test-Time Training", - "authors": "David Osowiechi, Gustavo A. Vargas Hakim, Mehrdad Noori, Milad Cheraghalikhani, Ali Bahri, Moslem Yazdanpanah, Ismail Ben Ayed, Christian Desrosiers", + "authors": [ + { + "first_name": "David", + "last_name": "Osowiechi" + }, + { + "first_name": "Gustavo", + "last_name": "A. Vargas Hakim" + }, + { + "first_name": "Mehrdad", + "last_name": "Noori" + }, + { + "first_name": "Milad", + "last_name": "Cheraghalikhani" + }, + { + "first_name": "Ali", + "last_name": "Bahri" + }, + { + "first_name": "Moslem", + "last_name": "Yazdanpanah" + }, + { + "first_name": "Ismail", + "last_name": "Ben Ayed" + }, + { + "first_name": "Christian", + "last_name": "Desrosiers" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "NetTrack: Tracking Highly Dynamic Objects with a Net", - "authors": "Guangze Zheng, Shijie Lin, Haobo Zuo, Changhong Fu, Jia Pan", + "authors": [ + { + "first_name": "Guangze", + "last_name": "Zheng" + }, + { + "first_name": "Shijie", + "last_name": "Lin" + }, + { + "first_name": "Haobo", + "last_name": "Zuo" + }, + { + "first_name": "Changhong", + "last_name": "Fu" + }, + { + "first_name": "Jia", + "last_name": "Pan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Grounded Question-Answering in Long Egocentric Videos", - "authors": "Shangzhe Di, Weidi Xie", + "authors": [ + { + "first_name": "Shangzhe", + "last_name": "Di" + }, + { + "first_name": "Weidi", + "last_name": "Xie" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HPNet: Dynamic Trajectory Forecasting with Historical Prediction Attention", - "authors": "Xiaolong Tang, Meina Kan, Shiguang Shan, Zhilong Ji, Jinfeng Bai, Xilin Chen", + "authors": [ + { + "first_name": "Xiaolong", + "last_name": "Tang" + }, + { + "first_name": "Meina", + "last_name": "Kan" + }, + { + "first_name": "Shiguang", + "last_name": "Shan" + }, + { + "first_name": "Zhilong", + "last_name": "Ji" + }, + { + "first_name": "Jinfeng", + "last_name": "Bai" + }, + { + "first_name": "Xilin", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Flexible Depth Completion for Sparse and Varying Point Densities", - "authors": "Jinhyung Park, Yu-Jhe Li, Kris Kitani", + "authors": [ + { + "first_name": "Jinhyung", + "last_name": "Park" + }, + { + "first_name": "Yu-Jhe", + "last_name": "Li" + }, + { + "first_name": "Kris", + "last_name": "Kitani" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Small Scale Data-Free Knowledge Distillation", - "authors": "He Liu, Yikai Wang, Huaping Liu, Fuchun Sun, Anbang Yao", + "authors": [ + { + "first_name": "He", + "last_name": "Liu" + }, + { + "first_name": "Yikai", + "last_name": "Wang" + }, + { + "first_name": "Huaping", + "last_name": "Liu" + }, + { + "first_name": "Fuchun", + "last_name": "Sun" + }, + { + "first_name": "Anbang", + "last_name": "Yao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Shadows Don't Lie and Lines Can't Bend! Generative Models don't know Projective Geometry...for now", - "authors": "Ayush Sarkar, Hanlin Mai, Amitabh Mahapatra, Svetlana Lazebnik, D.A. Forsyth, Anand Bhattad", + "authors": [ + { + "first_name": "Ayush", + "last_name": "Sarkar" + }, + { + "first_name": "Hanlin", + "last_name": "Mai" + }, + { + "first_name": "Amitabh", + "last_name": "Mahapatra" + }, + { + "first_name": "Svetlana", + "last_name": "Lazebnik" + }, + { + "first_name": "D.A.", + "last_name": "Forsyth" + }, + { + "first_name": "Anand", + "last_name": "Bhattad" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CFPL-FAS: Class Free Prompt Learning for Generalizable Face Anti-spoofing", - "authors": "Ajian Liu, Shuai Xue, Jianwen Gan, Jun Wan, Yanyan Liang, Jiankang Deng, Sergio Escalera, Zhen Lei", + "authors": [ + { + "first_name": "Ajian", + "last_name": "Liu" + }, + { + "first_name": "Shuai", + "last_name": "Xue" + }, + { + "first_name": "Jianwen", + "last_name": "Gan" + }, + { + "first_name": "Jun", + "last_name": "Wan" + }, + { + "first_name": "Yanyan", + "last_name": "Liang" + }, + { + "first_name": "Jiankang", + "last_name": "Deng" + }, + { + "first_name": "Sergio", + "last_name": "Escalera" + }, + { + "first_name": "Zhen", + "last_name": "Lei" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SI-MIL: Taming Deep MIL for Self-Interpretability in Gigapixel Histopathology", - "authors": "Saarthak Kapse, Pushpak Pati, Srijan Das, Jingwei Zhang, Chao Chen, Maria Vakalopoulou, Joel Saltz, Dimitris Samaras, Rajarsi R. Gupta, Prateek Prasanna", + "authors": [ + { + "first_name": "Saarthak", + "last_name": "Kapse" + }, + { + "first_name": "Pushpak", + "last_name": "Pati" + }, + { + "first_name": "Srijan", + "last_name": "Das" + }, + { + "first_name": "Jingwei", + "last_name": "Zhang" + }, + { + "first_name": "Chao", + "last_name": "Chen" + }, + { + "first_name": "Maria", + "last_name": "Vakalopoulou" + }, + { + "first_name": "Joel", + "last_name": "Saltz" + }, + { + "first_name": "Dimitris", + "last_name": "Samaras" + }, + { + "first_name": "Rajarsi", + "last_name": "R. Gupta" + }, + { + "first_name": "Prateek", + "last_name": "Prasanna" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GEARS: Local Geometry-aware Hand-object Interaction Synthesis", - "authors": "Keyang Zhou, Bharat Lal Bhatnagar, Jan Eric Lenssen, Gerard Pons-Moll", + "authors": [ + { + "first_name": "Keyang", + "last_name": "Zhou" + }, + { + "first_name": "Bharat", + "last_name": "Lal Bhatnagar" + }, + { + "first_name": "Jan", + "last_name": "Eric Lenssen" + }, + { + "first_name": "Gerard", + "last_name": "Pons-Moll" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Open Vocabulary Semantic Scene Sketch Understanding", - "authors": "Ahmed Bourouis, Judith E. Fan, Yulia Gryaditskaya", + "authors": [ + { + "first_name": "Ahmed", + "last_name": "Bourouis" + }, + { + "first_name": "Judith", + "last_name": "E. Fan" + }, + { + "first_name": "Yulia", + "last_name": "Gryaditskaya" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "IntrinsicAvatar: Physically Based Inverse Rendering of Dynamic Humans from Monocular Videos via Explicit Ray Tracing", - "authors": "Shaofei Wang, Bozidar Antic, Andreas Geiger, Siyu Tang", + "authors": [ + { + "first_name": "Shaofei", + "last_name": "Wang" + }, + { + "first_name": "Bozidar", + "last_name": "Antic" + }, + { + "first_name": "Andreas", + "last_name": "Geiger" + }, + { + "first_name": "Siyu", + "last_name": "Tang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Efficient Detection of Long Consistent Cycles and its Application to Distributed Synchronization", - "authors": "Shaohan Li, Yunpeng Shi, Gilad Lerman", + "authors": [ + { + "first_name": "Shaohan", + "last_name": "Li" + }, + { + "first_name": "Yunpeng", + "last_name": "Shi" + }, + { + "first_name": "Gilad", + "last_name": "Lerman" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LayoutFormer: Hierarchical Text Detection Towards Scene Text Understanding", - "authors": "Min Liang, Jia-Wei Ma, Xiaobin Zhu, Jingyan Qin, Xu-Cheng Yin", + "authors": [ + { + "first_name": "Min", + "last_name": "Liang" + }, + { + "first_name": "Jia-Wei", + "last_name": "Ma" + }, + { + "first_name": "Xiaobin", + "last_name": "Zhu" + }, + { + "first_name": "Jingyan", + "last_name": "Qin" + }, + { + "first_name": "Xu-Cheng", + "last_name": "Yin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Vlogger: Make Your Dream A Vlog", - "authors": "Shaobin Zhuang, Kunchang Li, Xinyuan Chen, Yaohui Wang, Ziwei Liu, Yu Qiao, Yali Wang", + "authors": [ + { + "first_name": "Shaobin", + "last_name": "Zhuang" + }, + { + "first_name": "Kunchang", + "last_name": "Li" + }, + { + "first_name": "Xinyuan", + "last_name": "Chen" + }, + { + "first_name": "Yaohui", + "last_name": "Wang" + }, + { + "first_name": "Ziwei", + "last_name": "Liu" + }, + { + "first_name": "Yu", + "last_name": "Qiao" + }, + { + "first_name": "Yali", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CodedEvents: Optimal Point-Spread-Function Engineering for 3D-Tracking with Event Cameras", - "authors": "Sachin Shah, Matthew A. Chan, Haoming Cai, Jingxi Chen, Sakshum Kulshrestha, Chahat Deep Singh, Yiannis Aloimonos, Christopher A. Metzler", + "authors": [ + { + "first_name": "Sachin", + "last_name": "Shah" + }, + { + "first_name": "Matthew", + "last_name": "A. Chan" + }, + { + "first_name": "Haoming", + "last_name": "Cai" + }, + { + "first_name": "Jingxi", + "last_name": "Chen" + }, + { + "first_name": "Sakshum", + "last_name": "Kulshrestha" + }, + { + "first_name": "Chahat", + "last_name": "Deep Singh" + }, + { + "first_name": "Yiannis", + "last_name": "Aloimonos" + }, + { + "first_name": "Christopher", + "last_name": "A. Metzler" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GLOW: Global Layout Aware Attacks on Object Detection", - "authors": "Jun Bao, Buyu Liu, Kui Ren, Jun Yu", + "authors": [ + { + "first_name": "Jun", + "last_name": "Bao" + }, + { + "first_name": "Buyu", + "last_name": "Liu" + }, + { + "first_name": "Kui", + "last_name": "Ren" + }, + { + "first_name": "Jun", + "last_name": "Yu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning Discriminative Dynamics with Label Corruption for Noisy Label Detection", - "authors": "Suyeon Kim, Dongha Lee, SeongKu Kang, Sukang Chae, Sanghwan Jang, Hwanjo Yu", + "authors": [ + { + "first_name": "Suyeon", + "last_name": "Kim" + }, + { + "first_name": "Dongha", + "last_name": "Lee" + }, + { + "first_name": "SeongKu", + "last_name": "Kang" + }, + { + "first_name": "Sukang", + "last_name": "Chae" + }, + { + "first_name": "Sanghwan", + "last_name": "Jang" + }, + { + "first_name": "Hwanjo", + "last_name": "Yu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Neural 3D Strokes: Creating Stylized 3D Scenes with Vectorized 3D Strokes", - "authors": "Hao-Bin Duan, Miao Wang, Yan-Xun Li, Yong-Liang Yang", + "authors": [ + { + "first_name": "Hao-Bin", + "last_name": "Duan" + }, + { + "first_name": "Miao", + "last_name": "Wang" + }, + { + "first_name": "Yan-Xun", + "last_name": "Li" + }, + { + "first_name": "Yong-Liang", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SIRA: Scalable Inter-frame Relation and Association for Radar Perception", - "authors": "Ryoma Yataka, Pu Wang, Petros Boufounos, Ryuhei Takahashi", + "authors": [ + { + "first_name": "Ryoma", + "last_name": "Yataka" + }, + { + "first_name": "Pu", + "last_name": "Wang" + }, + { + "first_name": "Petros", + "last_name": "Boufounos" + }, + { + "first_name": "Ryuhei", + "last_name": "Takahashi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "VOODOO 3D: Volumetric Portrait Disentanglement For One-Shot 3D Head Reenactment", - "authors": "Phong Tran, Egor Zakharov, Long-Nhat Ho, Anh Tuan Tran, Liwen Hu, Hao Li", + "authors": [ + { + "first_name": "Phong", + "last_name": "Tran" + }, + { + "first_name": "Egor", + "last_name": "Zakharov" + }, + { + "first_name": "Long-Nhat", + "last_name": "Ho" + }, + { + "first_name": "Anh", + "last_name": "Tuan Tran" + }, + { + "first_name": "Liwen", + "last_name": "Hu" + }, + { + "first_name": "Hao", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Visual Fact Checker: Enabling High-Fidelity Detailed Caption Generation", - "authors": "Yunhao Ge, Xiaohui Zeng, Jacob Samuel Huffman, Tsung-Yi Lin, Ming-Yu Liu, Yin Cui", + "authors": [ + { + "first_name": "Yunhao", + "last_name": "Ge" + }, + { + "first_name": "Xiaohui", + "last_name": "Zeng" + }, + { + "first_name": "Jacob", + "last_name": "Samuel Huffman" + }, + { + "first_name": "Tsung-Yi", + "last_name": "Lin" + }, + { + "first_name": "Ming-Yu", + "last_name": "Liu" + }, + { + "first_name": "Yin", + "last_name": "Cui" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Communication-Efficient Collaborative Perception via Information Filling with Codebook", - "authors": "Yue Hu, Juntong Peng, Sifei Liu, Junhao Ge, Si Liu, Siheng Chen", + "authors": [ + { + "first_name": "Yue", + "last_name": "Hu" + }, + { + "first_name": "Juntong", + "last_name": "Peng" + }, + { + "first_name": "Sifei", + "last_name": "Liu" + }, + { + "first_name": "Junhao", + "last_name": "Ge" + }, + { + "first_name": "Si", + "last_name": "Liu" + }, + { + "first_name": "Siheng", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DiPrompT: Disentangled Prompt Tuning for Multiple Latent Domain Generalization in Federated Learning", - "authors": "Sikai Bai, Jie Zhang, Song Guo, Shuaicheng Li, Jingcai Guo, Jun Hou, Tao Han, Xiaocheng Lu", + "authors": [ + { + "first_name": "Sikai", + "last_name": "Bai" + }, + { + "first_name": "Jie", + "last_name": "Zhang" + }, + { + "first_name": "Song", + "last_name": "Guo" + }, + { + "first_name": "Shuaicheng", + "last_name": "Li" + }, + { + "first_name": "Jingcai", + "last_name": "Guo" + }, + { + "first_name": "Jun", + "last_name": "Hou" + }, + { + "first_name": "Tao", + "last_name": "Han" + }, + { + "first_name": "Xiaocheng", + "last_name": "Lu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MVD-Fusion: Single-view 3D via Depth-consistent Multi-view Generation", - "authors": "Hanzhe Hu, Zhizhuo Zhou, Varun Jampani, Shubham Tulsiani", + "authors": [ + { + "first_name": "Hanzhe", + "last_name": "Hu" + }, + { + "first_name": "Zhizhuo", + "last_name": "Zhou" + }, + { + "first_name": "Varun", + "last_name": "Jampani" + }, + { + "first_name": "Shubham", + "last_name": "Tulsiani" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Effective Video Mirror Detection with Inconsistent Motion Cues", - "authors": "Alex Warren, Ke Xu, Jiaying Lin, Gary K.L. Tam, Rynson W.H. Lau", + "authors": [ + { + "first_name": "Alex", + "last_name": "Warren" + }, + { + "first_name": "Ke", + "last_name": "Xu" + }, + { + "first_name": "Jiaying", + "last_name": "Lin" + }, + { + "first_name": "Gary", + "last_name": "K.L. Tam" + }, + { + "first_name": "Rynson", + "last_name": "W.H. Lau" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Multi-Object Tracking in the Dark", - "authors": "Xinzhe Wang, Kang Ma, Qiankun Liu, Yunhao Zou, Ying Fu", + "authors": [ + { + "first_name": "Xinzhe", + "last_name": "Wang" + }, + { + "first_name": "Kang", + "last_name": "Ma" + }, + { + "first_name": "Qiankun", + "last_name": "Liu" + }, + { + "first_name": "Yunhao", + "last_name": "Zou" + }, + { + "first_name": "Ying", + "last_name": "Fu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "UniHuman: A Unified Model For Editing Human Images in the Wild", - "authors": "Nannan Li, Qing Liu, Krishna Kumar Singh, Yilin Wang, Jianming Zhang, Bryan A. Plummer, Zhe Lin", + "authors": [ + { + "first_name": "Nannan", + "last_name": "Li" + }, + { + "first_name": "Qing", + "last_name": "Liu" + }, + { + "first_name": "Krishna", + "last_name": "Kumar Singh" + }, + { + "first_name": "Yilin", + "last_name": "Wang" + }, + { + "first_name": "Jianming", + "last_name": "Zhang" + }, + { + "first_name": "Bryan", + "last_name": "A. Plummer" + }, + { + "first_name": "Zhe", + "last_name": "Lin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DiffAgent: Fast and Accurate Text-to-Image API Selection with Large Language Model", - "authors": "Lirui Zhao, Yue Yang, Kaipeng Zhang, Wenqi Shao, Yuxin Zhang, Yu Qiao, Ping Luo, Rongrong Ji", + "authors": [ + { + "first_name": "Lirui", + "last_name": "Zhao" + }, + { + "first_name": "Yue", + "last_name": "Yang" + }, + { + "first_name": "Kaipeng", + "last_name": "Zhang" + }, + { + "first_name": "Wenqi", + "last_name": "Shao" + }, + { + "first_name": "Yuxin", + "last_name": "Zhang" + }, + { + "first_name": "Yu", + "last_name": "Qiao" + }, + { + "first_name": "Ping", + "last_name": "Luo" + }, + { + "first_name": "Rongrong", + "last_name": "Ji" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "In Search of a Data Transformation That Accelerates Neural Field Training", - "authors": "Junwon Seo, Sangyoon Lee, Kwang In Kim, Jaeho Lee", + "authors": [ + { + "first_name": "Junwon", + "last_name": "Seo" + }, + { + "first_name": "Sangyoon", + "last_name": "Lee" + }, + { + "first_name": "Kwang", + "last_name": "In Kim" + }, + { + "first_name": "Jaeho", + "last_name": "Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Zero-Painter: Training-Free Layout Control for Text-to-Image Synthesis", - "authors": "Marianna Ohanyan, Hayk Manukyan, Zhangyang Wang, Shant Navasardyan, Humphrey Shi", + "authors": [ + { + "first_name": "Marianna", + "last_name": "Ohanyan" + }, + { + "first_name": "Hayk", + "last_name": "Manukyan" + }, + { + "first_name": "Zhangyang", + "last_name": "Wang" + }, + { + "first_name": "Shant", + "last_name": "Navasardyan" + }, + { + "first_name": "Humphrey", + "last_name": "Shi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DiffLoc: Diffusion Model for Outdoor LiDAR Localization", - "authors": "Wen Li, Yuyang Yang, Shangshu Yu, Guosheng Hu, Chenglu Wen, Ming Cheng, Cheng Wang", + "authors": [ + { + "first_name": "Wen", + "last_name": "Li" + }, + { + "first_name": "Yuyang", + "last_name": "Yang" + }, + { + "first_name": "Shangshu", + "last_name": "Yu" + }, + { + "first_name": "Guosheng", + "last_name": "Hu" + }, + { + "first_name": "Chenglu", + "last_name": "Wen" + }, + { + "first_name": "Ming", + "last_name": "Cheng" + }, + { + "first_name": "Cheng", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards 3D Vision with Low-Cost Single-Photon Cameras", - "authors": "Fangzhou Mu, Carter Sifferman, Sacha Jungerman, Yiquan Li, Mark Han, Michael Gleicher, Mohit Gupta, Yin Li", + "authors": [ + { + "first_name": "Fangzhou", + "last_name": "Mu" + }, + { + "first_name": "Carter", + "last_name": "Sifferman" + }, + { + "first_name": "Sacha", + "last_name": "Jungerman" + }, + { + "first_name": "Yiquan", + "last_name": "Li" + }, + { + "first_name": "Mark", + "last_name": "Han" + }, + { + "first_name": "Michael", + "last_name": "Gleicher" + }, + { + "first_name": "Mohit", + "last_name": "Gupta" + }, + { + "first_name": "Yin", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "WonderJourney: Going from Anywhere to Everywhere", - "authors": "Hong-Xing Yu, Haoyi Duan, Junhwa Hur, Kyle Sargent, Michael Rubinstein, William T. Freeman, Forrester Cole, Deqing Sun, Noah Snavely, Jiajun Wu, Charles Herrmann", + "authors": [ + { + "first_name": "Hong-Xing", + "last_name": "Yu" + }, + { + "first_name": "Haoyi", + "last_name": "Duan" + }, + { + "first_name": "Junhwa", + "last_name": "Hur" + }, + { + "first_name": "Kyle", + "last_name": "Sargent" + }, + { + "first_name": "Michael", + "last_name": "Rubinstein" + }, + { + "first_name": "William", + "last_name": "T. Freeman" + }, + { + "first_name": "Forrester", + "last_name": "Cole" + }, + { + "first_name": "Deqing", + "last_name": "Sun" + }, + { + "first_name": "Noah", + "last_name": "Snavely" + }, + { + "first_name": "Jiajun", + "last_name": "Wu" + }, + { + "first_name": "Charles", + "last_name": "Herrmann" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "On Scaling Up a Multilingual Vision and Language Model", - "authors": "Xi Chen, Josip Djolonga, Piotr Padlewski, Basil Mustafa, Soravit Changpinyo, Jialin Wu, Carlos Riquelme Ruiz, Sebastian Goodman, Xiao Wang, Yi Tay, Siamak Shakeri, Mostafa Dehghani, Daniel Salz, Mario Lucic, Michael Tschannen, Arsha Nagrani, Hexiang Hu, Mandar Joshi, Bo Pang, Ceslee Montgomery, Paulina Pietrzyk, Marvin Ritter, AJ Piergiovanni, Matthias Minderer, Filip Pavetic, Austin Waters, Gang Li, Ibrahim Alabdulmohsin, Lucas Beyer, Julien Amelot, Kenton Lee, Andreas Peter Steiner, Yang Li, Daniel Keysers, Anurag Arnab, Yuanzhong Xu, Keran Rong, Alexander Kolesnikov, Mojtaba Seyedhosseini, Anelia Angelova, Xiaohua Zhai, Neil Houlsby, Radu Soricut", + "authors": [ + { + "first_name": "Xi", + "last_name": "Chen" + }, + { + "first_name": "Josip", + "last_name": "Djolonga" + }, + { + "first_name": "Piotr", + "last_name": "Padlewski" + }, + { + "first_name": "Basil", + "last_name": "Mustafa" + }, + { + "first_name": "Soravit", + "last_name": "Changpinyo" + }, + { + "first_name": "Jialin", + "last_name": "Wu" + }, + { + "first_name": "Carlos", + "last_name": "Riquelme Ruiz" + }, + { + "first_name": "Sebastian", + "last_name": "Goodman" + }, + { + "first_name": "Xiao", + "last_name": "Wang" + }, + { + "first_name": "Yi", + "last_name": "Tay" + }, + { + "first_name": "Siamak", + "last_name": "Shakeri" + }, + { + "first_name": "Mostafa", + "last_name": "Dehghani" + }, + { + "first_name": "Daniel", + "last_name": "Salz" + }, + { + "first_name": "Mario", + "last_name": "Lucic" + }, + { + "first_name": "Michael", + "last_name": "Tschannen" + }, + { + "first_name": "Arsha", + "last_name": "Nagrani" + }, + { + "first_name": "Hexiang", + "last_name": "Hu" + }, + { + "first_name": "Mandar", + "last_name": "Joshi" + }, + { + "first_name": "Bo", + "last_name": "Pang" + }, + { + "first_name": "Ceslee", + "last_name": "Montgomery" + }, + { + "first_name": "Paulina", + "last_name": "Pietrzyk" + }, + { + "first_name": "Marvin", + "last_name": "Ritter" + }, + { + "first_name": "AJ", + "last_name": "Piergiovanni" + }, + { + "first_name": "Matthias", + "last_name": "Minderer" + }, + { + "first_name": "Filip", + "last_name": "Pavetic" + }, + { + "first_name": "Austin", + "last_name": "Waters" + }, + { + "first_name": "Gang", + "last_name": "Li" + }, + { + "first_name": "Ibrahim", + "last_name": "Alabdulmohsin" + }, + { + "first_name": "Lucas", + "last_name": "Beyer" + }, + { + "first_name": "Julien", + "last_name": "Amelot" + }, + { + "first_name": "Kenton", + "last_name": "Lee" + }, + { + "first_name": "Andreas", + "last_name": "Peter Steiner" + }, + { + "first_name": "Yang", + "last_name": "Li" + }, + { + "first_name": "Daniel", + "last_name": "Keysers" + }, + { + "first_name": "Anurag", + "last_name": "Arnab" + }, + { + "first_name": "Yuanzhong", + "last_name": "Xu" + }, + { + "first_name": "Keran", + "last_name": "Rong" + }, + { + "first_name": "Alexander", + "last_name": "Kolesnikov" + }, + { + "first_name": "Mojtaba", + "last_name": "Seyedhosseini" + }, + { + "first_name": "Anelia", + "last_name": "Angelova" + }, + { + "first_name": "Xiaohua", + "last_name": "Zhai" + }, + { + "first_name": "Neil", + "last_name": "Houlsby" + }, + { + "first_name": "Radu", + "last_name": "Soricut" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Day-Night Cross-domain Vehicle Re-identification", - "authors": "Hongchao Li, Jingong Chen, Aihua Zheng, Yong Wu, Yonglong Luo", + "authors": [ + { + "first_name": "Hongchao", + "last_name": "Li" + }, + { + "first_name": "Jingong", + "last_name": "Chen" + }, + { + "first_name": "Aihua", + "last_name": "Zheng" + }, + { + "first_name": "Yong", + "last_name": "Wu" + }, + { + "first_name": "Yonglong", + "last_name": "Luo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling", - "authors": "Sherwin Bahmani, Ivan Skorokhodov, Victor Rong, Gordon Wetzstein, Leonidas Guibas, Peter Wonka, Sergey Tulyakov, Jeong Joon Park, Andrea Tagliasacchi, David B. Lindell", + "authors": [ + { + "first_name": "Sherwin", + "last_name": "Bahmani" + }, + { + "first_name": "Ivan", + "last_name": "Skorokhodov" + }, + { + "first_name": "Victor", + "last_name": "Rong" + }, + { + "first_name": "Gordon", + "last_name": "Wetzstein" + }, + { + "first_name": "Leonidas", + "last_name": "Guibas" + }, + { + "first_name": "Peter", + "last_name": "Wonka" + }, + { + "first_name": "Sergey", + "last_name": "Tulyakov" + }, + { + "first_name": "Jeong", + "last_name": "Joon Park" + }, + { + "first_name": "Andrea", + "last_name": "Tagliasacchi" + }, + { + "first_name": "David", + "last_name": "B. Lindell" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Adversarial Distillation Based on Slack Matching and Attribution Region Alignment", - "authors": "Shenglin Yin, Zhen Xiao, Mingxuan Song, Jieyi Long", + "authors": [ + { + "first_name": "Shenglin", + "last_name": "Yin" + }, + { + "first_name": "Zhen", + "last_name": "Xiao" + }, + { + "first_name": "Mingxuan", + "last_name": "Song" + }, + { + "first_name": "Jieyi", + "last_name": "Long" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Boosting Spike Camera Image Reconstruction from a Perspective of Dealing with Spike Fluctuations", - "authors": "Rui Zhao, Ruiqin Xiong, Jing Zhao, Jian Zhang, Xiaopeng Fan, Zhaofei Yu, Tiejun Huang", + "authors": [ + { + "first_name": "Rui", + "last_name": "Zhao" + }, + { + "first_name": "Ruiqin", + "last_name": "Xiong" + }, + { + "first_name": "Jing", + "last_name": "Zhao" + }, + { + "first_name": "Jian", + "last_name": "Zhang" + }, + { + "first_name": "Xiaopeng", + "last_name": "Fan" + }, + { + "first_name": "Zhaofei", + "last_name": "Yu" + }, + { + "first_name": "Tiejun", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Text-guided Explorable Image Super-resolution", - "authors": "Kanchana Vaishnavi Gandikota, Paramanand Chandramouli", + "authors": [ + { + "first_name": "Kanchana", + "last_name": "Vaishnavi Gandikota" + }, + { + "first_name": "Paramanand", + "last_name": "Chandramouli" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FreeControl: Training-Free Spatial Control of Any Text-to-Image Diffusion Model with Any Condition", - "authors": "Sicheng Mo, Fangzhou Mu, Kuan Heng Lin, Yanli Liu, Bochen Guan, Yin Li, Bolei Zhou", + "authors": [ + { + "first_name": "Sicheng", + "last_name": "Mo" + }, + { + "first_name": "Fangzhou", + "last_name": "Mu" + }, + { + "first_name": "Kuan", + "last_name": "Heng Lin" + }, + { + "first_name": "Yanli", + "last_name": "Liu" + }, + { + "first_name": "Bochen", + "last_name": "Guan" + }, + { + "first_name": "Yin", + "last_name": "Li" + }, + { + "first_name": "Bolei", + "last_name": "Zhou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "VMC: Video Motion Customization using Temporal Attention Adaption for Text-to-Video Diffusion Models", - "authors": "Hyeonho Jeong, Geon Yeong Park, Jong Chul Ye", + "authors": [ + { + "first_name": "Hyeonho", + "last_name": "Jeong" + }, + { + "first_name": "Geon", + "last_name": "Yeong Park" + }, + { + "first_name": "Jong", + "last_name": "Chul Ye" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Holodeck: Language Guided Generation of 3D Embodied AI Environments", - "authors": "Yue Yang, Fan-Yun Sun, Luca Weihs, Eli VanderBilt, Alvaro Herrasti, Winson Han, Jiajun Wu, Nick Haber, Ranjay Krishna, Lingjie Liu, Chris Callison-Burch, Mark Yatskar, Aniruddha Kembhavi, Christopher Clark", + "authors": [ + { + "first_name": "Yue", + "last_name": "Yang" + }, + { + "first_name": "Fan-Yun", + "last_name": "Sun" + }, + { + "first_name": "Luca", + "last_name": "Weihs" + }, + { + "first_name": "Eli", + "last_name": "VanderBilt" + }, + { + "first_name": "Alvaro", + "last_name": "Herrasti" + }, + { + "first_name": "Winson", + "last_name": "Han" + }, + { + "first_name": "Jiajun", + "last_name": "Wu" + }, + { + "first_name": "Nick", + "last_name": "Haber" + }, + { + "first_name": "Ranjay", + "last_name": "Krishna" + }, + { + "first_name": "Lingjie", + "last_name": "Liu" + }, + { + "first_name": "Chris", + "last_name": "Callison-Burch" + }, + { + "first_name": "Mark", + "last_name": "Yatskar" + }, + { + "first_name": "Aniruddha", + "last_name": "Kembhavi" + }, + { + "first_name": "Christopher", + "last_name": "Clark" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Distilled Datamodel with Reverse Gradient Matching", - "authors": "Jingwen Ye, Ruonan Yu, Songhua Liu, Xinchao Wang", + "authors": [ + { + "first_name": "Jingwen", + "last_name": "Ye" + }, + { + "first_name": "Ruonan", + "last_name": "Yu" + }, + { + "first_name": "Songhua", + "last_name": "Liu" + }, + { + "first_name": "Xinchao", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models", - "authors": "Muyang Li, Tianle Cai, Jiaxin Cao, Qinsheng Zhang, Han Cai, Junjie Bai, Yangqing Jia, Kai Li, Song Han", + "authors": [ + { + "first_name": "Muyang", + "last_name": "Li" + }, + { + "first_name": "Tianle", + "last_name": "Cai" + }, + { + "first_name": "Jiaxin", + "last_name": "Cao" + }, + { + "first_name": "Qinsheng", + "last_name": "Zhang" + }, + { + "first_name": "Han", + "last_name": "Cai" + }, + { + "first_name": "Junjie", + "last_name": "Bai" + }, + { + "first_name": "Yangqing", + "last_name": "Jia" + }, + { + "first_name": "Kai", + "last_name": "Li" + }, + { + "first_name": "Song", + "last_name": "Han" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Improving the Generalization of Segmentation Foundation Model under Distribution Shift via Weakly Supervised Adaptation", - "authors": "Haojie Zhang, Yongyi Su, Xun Xu, Kui Jia", + "authors": [ + { + "first_name": "Haojie", + "last_name": "Zhang" + }, + { + "first_name": "Yongyi", + "last_name": "Su" + }, + { + "first_name": "Xun", + "last_name": "Xu" + }, + { + "first_name": "Kui", + "last_name": "Jia" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Pseudo Label Refinery for Unsupervised Domain Adaptation on Cross-dataset 3D Object Detection", - "authors": "Zhanwei Zhang, Minghao Chen, Shuai Xiao, Liang Peng, Hengjia Li, Binbin Lin, Ping Li, Wenxiao Wang, Boxi Wu, Deng Cai", + "authors": [ + { + "first_name": "Zhanwei", + "last_name": "Zhang" + }, + { + "first_name": "Minghao", + "last_name": "Chen" + }, + { + "first_name": "Shuai", + "last_name": "Xiao" + }, + { + "first_name": "Liang", + "last_name": "Peng" + }, + { + "first_name": "Hengjia", + "last_name": "Li" + }, + { + "first_name": "Binbin", + "last_name": "Lin" + }, + { + "first_name": "Ping", + "last_name": "Li" + }, + { + "first_name": "Wenxiao", + "last_name": "Wang" + }, + { + "first_name": "Boxi", + "last_name": "Wu" + }, + { + "first_name": "Deng", + "last_name": "Cai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Reconstructing Hands in 3D with Transformers", - "authors": "Georgios Pavlakos, Dandan Shan, Ilija Radosavovic, Angjoo Kanazawa, David Fouhey, Jitendra Malik", + "authors": [ + { + "first_name": "Georgios", + "last_name": "Pavlakos" + }, + { + "first_name": "Dandan", + "last_name": "Shan" + }, + { + "first_name": "Ilija", + "last_name": "Radosavovic" + }, + { + "first_name": "Angjoo", + "last_name": "Kanazawa" + }, + { + "first_name": "David", + "last_name": "Fouhey" + }, + { + "first_name": "Jitendra", + "last_name": "Malik" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "AZ-NAS: Assembling Zero-Cost Proxies for Network Architecture Search", - "authors": "Junghyup Lee, Bumsub Ham", + "authors": [ + { + "first_name": "Junghyup", + "last_name": "Lee" + }, + { + "first_name": "Bumsub", + "last_name": "Ham" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Correspondence-Free Non-Rigid Point Set Registration Using Unsupervised Clustering Analysis", - "authors": "Mingyang Zhao, Jingen Jiang, Lei Ma, Shiqing Xin, Gaofeng Meng, Dong-Ming Yan", + "authors": [ + { + "first_name": "Mingyang", + "last_name": "Zhao" + }, + { + "first_name": "Jingen", + "last_name": "Jiang" + }, + { + "first_name": "Lei", + "last_name": "Ma" + }, + { + "first_name": "Shiqing", + "last_name": "Xin" + }, + { + "first_name": "Gaofeng", + "last_name": "Meng" + }, + { + "first_name": "Dong-Ming", + "last_name": "Yan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Improving Physics-Augmented Continuum Neural Radiance Field-Based Geometry-Agnostic System Identification with Lagrangian Particle Optimization", - "authors": "Takuhiro Kaneko", + "authors": [ + { + "first_name": "Takuhiro", + "last_name": "Kaneko" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIP", - "authors": "Jiawang Bai, Kuofeng Gao, Shaobo Min, Shu-Tao Xia, Zhifeng Li, Wei Liu", + "authors": [ + { + "first_name": "Jiawang", + "last_name": "Bai" + }, + { + "first_name": "Kuofeng", + "last_name": "Gao" + }, + { + "first_name": "Shaobo", + "last_name": "Min" + }, + { + "first_name": "Shu-Tao", + "last_name": "Xia" + }, + { + "first_name": "Zhifeng", + "last_name": "Li" + }, + { + "first_name": "Wei", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Beyond Image Super-Resolution for Image Recognition with Task-Driven Perceptual Loss", - "authors": "Jaeha Kim, Junghun Oh, Kyoung Mu Lee", + "authors": [ + { + "first_name": "Jaeha", + "last_name": "Kim" + }, + { + "first_name": "Junghun", + "last_name": "Oh" + }, + { + "first_name": "Kyoung", + "last_name": "Mu Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PELA: Learning Parameter-Efficient Models with Low-Rank Approximation", - "authors": "Yangyang Guo, Guangzhi Wang, Mohan Kankanhalli", + "authors": [ + { + "first_name": "Yangyang", + "last_name": "Guo" + }, + { + "first_name": "Guangzhi", + "last_name": "Wang" + }, + { + "first_name": "Mohan", + "last_name": "Kankanhalli" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies", - "authors": "Xuanchi Ren, Jiahui Huang, Xiaohui Zeng, Ken Museth, Sanja Fidler, Francis Williams", + "authors": [ + { + "first_name": "Xuanchi", + "last_name": "Ren" + }, + { + "first_name": "Jiahui", + "last_name": "Huang" + }, + { + "first_name": "Xiaohui", + "last_name": "Zeng" + }, + { + "first_name": "Ken", + "last_name": "Museth" + }, + { + "first_name": "Sanja", + "last_name": "Fidler" + }, + { + "first_name": "Francis", + "last_name": "Williams" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PixelRNN: In-pixel Recurrent Neural Networks for End-to-end-optimized Perception with Neural Sensors", - "authors": "Haley M. So, Laurie Bose, Piotr Dudek, Gordon Wetzstein", + "authors": [ + { + "first_name": "Haley", + "last_name": "M. So" + }, + { + "first_name": "Laurie", + "last_name": "Bose" + }, + { + "first_name": "Piotr", + "last_name": "Dudek" + }, + { + "first_name": "Gordon", + "last_name": "Wetzstein" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Reconstruction-free Cascaded Adaptive Compressive Sensing", - "authors": "Chenxi Qiu, Tao Yue, Xuemei Hu", + "authors": [ + { + "first_name": "Chenxi", + "last_name": "Qiu" + }, + { + "first_name": "Tao", + "last_name": "Yue" + }, + { + "first_name": "Xuemei", + "last_name": "Hu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch", - "authors": "Xidong Wu, Shangqian Gao, Zeyu Zhang, Zhenzhen Li, Runxue Bao, Yanfu Zhang, Xiaoqian Wang, Heng Huang", + "authors": [ + { + "first_name": "Xidong", + "last_name": "Wu" + }, + { + "first_name": "Shangqian", + "last_name": "Gao" + }, + { + "first_name": "Zeyu", + "last_name": "Zhang" + }, + { + "first_name": "Zhenzhen", + "last_name": "Li" + }, + { + "first_name": "Runxue", + "last_name": "Bao" + }, + { + "first_name": "Yanfu", + "last_name": "Zhang" + }, + { + "first_name": "Xiaoqian", + "last_name": "Wang" + }, + { + "first_name": "Heng", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Constructing and Exploring Intermediate Domains in Mixed Domain Semi-supervised Medical Image Segmentation", - "authors": "Qinghe Ma, Jian Zhang, Lei Qi, Qian Yu, Yinghuan Shi, Yang Gao", + "authors": [ + { + "first_name": "Qinghe", + "last_name": "Ma" + }, + { + "first_name": "Jian", + "last_name": "Zhang" + }, + { + "first_name": "Lei", + "last_name": "Qi" + }, + { + "first_name": "Qian", + "last_name": "Yu" + }, + { + "first_name": "Yinghuan", + "last_name": "Shi" + }, + { + "first_name": "Yang", + "last_name": "Gao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DUSt3R: Geometric 3D Vision Made Easy", - "authors": "Shuzhe Wang, Vincent Leroy, Yohann Cabon, Boris Chidlovskii, Jerome Revaud", + "authors": [ + { + "first_name": "Shuzhe", + "last_name": "Wang" + }, + { + "first_name": "Vincent", + "last_name": "Leroy" + }, + { + "first_name": "Yohann", + "last_name": "Cabon" + }, + { + "first_name": "Boris", + "last_name": "Chidlovskii" + }, + { + "first_name": "Jerome", + "last_name": "Revaud" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "From Isolated Islands to Pangea: Unifying Semantic Space for Human Action Understanding", - "authors": "Yong-Lu Li, Xiaoqian Wu, Xinpeng Liu, Zehao Wang, Yiming Dou, Yikun Ji, Junyi Zhang, Yixing Li, Xudong Lu, Jingru Tan, Cewu Lu", + "authors": [ + { + "first_name": "Yong-Lu", + "last_name": "Li" + }, + { + "first_name": "Xiaoqian", + "last_name": "Wu" + }, + { + "first_name": "Xinpeng", + "last_name": "Liu" + }, + { + "first_name": "Zehao", + "last_name": "Wang" + }, + { + "first_name": "Yiming", + "last_name": "Dou" + }, + { + "first_name": "Yikun", + "last_name": "Ji" + }, + { + "first_name": "Junyi", + "last_name": "Zhang" + }, + { + "first_name": "Yixing", + "last_name": "Li" + }, + { + "first_name": "Xudong", + "last_name": "Lu" + }, + { + "first_name": "Jingru", + "last_name": "Tan" + }, + { + "first_name": "Cewu", + "last_name": "Lu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Bootstrapping Autonomous Driving Radars with Self-Supervised Learning", - "authors": "Yiduo Hao, Sohrab Madani, Junfeng Guan, Mohammed Alloulah, Saurabh Gupta, Haitham Hassanieh", + "authors": [ + { + "first_name": "Yiduo", + "last_name": "Hao" + }, + { + "first_name": "Sohrab", + "last_name": "Madani" + }, + { + "first_name": "Junfeng", + "last_name": "Guan" + }, + { + "first_name": "Mohammed", + "last_name": "Alloulah" + }, + { + "first_name": "Saurabh", + "last_name": "Gupta" + }, + { + "first_name": "Haitham", + "last_name": "Hassanieh" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Robust Distillation via Untargeted and Targeted Intermediate Adversarial Samples", - "authors": "Junhao Dong, Piotr Koniusz, Junxi Chen, Z. Jane Wang, Yew-Soon Ong", + "authors": [ + { + "first_name": "Junhao", + "last_name": "Dong" + }, + { + "first_name": "Piotr", + "last_name": "Koniusz" + }, + { + "first_name": "Junxi", + "last_name": "Chen" + }, + { + "first_name": "Z.", + "last_name": "Jane Wang" + }, + { + "first_name": "Yew-Soon", + "last_name": "Ong" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "USE: Universal Segment Embeddings for Open-Vocabulary Image Segmentation", - "authors": "Xiaoqi Wang, Wenbin He, Xiwei Xuan, Clint Sebastian, Jorge Piazentin Ono, Xin Li, Sima Behpour, Thang Doan, Liang Gou, Han-Wei Shen, Liu Ren", + "authors": [ + { + "first_name": "Xiaoqi", + "last_name": "Wang" + }, + { + "first_name": "Wenbin", + "last_name": "He" + }, + { + "first_name": "Xiwei", + "last_name": "Xuan" + }, + { + "first_name": "Clint", + "last_name": "Sebastian" + }, + { + "first_name": "Jorge", + "last_name": "Piazentin Ono" + }, + { + "first_name": "Xin", + "last_name": "Li" + }, + { + "first_name": "Sima", + "last_name": "Behpour" + }, + { + "first_name": "Thang", + "last_name": "Doan" + }, + { + "first_name": "Liang", + "last_name": "Gou" + }, + { + "first_name": "Han-Wei", + "last_name": "Shen" + }, + { + "first_name": "Liu", + "last_name": "Ren" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Functional Diffusion", - "authors": "Biao Zhang, Peter Wonka", + "authors": [ + { + "first_name": "Biao", + "last_name": "Zhang" + }, + { + "first_name": "Peter", + "last_name": "Wonka" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Soften to Defend: Towards Adversarial Robustness via Self-Guided Label Refinement", - "authors": "Zhuorong Li, Daiwei Yu, Lina Wei, Canghong Jin, Yun Zhang, Sixian Chan", + "authors": [ + { + "first_name": "Zhuorong", + "last_name": "Li" + }, + { + "first_name": "Daiwei", + "last_name": "Yu" + }, + { + "first_name": "Lina", + "last_name": "Wei" + }, + { + "first_name": "Canghong", + "last_name": "Jin" + }, + { + "first_name": "Yun", + "last_name": "Zhang" + }, + { + "first_name": "Sixian", + "last_name": "Chan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Weakly Supervised Monocular 3D Detection with a Single-View Image", - "authors": "Xueying Jiang, Sheng Jin, Lewei Lu, Xiaoqin Zhang, Shijian Lu", + "authors": [ + { + "first_name": "Xueying", + "last_name": "Jiang" + }, + { + "first_name": "Sheng", + "last_name": "Jin" + }, + { + "first_name": "Lewei", + "last_name": "Lu" + }, + { + "first_name": "Xiaoqin", + "last_name": "Zhang" + }, + { + "first_name": "Shijian", + "last_name": "Lu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Pose-Guided Self-Training with Two-Stage Clustering for Unsupervised Landmark Discovery", - "authors": "Siddharth Tourani, Ahmed Alwheibi, Arif Mahmood, Muhammad Haris Khan", + "authors": [ + { + "first_name": "Siddharth", + "last_name": "Tourani" + }, + { + "first_name": "Ahmed", + "last_name": "Alwheibi" + }, + { + "first_name": "Arif", + "last_name": "Mahmood" + }, + { + "first_name": "Muhammad", + "last_name": "Haris Khan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning from Synthetic Human Group Activities", - "authors": "Che-Jui Chang, Danrui Li, Deep Patel, Parth Goel, Honglu Zhou, Seonghyeon Moon, Samuel S. Sohn, Sejong Yoon, Vladimir Pavlovic, Mubbasir Kapadia", + "authors": [ + { + "first_name": "Che-Jui", + "last_name": "Chang" + }, + { + "first_name": "Danrui", + "last_name": "Li" + }, + { + "first_name": "Deep", + "last_name": "Patel" + }, + { + "first_name": "Parth", + "last_name": "Goel" + }, + { + "first_name": "Honglu", + "last_name": "Zhou" + }, + { + "first_name": "Seonghyeon", + "last_name": "Moon" + }, + { + "first_name": "Samuel", + "last_name": "S. Sohn" + }, + { + "first_name": "Sejong", + "last_name": "Yoon" + }, + { + "first_name": "Vladimir", + "last_name": "Pavlovic" + }, + { + "first_name": "Mubbasir", + "last_name": "Kapadia" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Blind Image Quality Assessment Based on Geometric Order Learning", - "authors": "Nyeong-Ho Shin, Seon-Ho Lee, Chang-Su Kim", + "authors": [ + { + "first_name": "Nyeong-Ho", + "last_name": "Shin" + }, + { + "first_name": "Seon-Ho", + "last_name": "Lee" + }, + { + "first_name": "Chang-Su", + "last_name": "Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Text Grouping Adapter: Adapting Pre-trained Text Detector for Layout Analysis", - "authors": "Tianci Bi, Xiaoyi Zhang, Zhizheng Zhang, Wenxuan Xie, Cuiling Lan, Yan Lu, Nanning Zheng", + "authors": [ + { + "first_name": "Tianci", + "last_name": "Bi" + }, + { + "first_name": "Xiaoyi", + "last_name": "Zhang" + }, + { + "first_name": "Zhizheng", + "last_name": "Zhang" + }, + { + "first_name": "Wenxuan", + "last_name": "Xie" + }, + { + "first_name": "Cuiling", + "last_name": "Lan" + }, + { + "first_name": "Yan", + "last_name": "Lu" + }, + { + "first_name": "Nanning", + "last_name": "Zheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Generalizable Whole Slide Image Classification with Fine-Grained Visual-Semantic Interaction", - "authors": "Hao Li, Ying Chen, Yifei Chen, Rongshan Yu, Wenxian Yang, Liansheng Wang, Bowen Ding, Yuchen Han", + "authors": [ + { + "first_name": "Hao", + "last_name": "Li" + }, + { + "first_name": "Ying", + "last_name": "Chen" + }, + { + "first_name": "Yifei", + "last_name": "Chen" + }, + { + "first_name": "Rongshan", + "last_name": "Yu" + }, + { + "first_name": "Wenxian", + "last_name": "Yang" + }, + { + "first_name": "Liansheng", + "last_name": "Wang" + }, + { + "first_name": "Bowen", + "last_name": "Ding" + }, + { + "first_name": "Yuchen", + "last_name": "Han" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "THRONE: An Object-based Hallucination Benchmark for the Free-form Generations of Large Vision-Language Models", - "authors": "Prannay Kaul, Zhizhong Li, Hao Yang, Yonatan Dukler, Ashwin Swaminathan, C. J. Taylor, Stefano Soatto", + "authors": [ + { + "first_name": "Prannay", + "last_name": "Kaul" + }, + { + "first_name": "Zhizhong", + "last_name": "Li" + }, + { + "first_name": "Hao", + "last_name": "Yang" + }, + { + "first_name": "Yonatan", + "last_name": "Dukler" + }, + { + "first_name": "Ashwin", + "last_name": "Swaminathan" + }, + { + "first_name": "C.", + "last_name": "J. Taylor" + }, + { + "first_name": "Stefano", + "last_name": "Soatto" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Wired Perspectives: Multi-View Wire Art Embraces Generative AI", - "authors": "Zhiyu Qu, Lan Yang, Honggang Zhang, Tao Xiang, Kaiyue Pang, Yi-Zhe Song", + "authors": [ + { + "first_name": "Zhiyu", + "last_name": "Qu" + }, + { + "first_name": "Lan", + "last_name": "Yang" + }, + { + "first_name": "Honggang", + "last_name": "Zhang" + }, + { + "first_name": "Tao", + "last_name": "Xiang" + }, + { + "first_name": "Kaiyue", + "last_name": "Pang" + }, + { + "first_name": "Yi-Zhe", + "last_name": "Song" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LUWA Dataset: Learning Lithic Use-Wear Analysis on Microscopic Images", - "authors": "Jing Zhang, Irving Fang, Hao Wu, Akshat Kaushik, Alice Rodriguez, Hanwen Zhao, Juexiao Zhang, Zhuo Zheng, Radu Iovita, Chen Feng", + "authors": [ + { + "first_name": "Jing", + "last_name": "Zhang" + }, + { + "first_name": "Irving", + "last_name": "Fang" + }, + { + "first_name": "Hao", + "last_name": "Wu" + }, + { + "first_name": "Akshat", + "last_name": "Kaushik" + }, + { + "first_name": "Alice", + "last_name": "Rodriguez" + }, + { + "first_name": "Hanwen", + "last_name": "Zhao" + }, + { + "first_name": "Juexiao", + "last_name": "Zhang" + }, + { + "first_name": "Zhuo", + "last_name": "Zheng" + }, + { + "first_name": "Radu", + "last_name": "Iovita" + }, + { + "first_name": "Chen", + "last_name": "Feng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Generalizing 6-DoF Grasp Detection via Domain Prior Knowledge", - "authors": "Haoxiang Ma, Modi Shi, Boyang Gao, Di Huang", + "authors": [ + { + "first_name": "Haoxiang", + "last_name": "Ma" + }, + { + "first_name": "Modi", + "last_name": "Shi" + }, + { + "first_name": "Boyang", + "last_name": "Gao" + }, + { + "first_name": "Di", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "The Audio-Visual Conversational Graph: From an Egocentric-Exocentric Perspective", - "authors": "Wenqi Jia, Miao Liu, Hao Jiang, Ishwarya Ananthabhotla, James M. Rehg, Vamsi Krishna Ithapu, Ruohan Gao", + "authors": [ + { + "first_name": "Wenqi", + "last_name": "Jia" + }, + { + "first_name": "Miao", + "last_name": "Liu" + }, + { + "first_name": "Hao", + "last_name": "Jiang" + }, + { + "first_name": "Ishwarya", + "last_name": "Ananthabhotla" + }, + { + "first_name": "James", + "last_name": "M. Rehg" + }, + { + "first_name": "Vamsi", + "last_name": "Krishna Ithapu" + }, + { + "first_name": "Ruohan", + "last_name": "Gao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Byzantine-robust Decentralized Federated Learning via Dual-domain Clustering and Trust Bootstrapping", - "authors": "Peng Sun, Xinyang Liu, Zhibo Wang, Bo Liu", + "authors": [ + { + "first_name": "Peng", + "last_name": "Sun" + }, + { + "first_name": "Xinyang", + "last_name": "Liu" + }, + { + "first_name": "Zhibo", + "last_name": "Wang" + }, + { + "first_name": "Bo", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Leveraging Camera Triplets for Efficient and Accurate Structure-from-Motion", - "authors": "Lalit Manam, Venu Madhav Govindu", + "authors": [ + { + "first_name": "Lalit", + "last_name": "Manam" + }, + { + "first_name": "Venu", + "last_name": "Madhav Govindu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SimDA: Simple Diffusion Adapter for Efficient Video Generation", - "authors": "Zhen Xing, Qi Dai, Han Hu, Zuxuan Wu, Yu-Gang Jiang", + "authors": [ + { + "first_name": "Zhen", + "last_name": "Xing" + }, + { + "first_name": "Qi", + "last_name": "Dai" + }, + { + "first_name": "Han", + "last_name": "Hu" + }, + { + "first_name": "Zuxuan", + "last_name": "Wu" + }, + { + "first_name": "Yu-Gang", + "last_name": "Jiang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Multi-view Aggregation Network for Dichotomous Image Segmentation", - "authors": "Qian Yu, Xiaoqi Zhao, Youwei Pang, Lihe Zhang, Huchuan Lu", + "authors": [ + { + "first_name": "Qian", + "last_name": "Yu" + }, + { + "first_name": "Xiaoqi", + "last_name": "Zhao" + }, + { + "first_name": "Youwei", + "last_name": "Pang" + }, + { + "first_name": "Lihe", + "last_name": "Zhang" + }, + { + "first_name": "Huchuan", + "last_name": "Lu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "A Recipe for Scaling up Text-to-Video Generation with Text-free Videos", - "authors": "Xiang Wang, Shiwei Zhang, Hangjie Yuan, Zhiwu Qing, Biao Gong, Yingya Zhang, Yujun Shen, Changxin Gao, Nong Sang", + "authors": [ + { + "first_name": "Xiang", + "last_name": "Wang" + }, + { + "first_name": "Shiwei", + "last_name": "Zhang" + }, + { + "first_name": "Hangjie", + "last_name": "Yuan" + }, + { + "first_name": "Zhiwu", + "last_name": "Qing" + }, + { + "first_name": "Biao", + "last_name": "Gong" + }, + { + "first_name": "Yingya", + "last_name": "Zhang" + }, + { + "first_name": "Yujun", + "last_name": "Shen" + }, + { + "first_name": "Changxin", + "last_name": "Gao" + }, + { + "first_name": "Nong", + "last_name": "Sang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Molecular Data Programming: Towards Molecule Pseudo-labeling with Systematic Weak Supervision", - "authors": "Xin Juan, Kaixiong Zhou, Ninghao Liu, Tianlong Chen, Xin Wang", + "authors": [ + { + "first_name": "Xin", + "last_name": "Juan" + }, + { + "first_name": "Kaixiong", + "last_name": "Zhou" + }, + { + "first_name": "Ninghao", + "last_name": "Liu" + }, + { + "first_name": "Tianlong", + "last_name": "Chen" + }, + { + "first_name": "Xin", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "RadSimReal: Bridging the Gap Between Synthetic and Real Data in Radar Object Detection With Simulation", - "authors": "Oded Bialer, Yuval Haitman", + "authors": [ + { + "first_name": "Oded", + "last_name": "Bialer" + }, + { + "first_name": "Yuval", + "last_name": "Haitman" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "No More Ambiguity in 360deg Room Layout via Bi-Layout Estimation", - "authors": "Yu-Ju Tsai, Jin-Cheng Jhang, Jingjing Zheng, Wei Wang, Albert Y. C. Chen, Min Sun, Cheng-Hao Kuo, Ming-Hsuan Yang", + "authors": [ + { + "first_name": "Yu-Ju", + "last_name": "Tsai" + }, + { + "first_name": "Jin-Cheng", + "last_name": "Jhang" + }, + { + "first_name": "Jingjing", + "last_name": "Zheng" + }, + { + "first_name": "Wei", + "last_name": "Wang" + }, + { + "first_name": "Albert", + "last_name": "Y. C. Chen" + }, + { + "first_name": "Min", + "last_name": "Sun" + }, + { + "first_name": "Cheng-Hao", + "last_name": "Kuo" + }, + { + "first_name": "Ming-Hsuan", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Residual Denoising Diffusion Models", - "authors": "Jiawei Liu, Qiang Wang, Huijie Fan, Yinong Wang, Yandong Tang, Liangqiong Qu", + "authors": [ + { + "first_name": "Jiawei", + "last_name": "Liu" + }, + { + "first_name": "Qiang", + "last_name": "Wang" + }, + { + "first_name": "Huijie", + "last_name": "Fan" + }, + { + "first_name": "Yinong", + "last_name": "Wang" + }, + { + "first_name": "Yandong", + "last_name": "Tang" + }, + { + "first_name": "Liangqiong", + "last_name": "Qu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards Accurate and Robust Architectures via Neural Architecture Search", - "authors": "Yuwei Ou, Yuqi Feng, Yanan Sun", + "authors": [ + { + "first_name": "Yuwei", + "last_name": "Ou" + }, + { + "first_name": "Yuqi", + "last_name": "Feng" + }, + { + "first_name": "Yanan", + "last_name": "Sun" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Closely Interactive Human Reconstruction with Proxemics and Physics-Guided Adaption", - "authors": "Buzhen Huang, Chen Li, Chongyang Xu, Liang Pan, Yangang Wang, Gim Hee Lee", + "authors": [ + { + "first_name": "Buzhen", + "last_name": "Huang" + }, + { + "first_name": "Chen", + "last_name": "Li" + }, + { + "first_name": "Chongyang", + "last_name": "Xu" + }, + { + "first_name": "Liang", + "last_name": "Pan" + }, + { + "first_name": "Yangang", + "last_name": "Wang" + }, + { + "first_name": "Gim", + "last_name": "Hee Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "A Noisy Elephant in the Room: Is Your Out-of-Distribution Detector Robust to Label Noise?", - "authors": "Galadrielle Humblot-Renaux, Sergio Escalera, Thomas B. Moeslund", + "authors": [ + { + "first_name": "Galadrielle", + "last_name": "Humblot-Renaux" + }, + { + "first_name": "Sergio", + "last_name": "Escalera" + }, + { + "first_name": "Thomas", + "last_name": "B. Moeslund" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "VideoMAC: Video Masked Autoencoders Meet ConvNets", - "authors": "Gensheng Pei, Tao Chen, Xiruo Jiang, Huafeng Liu, Zeren Sun, Yazhou Yao", + "authors": [ + { + "first_name": "Gensheng", + "last_name": "Pei" + }, + { + "first_name": "Tao", + "last_name": "Chen" + }, + { + "first_name": "Xiruo", + "last_name": "Jiang" + }, + { + "first_name": "Huafeng", + "last_name": "Liu" + }, + { + "first_name": "Zeren", + "last_name": "Sun" + }, + { + "first_name": "Yazhou", + "last_name": "Yao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Taming Stable Diffusion for Text to 360 Panorama Image Generation", - "authors": "Cheng Zhang, Qianyi Wu, Camilo Cruz Gambardella, Xiaoshui Huang, Dinh Phung, Wanli Ouyang, Jianfei Cai", + "authors": [ + { + "first_name": "Cheng", + "last_name": "Zhang" + }, + { + "first_name": "Qianyi", + "last_name": "Wu" + }, + { + "first_name": "Camilo", + "last_name": "Cruz Gambardella" + }, + { + "first_name": "Xiaoshui", + "last_name": "Huang" + }, + { + "first_name": "Dinh", + "last_name": "Phung" + }, + { + "first_name": "Wanli", + "last_name": "Ouyang" + }, + { + "first_name": "Jianfei", + "last_name": "Cai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "3DSFLabelling: Boosting 3D Scene Flow Estimation by Pseudo Auto-labelling", - "authors": "Chaokang Jiang, Guangming Wang, Jiuming Liu, Hesheng Wang, Zhuang Ma, Zhenqiang Liu, Zhujin Liang, Yi Shan, Dalong Du", + "authors": [ + { + "first_name": "Chaokang", + "last_name": "Jiang" + }, + { + "first_name": "Guangming", + "last_name": "Wang" + }, + { + "first_name": "Jiuming", + "last_name": "Liu" + }, + { + "first_name": "Hesheng", + "last_name": "Wang" + }, + { + "first_name": "Zhuang", + "last_name": "Ma" + }, + { + "first_name": "Zhenqiang", + "last_name": "Liu" + }, + { + "first_name": "Zhujin", + "last_name": "Liang" + }, + { + "first_name": "Yi", + "last_name": "Shan" + }, + { + "first_name": "Dalong", + "last_name": "Du" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Unsigned Orthogonal Distance Fields: An Accurate Neural Implicit Representation for Diverse 3D Shapes", - "authors": "Yujie Lu, Long Wan, Nayu Ding, Yulong Wang, Shuhan Shen, Shen Cai, Lin Gao", + "authors": [ + { + "first_name": "Yujie", + "last_name": "Lu" + }, + { + "first_name": "Long", + "last_name": "Wan" + }, + { + "first_name": "Nayu", + "last_name": "Ding" + }, + { + "first_name": "Yulong", + "last_name": "Wang" + }, + { + "first_name": "Shuhan", + "last_name": "Shen" + }, + { + "first_name": "Shen", + "last_name": "Cai" + }, + { + "first_name": "Lin", + "last_name": "Gao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Modular Blind Video Quality Assessment", - "authors": "Wen Wen, Mu Li, Yabin Zhang, Yiting Liao, Junlin Li, Li Zhang, Kede Ma", + "authors": [ + { + "first_name": "Wen", + "last_name": "Wen" + }, + { + "first_name": "Mu", + "last_name": "Li" + }, + { + "first_name": "Yabin", + "last_name": "Zhang" + }, + { + "first_name": "Yiting", + "last_name": "Liao" + }, + { + "first_name": "Junlin", + "last_name": "Li" + }, + { + "first_name": "Li", + "last_name": "Zhang" + }, + { + "first_name": "Kede", + "last_name": "Ma" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Question Aware Vision Transformer for Multimodal Reasoning", - "authors": "Roy Ganz, Yair Kittenplon, Aviad Aberdam, Elad Ben Avraham, Oren Nuriel, Shai Mazor, Ron Litman", + "authors": [ + { + "first_name": "Roy", + "last_name": "Ganz" + }, + { + "first_name": "Yair", + "last_name": "Kittenplon" + }, + { + "first_name": "Aviad", + "last_name": "Aberdam" + }, + { + "first_name": "Elad", + "last_name": "Ben Avraham" + }, + { + "first_name": "Oren", + "last_name": "Nuriel" + }, + { + "first_name": "Shai", + "last_name": "Mazor" + }, + { + "first_name": "Ron", + "last_name": "Litman" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "OST: Refining Text Knowledge with Optimal Spatio-Temporal Descriptor for General Video Recognition", - "authors": "Tongjia Chen, Hongshan Yu, Zhengeng Yang, Zechuan Li, Wei Sun, Chen Chen", + "authors": [ + { + "first_name": "Tongjia", + "last_name": "Chen" + }, + { + "first_name": "Hongshan", + "last_name": "Yu" + }, + { + "first_name": "Zhengeng", + "last_name": "Yang" + }, + { + "first_name": "Zechuan", + "last_name": "Li" + }, + { + "first_name": "Wei", + "last_name": "Sun" + }, + { + "first_name": "Chen", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Habitat Synthetic Scenes Dataset (HSSD-200): An Analysis of 3D Scene Scale and Realism Tradeoffs for ObjectGoal Navigation", - "authors": "Mukul Khanna, Yongsen Mao, Hanxiao Jiang, Sanjay Haresh, Brennan Shacklett, Dhruv Batra, Alexander Clegg, Eric Undersander, Angel X. Chang, Manolis Savva", + "authors": [ + { + "first_name": "Mukul", + "last_name": "Khanna" + }, + { + "first_name": "Yongsen", + "last_name": "Mao" + }, + { + "first_name": "Hanxiao", + "last_name": "Jiang" + }, + { + "first_name": "Sanjay", + "last_name": "Haresh" + }, + { + "first_name": "Brennan", + "last_name": "Shacklett" + }, + { + "first_name": "Dhruv", + "last_name": "Batra" + }, + { + "first_name": "Alexander", + "last_name": "Clegg" + }, + { + "first_name": "Eric", + "last_name": "Undersander" + }, + { + "first_name": "Angel", + "last_name": "X. Chang" + }, + { + "first_name": "Manolis", + "last_name": "Savva" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation", - "authors": "Bohao Peng, Xiaoyang Wu, Li Jiang, Yukang Chen, Hengshuang Zhao, Zhuotao Tian, Jiaya Jia", + "authors": [ + { + "first_name": "Bohao", + "last_name": "Peng" + }, + { + "first_name": "Xiaoyang", + "last_name": "Wu" + }, + { + "first_name": "Li", + "last_name": "Jiang" + }, + { + "first_name": "Yukang", + "last_name": "Chen" + }, + { + "first_name": "Hengshuang", + "last_name": "Zhao" + }, + { + "first_name": "Zhuotao", + "last_name": "Tian" + }, + { + "first_name": "Jiaya", + "last_name": "Jia" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "RELI11D: A Comprehensive Multimodal Human Motion Dataset and Method", - "authors": "Ming Yan, Yan Zhang, Shuqiang Cai, Shuqi Fan, Xincheng Lin, Yudi Dai, Siqi Shen, Chenglu Wen, Lan Xu, Yuexin Ma, Cheng Wang", + "authors": [ + { + "first_name": "Ming", + "last_name": "Yan" + }, + { + "first_name": "Yan", + "last_name": "Zhang" + }, + { + "first_name": "Shuqiang", + "last_name": "Cai" + }, + { + "first_name": "Shuqi", + "last_name": "Fan" + }, + { + "first_name": "Xincheng", + "last_name": "Lin" + }, + { + "first_name": "Yudi", + "last_name": "Dai" + }, + { + "first_name": "Siqi", + "last_name": "Shen" + }, + { + "first_name": "Chenglu", + "last_name": "Wen" + }, + { + "first_name": "Lan", + "last_name": "Xu" + }, + { + "first_name": "Yuexin", + "last_name": "Ma" + }, + { + "first_name": "Cheng", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Generative Image Dynamics", - "authors": "Zhengqi Li, Richard Tucker, Noah Snavely, Aleksander Holynski", + "authors": [ + { + "first_name": "Zhengqi", + "last_name": "Li" + }, + { + "first_name": "Richard", + "last_name": "Tucker" + }, + { + "first_name": "Noah", + "last_name": "Snavely" + }, + { + "first_name": "Aleksander", + "last_name": "Holynski" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "One-Class Face Anti-spoofing via Spoof Cue Map-Guided Feature Learning", - "authors": "Pei-Kai Huang, Cheng-Hsuan Chiang, Tzu-Hsien Chen, Jun-Xiong Chong, Tyng-Luh Liu, Chiou-Ting Hsu", + "authors": [ + { + "first_name": "Pei-Kai", + "last_name": "Huang" + }, + { + "first_name": "Cheng-Hsuan", + "last_name": "Chiang" + }, + { + "first_name": "Tzu-Hsien", + "last_name": "Chen" + }, + { + "first_name": "Jun-Xiong", + "last_name": "Chong" + }, + { + "first_name": "Tyng-Luh", + "last_name": "Liu" + }, + { + "first_name": "Chiou-Ting", + "last_name": "Hsu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "On the Test-Time Zero-Shot Generalization of Vision-Language Models: Do We Really Need Prompt Learning?", - "authors": "Maxime Zanella, Ismail Ben Ayed", + "authors": [ + { + "first_name": "Maxime", + "last_name": "Zanella" + }, + { + "first_name": "Ismail", + "last_name": "Ben Ayed" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "InteractDiffusion: Interaction Control in Text-to-Image Diffusion Models", - "authors": "Jiun Tian Hoe, Xudong Jiang, Chee Seng Chan, Yap-Peng Tan, Weipeng Hu", + "authors": [ + { + "first_name": "Jiun", + "last_name": "Tian Hoe" + }, + { + "first_name": "Xudong", + "last_name": "Jiang" + }, + { + "first_name": "Chee", + "last_name": "Seng Chan" + }, + { + "first_name": "Yap-Peng", + "last_name": "Tan" + }, + { + "first_name": "Weipeng", + "last_name": "Hu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "NViST: In the Wild New View Synthesis from a Single Image with Transformers", - "authors": "Wonbong Jang, Lourdes Agapito", + "authors": [ + { + "first_name": "Wonbong", + "last_name": "Jang" + }, + { + "first_name": "Lourdes", + "last_name": "Agapito" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Beyond Text: Frozen Large Language Models in Visual Signal Comprehension", - "authors": "Lei Zhu, Fangyun Wei, Yanye Lu", + "authors": [ + { + "first_name": "Lei", + "last_name": "Zhu" + }, + { + "first_name": "Fangyun", + "last_name": "Wei" + }, + { + "first_name": "Yanye", + "last_name": "Lu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Rotated Multi-Scale Interaction Network for Referring Remote Sensing Image Segmentation", - "authors": "Sihan Liu, Yiwei Ma, Xiaoqing Zhang, Haowei Wang, Jiayi Ji, Xiaoshuai Sun, Rongrong Ji", + "authors": [ + { + "first_name": "Sihan", + "last_name": "Liu" + }, + { + "first_name": "Yiwei", + "last_name": "Ma" + }, + { + "first_name": "Xiaoqing", + "last_name": "Zhang" + }, + { + "first_name": "Haowei", + "last_name": "Wang" + }, + { + "first_name": "Jiayi", + "last_name": "Ji" + }, + { + "first_name": "Xiaoshuai", + "last_name": "Sun" + }, + { + "first_name": "Rongrong", + "last_name": "Ji" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GLACE: Global Local Accelerated Coordinate Encoding", - "authors": "Fangjinhua Wang, Xudong Jiang, Silvano Galliani, Christoph Vogel, Marc Pollefeys", + "authors": [ + { + "first_name": "Fangjinhua", + "last_name": "Wang" + }, + { + "first_name": "Xudong", + "last_name": "Jiang" + }, + { + "first_name": "Silvano", + "last_name": "Galliani" + }, + { + "first_name": "Christoph", + "last_name": "Vogel" + }, + { + "first_name": "Marc", + "last_name": "Pollefeys" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Emergent Open-Vocabulary Semantic Segmentation from Off-the-shelf Vision-Language Models", - "authors": "Jiayun Luo, Siddhesh Khandelwal, Leonid Sigal, Boyang Li", + "authors": [ + { + "first_name": "Jiayun", + "last_name": "Luo" + }, + { + "first_name": "Siddhesh", + "last_name": "Khandelwal" + }, + { + "first_name": "Leonid", + "last_name": "Sigal" + }, + { + "first_name": "Boyang", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Localization Is All You Evaluate: Data Leakage in Online Mapping Datasets and How to Fix It", - "authors": "Adam Lilja, Junsheng Fu, Erik Stenborg, Lars Hammarstrand", + "authors": [ + { + "first_name": "Adam", + "last_name": "Lilja" + }, + { + "first_name": "Junsheng", + "last_name": "Fu" + }, + { + "first_name": "Erik", + "last_name": "Stenborg" + }, + { + "first_name": "Lars", + "last_name": "Hammarstrand" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Alchemist: Parametric Control of Material Properties with Diffusion Models", - "authors": "Prafull Sharma, Varun Jampani, Yuanzhen Li, Xuhui Jia, Dmitry Lagun, Fredo Durand, Bill Freeman, Mark Matthews", + "authors": [ + { + "first_name": "Prafull", + "last_name": "Sharma" + }, + { + "first_name": "Varun", + "last_name": "Jampani" + }, + { + "first_name": "Yuanzhen", + "last_name": "Li" + }, + { + "first_name": "Xuhui", + "last_name": "Jia" + }, + { + "first_name": "Dmitry", + "last_name": "Lagun" + }, + { + "first_name": "Fredo", + "last_name": "Durand" + }, + { + "first_name": "Bill", + "last_name": "Freeman" + }, + { + "first_name": "Mark", + "last_name": "Matthews" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Step Differences in Instructional Video", - "authors": "Tushar Nagarajan, Lorenzo Torresani", + "authors": [ + { + "first_name": "Tushar", + "last_name": "Nagarajan" + }, + { + "first_name": "Lorenzo", + "last_name": "Torresani" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data", - "authors": "Lihe Yang, Bingyi Kang, Zilong Huang, Xiaogang Xu, Jiashi Feng, Hengshuang Zhao", + "authors": [ + { + "first_name": "Lihe", + "last_name": "Yang" + }, + { + "first_name": "Bingyi", + "last_name": "Kang" + }, + { + "first_name": "Zilong", + "last_name": "Huang" + }, + { + "first_name": "Xiaogang", + "last_name": "Xu" + }, + { + "first_name": "Jiashi", + "last_name": "Feng" + }, + { + "first_name": "Hengshuang", + "last_name": "Zhao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SelfPose3d: Self-Supervised Multi-Person Multi-View 3d Pose Estimation", - "authors": "Vinkle Srivastav, Keqi Chen, Nicolas Padoy", + "authors": [ + { + "first_name": "Vinkle", + "last_name": "Srivastav" + }, + { + "first_name": "Keqi", + "last_name": "Chen" + }, + { + "first_name": "Nicolas", + "last_name": "Padoy" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MoDE: CLIP Data Experts via Clustering", - "authors": "Jiawei Ma, Po-Yao Huang, Saining Xie, Shang-Wen Li, Luke Zettlemoyer, Shih-Fu Chang, Wen-Tau Yih, Hu Xu", + "authors": [ + { + "first_name": "Jiawei", + "last_name": "Ma" + }, + { + "first_name": "Po-Yao", + "last_name": "Huang" + }, + { + "first_name": "Saining", + "last_name": "Xie" + }, + { + "first_name": "Shang-Wen", + "last_name": "Li" + }, + { + "first_name": "Luke", + "last_name": "Zettlemoyer" + }, + { + "first_name": "Shih-Fu", + "last_name": "Chang" + }, + { + "first_name": "Wen-Tau", + "last_name": "Yih" + }, + { + "first_name": "Hu", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Joint2Human: High-Quality 3D Human Generation via Compact Spherical Embedding of 3D Joints", - "authors": "Muxin Zhang, Qiao Feng, Zhuo Su, Chao Wen, Zhou Xue, Kun Li", + "authors": [ + { + "first_name": "Muxin", + "last_name": "Zhang" + }, + { + "first_name": "Qiao", + "last_name": "Feng" + }, + { + "first_name": "Zhuo", + "last_name": "Su" + }, + { + "first_name": "Chao", + "last_name": "Wen" + }, + { + "first_name": "Zhou", + "last_name": "Xue" + }, + { + "first_name": "Kun", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Prompt-Free Diffusion: Taking "Text" out of Text-to-Image Diffusion Models", - "authors": "Xingqian Xu, Jiayi Guo, Zhangyang Wang, Gao Huang, Irfan Essa, Humphrey Shi", + "authors": [ + { + "first_name": "Xingqian", + "last_name": "Xu" + }, + { + "first_name": "Jiayi", + "last_name": "Guo" + }, + { + "first_name": "Zhangyang", + "last_name": "Wang" + }, + { + "first_name": "Gao", + "last_name": "Huang" + }, + { + "first_name": "Irfan", + "last_name": "Essa" + }, + { + "first_name": "Humphrey", + "last_name": "Shi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MPOD123: One Image to 3D Content Generation Using Mask-enhanced Progressive Outline-to-Detail Optimization", - "authors": "Jimin Xu, Tianbao Wang, Tao Jin, Shengyu Zhang, Dongjie Fu, Zhe Wang, Jiangjing Lyu, Chengfei Lv, Chaoyue Niu, Zhou Yu, Zhou Zhao, Fei Wu", + "authors": [ + { + "first_name": "Jimin", + "last_name": "Xu" + }, + { + "first_name": "Tianbao", + "last_name": "Wang" + }, + { + "first_name": "Tao", + "last_name": "Jin" + }, + { + "first_name": "Shengyu", + "last_name": "Zhang" + }, + { + "first_name": "Dongjie", + "last_name": "Fu" + }, + { + "first_name": "Zhe", + "last_name": "Wang" + }, + { + "first_name": "Jiangjing", + "last_name": "Lyu" + }, + { + "first_name": "Chengfei", + "last_name": "Lv" + }, + { + "first_name": "Chaoyue", + "last_name": "Niu" + }, + { + "first_name": "Zhou", + "last_name": "Yu" + }, + { + "first_name": "Zhou", + "last_name": "Zhao" + }, + { + "first_name": "Fei", + "last_name": "Wu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioning", - "authors": "Jaewoo Jeong, Daehee Park, Kuk-Jin Yoon", + "authors": [ + { + "first_name": "Jaewoo", + "last_name": "Jeong" + }, + { + "first_name": "Daehee", + "last_name": "Park" + }, + { + "first_name": "Kuk-Jin", + "last_name": "Yoon" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "UnionFormer: Unified-Learning Transformer with Multi-View Representation for Image Manipulation Detection and Localization", - "authors": "Shuaibo Li, Wei Ma, Jianwei Guo, Shibiao Xu, Benchong Li, Xiaopeng Zhang", + "authors": [ + { + "first_name": "Shuaibo", + "last_name": "Li" + }, + { + "first_name": "Wei", + "last_name": "Ma" + }, + { + "first_name": "Jianwei", + "last_name": "Guo" + }, + { + "first_name": "Shibiao", + "last_name": "Xu" + }, + { + "first_name": "Benchong", + "last_name": "Li" + }, + { + "first_name": "Xiaopeng", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Situational Awareness Matters in 3D Vision Language Reasoning", - "authors": "Yunze Man, Liang-Yan Gui, Yu-Xiong Wang", + "authors": [ + { + "first_name": "Yunze", + "last_name": "Man" + }, + { + "first_name": "Liang-Yan", + "last_name": "Gui" + }, + { + "first_name": "Yu-Xiong", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "RCBEVDet: Radar-camera Fusion in Bird's Eye View for 3D Object Detection", - "authors": "Zhiwei Lin, Zhe Liu, Zhongyu Xia, Xinhao Wang, Yongtao Wang, Shengxiang Qi, Yang Dong, Nan Dong, Le Zhang, Ce Zhu", + "authors": [ + { + "first_name": "Zhiwei", + "last_name": "Lin" + }, + { + "first_name": "Zhe", + "last_name": "Liu" + }, + { + "first_name": "Zhongyu", + "last_name": "Xia" + }, + { + "first_name": "Xinhao", + "last_name": "Wang" + }, + { + "first_name": "Yongtao", + "last_name": "Wang" + }, + { + "first_name": "Shengxiang", + "last_name": "Qi" + }, + { + "first_name": "Yang", + "last_name": "Dong" + }, + { + "first_name": "Nan", + "last_name": "Dong" + }, + { + "first_name": "Le", + "last_name": "Zhang" + }, + { + "first_name": "Ce", + "last_name": "Zhu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CLOAF: CoLlisiOn-Aware Human Flow", - "authors": "Andrey Davydov, Martin Engilberge, Mathieu Salzmann, Pascal Fua", + "authors": [ + { + "first_name": "Andrey", + "last_name": "Davydov" + }, + { + "first_name": "Martin", + "last_name": "Engilberge" + }, + { + "first_name": "Mathieu", + "last_name": "Salzmann" + }, + { + "first_name": "Pascal", + "last_name": "Fua" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Hybrid Functional Maps for Crease-Aware Non-Isometric Shape Matching", - "authors": "Lennart Bastian, Yizheng Xie, Nassir Navab, Zorah Lähner", + "authors": [ + { + "first_name": "Lennart", + "last_name": "Bastian" + }, + { + "first_name": "Yizheng", + "last_name": "Xie" + }, + { + "first_name": "Nassir", + "last_name": "Navab" + }, + { + "first_name": "Zorah", + "last_name": "Lähner" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Density-Guided Semi-Supervised 3D Semantic Segmentation with Dual-Space Hardness Sampling", - "authors": "Jianan Li, Qiulei Dong", + "authors": [ + { + "first_name": "Jianan", + "last_name": "Li" + }, + { + "first_name": "Qiulei", + "last_name": "Dong" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Adaptive Softassign via Hadamard-Equipped Sinkhorn", - "authors": "Binrui Shen, Qiang Niu, Shengxin Zhu", + "authors": [ + { + "first_name": "Binrui", + "last_name": "Shen" + }, + { + "first_name": "Qiang", + "last_name": "Niu" + }, + { + "first_name": "Shengxin", + "last_name": "Zhu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Re-thinking Data Availability Attacks Against Deep Neural Networks", - "authors": "Bin Fang, Bo Li, Shuang Wu, Shouhong Ding, Ran Yi, Lizhuang Ma", + "authors": [ + { + "first_name": "Bin", + "last_name": "Fang" + }, + { + "first_name": "Bo", + "last_name": "Li" + }, + { + "first_name": "Shuang", + "last_name": "Wu" + }, + { + "first_name": "Shouhong", + "last_name": "Ding" + }, + { + "first_name": "Ran", + "last_name": "Yi" + }, + { + "first_name": "Lizhuang", + "last_name": "Ma" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ElasticDiffusion: Training-free Arbitrary Size Image Generation through Global-Local Content Separation", - "authors": "Moayed Haji-Ali, Guha Balakrishnan, Vicente Ordonez", + "authors": [ + { + "first_name": "Moayed", + "last_name": "Haji-Ali" + }, + { + "first_name": "Guha", + "last_name": "Balakrishnan" + }, + { + "first_name": "Vicente", + "last_name": "Ordonez" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Locally Adaptive Neural 3D Morphable Models", - "authors": "Michail Tarasiou, Rolandos Alexandros Potamias, Eimear O'Sullivan, Stylianos Ploumpis, Stefanos Zafeiriou", + "authors": [ + { + "first_name": "Michail", + "last_name": "Tarasiou" + }, + { + "first_name": "Rolandos", + "last_name": "Alexandros Potamias" + }, + { + "first_name": "Eimear", + "last_name": "O'Sullivan" + }, + { + "first_name": "Stylianos", + "last_name": "Ploumpis" + }, + { + "first_name": "Stefanos", + "last_name": "Zafeiriou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ICON: Incremental CONfidence for Joint Pose and Radiance Field Optimization", - "authors": "Weiyao Wang, Pierre Gleize, Hao Tang, Xingyu Chen, Kevin J Liang, Matt Feiszli", + "authors": [ + { + "first_name": "Weiyao", + "last_name": "Wang" + }, + { + "first_name": "Pierre", + "last_name": "Gleize" + }, + { + "first_name": "Hao", + "last_name": "Tang" + }, + { + "first_name": "Xingyu", + "last_name": "Chen" + }, + { + "first_name": "Kevin", + "last_name": "J Liang" + }, + { + "first_name": "Matt", + "last_name": "Feiszli" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learned Scanpaths Aid Blind Panoramic Video Quality Assessment", - "authors": "Kanglong Fan, Wen Wen, Mu Li, Yifan Peng, Kede Ma", + "authors": [ + { + "first_name": "Kanglong", + "last_name": "Fan" + }, + { + "first_name": "Wen", + "last_name": "Wen" + }, + { + "first_name": "Mu", + "last_name": "Li" + }, + { + "first_name": "Yifan", + "last_name": "Peng" + }, + { + "first_name": "Kede", + "last_name": "Ma" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FineSports: A Multi-person Hierarchical Sports Video Dataset for Fine-grained Action Understanding", - "authors": "Jinglin Xu, Guohao Zhao, Sibo Yin, Wenhao Zhou, Yuxin Peng", + "authors": [ + { + "first_name": "Jinglin", + "last_name": "Xu" + }, + { + "first_name": "Guohao", + "last_name": "Zhao" + }, + { + "first_name": "Sibo", + "last_name": "Yin" + }, + { + "first_name": "Wenhao", + "last_name": "Zhou" + }, + { + "first_name": "Yuxin", + "last_name": "Peng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SHiNe: Semantic Hierarchy Nexus for Open-vocabulary Object Detection", - "authors": "Mingxuan Liu, Tyler L. Hayes, Elisa Ricci, Gabriela Csurka, Riccardo Volpi", + "authors": [ + { + "first_name": "Mingxuan", + "last_name": "Liu" + }, + { + "first_name": "Tyler", + "last_name": "L. Hayes" + }, + { + "first_name": "Elisa", + "last_name": "Ricci" + }, + { + "first_name": "Gabriela", + "last_name": "Csurka" + }, + { + "first_name": "Riccardo", + "last_name": "Volpi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "TI2V-Zero: Zero-Shot Image Conditioning for Text-to-Video Diffusion Models", - "authors": "Haomiao Ni, Bernhard Egger, Suhas Lohit, Anoop Cherian, Ye Wang, Toshiaki Koike-Akino, Sharon X. Huang, Tim K. Marks", + "authors": [ + { + "first_name": "Haomiao", + "last_name": "Ni" + }, + { + "first_name": "Bernhard", + "last_name": "Egger" + }, + { + "first_name": "Suhas", + "last_name": "Lohit" + }, + { + "first_name": "Anoop", + "last_name": "Cherian" + }, + { + "first_name": "Ye", + "last_name": "Wang" + }, + { + "first_name": "Toshiaki", + "last_name": "Koike-Akino" + }, + { + "first_name": "Sharon", + "last_name": "X. Huang" + }, + { + "first_name": "Tim", + "last_name": "K. Marks" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Ranking Distillation for Open-Ended Video Question Answering with Insufficient Labels", - "authors": "Tianming Liang, Chaolei Tan, Beihao Xia, Wei-Shi Zheng, Jian-Fang Hu", + "authors": [ + { + "first_name": "Tianming", + "last_name": "Liang" + }, + { + "first_name": "Chaolei", + "last_name": "Tan" + }, + { + "first_name": "Beihao", + "last_name": "Xia" + }, + { + "first_name": "Wei-Shi", + "last_name": "Zheng" + }, + { + "first_name": "Jian-Fang", + "last_name": "Hu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GARField: Group Anything with Radiance Fields", - "authors": "Chung Min Kim, Mingxuan Wu, Justin Kerr, Ken Goldberg, Matthew Tancik, Angjoo Kanazawa", + "authors": [ + { + "first_name": "Chung", + "last_name": "Min Kim" + }, + { + "first_name": "Mingxuan", + "last_name": "Wu" + }, + { + "first_name": "Justin", + "last_name": "Kerr" + }, + { + "first_name": "Ken", + "last_name": "Goldberg" + }, + { + "first_name": "Matthew", + "last_name": "Tancik" + }, + { + "first_name": "Angjoo", + "last_name": "Kanazawa" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Depth-Aware Concealed Crop Detection in Dense Agricultural Scenes", - "authors": "Liqiong Wang, Jinyu Yang, Yanfu Zhang, Fangyi Wang, Feng Zheng", + "authors": [ + { + "first_name": "Liqiong", + "last_name": "Wang" + }, + { + "first_name": "Jinyu", + "last_name": "Yang" + }, + { + "first_name": "Yanfu", + "last_name": "Zhang" + }, + { + "first_name": "Fangyi", + "last_name": "Wang" + }, + { + "first_name": "Feng", + "last_name": "Zheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning Equi-angular Representations for Online Continual Learning", - "authors": "Minhyuk Seo, Hyunseo Koh, Wonje Jeung, Minjae Lee, San Kim, Hankook Lee, Sungjun Cho, Sungik Choi, Hyunwoo Kim, Jonghyun Choi", + "authors": [ + { + "first_name": "Minhyuk", + "last_name": "Seo" + }, + { + "first_name": "Hyunseo", + "last_name": "Koh" + }, + { + "first_name": "Wonje", + "last_name": "Jeung" + }, + { + "first_name": "Minjae", + "last_name": "Lee" + }, + { + "first_name": "San", + "last_name": "Kim" + }, + { + "first_name": "Hankook", + "last_name": "Lee" + }, + { + "first_name": "Sungjun", + "last_name": "Cho" + }, + { + "first_name": "Sungik", + "last_name": "Choi" + }, + { + "first_name": "Hyunwoo", + "last_name": "Kim" + }, + { + "first_name": "Jonghyun", + "last_name": "Choi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "iToF-flow-based High Frame Rate Depth Imaging", - "authors": "Yu Meng, Zhou Xue, Xu Chang, Xuemei Hu, Tao Yue", + "authors": [ + { + "first_name": "Yu", + "last_name": "Meng" + }, + { + "first_name": "Zhou", + "last_name": "Xue" + }, + { + "first_name": "Xu", + "last_name": "Chang" + }, + { + "first_name": "Xuemei", + "last_name": "Hu" + }, + { + "first_name": "Tao", + "last_name": "Yue" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Solving the Catastrophic Forgetting Problem in Generalized Category Discovery", - "authors": "Xinzi Cao, Xiawu Zheng, Guanhong Wang, Weijiang Yu, Yunhang Shen, Ke Li, Yutong Lu, Yonghong Tian", + "authors": [ + { + "first_name": "Xinzi", + "last_name": "Cao" + }, + { + "first_name": "Xiawu", + "last_name": "Zheng" + }, + { + "first_name": "Guanhong", + "last_name": "Wang" + }, + { + "first_name": "Weijiang", + "last_name": "Yu" + }, + { + "first_name": "Yunhang", + "last_name": "Shen" + }, + { + "first_name": "Ke", + "last_name": "Li" + }, + { + "first_name": "Yutong", + "last_name": "Lu" + }, + { + "first_name": "Yonghong", + "last_name": "Tian" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Data-Efficient Unsupervised Interpolation Without Any Intermediate Frame for 4D Medical Images", - "authors": "JungEun Kim, Hangyul Yoon, Geondo Park, Kyungsu Kim, Eunho Yang", + "authors": [ + { + "first_name": "JungEun", + "last_name": "Kim" + }, + { + "first_name": "Hangyul", + "last_name": "Yoon" + }, + { + "first_name": "Geondo", + "last_name": "Park" + }, + { + "first_name": "Kyungsu", + "last_name": "Kim" + }, + { + "first_name": "Eunho", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "POCE: Primal Policy Optimization with Conservative Estimation for Multi-constraint Offline Reinforcement Learning", - "authors": "Jiayi Guan, Li Shen, Ao Zhou, Lusong Li, Han Hu, Xiaodong He, Guang Chen, Changjun Jiang", + "authors": [ + { + "first_name": "Jiayi", + "last_name": "Guan" + }, + { + "first_name": "Li", + "last_name": "Shen" + }, + { + "first_name": "Ao", + "last_name": "Zhou" + }, + { + "first_name": "Lusong", + "last_name": "Li" + }, + { + "first_name": "Han", + "last_name": "Hu" + }, + { + "first_name": "Xiaodong", + "last_name": "He" + }, + { + "first_name": "Guang", + "last_name": "Chen" + }, + { + "first_name": "Changjun", + "last_name": "Jiang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning the 3D Fauna of the Web", - "authors": "Zizhang Li, Dor Litvak, Ruining Li, Yunzhi Zhang, Tomas Jakab, Christian Rupprecht, Shangzhe Wu, Andrea Vedaldi, Jiajun Wu", + "authors": [ + { + "first_name": "Zizhang", + "last_name": "Li" + }, + { + "first_name": "Dor", + "last_name": "Litvak" + }, + { + "first_name": "Ruining", + "last_name": "Li" + }, + { + "first_name": "Yunzhi", + "last_name": "Zhang" + }, + { + "first_name": "Tomas", + "last_name": "Jakab" + }, + { + "first_name": "Christian", + "last_name": "Rupprecht" + }, + { + "first_name": "Shangzhe", + "last_name": "Wu" + }, + { + "first_name": "Andrea", + "last_name": "Vedaldi" + }, + { + "first_name": "Jiajun", + "last_name": "Wu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Masked Spatial Propagation Network for Sparsity-Adaptive Depth Refinement", - "authors": "Jinyoung Jun, Jae-Han Lee, Chang-Su Kim", + "authors": [ + { + "first_name": "Jinyoung", + "last_name": "Jun" + }, + { + "first_name": "Jae-Han", + "last_name": "Lee" + }, + { + "first_name": "Chang-Su", + "last_name": "Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LISA: Reasoning Segmentation via Large Language Model", - "authors": "Xin Lai, Zhuotao Tian, Yukang Chen, Yanwei Li, Yuhui Yuan, Shu Liu, Jiaya Jia", + "authors": [ + { + "first_name": "Xin", + "last_name": "Lai" + }, + { + "first_name": "Zhuotao", + "last_name": "Tian" + }, + { + "first_name": "Yukang", + "last_name": "Chen" + }, + { + "first_name": "Yanwei", + "last_name": "Li" + }, + { + "first_name": "Yuhui", + "last_name": "Yuan" + }, + { + "first_name": "Shu", + "last_name": "Liu" + }, + { + "first_name": "Jiaya", + "last_name": "Jia" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Relightful Harmonization: Lighting-aware Portrait Background Replacement", - "authors": "Mengwei Ren, Wei Xiong, Jae Shin Yoon, Zhixin Shu, Jianming Zhang, HyunJoon Jung, Guido Gerig, He Zhang", + "authors": [ + { + "first_name": "Mengwei", + "last_name": "Ren" + }, + { + "first_name": "Wei", + "last_name": "Xiong" + }, + { + "first_name": "Jae", + "last_name": "Shin Yoon" + }, + { + "first_name": "Zhixin", + "last_name": "Shu" + }, + { + "first_name": "Jianming", + "last_name": "Zhang" + }, + { + "first_name": "HyunJoon", + "last_name": "Jung" + }, + { + "first_name": "Guido", + "last_name": "Gerig" + }, + { + "first_name": "He", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight Detection", - "authors": "Yicheng Xiao, Zhuoyan Luo, Yong Liu, Yue Ma, Hengwei Bian, Yatai Ji, Yujiu Yang, Xiu Li", + "authors": [ + { + "first_name": "Yicheng", + "last_name": "Xiao" + }, + { + "first_name": "Zhuoyan", + "last_name": "Luo" + }, + { + "first_name": "Yong", + "last_name": "Liu" + }, + { + "first_name": "Yue", + "last_name": "Ma" + }, + { + "first_name": "Hengwei", + "last_name": "Bian" + }, + { + "first_name": "Yatai", + "last_name": "Ji" + }, + { + "first_name": "Yujiu", + "last_name": "Yang" + }, + { + "first_name": "Xiu", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MuseChat: A Conversational Music Recommendation System for Videos", - "authors": "Zhikang Dong, Xiulong Liu, Bin Chen, Pawel Polak, Peng Zhang", + "authors": [ + { + "first_name": "Zhikang", + "last_name": "Dong" + }, + { + "first_name": "Xiulong", + "last_name": "Liu" + }, + { + "first_name": "Bin", + "last_name": "Chen" + }, + { + "first_name": "Pawel", + "last_name": "Polak" + }, + { + "first_name": "Peng", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Mitigating Motion Blur in Neural Radiance Fields with Events and Frames", - "authors": "Marco Cannici, Davide Scaramuzza", + "authors": [ + { + "first_name": "Marco", + "last_name": "Cannici" + }, + { + "first_name": "Davide", + "last_name": "Scaramuzza" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "C3Net: Compound Conditioned ControlNet for Multimodal Content Generation", - "authors": "Juntao Zhang, Yuehuai Liu, Yu-Wing Tai, Chi-Keung Tang", + "authors": [ + { + "first_name": "Juntao", + "last_name": "Zhang" + }, + { + "first_name": "Yuehuai", + "last_name": "Liu" + }, + { + "first_name": "Yu-Wing", + "last_name": "Tai" + }, + { + "first_name": "Chi-Keung", + "last_name": "Tang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Device-Wise Federated Network Pruning", - "authors": "Shangqian Gao, Junyi Li, Zeyu Zhang, Yanfu Zhang, Weidong Cai, Heng Huang", + "authors": [ + { + "first_name": "Shangqian", + "last_name": "Gao" + }, + { + "first_name": "Junyi", + "last_name": "Li" + }, + { + "first_name": "Zeyu", + "last_name": "Zhang" + }, + { + "first_name": "Yanfu", + "last_name": "Zhang" + }, + { + "first_name": "Weidong", + "last_name": "Cai" + }, + { + "first_name": "Heng", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Adapt Before Comparison: A New Perspective on Cross-Domain Few-Shot Segmentation", - "authors": "Jonas Herzog", + "authors": [ + { + "first_name": "Jonas", + "last_name": "Herzog" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation", - "authors": "Sai Kumar Dwivedi, Yu Sun, Priyanka Patel, Yao Feng, Michael J. Black", + "authors": [ + { + "first_name": "Sai", + "last_name": "Kumar Dwivedi" + }, + { + "first_name": "Yu", + "last_name": "Sun" + }, + { + "first_name": "Priyanka", + "last_name": "Patel" + }, + { + "first_name": "Yao", + "last_name": "Feng" + }, + { + "first_name": "Michael", + "last_name": "J. Black" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MoReVQA: Exploring Modular Reasoning Models for Video Question Answering", - "authors": "Juhong Min, Shyamal Buch, Arsha Nagrani, Minsu Cho, Cordelia Schmid", + "authors": [ + { + "first_name": "Juhong", + "last_name": "Min" + }, + { + "first_name": "Shyamal", + "last_name": "Buch" + }, + { + "first_name": "Arsha", + "last_name": "Nagrani" + }, + { + "first_name": "Minsu", + "last_name": "Cho" + }, + { + "first_name": "Cordelia", + "last_name": "Schmid" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Low-Rank Rescaled Vision Transformer Fine-Tuning: A Residual Design Approach", - "authors": "Wei Dong, Xing Zhang, Bihui Chen, Dawei Yan, Zhijun Lin, Qingsen Yan, Peng Wang, Yang Yang", + "authors": [ + { + "first_name": "Wei", + "last_name": "Dong" + }, + { + "first_name": "Xing", + "last_name": "Zhang" + }, + { + "first_name": "Bihui", + "last_name": "Chen" + }, + { + "first_name": "Dawei", + "last_name": "Yan" + }, + { + "first_name": "Zhijun", + "last_name": "Lin" + }, + { + "first_name": "Qingsen", + "last_name": "Yan" + }, + { + "first_name": "Peng", + "last_name": "Wang" + }, + { + "first_name": "Yang", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FaceCom: Towards High-fidelity 3D Facial Shape Completion via Optimization and Inpainting Guidance", - "authors": "Yinglong Li, Hongyu Wu, Xiaogang Wang, Qingzhao Qin, Yijiao Zhao, Yong Wang, Aimin Hao", + "authors": [ + { + "first_name": "Yinglong", + "last_name": "Li" + }, + { + "first_name": "Hongyu", + "last_name": "Wu" + }, + { + "first_name": "Xiaogang", + "last_name": "Wang" + }, + { + "first_name": "Qingzhao", + "last_name": "Qin" + }, + { + "first_name": "Yijiao", + "last_name": "Zhao" + }, + { + "first_name": "Yong", + "last_name": "Wang" + }, + { + "first_name": "Aimin", + "last_name": "Hao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Distribution-aware Knowledge Prototyping for Non-exemplar Lifelong Person Re-identification", - "authors": "Kunlun Xu, Xu Zou, Yuxin Peng, Jiahuan Zhou", + "authors": [ + { + "first_name": "Kunlun", + "last_name": "Xu" + }, + { + "first_name": "Xu", + "last_name": "Zou" + }, + { + "first_name": "Yuxin", + "last_name": "Peng" + }, + { + "first_name": "Jiahuan", + "last_name": "Zhou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LightOctree: Lightweight 3D Spatially-Coherent Indoor Lighting Estimation", - "authors": "Xuecan Wang, Shibang Xiao, Xiaohui Liang", + "authors": [ + { + "first_name": "Xuecan", + "last_name": "Wang" + }, + { + "first_name": "Shibang", + "last_name": "Xiao" + }, + { + "first_name": "Xiaohui", + "last_name": "Liang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Generating Enhanced Negatives for Training Language-Based Object Detectors", - "authors": "Shiyu Zhao, Long Zhao, Vijay Kumar B G, Yumin Suh, Dimitris N. Metaxas, Manmohan Chandraker, Samuel Schulter", + "authors": [ + { + "first_name": "Shiyu", + "last_name": "Zhao" + }, + { + "first_name": "Long", + "last_name": "Zhao" + }, + { + "first_name": "Vijay", + "last_name": "Kumar B G" + }, + { + "first_name": "Yumin", + "last_name": "Suh" + }, + { + "first_name": "Dimitris", + "last_name": "N. Metaxas" + }, + { + "first_name": "Manmohan", + "last_name": "Chandraker" + }, + { + "first_name": "Samuel", + "last_name": "Schulter" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Insect-Foundation: A Foundation Model and Large-scale 1M Dataset for Visual Insect Understanding", - "authors": "Hoang-Quan Nguyen, Thanh-Dat Truong, Xuan Bac Nguyen, Ashley Dowling, Xin Li, Khoa Luu", + "authors": [ + { + "first_name": "Hoang-Quan", + "last_name": "Nguyen" + }, + { + "first_name": "Thanh-Dat", + "last_name": "Truong" + }, + { + "first_name": "Xuan", + "last_name": "Bac Nguyen" + }, + { + "first_name": "Ashley", + "last_name": "Dowling" + }, + { + "first_name": "Xin", + "last_name": "Li" + }, + { + "first_name": "Khoa", + "last_name": "Luu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Data-Efficient Multimodal Fusion on a Single GPU", - "authors": "Noël Vouitsis, Zhaoyan Liu, Satya Krishna Gorti, Valentin Villecroze, Jesse C. Cresswell, Guangwei Yu, Gabriel Loaiza-Ganem, Maksims Volkovs", + "authors": [ + { + "first_name": "Noël", + "last_name": "Vouitsis" + }, + { + "first_name": "Zhaoyan", + "last_name": "Liu" + }, + { + "first_name": "Satya", + "last_name": "Krishna Gorti" + }, + { + "first_name": "Valentin", + "last_name": "Villecroze" + }, + { + "first_name": "Jesse", + "last_name": "C. Cresswell" + }, + { + "first_name": "Guangwei", + "last_name": "Yu" + }, + { + "first_name": "Gabriel", + "last_name": "Loaiza-Ganem" + }, + { + "first_name": "Maksims", + "last_name": "Volkovs" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FedSelect: Personalized Federated Learning with Customized Selection of Parameters for Fine-Tuning", - "authors": "Rishub Tamirisa, Chulin Xie, Wenxuan Bao, Andy Zhou, Ron Arel, Aviv Shamsian", + "authors": [ + { + "first_name": "Rishub", + "last_name": "Tamirisa" + }, + { + "first_name": "Chulin", + "last_name": "Xie" + }, + { + "first_name": "Wenxuan", + "last_name": "Bao" + }, + { + "first_name": "Andy", + "last_name": "Zhou" + }, + { + "first_name": "Ron", + "last_name": "Arel" + }, + { + "first_name": "Aviv", + "last_name": "Shamsian" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FaceLift: Semi-supervised 3D Facial Landmark Localization", - "authors": "David Ferman, Pablo Garrido, Gaurav Bharaj", + "authors": [ + { + "first_name": "David", + "last_name": "Ferman" + }, + { + "first_name": "Pablo", + "last_name": "Garrido" + }, + { + "first_name": "Gaurav", + "last_name": "Bharaj" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PSDPM: Prototype-based Secondary Discriminative Pixels Mining for Weakly Supervised Semantic Segmentation", - "authors": "Xinqiao Zhao, Ziqian Yang, Tianhong Dai, Bingfeng Zhang, Jimin Xiao", + "authors": [ + { + "first_name": "Xinqiao", + "last_name": "Zhao" + }, + { + "first_name": "Ziqian", + "last_name": "Yang" + }, + { + "first_name": "Tianhong", + "last_name": "Dai" + }, + { + "first_name": "Bingfeng", + "last_name": "Zhang" + }, + { + "first_name": "Jimin", + "last_name": "Xiao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Bidirectional Multi-Scale Implicit Neural Representations for Image Deraining", - "authors": "Xiang Chen, Jinshan Pan, Jiangxin Dong", + "authors": [ + { + "first_name": "Xiang", + "last_name": "Chen" + }, + { + "first_name": "Jinshan", + "last_name": "Pan" + }, + { + "first_name": "Jiangxin", + "last_name": "Dong" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Frozen CLIP: A Strong Backbone for Weakly Supervised Semantic Segmentation", - "authors": "Bingfeng Zhang, Siyue Yu, Yunchao Wei, Yao Zhao, Jimin Xiao", + "authors": [ + { + "first_name": "Bingfeng", + "last_name": "Zhang" + }, + { + "first_name": "Siyue", + "last_name": "Yu" + }, + { + "first_name": "Yunchao", + "last_name": "Wei" + }, + { + "first_name": "Yao", + "last_name": "Zhao" + }, + { + "first_name": "Jimin", + "last_name": "Xiao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FedAS: Bridging Inconsistency in Personalized Federated Learning", - "authors": "Xiyuan Yang, Wenke Huang, Mang Ye", + "authors": [ + { + "first_name": "Xiyuan", + "last_name": "Yang" + }, + { + "first_name": "Wenke", + "last_name": "Huang" + }, + { + "first_name": "Mang", + "last_name": "Ye" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LAFS: Landmark-based Facial Self-supervised Learning for Face Recognition", - "authors": "Zhonglin Sun, Chen Feng, Ioannis Patras, Georgios Tzimiropoulos", + "authors": [ + { + "first_name": "Zhonglin", + "last_name": "Sun" + }, + { + "first_name": "Chen", + "last_name": "Feng" + }, + { + "first_name": "Ioannis", + "last_name": "Patras" + }, + { + "first_name": "Georgios", + "last_name": "Tzimiropoulos" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation", - "authors": "Bin Xie, Jiale Cao, Jin Xie, Fahad Shahbaz Khan, Yanwei Pang", + "authors": [ + { + "first_name": "Bin", + "last_name": "Xie" + }, + { + "first_name": "Jiale", + "last_name": "Cao" + }, + { + "first_name": "Jin", + "last_name": "Xie" + }, + { + "first_name": "Fahad", + "last_name": "Shahbaz Khan" + }, + { + "first_name": "Yanwei", + "last_name": "Pang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GPLD3D: Latent Diffusion of 3D Shape Generative Models by Enforcing Geometric and Physical Priors", - "authors": "Yuan Dong, Qi Zuo, Xiaodong Gu, Weihao Yuan, Zhengyi Zhao, Zilong Dong, Liefeng Bo, Qixing Huang", + "authors": [ + { + "first_name": "Yuan", + "last_name": "Dong" + }, + { + "first_name": "Qi", + "last_name": "Zuo" + }, + { + "first_name": "Xiaodong", + "last_name": "Gu" + }, + { + "first_name": "Weihao", + "last_name": "Yuan" + }, + { + "first_name": "Zhengyi", + "last_name": "Zhao" + }, + { + "first_name": "Zilong", + "last_name": "Dong" + }, + { + "first_name": "Liefeng", + "last_name": "Bo" + }, + { + "first_name": "Qixing", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Enhancing Quality of Compressed Images by Mitigating Enhancement Bias Towards Compression Domain", - "authors": "Qunliang Xing, Mai Xu, Shengxi Li, Xin Deng, Meisong Zheng, Huaida Liu, Ying Chen", + "authors": [ + { + "first_name": "Qunliang", + "last_name": "Xing" + }, + { + "first_name": "Mai", + "last_name": "Xu" + }, + { + "first_name": "Shengxi", + "last_name": "Li" + }, + { + "first_name": "Xin", + "last_name": "Deng" + }, + { + "first_name": "Meisong", + "last_name": "Zheng" + }, + { + "first_name": "Huaida", + "last_name": "Liu" + }, + { + "first_name": "Ying", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LangSplat: 3D Language Gaussian Splatting", - "authors": "Minghan Qin, Wanhua Li, Jiawei Zhou, Haoqian Wang, Hanspeter Pfister", + "authors": [ + { + "first_name": "Minghan", + "last_name": "Qin" + }, + { + "first_name": "Wanhua", + "last_name": "Li" + }, + { + "first_name": "Jiawei", + "last_name": "Zhou" + }, + { + "first_name": "Haoqian", + "last_name": "Wang" + }, + { + "first_name": "Hanspeter", + "last_name": "Pfister" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MoST: Multi-Modality Scene Tokenization for Motion Prediction", - "authors": "Norman Mu, Jingwei Ji, Zhenpei Yang, Nate Harada, Haotian Tang, Kan Chen, Charles R. Qi, Runzhou Ge, Kratarth Goel, Zoey Yang, Scott Ettinger, Rami Al-Rfou, Dragomir Anguelov, Yin Zhou", + "authors": [ + { + "first_name": "Norman", + "last_name": "Mu" + }, + { + "first_name": "Jingwei", + "last_name": "Ji" + }, + { + "first_name": "Zhenpei", + "last_name": "Yang" + }, + { + "first_name": "Nate", + "last_name": "Harada" + }, + { + "first_name": "Haotian", + "last_name": "Tang" + }, + { + "first_name": "Kan", + "last_name": "Chen" + }, + { + "first_name": "Charles", + "last_name": "R. Qi" + }, + { + "first_name": "Runzhou", + "last_name": "Ge" + }, + { + "first_name": "Kratarth", + "last_name": "Goel" + }, + { + "first_name": "Zoey", + "last_name": "Yang" + }, + { + "first_name": "Scott", + "last_name": "Ettinger" + }, + { + "first_name": "Rami", + "last_name": "Al-Rfou" + }, + { + "first_name": "Dragomir", + "last_name": "Anguelov" + }, + { + "first_name": "Yin", + "last_name": "Zhou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PIGEON: Predicting Image Geolocations", - "authors": "Lukas Haas, Michal Skreta, Silas Alberti, Chelsea Finn", + "authors": [ + { + "first_name": "Lukas", + "last_name": "Haas" + }, + { + "first_name": "Michal", + "last_name": "Skreta" + }, + { + "first_name": "Silas", + "last_name": "Alberti" + }, + { + "first_name": "Chelsea", + "last_name": "Finn" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Improving Spectral Snapshot Reconstruction with Spectral-Spatial Rectification", - "authors": "Jiancheng Zhang, Haijin Zeng, Yongyong Chen, Dengxiu Yu, Yin-Ping Zhao", + "authors": [ + { + "first_name": "Jiancheng", + "last_name": "Zhang" + }, + { + "first_name": "Haijin", + "last_name": "Zeng" + }, + { + "first_name": "Yongyong", + "last_name": "Chen" + }, + { + "first_name": "Dengxiu", + "last_name": "Yu" + }, + { + "first_name": "Yin-Ping", + "last_name": "Zhao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Self-correcting LLM-controlled Diffusion Models", - "authors": "Tsung-Han Wu, Long Lian, Joseph E. Gonzalez, Boyi Li, Trevor Darrell", + "authors": [ + { + "first_name": "Tsung-Han", + "last_name": "Wu" + }, + { + "first_name": "Long", + "last_name": "Lian" + }, + { + "first_name": "Joseph", + "last_name": "E. Gonzalez" + }, + { + "first_name": "Boyi", + "last_name": "Li" + }, + { + "first_name": "Trevor", + "last_name": "Darrell" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PACER+: On-Demand Pedestrian Animation Controller in Driving Scenarios", - "authors": "Jingbo Wang, Zhengyi Luo, Ye Yuan, Yixuan Li, Bo Dai", + "authors": [ + { + "first_name": "Jingbo", + "last_name": "Wang" + }, + { + "first_name": "Zhengyi", + "last_name": "Luo" + }, + { + "first_name": "Ye", + "last_name": "Yuan" + }, + { + "first_name": "Yixuan", + "last_name": "Li" + }, + { + "first_name": "Bo", + "last_name": "Dai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LTM: Lightweight Textured Mesh Extraction and Refinement of Large Unbounded Scenes for Efficient Storage and Real-time Rendering", - "authors": "Jaehoon Choi, Rajvi Shah, Qinbo Li, Yipeng Wang, Ayush Saraf, Changil Kim, Jia-Bin Huang, Dinesh Manocha, Suhib Alsisan, Johannes Kopf", + "authors": [ + { + "first_name": "Jaehoon", + "last_name": "Choi" + }, + { + "first_name": "Rajvi", + "last_name": "Shah" + }, + { + "first_name": "Qinbo", + "last_name": "Li" + }, + { + "first_name": "Yipeng", + "last_name": "Wang" + }, + { + "first_name": "Ayush", + "last_name": "Saraf" + }, + { + "first_name": "Changil", + "last_name": "Kim" + }, + { + "first_name": "Jia-Bin", + "last_name": "Huang" + }, + { + "first_name": "Dinesh", + "last_name": "Manocha" + }, + { + "first_name": "Suhib", + "last_name": "Alsisan" + }, + { + "first_name": "Johannes", + "last_name": "Kopf" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Don't Drop Your Samples! Coherence-Aware Training Benefits Conditional Diffusion", - "authors": "Nicolas Dufour, Victor Besnier, Vicky Kalogeiton, David Picard", + "authors": [ + { + "first_name": "Nicolas", + "last_name": "Dufour" + }, + { + "first_name": "Victor", + "last_name": "Besnier" + }, + { + "first_name": "Vicky", + "last_name": "Kalogeiton" + }, + { + "first_name": "David", + "last_name": "Picard" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Flow-Guided Online Stereo Rectification for Wide Baseline Stereo", - "authors": "Anush Kumar, Fahim Mannan, Omid Hosseini Jafari, Shile Li, Felix Heide", + "authors": [ + { + "first_name": "Anush", + "last_name": "Kumar" + }, + { + "first_name": "Fahim", + "last_name": "Mannan" + }, + { + "first_name": "Omid", + "last_name": "Hosseini Jafari" + }, + { + "first_name": "Shile", + "last_name": "Li" + }, + { + "first_name": "Felix", + "last_name": "Heide" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization", - "authors": "Jiahe Li, Jiawei Zhang, Xiao Bai, Jin Zheng, Xin Ning, Jun Zhou, Lin Gu", + "authors": [ + { + "first_name": "Jiahe", + "last_name": "Li" + }, + { + "first_name": "Jiawei", + "last_name": "Zhang" + }, + { + "first_name": "Xiao", + "last_name": "Bai" + }, + { + "first_name": "Jin", + "last_name": "Zheng" + }, + { + "first_name": "Xin", + "last_name": "Ning" + }, + { + "first_name": "Jun", + "last_name": "Zhou" + }, + { + "first_name": "Lin", + "last_name": "Gu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ColorPCR: Color Point Cloud Registration with Multi-Stage Geometric-Color Fusion", - "authors": "Juncheng Mu, Lin Bie, Shaoyi Du, Yue Gao", + "authors": [ + { + "first_name": "Juncheng", + "last_name": "Mu" + }, + { + "first_name": "Lin", + "last_name": "Bie" + }, + { + "first_name": "Shaoyi", + "last_name": "Du" + }, + { + "first_name": "Yue", + "last_name": "Gao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HomoFormer: Homogenized Transformer for Image Shadow Removal", - "authors": "Jie Xiao, Xueyang Fu, Yurui Zhu, Dong Li, Jie Huang, Kai Zhu, Zheng-Jun Zha", + "authors": [ + { + "first_name": "Jie", + "last_name": "Xiao" + }, + { + "first_name": "Xueyang", + "last_name": "Fu" + }, + { + "first_name": "Yurui", + "last_name": "Zhu" + }, + { + "first_name": "Dong", + "last_name": "Li" + }, + { + "first_name": "Jie", + "last_name": "Huang" + }, + { + "first_name": "Kai", + "last_name": "Zhu" + }, + { + "first_name": "Zheng-Jun", + "last_name": "Zha" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "What If the TV Was Off? Examining Counterfactual Reasoning Abilities of Multi-modal Language Models", - "authors": "Letian Zhang, Xiaotong Zhai, Zhongkai Zhao, Yongshuo Zong, Xin Wen, Bingchen Zhao", + "authors": [ + { + "first_name": "Letian", + "last_name": "Zhang" + }, + { + "first_name": "Xiaotong", + "last_name": "Zhai" + }, + { + "first_name": "Zhongkai", + "last_name": "Zhao" + }, + { + "first_name": "Yongshuo", + "last_name": "Zong" + }, + { + "first_name": "Xin", + "last_name": "Wen" + }, + { + "first_name": "Bingchen", + "last_name": "Zhao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "What Do You See in Vehicle? Comprehensive Vision Solution for In-Vehicle Gaze Estimation", - "authors": "Yihua Cheng, Yaning Zhu, Zongji Wang, Hongquan Hao, Yongwei Liu, Shiqing Cheng, Xi Wang, Hyung Jin Chang", + "authors": [ + { + "first_name": "Yihua", + "last_name": "Cheng" + }, + { + "first_name": "Yaning", + "last_name": "Zhu" + }, + { + "first_name": "Zongji", + "last_name": "Wang" + }, + { + "first_name": "Hongquan", + "last_name": "Hao" + }, + { + "first_name": "Yongwei", + "last_name": "Liu" + }, + { + "first_name": "Shiqing", + "last_name": "Cheng" + }, + { + "first_name": "Xi", + "last_name": "Wang" + }, + { + "first_name": "Hyung", + "last_name": "Jin Chang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Driving Everywhere with Large Language Model Policy Adaptation", - "authors": "Boyi Li, Yue Wang, Jiageng Mao, Boris Ivanovic, Sushant Veer, Karen Leung, Marco Pavone", + "authors": [ + { + "first_name": "Boyi", + "last_name": "Li" + }, + { + "first_name": "Yue", + "last_name": "Wang" + }, + { + "first_name": "Jiageng", + "last_name": "Mao" + }, + { + "first_name": "Boris", + "last_name": "Ivanovic" + }, + { + "first_name": "Sushant", + "last_name": "Veer" + }, + { + "first_name": "Karen", + "last_name": "Leung" + }, + { + "first_name": "Marco", + "last_name": "Pavone" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "UFORecon: Generalizable Sparse-View Surface Reconstruction from Arbitrary and Unfavorable Sets", - "authors": "Youngju Na, Woo Jae Kim, Kyu Beom Han, Suhyeon Ha, Sung-Eui Yoon", + "authors": [ + { + "first_name": "Youngju", + "last_name": "Na" + }, + { + "first_name": "Woo", + "last_name": "Jae Kim" + }, + { + "first_name": "Kyu", + "last_name": "Beom Han" + }, + { + "first_name": "Suhyeon", + "last_name": "Ha" + }, + { + "first_name": "Sung-Eui", + "last_name": "Yoon" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FAR: Flexible Accurate and Robust 6DoF Relative Camera Pose Estimation", - "authors": "Chris Rockwell, Nilesh Kulkarni, Linyi Jin, Jeong Joon Park, Justin Johnson, David F. Fouhey", + "authors": [ + { + "first_name": "Chris", + "last_name": "Rockwell" + }, + { + "first_name": "Nilesh", + "last_name": "Kulkarni" + }, + { + "first_name": "Linyi", + "last_name": "Jin" + }, + { + "first_name": "Jeong", + "last_name": "Joon Park" + }, + { + "first_name": "Justin", + "last_name": "Johnson" + }, + { + "first_name": "David", + "last_name": "F. Fouhey" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "eTraM: Event-based Traffic Monitoring Dataset", - "authors": "Aayush Atul Verma, Bharatesh Chakravarthi, Arpitsinh Vaghela, Hua Wei, Yezhou Yang", + "authors": [ + { + "first_name": "Aayush", + "last_name": "Atul Verma" + }, + { + "first_name": "Bharatesh", + "last_name": "Chakravarthi" + }, + { + "first_name": "Arpitsinh", + "last_name": "Vaghela" + }, + { + "first_name": "Hua", + "last_name": "Wei" + }, + { + "first_name": "Yezhou", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MoCha-Stereo: Motif Channel Attention Network for Stereo Matching", - "authors": "Ziyang Chen, Wei Long, He Yao, Yongjun Zhang, Bingshu Wang, Yongbin Qin, Jia Wu", + "authors": [ + { + "first_name": "Ziyang", + "last_name": "Chen" + }, + { + "first_name": "Wei", + "last_name": "Long" + }, + { + "first_name": "He", + "last_name": "Yao" + }, + { + "first_name": "Yongjun", + "last_name": "Zhang" + }, + { + "first_name": "Bingshu", + "last_name": "Wang" + }, + { + "first_name": "Yongbin", + "last_name": "Qin" + }, + { + "first_name": "Jia", + "last_name": "Wu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Koala: Key Frame-Conditioned Long Video-LLM", - "authors": "Reuben Tan, Ximeng Sun, Ping Hu, Jui-hsien Wang, Hanieh Deilamsalehy, Bryan A. Plummer, Bryan Russell, Kate Saenko", + "authors": [ + { + "first_name": "Reuben", + "last_name": "Tan" + }, + { + "first_name": "Ximeng", + "last_name": "Sun" + }, + { + "first_name": "Ping", + "last_name": "Hu" + }, + { + "first_name": "Jui-hsien", + "last_name": "Wang" + }, + { + "first_name": "Hanieh", + "last_name": "Deilamsalehy" + }, + { + "first_name": "Bryan", + "last_name": "A. Plummer" + }, + { + "first_name": "Bryan", + "last_name": "Russell" + }, + { + "first_name": "Kate", + "last_name": "Saenko" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Extend Your Own Correspondences: Unsupervised Distant Point Cloud Registration by Progressive Distance Extension", - "authors": "Quan Liu, Hongzi Zhu, Zhenxi Wang, Yunsong Zhou, Shan Chang, Minyi Guo", + "authors": [ + { + "first_name": "Quan", + "last_name": "Liu" + }, + { + "first_name": "Hongzi", + "last_name": "Zhu" + }, + { + "first_name": "Zhenxi", + "last_name": "Wang" + }, + { + "first_name": "Yunsong", + "last_name": "Zhou" + }, + { + "first_name": "Shan", + "last_name": "Chang" + }, + { + "first_name": "Minyi", + "last_name": "Guo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models", - "authors": "Tianrui Guan, Fuxiao Liu, Xiyang Wu, Ruiqi Xian, Zongxia Li, Xiaoyu Liu, Xijun Wang, Lichang Chen, Furong Huang, Yaser Yacoob, Dinesh Manocha, Tianyi Zhou", + "authors": [ + { + "first_name": "Tianrui", + "last_name": "Guan" + }, + { + "first_name": "Fuxiao", + "last_name": "Liu" + }, + { + "first_name": "Xiyang", + "last_name": "Wu" + }, + { + "first_name": "Ruiqi", + "last_name": "Xian" + }, + { + "first_name": "Zongxia", + "last_name": "Li" + }, + { + "first_name": "Xiaoyu", + "last_name": "Liu" + }, + { + "first_name": "Xijun", + "last_name": "Wang" + }, + { + "first_name": "Lichang", + "last_name": "Chen" + }, + { + "first_name": "Furong", + "last_name": "Huang" + }, + { + "first_name": "Yaser", + "last_name": "Yacoob" + }, + { + "first_name": "Dinesh", + "last_name": "Manocha" + }, + { + "first_name": "Tianyi", + "last_name": "Zhou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ID-like Prompt Learning for Few-Shot Out-of-Distribution Detection", - "authors": "Yichen Bai, Zongbo Han, Bing Cao, Xiaoheng Jiang, Qinghua Hu, Changqing Zhang", + "authors": [ + { + "first_name": "Yichen", + "last_name": "Bai" + }, + { + "first_name": "Zongbo", + "last_name": "Han" + }, + { + "first_name": "Bing", + "last_name": "Cao" + }, + { + "first_name": "Xiaoheng", + "last_name": "Jiang" + }, + { + "first_name": "Qinghua", + "last_name": "Hu" + }, + { + "first_name": "Changqing", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Breathing Life Into Sketches Using Text-to-Video Priors", - "authors": "Rinon Gal, Yael Vinker, Yuval Alaluf, Amit Bermano, Daniel Cohen-Or, Ariel Shamir, Gal Chechik", + "authors": [ + { + "first_name": "Rinon", + "last_name": "Gal" + }, + { + "first_name": "Yael", + "last_name": "Vinker" + }, + { + "first_name": "Yuval", + "last_name": "Alaluf" + }, + { + "first_name": "Amit", + "last_name": "Bermano" + }, + { + "first_name": "Daniel", + "last_name": "Cohen-Or" + }, + { + "first_name": "Ariel", + "last_name": "Shamir" + }, + { + "first_name": "Gal", + "last_name": "Chechik" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Multi-modal Learning for Geospatial Vegetation Forecasting", - "authors": "Vitus Benson, Claire Robin, Christian Requena-Mesa, Lazaro Alonso, Nuno Carvalhais, José Cortés, Zhihan Gao, Nora Linscheid, Mélanie Weynants, Markus Reichstein", + "authors": [ + { + "first_name": "Vitus", + "last_name": "Benson" + }, + { + "first_name": "Claire", + "last_name": "Robin" + }, + { + "first_name": "Christian", + "last_name": "Requena-Mesa" + }, + { + "first_name": "Lazaro", + "last_name": "Alonso" + }, + { + "first_name": "Nuno", + "last_name": "Carvalhais" + }, + { + "first_name": "José", + "last_name": "Cortés" + }, + { + "first_name": "Zhihan", + "last_name": "Gao" + }, + { + "first_name": "Nora", + "last_name": "Linscheid" + }, + { + "first_name": "Mélanie", + "last_name": "Weynants" + }, + { + "first_name": "Markus", + "last_name": "Reichstein" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning Diffusion Texture Priors for Image Restoration", - "authors": "Tian Ye, Sixiang Chen, Wenhao Chai, Zhaohu Xing, Jing Qin, Ge Lin, Lei Zhu", + "authors": [ + { + "first_name": "Tian", + "last_name": "Ye" + }, + { + "first_name": "Sixiang", + "last_name": "Chen" + }, + { + "first_name": "Wenhao", + "last_name": "Chai" + }, + { + "first_name": "Zhaohu", + "last_name": "Xing" + }, + { + "first_name": "Jing", + "last_name": "Qin" + }, + { + "first_name": "Ge", + "last_name": "Lin" + }, + { + "first_name": "Lei", + "last_name": "Zhu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Bring Event into RGB and LiDAR: Hierarchical Visual-Motion Fusion for Scene Flow", - "authors": "Hanyu Zhou, Yi Chang, Zhiwei Shi", + "authors": [ + { + "first_name": "Hanyu", + "last_name": "Zhou" + }, + { + "first_name": "Yi", + "last_name": "Chang" + }, + { + "first_name": "Zhiwei", + "last_name": "Shi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Entangled View-Epipolar Information Aggregation for Generalizable Neural Radiance Fields", - "authors": "Zhiyuan Min, Yawei Luo, Wei Yang, Yuesong Wang, Yi Yang", + "authors": [ + { + "first_name": "Zhiyuan", + "last_name": "Min" + }, + { + "first_name": "Yawei", + "last_name": "Luo" + }, + { + "first_name": "Wei", + "last_name": "Yang" + }, + { + "first_name": "Yuesong", + "last_name": "Wang" + }, + { + "first_name": "Yi", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Jack of All Tasks Master of Many: Designing General-Purpose Coarse-to-Fine Vision-Language Model", - "authors": "Shraman Pramanick, Guangxing Han, Rui Hou, Sayan Nag, Ser-Nam Lim, Nicolas Ballas, Qifan Wang, Rama Chellappa, Amjad Almahairi", + "authors": [ + { + "first_name": "Shraman", + "last_name": "Pramanick" + }, + { + "first_name": "Guangxing", + "last_name": "Han" + }, + { + "first_name": "Rui", + "last_name": "Hou" + }, + { + "first_name": "Sayan", + "last_name": "Nag" + }, + { + "first_name": "Ser-Nam", + "last_name": "Lim" + }, + { + "first_name": "Nicolas", + "last_name": "Ballas" + }, + { + "first_name": "Qifan", + "last_name": "Wang" + }, + { + "first_name": "Rama", + "last_name": "Chellappa" + }, + { + "first_name": "Amjad", + "last_name": "Almahairi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MMVP: A Multimodal MoCap Dataset with Vision and Pressure Sensors", - "authors": "He Zhang, Shenghao Ren, Haolei Yuan, Jianhui Zhao, Fan Li, Shuangpeng Sun, Zhenghao Liang, Tao Yu, Qiu Shen, Xun Cao", + "authors": [ + { + "first_name": "He", + "last_name": "Zhang" + }, + { + "first_name": "Shenghao", + "last_name": "Ren" + }, + { + "first_name": "Haolei", + "last_name": "Yuan" + }, + { + "first_name": "Jianhui", + "last_name": "Zhao" + }, + { + "first_name": "Fan", + "last_name": "Li" + }, + { + "first_name": "Shuangpeng", + "last_name": "Sun" + }, + { + "first_name": "Zhenghao", + "last_name": "Liang" + }, + { + "first_name": "Tao", + "last_name": "Yu" + }, + { + "first_name": "Qiu", + "last_name": "Shen" + }, + { + "first_name": "Xun", + "last_name": "Cao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "YolOOD: Utilizing Object Detection Concepts for Multi-Label Out-of-Distribution Detection", - "authors": "Alon Zolfi, Guy Amit, Amit Baras, Satoru Koda, Ikuya Morikawa, Yuval Elovici, Asaf Shabtai", + "authors": [ + { + "first_name": "Alon", + "last_name": "Zolfi" + }, + { + "first_name": "Guy", + "last_name": "Amit" + }, + { + "first_name": "Amit", + "last_name": "Baras" + }, + { + "first_name": "Satoru", + "last_name": "Koda" + }, + { + "first_name": "Ikuya", + "last_name": "Morikawa" + }, + { + "first_name": "Yuval", + "last_name": "Elovici" + }, + { + "first_name": "Asaf", + "last_name": "Shabtai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SchurVINS: Schur Complement-Based Lightweight Visual Inertial Navigation System", - "authors": "Yunfei Fan, Tianyu Zhao, Guidong Wang", + "authors": [ + { + "first_name": "Yunfei", + "last_name": "Fan" + }, + { + "first_name": "Tianyu", + "last_name": "Zhao" + }, + { + "first_name": "Guidong", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Collaborating Foundation Models for Domain Generalized Semantic Segmentation", - "authors": "Yasser Benigmim, Subhankar Roy, Slim Essid, Vicky Kalogeiton, Stéphane Lathuilière", + "authors": [ + { + "first_name": "Yasser", + "last_name": "Benigmim" + }, + { + "first_name": "Subhankar", + "last_name": "Roy" + }, + { + "first_name": "Slim", + "last_name": "Essid" + }, + { + "first_name": "Vicky", + "last_name": "Kalogeiton" + }, + { + "first_name": "Stéphane", + "last_name": "Lathuilière" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards Variable and Coordinated Holistic Co-Speech Motion Generation", - "authors": "Yifei Liu, Qiong Cao, Yandong Wen, Huaiguang Jiang, Changxing Ding", + "authors": [ + { + "first_name": "Yifei", + "last_name": "Liu" + }, + { + "first_name": "Qiong", + "last_name": "Cao" + }, + { + "first_name": "Yandong", + "last_name": "Wen" + }, + { + "first_name": "Huaiguang", + "last_name": "Jiang" + }, + { + "first_name": "Changxing", + "last_name": "Ding" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "JoAPR: Cleaning the Lens of Prompt Learning for Vision-Language Models", - "authors": "Yuncheng Guo, Xiaodong Gu", + "authors": [ + { + "first_name": "Yuncheng", + "last_name": "Guo" + }, + { + "first_name": "Xiaodong", + "last_name": "Gu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "AllSpark: Reborn Labeled Features from Unlabeled in Transformer for Semi-Supervised Semantic Segmentation", - "authors": "Haonan Wang, Qixiang Zhang, Yi Li, Xiaomeng Li", + "authors": [ + { + "first_name": "Haonan", + "last_name": "Wang" + }, + { + "first_name": "Qixiang", + "last_name": "Zhang" + }, + { + "first_name": "Yi", + "last_name": "Li" + }, + { + "first_name": "Xiaomeng", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Open-Vocabulary 3D Semantic Segmentation with Foundation Models", - "authors": "Li Jiang, Shaoshuai Shi, Bernt Schiele", + "authors": [ + { + "first_name": "Li", + "last_name": "Jiang" + }, + { + "first_name": "Shaoshuai", + "last_name": "Shi" + }, + { + "first_name": "Bernt", + "last_name": "Schiele" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SIGNeRF: Scene Integrated Generation for Neural Radiance Fields", - "authors": "Jan-Niklas Dihlmann, Andreas Engelhardt, Hendrik Lensch", + "authors": [ + { + "first_name": "Jan-Niklas", + "last_name": "Dihlmann" + }, + { + "first_name": "Andreas", + "last_name": "Engelhardt" + }, + { + "first_name": "Hendrik", + "last_name": "Lensch" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts", - "authors": "Mu Cai, Haotian Liu, Siva Karthik Mustikovela, Gregory P. Meyer, Yuning Chai, Dennis Park, Yong Jae Lee", + "authors": [ + { + "first_name": "Mu", + "last_name": "Cai" + }, + { + "first_name": "Haotian", + "last_name": "Liu" + }, + { + "first_name": "Siva", + "last_name": "Karthik Mustikovela" + }, + { + "first_name": "Gregory", + "last_name": "P. Meyer" + }, + { + "first_name": "Yuning", + "last_name": "Chai" + }, + { + "first_name": "Dennis", + "last_name": "Park" + }, + { + "first_name": "Yong", + "last_name": "Jae Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "OVER-NAV: Elevating Iterative Vision-and-Language Navigation with Open-Vocabulary Detection and StructurEd Representation", - "authors": "Ganlong Zhao, Guanbin Li, Weikai Chen, Yizhou Yu", + "authors": [ + { + "first_name": "Ganlong", + "last_name": "Zhao" + }, + { + "first_name": "Guanbin", + "last_name": "Li" + }, + { + "first_name": "Weikai", + "last_name": "Chen" + }, + { + "first_name": "Yizhou", + "last_name": "Yu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "1-Lipschitz Layers Compared: Memory Speed and Certifiable Robustness", - "authors": "Bernd Prach, Fabio Brau, Giorgio Buttazzo, Christoph H. Lampert", + "authors": [ + { + "first_name": "Bernd", + "last_name": "Prach" + }, + { + "first_name": "Fabio", + "last_name": "Brau" + }, + { + "first_name": "Giorgio", + "last_name": "Buttazzo" + }, + { + "first_name": "Christoph", + "last_name": "H. Lampert" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "All Rivers Run to the Sea: Private Learning with Asymmetric Flows", - "authors": "Yue Niu, Ramy E. Ali, Saurav Prakash, Salman Avestimehr", + "authors": [ + { + "first_name": "Yue", + "last_name": "Niu" + }, + { + "first_name": "Ramy", + "last_name": "E. Ali" + }, + { + "first_name": "Saurav", + "last_name": "Prakash" + }, + { + "first_name": "Salman", + "last_name": "Avestimehr" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Generating Illustrated Instructions", - "authors": "Sachit Menon, Ishan Misra, Rohit Girdhar", + "authors": [ + { + "first_name": "Sachit", + "last_name": "Menon" + }, + { + "first_name": "Ishan", + "last_name": "Misra" + }, + { + "first_name": "Rohit", + "last_name": "Girdhar" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Construct to Associate: Cooperative Context Learning for Domain Adaptive Point Cloud Segmentation", - "authors": "Guangrui Li", + "authors": [ + { + "first_name": "Guangrui", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Robust Image Denoising through Adversarial Frequency Mixup", - "authors": "Donghun Ryou, Inju Ha, Hyewon Yoo, Dongwan Kim, Bohyung Han", + "authors": [ + { + "first_name": "Donghun", + "last_name": "Ryou" + }, + { + "first_name": "Inju", + "last_name": "Ha" + }, + { + "first_name": "Hyewon", + "last_name": "Yoo" + }, + { + "first_name": "Dongwan", + "last_name": "Kim" + }, + { + "first_name": "Bohyung", + "last_name": "Han" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object Interactions", - "authors": "Hao Xu, Haipeng Li, Yinqiao Wang, Shuaicheng Liu, Chi-Wing Fu", + "authors": [ + { + "first_name": "Hao", + "last_name": "Xu" + }, + { + "first_name": "Haipeng", + "last_name": "Li" + }, + { + "first_name": "Yinqiao", + "last_name": "Wang" + }, + { + "first_name": "Shuaicheng", + "last_name": "Liu" + }, + { + "first_name": "Chi-Wing", + "last_name": "Fu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "A-Teacher: Asymmetric Network for 3D Semi-Supervised Object Detection", - "authors": "Hanshi Wang, Zhipeng Zhang, Jin Gao, Weiming Hu", + "authors": [ + { + "first_name": "Hanshi", + "last_name": "Wang" + }, + { + "first_name": "Zhipeng", + "last_name": "Zhang" + }, + { + "first_name": "Jin", + "last_name": "Gao" + }, + { + "first_name": "Weiming", + "last_name": "Hu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GoMVS: Geometrically Consistent Cost Aggregation for Multi-View Stereo", - "authors": "Jiang Wu, Rui Li, Haofei Xu, Wenxun Zhao, Yu Zhu, Jinqiu Sun, Yanning Zhang", + "authors": [ + { + "first_name": "Jiang", + "last_name": "Wu" + }, + { + "first_name": "Rui", + "last_name": "Li" + }, + { + "first_name": "Haofei", + "last_name": "Xu" + }, + { + "first_name": "Wenxun", + "last_name": "Zhao" + }, + { + "first_name": "Yu", + "last_name": "Zhu" + }, + { + "first_name": "Jinqiu", + "last_name": "Sun" + }, + { + "first_name": "Yanning", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Evaluating Transferability in Retrieval Tasks: An Approach Using MMD and Kernel Methods", - "authors": "Mengyu Dai, Amir Hossein Raffiee, Aashish Jain, Joshua Correa", + "authors": [ + { + "first_name": "Mengyu", + "last_name": "Dai" + }, + { + "first_name": "Amir", + "last_name": "Hossein Raffiee" + }, + { + "first_name": "Aashish", + "last_name": "Jain" + }, + { + "first_name": "Joshua", + "last_name": "Correa" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "AnyScene: Customized Image Synthesis with Composited Foreground", - "authors": "Ruidong Chen, Lanjun Wang, Weizhi Nie, Yongdong Zhang, An-An Liu", + "authors": [ + { + "first_name": "Ruidong", + "last_name": "Chen" + }, + { + "first_name": "Lanjun", + "last_name": "Wang" + }, + { + "first_name": "Weizhi", + "last_name": "Nie" + }, + { + "first_name": "Yongdong", + "last_name": "Zhang" + }, + { + "first_name": "An-An", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Training Generative Image Super-Resolution Models by Wavelet-Domain Losses Enables Better Control of Artifacts", - "authors": "Cansu Korkmaz, A. Murat Tekalp, Zafer Dogan", + "authors": [ + { + "first_name": "Cansu", + "last_name": "Korkmaz" + }, + { + "first_name": "A.", + "last_name": "Murat Tekalp" + }, + { + "first_name": "Zafer", + "last_name": "Dogan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Visual Objectification in Films: Towards a New AI Task for Video Interpretation", - "authors": "Julie Tores, Lucile Sassatelli, Hui-Yin Wu, Clement Bergman, Léa Andolfi, Victor Ecrement, Frédéric Precioso, Thierry Devars, Magali Guaresi, Virginie Julliard, Sarah Lecossais", + "authors": [ + { + "first_name": "Julie", + "last_name": "Tores" + }, + { + "first_name": "Lucile", + "last_name": "Sassatelli" + }, + { + "first_name": "Hui-Yin", + "last_name": "Wu" + }, + { + "first_name": "Clement", + "last_name": "Bergman" + }, + { + "first_name": "Léa", + "last_name": "Andolfi" + }, + { + "first_name": "Victor", + "last_name": "Ecrement" + }, + { + "first_name": "Frédéric", + "last_name": "Precioso" + }, + { + "first_name": "Thierry", + "last_name": "Devars" + }, + { + "first_name": "Magali", + "last_name": "Guaresi" + }, + { + "first_name": "Virginie", + "last_name": "Julliard" + }, + { + "first_name": "Sarah", + "last_name": "Lecossais" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "OMG-Seg: Is One Model Good Enough For All Segmentation?", - "authors": "Xiangtai Li, Haobo Yuan, Wei Li, Henghui Ding, Size Wu, Wenwei Zhang, Yining Li, Kai Chen, Chen Change Loy", + "authors": [ + { + "first_name": "Xiangtai", + "last_name": "Li" + }, + { + "first_name": "Haobo", + "last_name": "Yuan" + }, + { + "first_name": "Wei", + "last_name": "Li" + }, + { + "first_name": "Henghui", + "last_name": "Ding" + }, + { + "first_name": "Size", + "last_name": "Wu" + }, + { + "first_name": "Wenwei", + "last_name": "Zhang" + }, + { + "first_name": "Yining", + "last_name": "Li" + }, + { + "first_name": "Kai", + "last_name": "Chen" + }, + { + "first_name": "Chen", + "last_name": "Change Loy" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "BiTT: Bi-directional Texture Reconstruction of Interacting Two Hands from a Single Image", - "authors": "Minje Kim, Tae-Kyun Kim", + "authors": [ + { + "first_name": "Minje", + "last_name": "Kim" + }, + { + "first_name": "Tae-Kyun", + "last_name": "Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DetCLIPv3: Towards Versatile Generative Open-vocabulary Object Detection", - "authors": "Lewei Yao, Renjie Pi, Jianhua Han, Xiaodan Liang, Hang Xu, Wei Zhang, Zhenguo Li, Dan Xu", + "authors": [ + { + "first_name": "Lewei", + "last_name": "Yao" + }, + { + "first_name": "Renjie", + "last_name": "Pi" + }, + { + "first_name": "Jianhua", + "last_name": "Han" + }, + { + "first_name": "Xiaodan", + "last_name": "Liang" + }, + { + "first_name": "Hang", + "last_name": "Xu" + }, + { + "first_name": "Wei", + "last_name": "Zhang" + }, + { + "first_name": "Zhenguo", + "last_name": "Li" + }, + { + "first_name": "Dan", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "UVEB: A Large-scale Benchmark and Baseline Towards Real-World Underwater Video Enhancement", - "authors": "Yaofeng Xie, Lingwei Kong, Kai Chen, Ziqiang Zheng, Xiao Yu, Zhibin Yu, Bing Zheng", + "authors": [ + { + "first_name": "Yaofeng", + "last_name": "Xie" + }, + { + "first_name": "Lingwei", + "last_name": "Kong" + }, + { + "first_name": "Kai", + "last_name": "Chen" + }, + { + "first_name": "Ziqiang", + "last_name": "Zheng" + }, + { + "first_name": "Xiao", + "last_name": "Yu" + }, + { + "first_name": "Zhibin", + "last_name": "Yu" + }, + { + "first_name": "Bing", + "last_name": "Zheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs", - "authors": "Kanchana Ranasinghe, Satya Narayan Shukla, Omid Poursaeed, Michael S. Ryoo, Tsung-Yu Lin", + "authors": [ + { + "first_name": "Kanchana", + "last_name": "Ranasinghe" + }, + { + "first_name": "Satya", + "last_name": "Narayan Shukla" + }, + { + "first_name": "Omid", + "last_name": "Poursaeed" + }, + { + "first_name": "Michael", + "last_name": "S. Ryoo" + }, + { + "first_name": "Tsung-Yu", + "last_name": "Lin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Monocular Identity-Conditioned Facial Reflectance Reconstruction", - "authors": "Xingyu Ren, Jiankang Deng, Yuhao Cheng, Jia Guo, Chao Ma, Yichao Yan, Wenhan Zhu, Xiaokang Yang", + "authors": [ + { + "first_name": "Xingyu", + "last_name": "Ren" + }, + { + "first_name": "Jiankang", + "last_name": "Deng" + }, + { + "first_name": "Yuhao", + "last_name": "Cheng" + }, + { + "first_name": "Jia", + "last_name": "Guo" + }, + { + "first_name": "Chao", + "last_name": "Ma" + }, + { + "first_name": "Yichao", + "last_name": "Yan" + }, + { + "first_name": "Wenhan", + "last_name": "Zhu" + }, + { + "first_name": "Xiaokang", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "C3: High-Performance and Low-Complexity Neural Compression from a Single Image or Video", - "authors": "Hyunjik Kim, Matthias Bauer, Lucas Theis, Jonathan Richard Schwarz, Emilien Dupont", + "authors": [ + { + "first_name": "Hyunjik", + "last_name": "Kim" + }, + { + "first_name": "Matthias", + "last_name": "Bauer" + }, + { + "first_name": "Lucas", + "last_name": "Theis" + }, + { + "first_name": "Jonathan", + "last_name": "Richard Schwarz" + }, + { + "first_name": "Emilien", + "last_name": "Dupont" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectors", - "authors": "Nicolae-C?t?lin Ristea, Florinel-Alin Croitoru, Radu Tudor Ionescu, Marius Popescu, Fahad Shahbaz Khan, Mubarak Shah", + "authors": [ + { + "first_name": "Nicolae-C?t?lin", + "last_name": "Ristea" + }, + { + "first_name": "Florinel-Alin", + "last_name": "Croitoru" + }, + { + "first_name": "Radu", + "last_name": "Tudor Ionescu" + }, + { + "first_name": "Marius", + "last_name": "Popescu" + }, + { + "first_name": "Fahad", + "last_name": "Shahbaz Khan" + }, + { + "first_name": "Mubarak", + "last_name": "Shah" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Revisiting Non-Autoregressive Transformers for Efficient Image Synthesis", - "authors": "Zanlin Ni, Yulin Wang, Renping Zhou, Jiayi Guo, Jinyi Hu, Zhiyuan Liu, Shiji Song, Yuan Yao, Gao Huang", + "authors": [ + { + "first_name": "Zanlin", + "last_name": "Ni" + }, + { + "first_name": "Yulin", + "last_name": "Wang" + }, + { + "first_name": "Renping", + "last_name": "Zhou" + }, + { + "first_name": "Jiayi", + "last_name": "Guo" + }, + { + "first_name": "Jinyi", + "last_name": "Hu" + }, + { + "first_name": "Zhiyuan", + "last_name": "Liu" + }, + { + "first_name": "Shiji", + "last_name": "Song" + }, + { + "first_name": "Yuan", + "last_name": "Yao" + }, + { + "first_name": "Gao", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Distilling Vision-Language Models on Millions of Videos", - "authors": "Yue Zhao, Long Zhao, Xingyi Zhou, Jialin Wu, Chun-Te Chu, Hui Miao, Florian Schroff, Hartwig Adam, Ting Liu, Boqing Gong, Philipp Krahenbuhl, Liangzhe Yuan", + "authors": [ + { + "first_name": "Yue", + "last_name": "Zhao" + }, + { + "first_name": "Long", + "last_name": "Zhao" + }, + { + "first_name": "Xingyi", + "last_name": "Zhou" + }, + { + "first_name": "Jialin", + "last_name": "Wu" + }, + { + "first_name": "Chun-Te", + "last_name": "Chu" + }, + { + "first_name": "Hui", + "last_name": "Miao" + }, + { + "first_name": "Florian", + "last_name": "Schroff" + }, + { + "first_name": "Hartwig", + "last_name": "Adam" + }, + { + "first_name": "Ting", + "last_name": "Liu" + }, + { + "first_name": "Boqing", + "last_name": "Gong" + }, + { + "first_name": "Philipp", + "last_name": "Krahenbuhl" + }, + { + "first_name": "Liangzhe", + "last_name": "Yuan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ANIM: Accurate Neural Implicit Model for Human Reconstruction from a single RGB-D Image", - "authors": "Marco Pesavento, Yuanlu Xu, Nikolaos Sarafianos, Robert Maier, Ziyan Wang, Chun-Han Yao, Marco Volino, Edmond Boyer, Adrian Hilton, Tony Tung", + "authors": [ + { + "first_name": "Marco", + "last_name": "Pesavento" + }, + { + "first_name": "Yuanlu", + "last_name": "Xu" + }, + { + "first_name": "Nikolaos", + "last_name": "Sarafianos" + }, + { + "first_name": "Robert", + "last_name": "Maier" + }, + { + "first_name": "Ziyan", + "last_name": "Wang" + }, + { + "first_name": "Chun-Han", + "last_name": "Yao" + }, + { + "first_name": "Marco", + "last_name": "Volino" + }, + { + "first_name": "Edmond", + "last_name": "Boyer" + }, + { + "first_name": "Adrian", + "last_name": "Hilton" + }, + { + "first_name": "Tony", + "last_name": "Tung" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Real-Time Simulated Avatar from Head-Mounted Sensors", - "authors": "Zhengyi Luo, Jinkun Cao, Rawal Khirodkar, Alexander Winkler, Kris Kitani, Weipeng Xu", + "authors": [ + { + "first_name": "Zhengyi", + "last_name": "Luo" + }, + { + "first_name": "Jinkun", + "last_name": "Cao" + }, + { + "first_name": "Rawal", + "last_name": "Khirodkar" + }, + { + "first_name": "Alexander", + "last_name": "Winkler" + }, + { + "first_name": "Kris", + "last_name": "Kitani" + }, + { + "first_name": "Weipeng", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Discovering Syntactic Interaction Clues for Human-Object Interaction Detection", - "authors": "Jinguo Luo, Weihong Ren, Weibo Jiang, Xi'ai Chen, Qiang Wang, Zhi Han, Honghai Liu", + "authors": [ + { + "first_name": "Jinguo", + "last_name": "Luo" + }, + { + "first_name": "Weihong", + "last_name": "Ren" + }, + { + "first_name": "Weibo", + "last_name": "Jiang" + }, + { + "first_name": "Xi'ai", + "last_name": "Chen" + }, + { + "first_name": "Qiang", + "last_name": "Wang" + }, + { + "first_name": "Zhi", + "last_name": "Han" + }, + { + "first_name": "Honghai", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Inter-X: Towards Versatile Human-Human Interaction Analysis", - "authors": "Liang Xu, Xintao Lv, Yichao Yan, Xin Jin, Shuwen Wu, Congsheng Xu, Yifan Liu, Yizhou Zhou, Fengyun Rao, Xingdong Sheng, Yunhui Liu, Wenjun Zeng, Xiaokang Yang", + "authors": [ + { + "first_name": "Liang", + "last_name": "Xu" + }, + { + "first_name": "Xintao", + "last_name": "Lv" + }, + { + "first_name": "Yichao", + "last_name": "Yan" + }, + { + "first_name": "Xin", + "last_name": "Jin" + }, + { + "first_name": "Shuwen", + "last_name": "Wu" + }, + { + "first_name": "Congsheng", + "last_name": "Xu" + }, + { + "first_name": "Yifan", + "last_name": "Liu" + }, + { + "first_name": "Yizhou", + "last_name": "Zhou" + }, + { + "first_name": "Fengyun", + "last_name": "Rao" + }, + { + "first_name": "Xingdong", + "last_name": "Sheng" + }, + { + "first_name": "Yunhui", + "last_name": "Liu" + }, + { + "first_name": "Wenjun", + "last_name": "Zeng" + }, + { + "first_name": "Xiaokang", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Generalized Predictive Model for Autonomous Driving", - "authors": "Jiazhi Yang, Shenyuan Gao, Yihang Qiu, Li Chen, Tianyu Li, Bo Dai, Kashyap Chitta, Penghao Wu, Jia Zeng, Ping Luo, Jun Zhang, Andreas Geiger, Yu Qiao, Hongyang Li", + "authors": [ + { + "first_name": "Jiazhi", + "last_name": "Yang" + }, + { + "first_name": "Shenyuan", + "last_name": "Gao" + }, + { + "first_name": "Yihang", + "last_name": "Qiu" + }, + { + "first_name": "Li", + "last_name": "Chen" + }, + { + "first_name": "Tianyu", + "last_name": "Li" + }, + { + "first_name": "Bo", + "last_name": "Dai" + }, + { + "first_name": "Kashyap", + "last_name": "Chitta" + }, + { + "first_name": "Penghao", + "last_name": "Wu" + }, + { + "first_name": "Jia", + "last_name": "Zeng" + }, + { + "first_name": "Ping", + "last_name": "Luo" + }, + { + "first_name": "Jun", + "last_name": "Zhang" + }, + { + "first_name": "Andreas", + "last_name": "Geiger" + }, + { + "first_name": "Yu", + "last_name": "Qiao" + }, + { + "first_name": "Hongyang", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FACT: Frame-Action Cross-Attention Temporal Modeling for Efficient Action Segmentation", - "authors": "Zijia Lu, Ehsan Elhamifar", + "authors": [ + { + "first_name": "Zijia", + "last_name": "Lu" + }, + { + "first_name": "Ehsan", + "last_name": "Elhamifar" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Test-Time Zero-Shot Temporal Action Localization", - "authors": "Benedetta Liberatori, Alessandro Conti, Paolo Rota, Yiming Wang, Elisa Ricci", + "authors": [ + { + "first_name": "Benedetta", + "last_name": "Liberatori" + }, + { + "first_name": "Alessandro", + "last_name": "Conti" + }, + { + "first_name": "Paolo", + "last_name": "Rota" + }, + { + "first_name": "Yiming", + "last_name": "Wang" + }, + { + "first_name": "Elisa", + "last_name": "Ricci" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "AM-RADIO: Agglomerative Vision Foundation Model Reduce All Domains Into One", - "authors": "Mike Ranzinger, Greg Heinrich, Jan Kautz, Pavlo Molchanov", + "authors": [ + { + "first_name": "Mike", + "last_name": "Ranzinger" + }, + { + "first_name": "Greg", + "last_name": "Heinrich" + }, + { + "first_name": "Jan", + "last_name": "Kautz" + }, + { + "first_name": "Pavlo", + "last_name": "Molchanov" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MaskClustering: View Consensus based Mask Graph Clustering for Open-Vocabulary 3D Instance Segmentation", - "authors": "Mi Yan, Jiazhao Zhang, Yan Zhu, He Wang", + "authors": [ + { + "first_name": "Mi", + "last_name": "Yan" + }, + { + "first_name": "Jiazhao", + "last_name": "Zhang" + }, + { + "first_name": "Yan", + "last_name": "Zhu" + }, + { + "first_name": "He", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Seamless Human Motion Composition with Blended Positional Encodings", - "authors": "German Barquero, Sergio Escalera, Cristina Palmero", + "authors": [ + { + "first_name": "German", + "last_name": "Barquero" + }, + { + "first_name": "Sergio", + "last_name": "Escalera" + }, + { + "first_name": "Cristina", + "last_name": "Palmero" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PeerAiD: Improving Adversarial Distillation from a Specialized Peer Tutor", - "authors": "Jaewon Jung, Hongsun Jang, Jaeyong Song, Jinho Lee", + "authors": [ + { + "first_name": "Jaewon", + "last_name": "Jung" + }, + { + "first_name": "Hongsun", + "last_name": "Jang" + }, + { + "first_name": "Jaeyong", + "last_name": "Song" + }, + { + "first_name": "Jinho", + "last_name": "Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Scaling Laws for Data Filtering-- Data Curation cannot be Compute Agnostic", - "authors": "Sachin Goyal, Pratyush Maini, Zachary C. Lipton, Aditi Raghunathan, J. Zico Kolter", + "authors": [ + { + "first_name": "Sachin", + "last_name": "Goyal" + }, + { + "first_name": "Pratyush", + "last_name": "Maini" + }, + { + "first_name": "Zachary", + "last_name": "C. Lipton" + }, + { + "first_name": "Aditi", + "last_name": "Raghunathan" + }, + { + "first_name": "J.", + "last_name": "Zico Kolter" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FastMAC: Stochastic Spectral Sampling of Correspondence Graph", - "authors": "Yifei Zhang, Hao Zhao, Hongyang Li, Siheng Chen", + "authors": [ + { + "first_name": "Yifei", + "last_name": "Zhang" + }, + { + "first_name": "Hao", + "last_name": "Zhao" + }, + { + "first_name": "Hongyang", + "last_name": "Li" + }, + { + "first_name": "Siheng", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FedUV: Uniformity and Variance for Heterogeneous Federated Learning", - "authors": "Ha Min Son, Moon-Hyun Kim, Tai-Myoung Chung, Chao Huang, Xin Liu", + "authors": [ + { + "first_name": "Ha", + "last_name": "Min Son" + }, + { + "first_name": "Moon-Hyun", + "last_name": "Kim" + }, + { + "first_name": "Tai-Myoung", + "last_name": "Chung" + }, + { + "first_name": "Chao", + "last_name": "Huang" + }, + { + "first_name": "Xin", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FedSOL: Stabilized Orthogonal Learning with Proximal Restrictions in Federated Learning", - "authors": "Gihun Lee, Minchan Jeong, Sangmook Kim, Jaehoon Oh, Se-Young Yun", + "authors": [ + { + "first_name": "Gihun", + "last_name": "Lee" + }, + { + "first_name": "Minchan", + "last_name": "Jeong" + }, + { + "first_name": "Sangmook", + "last_name": "Kim" + }, + { + "first_name": "Jaehoon", + "last_name": "Oh" + }, + { + "first_name": "Se-Young", + "last_name": "Yun" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learning", - "authors": "Ye Yuan, Xueting Li, Yangyi Huang, Shalini De Mello, Koki Nagano, Jan Kautz, Umar Iqbal", + "authors": [ + { + "first_name": "Ye", + "last_name": "Yuan" + }, + { + "first_name": "Xueting", + "last_name": "Li" + }, + { + "first_name": "Yangyi", + "last_name": "Huang" + }, + { + "first_name": "Shalini", + "last_name": "De Mello" + }, + { + "first_name": "Koki", + "last_name": "Nagano" + }, + { + "first_name": "Jan", + "last_name": "Kautz" + }, + { + "first_name": "Umar", + "last_name": "Iqbal" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Beyond Average: Individualized Visual Scanpath Prediction", - "authors": "Xianyu Chen, Ming Jiang, Qi Zhao", + "authors": [ + { + "first_name": "Xianyu", + "last_name": "Chen" + }, + { + "first_name": "Ming", + "last_name": "Jiang" + }, + { + "first_name": "Qi", + "last_name": "Zhao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "A Category Agnostic Model for Visual Rearrangment", - "authors": "Yuyi Liu, Xinhang Song, Weijie Li, Xiaohan Wang, Shuqiang Jiang", + "authors": [ + { + "first_name": "Yuyi", + "last_name": "Liu" + }, + { + "first_name": "Xinhang", + "last_name": "Song" + }, + { + "first_name": "Weijie", + "last_name": "Li" + }, + { + "first_name": "Xiaohan", + "last_name": "Wang" + }, + { + "first_name": "Shuqiang", + "last_name": "Jiang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Grounding Everything: Emerging Localization Properties in Vision-Language Transformers", - "authors": "Walid Bousselham, Felix Petersen, Vittorio Ferrari, Hilde Kuehne", + "authors": [ + { + "first_name": "Walid", + "last_name": "Bousselham" + }, + { + "first_name": "Felix", + "last_name": "Petersen" + }, + { + "first_name": "Vittorio", + "last_name": "Ferrari" + }, + { + "first_name": "Hilde", + "last_name": "Kuehne" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Seeing Motion at Nighttime with an Event Camera", - "authors": "Haoyue Liu, Shihan Peng, Lin Zhu, Yi Chang, Hanyu Zhou, Luxin Yan", + "authors": [ + { + "first_name": "Haoyue", + "last_name": "Liu" + }, + { + "first_name": "Shihan", + "last_name": "Peng" + }, + { + "first_name": "Lin", + "last_name": "Zhu" + }, + { + "first_name": "Yi", + "last_name": "Chang" + }, + { + "first_name": "Hanyu", + "last_name": "Zhou" + }, + { + "first_name": "Luxin", + "last_name": "Yan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Representing Part-Whole Hierarchies in Foundation Models by Learning Localizability Composability and Decomposability from Anatomy via Self Supervision", - "authors": "Mohammad Reza Hosseinzadeh Taher, Michael B. Gotway, Jianming Liang", + "authors": [ + { + "first_name": "Mohammad", + "last_name": "Reza Hosseinzadeh Taher" + }, + { + "first_name": "Michael", + "last_name": "B. Gotway" + }, + { + "first_name": "Jianming", + "last_name": "Liang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Efficient Test-Time Adaptation of Vision-Language Models", - "authors": "Adilbek Karmanov, Dayan Guan, Shijian Lu, Abdulmotaleb El Saddik, Eric Xing", + "authors": [ + { + "first_name": "Adilbek", + "last_name": "Karmanov" + }, + { + "first_name": "Dayan", + "last_name": "Guan" + }, + { + "first_name": "Shijian", + "last_name": "Lu" + }, + { + "first_name": "Abdulmotaleb", + "last_name": "El Saddik" + }, + { + "first_name": "Eric", + "last_name": "Xing" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs", - "authors": "Shengbang Tong, Zhuang Liu, Yuexiang Zhai, Yi Ma, Yann LeCun, Saining Xie", + "authors": [ + { + "first_name": "Shengbang", + "last_name": "Tong" + }, + { + "first_name": "Zhuang", + "last_name": "Liu" + }, + { + "first_name": "Yuexiang", + "last_name": "Zhai" + }, + { + "first_name": "Yi", + "last_name": "Ma" + }, + { + "first_name": "Yann", + "last_name": "LeCun" + }, + { + "first_name": "Saining", + "last_name": "Xie" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Mean-Shift Feature Transformer", - "authors": "Takumi Kobayashi", + "authors": [ + { + "first_name": "Takumi", + "last_name": "Kobayashi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Domain Separation Graph Neural Networks for Saliency Object Ranking", - "authors": "Zijian Wu, Jun Lu, Jing Han, Lianfa Bai, Yi Zhang, Zhuang Zhao, Siyang Song", + "authors": [ + { + "first_name": "Zijian", + "last_name": "Wu" + }, + { + "first_name": "Jun", + "last_name": "Lu" + }, + { + "first_name": "Jing", + "last_name": "Han" + }, + { + "first_name": "Lianfa", + "last_name": "Bai" + }, + { + "first_name": "Yi", + "last_name": "Zhang" + }, + { + "first_name": "Zhuang", + "last_name": "Zhao" + }, + { + "first_name": "Siyang", + "last_name": "Song" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Mind Marginal Non-Crack Regions: Clustering-Inspired Representation Learning for Crack Segmentation", - "authors": "Zhuangzhuang Chen, Zhuonan Lai, Jie Chen, Jianqiang Li", + "authors": [ + { + "first_name": "Zhuangzhuang", + "last_name": "Chen" + }, + { + "first_name": "Zhuonan", + "last_name": "Lai" + }, + { + "first_name": "Jie", + "last_name": "Chen" + }, + { + "first_name": "Jianqiang", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FISBe: A Real-World Benchmark Dataset for Instance Segmentation of Long-Range Thin Filamentous Structures", - "authors": "Lisa Mais, Peter Hirsch, Claire Managan, Ramya Kandarpa, Josef Lorenz Rumberger, Annika Reinke, Lena Maier-Hein, Gudrun Ihrke, Dagmar Kainmueller", + "authors": [ + { + "first_name": "Lisa", + "last_name": "Mais" + }, + { + "first_name": "Peter", + "last_name": "Hirsch" + }, + { + "first_name": "Claire", + "last_name": "Managan" + }, + { + "first_name": "Ramya", + "last_name": "Kandarpa" + }, + { + "first_name": "Josef", + "last_name": "Lorenz Rumberger" + }, + { + "first_name": "Annika", + "last_name": "Reinke" + }, + { + "first_name": "Lena", + "last_name": "Maier-Hein" + }, + { + "first_name": "Gudrun", + "last_name": "Ihrke" + }, + { + "first_name": "Dagmar", + "last_name": "Kainmueller" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "RegionGPT: Towards Region Understanding Vision Language Model", - "authors": "Qiushan Guo, Shalini De Mello, Hongxu Yin, Wonmin Byeon, Ka Chun Cheung, Yizhou Yu, Ping Luo, Sifei Liu", + "authors": [ + { + "first_name": "Qiushan", + "last_name": "Guo" + }, + { + "first_name": "Shalini", + "last_name": "De Mello" + }, + { + "first_name": "Hongxu", + "last_name": "Yin" + }, + { + "first_name": "Wonmin", + "last_name": "Byeon" + }, + { + "first_name": "Ka", + "last_name": "Chun Cheung" + }, + { + "first_name": "Yizhou", + "last_name": "Yu" + }, + { + "first_name": "Ping", + "last_name": "Luo" + }, + { + "first_name": "Sifei", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding Reasoning and Planning", - "authors": "Sijin Chen, Xin Chen, Chi Zhang, Mingsheng Li, Gang Yu, Hao Fei, Hongyuan Zhu, Jiayuan Fan, Tao Chen", + "authors": [ + { + "first_name": "Sijin", + "last_name": "Chen" + }, + { + "first_name": "Xin", + "last_name": "Chen" + }, + { + "first_name": "Chi", + "last_name": "Zhang" + }, + { + "first_name": "Mingsheng", + "last_name": "Li" + }, + { + "first_name": "Gang", + "last_name": "Yu" + }, + { + "first_name": "Hao", + "last_name": "Fei" + }, + { + "first_name": "Hongyuan", + "last_name": "Zhu" + }, + { + "first_name": "Jiayuan", + "last_name": "Fan" + }, + { + "first_name": "Tao", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "4D Gaussian Splatting for Real-Time Dynamic Scene Rendering", - "authors": "Guanjun Wu, Taoran Yi, Jiemin Fang, Lingxi Xie, Xiaopeng Zhang, Wei Wei, Wenyu Liu, Qi Tian, Xinggang Wang", + "authors": [ + { + "first_name": "Guanjun", + "last_name": "Wu" + }, + { + "first_name": "Taoran", + "last_name": "Yi" + }, + { + "first_name": "Jiemin", + "last_name": "Fang" + }, + { + "first_name": "Lingxi", + "last_name": "Xie" + }, + { + "first_name": "Xiaopeng", + "last_name": "Zhang" + }, + { + "first_name": "Wei", + "last_name": "Wei" + }, + { + "first_name": "Wenyu", + "last_name": "Liu" + }, + { + "first_name": "Qi", + "last_name": "Tian" + }, + { + "first_name": "Xinggang", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "RAM-Avatar: Real-time Photo-Realistic Avatar from Monocular Videos with Full-body Control", - "authors": "Xiang Deng, Zerong Zheng, Yuxiang Zhang, Jingxiang Sun, Chao Xu, Xiaodong Yang, Lizhen Wang, Yebin Liu", + "authors": [ + { + "first_name": "Xiang", + "last_name": "Deng" + }, + { + "first_name": "Zerong", + "last_name": "Zheng" + }, + { + "first_name": "Yuxiang", + "last_name": "Zhang" + }, + { + "first_name": "Jingxiang", + "last_name": "Sun" + }, + { + "first_name": "Chao", + "last_name": "Xu" + }, + { + "first_name": "Xiaodong", + "last_name": "Yang" + }, + { + "first_name": "Lizhen", + "last_name": "Wang" + }, + { + "first_name": "Yebin", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matching", - "authors": "Xianqi Wang, Gangwei Xu, Hao Jia, Xin Yang", + "authors": [ + { + "first_name": "Xianqi", + "last_name": "Wang" + }, + { + "first_name": "Gangwei", + "last_name": "Xu" + }, + { + "first_name": "Hao", + "last_name": "Jia" + }, + { + "first_name": "Xin", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees", - "authors": "Chulin Xie, De-An Huang, Wenda Chu, Daguang Xu, Chaowei Xiao, Bo Li, Anima Anandkumar", + "authors": [ + { + "first_name": "Chulin", + "last_name": "Xie" + }, + { + "first_name": "De-An", + "last_name": "Huang" + }, + { + "first_name": "Wenda", + "last_name": "Chu" + }, + { + "first_name": "Daguang", + "last_name": "Xu" + }, + { + "first_name": "Chaowei", + "last_name": "Xiao" + }, + { + "first_name": "Bo", + "last_name": "Li" + }, + { + "first_name": "Anima", + "last_name": "Anandkumar" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MAFA: Managing False Negatives for Vision-Language Pre-training", - "authors": "Jaeseok Byun, Dohoon Kim, Taesup Moon", + "authors": [ + { + "first_name": "Jaeseok", + "last_name": "Byun" + }, + { + "first_name": "Dohoon", + "last_name": "Kim" + }, + { + "first_name": "Taesup", + "last_name": "Moon" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Video Prediction by Modeling Videos as Continuous Multi-Dimensional Processes", - "authors": "Gaurav Shrivastava, Abhinav Shrivastava", + "authors": [ + { + "first_name": "Gaurav", + "last_name": "Shrivastava" + }, + { + "first_name": "Abhinav", + "last_name": "Shrivastava" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PICTURE: PhotorealistIC virtual Try-on from UnconstRained dEsigns", - "authors": "Shuliang Ning, Duomin Wang, Yipeng Qin, Zirong Jin, Baoyuan Wang, Xiaoguang Han", + "authors": [ + { + "first_name": "Shuliang", + "last_name": "Ning" + }, + { + "first_name": "Duomin", + "last_name": "Wang" + }, + { + "first_name": "Yipeng", + "last_name": "Qin" + }, + { + "first_name": "Zirong", + "last_name": "Jin" + }, + { + "first_name": "Baoyuan", + "last_name": "Wang" + }, + { + "first_name": "Xiaoguang", + "last_name": "Han" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learning", - "authors": "Yan-Shuo Liang, Wu-Jun Li", + "authors": [ + { + "first_name": "Yan-Shuo", + "last_name": "Liang" + }, + { + "first_name": "Wu-Jun", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards Robust 3D Pose Transfer with Adversarial Learning", - "authors": "Haoyu Chen, Hao Tang, Ehsan Adeli, Guoying Zhao", + "authors": [ + { + "first_name": "Haoyu", + "last_name": "Chen" + }, + { + "first_name": "Hao", + "last_name": "Tang" + }, + { + "first_name": "Ehsan", + "last_name": "Adeli" + }, + { + "first_name": "Guoying", + "last_name": "Zhao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Error Detection in Egocentric Procedural Task Videos", - "authors": "Shih-Po Lee, Zijia Lu, Zekun Zhang, Minh Hoai, Ehsan Elhamifar", + "authors": [ + { + "first_name": "Shih-Po", + "last_name": "Lee" + }, + { + "first_name": "Zijia", + "last_name": "Lu" + }, + { + "first_name": "Zekun", + "last_name": "Zhang" + }, + { + "first_name": "Minh", + "last_name": "Hoai" + }, + { + "first_name": "Ehsan", + "last_name": "Elhamifar" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "EAGLE: Eigen Aggregation Learning for Object-Centric Unsupervised Semantic Segmentation", - "authors": "Chanyoung Kim, Woojung Han, Dayun Ju, Seong Jae Hwang", + "authors": [ + { + "first_name": "Chanyoung", + "last_name": "Kim" + }, + { + "first_name": "Woojung", + "last_name": "Han" + }, + { + "first_name": "Dayun", + "last_name": "Ju" + }, + { + "first_name": "Seong", + "last_name": "Jae Hwang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "AVID: Any-Length Video Inpainting with Diffusion Model", - "authors": "Zhixing Zhang, Bichen Wu, Xiaoyan Wang, Yaqiao Luo, Luxin Zhang, Yinan Zhao, Peter Vajda, Dimitris Metaxas, Licheng Yu", + "authors": [ + { + "first_name": "Zhixing", + "last_name": "Zhang" + }, + { + "first_name": "Bichen", + "last_name": "Wu" + }, + { + "first_name": "Xiaoyan", + "last_name": "Wang" + }, + { + "first_name": "Yaqiao", + "last_name": "Luo" + }, + { + "first_name": "Luxin", + "last_name": "Zhang" + }, + { + "first_name": "Yinan", + "last_name": "Zhao" + }, + { + "first_name": "Peter", + "last_name": "Vajda" + }, + { + "first_name": "Dimitris", + "last_name": "Metaxas" + }, + { + "first_name": "Licheng", + "last_name": "Yu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "NoiseCollage: A Layout-Aware Text-to-Image Diffusion Model Based on Noise Cropping and Merging", - "authors": "Takahiro Shirakawa, Seiichi Uchida", + "authors": [ + { + "first_name": "Takahiro", + "last_name": "Shirakawa" + }, + { + "first_name": "Seiichi", + "last_name": "Uchida" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Uncertainty-Guided Never-Ending Learning to Drive", - "authors": "Lei Lai, Eshed Ohn-Bar, Sanjay Arora, John Seon Keun Yi", + "authors": [ + { + "first_name": "Lei", + "last_name": "Lai" + }, + { + "first_name": "Eshed", + "last_name": "Ohn-Bar" + }, + { + "first_name": "Sanjay", + "last_name": "Arora" + }, + { + "first_name": "John", + "last_name": "Seon Keun Yi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FakeInversion: Learning to Detect Images from Unseen Text-to-Image Models by Inverting Stable Diffusion", - "authors": "George Cazenavette, Avneesh Sud, Thomas Leung, Ben Usman", + "authors": [ + { + "first_name": "George", + "last_name": "Cazenavette" + }, + { + "first_name": "Avneesh", + "last_name": "Sud" + }, + { + "first_name": "Thomas", + "last_name": "Leung" + }, + { + "first_name": "Ben", + "last_name": "Usman" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PLGSLAM: Progressive Neural Scene Represenation with Local to Global Bundle Adjustment", - "authors": "Tianchen Deng, Guole Shen, Tong Qin, Jianyu Wang, Wentao Zhao, Jingchuan Wang, Danwei Wang, Weidong Chen", + "authors": [ + { + "first_name": "Tianchen", + "last_name": "Deng" + }, + { + "first_name": "Guole", + "last_name": "Shen" + }, + { + "first_name": "Tong", + "last_name": "Qin" + }, + { + "first_name": "Jianyu", + "last_name": "Wang" + }, + { + "first_name": "Wentao", + "last_name": "Zhao" + }, + { + "first_name": "Jingchuan", + "last_name": "Wang" + }, + { + "first_name": "Danwei", + "last_name": "Wang" + }, + { + "first_name": "Weidong", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Multi-Task Dense Prediction via Mixture of Low-Rank Experts", - "authors": "Yuqi Yang, Peng-Tao Jiang, Qibin Hou, Hao Zhang, Jinwei Chen, Bo Li", + "authors": [ + { + "first_name": "Yuqi", + "last_name": "Yang" + }, + { + "first_name": "Peng-Tao", + "last_name": "Jiang" + }, + { + "first_name": "Qibin", + "last_name": "Hou" + }, + { + "first_name": "Hao", + "last_name": "Zhang" + }, + { + "first_name": "Jinwei", + "last_name": "Chen" + }, + { + "first_name": "Bo", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Binding Touch to Everything: Learning Unified Multimodal Tactile Representations", - "authors": "Fengyu Yang, Chao Feng, Ziyang Chen, Hyoungseob Park, Daniel Wang, Yiming Dou, Ziyao Zeng, Xien Chen, Rit Gangopadhyay, Andrew Owens, Alex Wong", + "authors": [ + { + "first_name": "Fengyu", + "last_name": "Yang" + }, + { + "first_name": "Chao", + "last_name": "Feng" + }, + { + "first_name": "Ziyang", + "last_name": "Chen" + }, + { + "first_name": "Hyoungseob", + "last_name": "Park" + }, + { + "first_name": "Daniel", + "last_name": "Wang" + }, + { + "first_name": "Yiming", + "last_name": "Dou" + }, + { + "first_name": "Ziyao", + "last_name": "Zeng" + }, + { + "first_name": "Xien", + "last_name": "Chen" + }, + { + "first_name": "Rit", + "last_name": "Gangopadhyay" + }, + { + "first_name": "Andrew", + "last_name": "Owens" + }, + { + "first_name": "Alex", + "last_name": "Wong" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Attribute-Guided Pedestrian Retrieval: Bridging Person Re-ID with Internal Attribute Variability", - "authors": "Yan Huang, Zhang Zhang, Qiang Wu, Yi Zhong, Liang Wang", + "authors": [ + { + "first_name": "Yan", + "last_name": "Huang" + }, + { + "first_name": "Zhang", + "last_name": "Zhang" + }, + { + "first_name": "Qiang", + "last_name": "Wu" + }, + { + "first_name": "Yi", + "last_name": "Zhong" + }, + { + "first_name": "Liang", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Text Is MASS: Modeling as Stochastic Embedding for Text-Video Retrieval", - "authors": "Jiamian Wang, Guohao Sun, Pichao Wang, Dongfang Liu, Sohail Dianat, Majid Rabbani, Raghuveer Rao, Zhiqiang Tao", + "authors": [ + { + "first_name": "Jiamian", + "last_name": "Wang" + }, + { + "first_name": "Guohao", + "last_name": "Sun" + }, + { + "first_name": "Pichao", + "last_name": "Wang" + }, + { + "first_name": "Dongfang", + "last_name": "Liu" + }, + { + "first_name": "Sohail", + "last_name": "Dianat" + }, + { + "first_name": "Majid", + "last_name": "Rabbani" + }, + { + "first_name": "Raghuveer", + "last_name": "Rao" + }, + { + "first_name": "Zhiqiang", + "last_name": "Tao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Your Transferability Barrier is Fragile: Free-Lunch for Transferring the Non-Transferable Learning", - "authors": "Ziming Hong, Li Shen, Tongliang Liu", + "authors": [ + { + "first_name": "Ziming", + "last_name": "Hong" + }, + { + "first_name": "Li", + "last_name": "Shen" + }, + { + "first_name": "Tongliang", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Arbitrary Motion Style Transfer with Multi-condition Motion Latent Diffusion Model", - "authors": "Wenfeng Song, Xingliang Jin, Shuai Li, Chenglizhao Chen, Aimin Hao, Xia Hou, Ning Li, Hong Qin", + "authors": [ + { + "first_name": "Wenfeng", + "last_name": "Song" + }, + { + "first_name": "Xingliang", + "last_name": "Jin" + }, + { + "first_name": "Shuai", + "last_name": "Li" + }, + { + "first_name": "Chenglizhao", + "last_name": "Chen" + }, + { + "first_name": "Aimin", + "last_name": "Hao" + }, + { + "first_name": "Xia", + "last_name": "Hou" + }, + { + "first_name": "Ning", + "last_name": "Li" + }, + { + "first_name": "Hong", + "last_name": "Qin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoning", - "authors": "Rui Li, Tobias Fischer, Mattia Segu, Marc Pollefeys, Luc Van Gool, Federico Tombari", + "authors": [ + { + "first_name": "Rui", + "last_name": "Li" + }, + { + "first_name": "Tobias", + "last_name": "Fischer" + }, + { + "first_name": "Mattia", + "last_name": "Segu" + }, + { + "first_name": "Marc", + "last_name": "Pollefeys" + }, + { + "first_name": "Luc", + "last_name": "Van Gool" + }, + { + "first_name": "Federico", + "last_name": "Tombari" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Complementing Event Streams and RGB Frames for Hand Mesh Reconstruction", - "authors": "Jianping Jiang, Xinyu Zhou, Bingxuan Wang, Xiaoming Deng, Chao Xu, Boxin Shi", + "authors": [ + { + "first_name": "Jianping", + "last_name": "Jiang" + }, + { + "first_name": "Xinyu", + "last_name": "Zhou" + }, + { + "first_name": "Bingxuan", + "last_name": "Wang" + }, + { + "first_name": "Xiaoming", + "last_name": "Deng" + }, + { + "first_name": "Chao", + "last_name": "Xu" + }, + { + "first_name": "Boxin", + "last_name": "Shi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Empowering Resampling Operation for Ultra-High-Definition Image Enhancement with Model-Aware Guidance", - "authors": "Wei Yu, Jie Huang, Bing Li, Kaiwen Zheng, Qi Zhu, Man Zhou, Feng Zhao", + "authors": [ + { + "first_name": "Wei", + "last_name": "Yu" + }, + { + "first_name": "Jie", + "last_name": "Huang" + }, + { + "first_name": "Bing", + "last_name": "Li" + }, + { + "first_name": "Kaiwen", + "last_name": "Zheng" + }, + { + "first_name": "Qi", + "last_name": "Zhu" + }, + { + "first_name": "Man", + "last_name": "Zhou" + }, + { + "first_name": "Feng", + "last_name": "Zhao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions", - "authors": "Chunlong Xia, Xinliang Wang, Feng Lv, Xin Hao, Yifeng Shi", + "authors": [ + { + "first_name": "Chunlong", + "last_name": "Xia" + }, + { + "first_name": "Xinliang", + "last_name": "Wang" + }, + { + "first_name": "Feng", + "last_name": "Lv" + }, + { + "first_name": "Xin", + "last_name": "Hao" + }, + { + "first_name": "Yifeng", + "last_name": "Shi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PromptCoT: Align Prompt Distribution via Adapted Chain-of-Thought", - "authors": "Junyi Yao, Yijiang Liu, Zhen Dong, Mingfei Guo, Helan Hu, Kurt Keutzer, Li Du, Daquan Zhou, Shanghang Zhang", + "authors": [ + { + "first_name": "Junyi", + "last_name": "Yao" + }, + { + "first_name": "Yijiang", + "last_name": "Liu" + }, + { + "first_name": "Zhen", + "last_name": "Dong" + }, + { + "first_name": "Mingfei", + "last_name": "Guo" + }, + { + "first_name": "Helan", + "last_name": "Hu" + }, + { + "first_name": "Kurt", + "last_name": "Keutzer" + }, + { + "first_name": "Li", + "last_name": "Du" + }, + { + "first_name": "Daquan", + "last_name": "Zhou" + }, + { + "first_name": "Shanghang", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Hallucination Augmented Contrastive Learning for Multimodal Large Language Model", - "authors": "Chaoya Jiang, Haiyang Xu, Mengfan Dong, Jiaxing Chen, Wei Ye, Ming Yan, Qinghao Ye, Ji Zhang, Fei Huang, Shikun Zhang", + "authors": [ + { + "first_name": "Chaoya", + "last_name": "Jiang" + }, + { + "first_name": "Haiyang", + "last_name": "Xu" + }, + { + "first_name": "Mengfan", + "last_name": "Dong" + }, + { + "first_name": "Jiaxing", + "last_name": "Chen" + }, + { + "first_name": "Wei", + "last_name": "Ye" + }, + { + "first_name": "Ming", + "last_name": "Yan" + }, + { + "first_name": "Qinghao", + "last_name": "Ye" + }, + { + "first_name": "Ji", + "last_name": "Zhang" + }, + { + "first_name": "Fei", + "last_name": "Huang" + }, + { + "first_name": "Shikun", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Preserving Fairness Generalization in Deepfake Detection", - "authors": "Li Lin, Xinan He, Yan Ju, Xin Wang, Feng Ding, Shu Hu", + "authors": [ + { + "first_name": "Li", + "last_name": "Lin" + }, + { + "first_name": "Xinan", + "last_name": "He" + }, + { + "first_name": "Yan", + "last_name": "Ju" + }, + { + "first_name": "Xin", + "last_name": "Wang" + }, + { + "first_name": "Feng", + "last_name": "Ding" + }, + { + "first_name": "Shu", + "last_name": "Hu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Anomaly Score: Evaluating Generative Models and Individual Generated Images based on Complexity and Vulnerability", - "authors": "Jaehui Hwang, Junghyuk Lee, Jong-Seok Lee", + "authors": [ + { + "first_name": "Jaehui", + "last_name": "Hwang" + }, + { + "first_name": "Junghyuk", + "last_name": "Lee" + }, + { + "first_name": "Jong-Seok", + "last_name": "Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Structure-Aware Sparse-View X-ray 3D Reconstruction", - "authors": "Yuanhao Cai, Jiahao Wang, Alan Yuille, Zongwei Zhou, Angtian Wang", + "authors": [ + { + "first_name": "Yuanhao", + "last_name": "Cai" + }, + { + "first_name": "Jiahao", + "last_name": "Wang" + }, + { + "first_name": "Alan", + "last_name": "Yuille" + }, + { + "first_name": "Zongwei", + "last_name": "Zhou" + }, + { + "first_name": "Angtian", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Dexterous Grasp Transformer", - "authors": "Guo-Hao Xu, Yi-Lin Wei, Dian Zheng, Xiao-Ming Wu, Wei-Shi Zheng", + "authors": [ + { + "first_name": "Guo-Hao", + "last_name": "Xu" + }, + { + "first_name": "Yi-Lin", + "last_name": "Wei" + }, + { + "first_name": "Dian", + "last_name": "Zheng" + }, + { + "first_name": "Xiao-Ming", + "last_name": "Wu" + }, + { + "first_name": "Wei-Shi", + "last_name": "Zheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Cooperation Does Matter: Exploring Multi-Order Bilateral Relations for Audio-Visual Segmentation", - "authors": "Qi Yang, Xing Nie, Tong Li, Pengfei Gao, Ying Guo, Cheng Zhen, Pengfei Yan, Shiming Xiang", + "authors": [ + { + "first_name": "Qi", + "last_name": "Yang" + }, + { + "first_name": "Xing", + "last_name": "Nie" + }, + { + "first_name": "Tong", + "last_name": "Li" + }, + { + "first_name": "Pengfei", + "last_name": "Gao" + }, + { + "first_name": "Ying", + "last_name": "Guo" + }, + { + "first_name": "Cheng", + "last_name": "Zhen" + }, + { + "first_name": "Pengfei", + "last_name": "Yan" + }, + { + "first_name": "Shiming", + "last_name": "Xiang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "EgoThink: Evaluating First-Person Perspective Thinking Capability of Vision-Language Models", - "authors": "Sijie Cheng, Zhicheng Guo, Jingwen Wu, Kechen Fang, Peng Li, Huaping Liu, Yang Liu", + "authors": [ + { + "first_name": "Sijie", + "last_name": "Cheng" + }, + { + "first_name": "Zhicheng", + "last_name": "Guo" + }, + { + "first_name": "Jingwen", + "last_name": "Wu" + }, + { + "first_name": "Kechen", + "last_name": "Fang" + }, + { + "first_name": "Peng", + "last_name": "Li" + }, + { + "first_name": "Huaping", + "last_name": "Liu" + }, + { + "first_name": "Yang", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Hearing Anything Anywhere", - "authors": "Mason Long Wang, Ryosuke Sawata, Samuel Clarke, Ruohan Gao, Shangzhe Wu, Jiajun Wu", + "authors": [ + { + "first_name": "Mason", + "last_name": "Long Wang" + }, + { + "first_name": "Ryosuke", + "last_name": "Sawata" + }, + { + "first_name": "Samuel", + "last_name": "Clarke" + }, + { + "first_name": "Ruohan", + "last_name": "Gao" + }, + { + "first_name": "Shangzhe", + "last_name": "Wu" + }, + { + "first_name": "Jiajun", + "last_name": "Wu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PatchFusion: An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimation", - "authors": "Zhenyu Li, Shariq Farooq Bhat, Peter Wonka", + "authors": [ + { + "first_name": "Zhenyu", + "last_name": "Li" + }, + { + "first_name": "Shariq", + "last_name": "Farooq Bhat" + }, + { + "first_name": "Peter", + "last_name": "Wonka" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GeneAvatar: Generic Expression-Aware Volumetric Head Avatar Editing from a Single Image", - "authors": "Chong Bao, Yinda Zhang, Yuan Li, Xiyu Zhang, Bangbang Yang, Hujun Bao, Marc Pollefeys, Guofeng Zhang, Zhaopeng Cui", + "authors": [ + { + "first_name": "Chong", + "last_name": "Bao" + }, + { + "first_name": "Yinda", + "last_name": "Zhang" + }, + { + "first_name": "Yuan", + "last_name": "Li" + }, + { + "first_name": "Xiyu", + "last_name": "Zhang" + }, + { + "first_name": "Bangbang", + "last_name": "Yang" + }, + { + "first_name": "Hujun", + "last_name": "Bao" + }, + { + "first_name": "Marc", + "last_name": "Pollefeys" + }, + { + "first_name": "Guofeng", + "last_name": "Zhang" + }, + { + "first_name": "Zhaopeng", + "last_name": "Cui" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Improved Self-Training for Test-Time Adaptation", - "authors": "Jing Ma", + "authors": [ + { + "first_name": "Jing", + "last_name": "Ma" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learn to Rectify the Bias of CLIP for Unsupervised Semantic Segmentation", - "authors": "Jingyun Wang, Guoliang Kang", + "authors": [ + { + "first_name": "Jingyun", + "last_name": "Wang" + }, + { + "first_name": "Guoliang", + "last_name": "Kang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Unsupervised Feature Learning with Emergent Data-Driven Prototypicality", - "authors": "Yunhui Guo, Youren Zhang, Yubei Chen, Stella X. Yu", + "authors": [ + { + "first_name": "Yunhui", + "last_name": "Guo" + }, + { + "first_name": "Youren", + "last_name": "Zhang" + }, + { + "first_name": "Yubei", + "last_name": "Chen" + }, + { + "first_name": "Stella", + "last_name": "X. Yu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Unlocking Pre-trained Image Backbones for Semantic Image Synthesis", - "authors": "Tariq Berrada Ifriqi, Jakob Verbeek, Camille Couprie, Karteek Alahari", + "authors": [ + { + "first_name": "Tariq", + "last_name": "Berrada Ifriqi" + }, + { + "first_name": "Jakob", + "last_name": "Verbeek" + }, + { + "first_name": "Camille", + "last_name": "Couprie" + }, + { + "first_name": "Karteek", + "last_name": "Alahari" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Retrieval-Augmented Egocentric Video Captioning", - "authors": "Jilan Xu, Yifei Huang, Junlin Hou, Guo Chen, Yuejie Zhang, Rui Feng, Weidi Xie", + "authors": [ + { + "first_name": "Jilan", + "last_name": "Xu" + }, + { + "first_name": "Yifei", + "last_name": "Huang" + }, + { + "first_name": "Junlin", + "last_name": "Hou" + }, + { + "first_name": "Guo", + "last_name": "Chen" + }, + { + "first_name": "Yuejie", + "last_name": "Zhang" + }, + { + "first_name": "Rui", + "last_name": "Feng" + }, + { + "first_name": "Weidi", + "last_name": "Xie" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SkillDiffuser: Interpretable Hierarchical Planning via Skill Abstractions in Diffusion-Based Task Execution", - "authors": "Zhixuan Liang, Yao Mu, Hengbo Ma, Masayoshi Tomizuka, Mingyu Ding, Ping Luo", + "authors": [ + { + "first_name": "Zhixuan", + "last_name": "Liang" + }, + { + "first_name": "Yao", + "last_name": "Mu" + }, + { + "first_name": "Hengbo", + "last_name": "Ma" + }, + { + "first_name": "Masayoshi", + "last_name": "Tomizuka" + }, + { + "first_name": "Mingyu", + "last_name": "Ding" + }, + { + "first_name": "Ping", + "last_name": "Luo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Improving Generalized Zero-Shot Learning by Exploring the Diverse Semantics from External Class Names", - "authors": "Yapeng Li, Yong Luo, Zengmao Wang, Bo Du", + "authors": [ + { + "first_name": "Yapeng", + "last_name": "Li" + }, + { + "first_name": "Yong", + "last_name": "Luo" + }, + { + "first_name": "Zengmao", + "last_name": "Wang" + }, + { + "first_name": "Bo", + "last_name": "Du" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "TeMO: Towards Text-Driven 3D Stylization for Multi-Object Meshes", - "authors": "Xuying Zhang, Bo-Wen Yin, Yuming Chen, Zheng Lin, Yunheng Li, Qibin Hou, Ming-Ming Cheng", + "authors": [ + { + "first_name": "Xuying", + "last_name": "Zhang" + }, + { + "first_name": "Bo-Wen", + "last_name": "Yin" + }, + { + "first_name": "Yuming", + "last_name": "Chen" + }, + { + "first_name": "Zheng", + "last_name": "Lin" + }, + { + "first_name": "Yunheng", + "last_name": "Li" + }, + { + "first_name": "Qibin", + "last_name": "Hou" + }, + { + "first_name": "Ming-Ming", + "last_name": "Cheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "TE-TAD: Towards Full End-to-End Temporal Action Detection via Time-Aligned Coordinate Expression", - "authors": "Ho-Joong Kim, Jung-Ho Hong, Heejo Kong, Seong-Whan Lee", + "authors": [ + { + "first_name": "Ho-Joong", + "last_name": "Kim" + }, + { + "first_name": "Jung-Ho", + "last_name": "Hong" + }, + { + "first_name": "Heejo", + "last_name": "Kong" + }, + { + "first_name": "Seong-Whan", + "last_name": "Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GSNeRF: Generalizable Semantic Neural Radiance Fields with Enhanced 3D Scene Understanding", - "authors": "Zi-Ting Chou, Sheng-Yu Huang, I-Jieh Liu, Yu-Chiang Frank Wang", + "authors": [ + { + "first_name": "Zi-Ting", + "last_name": "Chou" + }, + { + "first_name": "Sheng-Yu", + "last_name": "Huang" + }, + { + "first_name": "I-Jieh", + "last_name": "Liu" + }, + { + "first_name": "Yu-Chiang", + "last_name": "Frank Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Alpha Invariance: On Inverse Scaling Between Distance and Volume Density in Neural Radiance Fields", - "authors": "Joshua Ahn, Haochen Wang, Raymond A. Yeh, Greg Shakhnarovich", + "authors": [ + { + "first_name": "Joshua", + "last_name": "Ahn" + }, + { + "first_name": "Haochen", + "last_name": "Wang" + }, + { + "first_name": "Raymond", + "last_name": "A. Yeh" + }, + { + "first_name": "Greg", + "last_name": "Shakhnarovich" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "TexTile: A Differentiable Metric for Texture Tileability", - "authors": "Carlos Rodriguez-Pardo, Dan Casas, Elena Garces, Jorge Lopez-Moreno", + "authors": [ + { + "first_name": "Carlos", + "last_name": "Rodriguez-Pardo" + }, + { + "first_name": "Dan", + "last_name": "Casas" + }, + { + "first_name": "Elena", + "last_name": "Garces" + }, + { + "first_name": "Jorge", + "last_name": "Lopez-Moreno" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "D3T: Distinctive Dual-Domain Teacher Zigzagging Across RGB-Thermal Gap for Domain-Adaptive Object Detection", - "authors": "Dinh Phat Do, Taehoon Kim, Jaemin Na, Jiwon Kim, Keonho Lee, Kyunghwan Cho, Wonjun Hwang", + "authors": [ + { + "first_name": "Dinh", + "last_name": "Phat Do" + }, + { + "first_name": "Taehoon", + "last_name": "Kim" + }, + { + "first_name": "Jaemin", + "last_name": "Na" + }, + { + "first_name": "Jiwon", + "last_name": "Kim" + }, + { + "first_name": "Keonho", + "last_name": "Lee" + }, + { + "first_name": "Kyunghwan", + "last_name": "Cho" + }, + { + "first_name": "Wonjun", + "last_name": "Hwang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Positive-Unlabeled Learning by Latent Group-Aware Meta Disambiguation", - "authors": "Lin Long, Haobo Wang, Zhijie Jiang, Lei Feng, Chang Yao, Gang Chen, Junbo Zhao", + "authors": [ + { + "first_name": "Lin", + "last_name": "Long" + }, + { + "first_name": "Haobo", + "last_name": "Wang" + }, + { + "first_name": "Zhijie", + "last_name": "Jiang" + }, + { + "first_name": "Lei", + "last_name": "Feng" + }, + { + "first_name": "Chang", + "last_name": "Yao" + }, + { + "first_name": "Gang", + "last_name": "Chen" + }, + { + "first_name": "Junbo", + "last_name": "Zhao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Improving Image Restoration through Removing Degradations in Textual Representations", - "authors": "Jingbo Lin, Zhilu Zhang, Yuxiang Wei, Dongwei Ren, Dongsheng Jiang, Qi Tian, Wangmeng Zuo", + "authors": [ + { + "first_name": "Jingbo", + "last_name": "Lin" + }, + { + "first_name": "Zhilu", + "last_name": "Zhang" + }, + { + "first_name": "Yuxiang", + "last_name": "Wei" + }, + { + "first_name": "Dongwei", + "last_name": "Ren" + }, + { + "first_name": "Dongsheng", + "last_name": "Jiang" + }, + { + "first_name": "Qi", + "last_name": "Tian" + }, + { + "first_name": "Wangmeng", + "last_name": "Zuo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ZONE: Zero-Shot Instruction-Guided Local Editing", - "authors": "Shanglin Li, Bohan Zeng, Yutang Feng, Sicheng Gao, Xiuhui Liu, Jiaming Liu, Lin Li, Xu Tang, Yao Hu, Jianzhuang Liu, Baochang Zhang", + "authors": [ + { + "first_name": "Shanglin", + "last_name": "Li" + }, + { + "first_name": "Bohan", + "last_name": "Zeng" + }, + { + "first_name": "Yutang", + "last_name": "Feng" + }, + { + "first_name": "Sicheng", + "last_name": "Gao" + }, + { + "first_name": "Xiuhui", + "last_name": "Liu" + }, + { + "first_name": "Jiaming", + "last_name": "Liu" + }, + { + "first_name": "Lin", + "last_name": "Li" + }, + { + "first_name": "Xu", + "last_name": "Tang" + }, + { + "first_name": "Yao", + "last_name": "Hu" + }, + { + "first_name": "Jianzhuang", + "last_name": "Liu" + }, + { + "first_name": "Baochang", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "U-VAP: User-specified Visual Appearance Personalization via Decoupled Self Augmentation", - "authors": "You Wu, Kean Liu, Xiaoyue Mi, Fan Tang, Juan Cao, Jintao Li", + "authors": [ + { + "first_name": "You", + "last_name": "Wu" + }, + { + "first_name": "Kean", + "last_name": "Liu" + }, + { + "first_name": "Xiaoyue", + "last_name": "Mi" + }, + { + "first_name": "Fan", + "last_name": "Tang" + }, + { + "first_name": "Juan", + "last_name": "Cao" + }, + { + "first_name": "Jintao", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PointBeV: A Sparse Approach for BeV Predictions", - "authors": "Loick Chambon, Eloi Zablocki, Mickaël Chen, Florent Bartoccioni, Patrick Pérez, Matthieu Cord", + "authors": [ + { + "first_name": "Loick", + "last_name": "Chambon" + }, + { + "first_name": "Eloi", + "last_name": "Zablocki" + }, + { + "first_name": "Mickaël", + "last_name": "Chen" + }, + { + "first_name": "Florent", + "last_name": "Bartoccioni" + }, + { + "first_name": "Patrick", + "last_name": "Pérez" + }, + { + "first_name": "Matthieu", + "last_name": "Cord" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "From-Ground-To-Objects: Coarse-to-Fine Self-supervised Monocular Depth Estimation of Dynamic Objects with Ground Contact Prior", - "authors": "Jaeho Moon, Juan Luis Gonzalez Bello, Byeongjun Kwon, Munchurl Kim", + "authors": [ + { + "first_name": "Jaeho", + "last_name": "Moon" + }, + { + "first_name": "Juan", + "last_name": "Luis Gonzalez Bello" + }, + { + "first_name": "Byeongjun", + "last_name": "Kwon" + }, + { + "first_name": "Munchurl", + "last_name": "Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Linguistic-Aware Patch Slimming Framework for Fine-grained Cross-Modal Alignment", - "authors": "Zheren Fu, Lei Zhang, Hou Xia, Zhendong Mao", + "authors": [ + { + "first_name": "Zheren", + "last_name": "Fu" + }, + { + "first_name": "Lei", + "last_name": "Zhang" + }, + { + "first_name": "Hou", + "last_name": "Xia" + }, + { + "first_name": "Zhendong", + "last_name": "Mao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HHMR: Holistic Hand Mesh Recovery by Enhancing the Multimodal Controllability of Graph Diffusion Models", - "authors": "Mengcheng Li, Hongwen Zhang, Yuxiang Zhang, Ruizhi Shao, Tao Yu, Yebin Liu", + "authors": [ + { + "first_name": "Mengcheng", + "last_name": "Li" + }, + { + "first_name": "Hongwen", + "last_name": "Zhang" + }, + { + "first_name": "Yuxiang", + "last_name": "Zhang" + }, + { + "first_name": "Ruizhi", + "last_name": "Shao" + }, + { + "first_name": "Tao", + "last_name": "Yu" + }, + { + "first_name": "Yebin", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SRTube: Video-Language Pre-Training with Action-Centric Video Tube Features and Semantic Role Labeling", - "authors": "Ju-Hee Lee, Je-Won Kang", + "authors": [ + { + "first_name": "Ju-Hee", + "last_name": "Lee" + }, + { + "first_name": "Je-Won", + "last_name": "Kang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Prompt Highlighter: Interactive Control for Multi-Modal LLMs", - "authors": "Yuechen Zhang, Shengju Qian, Bohao Peng, Shu Liu, Jiaya Jia", + "authors": [ + { + "first_name": "Yuechen", + "last_name": "Zhang" + }, + { + "first_name": "Shengju", + "last_name": "Qian" + }, + { + "first_name": "Bohao", + "last_name": "Peng" + }, + { + "first_name": "Shu", + "last_name": "Liu" + }, + { + "first_name": "Jiaya", + "last_name": "Jia" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Domain-Rectifying Adapter for Cross-Domain Few-Shot Segmentation", - "authors": "Jiapeng Su, Qi Fan, Wenjie Pei, Guangming Lu, Fanglin Chen", + "authors": [ + { + "first_name": "Jiapeng", + "last_name": "Su" + }, + { + "first_name": "Qi", + "last_name": "Fan" + }, + { + "first_name": "Wenjie", + "last_name": "Pei" + }, + { + "first_name": "Guangming", + "last_name": "Lu" + }, + { + "first_name": "Fanglin", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Robust Self-calibration of Focal Lengths from the Fundamental Matrix", - "authors": "Viktor Kocur, Daniel Kyselica, Zuzana Kukelova", + "authors": [ + { + "first_name": "Viktor", + "last_name": "Kocur" + }, + { + "first_name": "Daniel", + "last_name": "Kyselica" + }, + { + "first_name": "Zuzana", + "last_name": "Kukelova" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Continual Learning for Motion Prediction Model via Meta-Representation Learning and Optimal Memory Buffer Retention Strategy", - "authors": "DaeJun Kang, Dongsuk Kum, Sanmin Kim", + "authors": [ + { + "first_name": "DaeJun", + "last_name": "Kang" + }, + { + "first_name": "Dongsuk", + "last_name": "Kum" + }, + { + "first_name": "Sanmin", + "last_name": "Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PartDistill: 3D Shape Part Segmentation by Vision-Language Model Distillation", - "authors": "Ardian Umam, Cheng-Kun Yang, Min-Hung Chen, Jen-Hui Chuang, Yen-Yu Lin", + "authors": [ + { + "first_name": "Ardian", + "last_name": "Umam" + }, + { + "first_name": "Cheng-Kun", + "last_name": "Yang" + }, + { + "first_name": "Min-Hung", + "last_name": "Chen" + }, + { + "first_name": "Jen-Hui", + "last_name": "Chuang" + }, + { + "first_name": "Yen-Yu", + "last_name": "Lin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CPP-Net: Embracing Multi-Scale Feature Fusion into Deep Unfolding CP-PPA Network for Compressive Sensing", - "authors": "Zhen Guo, Hongping Gan", + "authors": [ + { + "first_name": "Zhen", + "last_name": "Guo" + }, + { + "first_name": "Hongping", + "last_name": "Gan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "EditGuard: Versatile Image Watermarking for Tamper Localization and Copyright Protection", - "authors": "Xuanyu Zhang, Runyi Li, Jiwen Yu, Youmin Xu, Weiqi Li, Jian Zhang", + "authors": [ + { + "first_name": "Xuanyu", + "last_name": "Zhang" + }, + { + "first_name": "Runyi", + "last_name": "Li" + }, + { + "first_name": "Jiwen", + "last_name": "Yu" + }, + { + "first_name": "Youmin", + "last_name": "Xu" + }, + { + "first_name": "Weiqi", + "last_name": "Li" + }, + { + "first_name": "Jian", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "3DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videos", - "authors": "Jiakai Sun, Han Jiao, Guangyuan Li, Zhanjie Zhang, Lei Zhao, Wei Xing", + "authors": [ + { + "first_name": "Jiakai", + "last_name": "Sun" + }, + { + "first_name": "Han", + "last_name": "Jiao" + }, + { + "first_name": "Guangyuan", + "last_name": "Li" + }, + { + "first_name": "Zhanjie", + "last_name": "Zhang" + }, + { + "first_name": "Lei", + "last_name": "Zhao" + }, + { + "first_name": "Wei", + "last_name": "Xing" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FairRAG: Fair Human Generation via Fair Retrieval Augmentation", - "authors": "Robik Shrestha, Yang Zou, Qiuyu Chen, Zhiheng Li, Yusheng Xie, Siqi Deng", + "authors": [ + { + "first_name": "Robik", + "last_name": "Shrestha" + }, + { + "first_name": "Yang", + "last_name": "Zou" + }, + { + "first_name": "Qiuyu", + "last_name": "Chen" + }, + { + "first_name": "Zhiheng", + "last_name": "Li" + }, + { + "first_name": "Yusheng", + "last_name": "Xie" + }, + { + "first_name": "Siqi", + "last_name": "Deng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing", - "authors": "Yujun Shi, Chuhui Xue, Jun Hao Liew, Jiachun Pan, Hanshu Yan, Wenqing Zhang, Vincent Y. F. Tan, Song Bai", + "authors": [ + { + "first_name": "Yujun", + "last_name": "Shi" + }, + { + "first_name": "Chuhui", + "last_name": "Xue" + }, + { + "first_name": "Jun", + "last_name": "Hao Liew" + }, + { + "first_name": "Jiachun", + "last_name": "Pan" + }, + { + "first_name": "Hanshu", + "last_name": "Yan" + }, + { + "first_name": "Wenqing", + "last_name": "Zhang" + }, + { + "first_name": "Vincent", + "last_name": "Y. F. Tan" + }, + { + "first_name": "Song", + "last_name": "Bai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models", - "authors": "Shivangi Aneja, Justus Thies, Angela Dai, Matthias Nießner", + "authors": [ + { + "first_name": "Shivangi", + "last_name": "Aneja" + }, + { + "first_name": "Justus", + "last_name": "Thies" + }, + { + "first_name": "Angela", + "last_name": "Dai" + }, + { + "first_name": "Matthias", + "last_name": "Nießner" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Mip-Splatting: Alias-free 3D Gaussian Splatting", - "authors": "Zehao Yu, Anpei Chen, Binbin Huang, Torsten Sattler, Andreas Geiger", + "authors": [ + { + "first_name": "Zehao", + "last_name": "Yu" + }, + { + "first_name": "Anpei", + "last_name": "Chen" + }, + { + "first_name": "Binbin", + "last_name": "Huang" + }, + { + "first_name": "Torsten", + "last_name": "Sattler" + }, + { + "first_name": "Andreas", + "last_name": "Geiger" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning Coupled Dictionaries from Unpaired Data for Image Super-Resolution", - "authors": "Longguang Wang, Juncheng Li, Yingqian Wang, Qingyong Hu, Yulan Guo", + "authors": [ + { + "first_name": "Longguang", + "last_name": "Wang" + }, + { + "first_name": "Juncheng", + "last_name": "Li" + }, + { + "first_name": "Yingqian", + "last_name": "Wang" + }, + { + "first_name": "Qingyong", + "last_name": "Hu" + }, + { + "first_name": "Yulan", + "last_name": "Guo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Template Free Reconstruction of Human-object Interaction with Procedural Interaction Generation", - "authors": "Xianghui Xie, Bharat Lal Bhatnagar, Jan Eric Lenssen, Gerard Pons-Moll", + "authors": [ + { + "first_name": "Xianghui", + "last_name": "Xie" + }, + { + "first_name": "Bharat", + "last_name": "Lal Bhatnagar" + }, + { + "first_name": "Jan", + "last_name": "Eric Lenssen" + }, + { + "first_name": "Gerard", + "last_name": "Pons-Moll" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Deep Video Inverse Tone Mapping Based on Temporal Clues", - "authors": "Yuyao Ye, Ning Zhang, Yang Zhao, Hongbin Cao, Ronggang Wang", + "authors": [ + { + "first_name": "Yuyao", + "last_name": "Ye" + }, + { + "first_name": "Ning", + "last_name": "Zhang" + }, + { + "first_name": "Yang", + "last_name": "Zhao" + }, + { + "first_name": "Hongbin", + "last_name": "Cao" + }, + { + "first_name": "Ronggang", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "NeRF-HuGS: Improved Neural Radiance Fields in Non-static Scenes Using Heuristics-Guided Segmentation", - "authors": "Jiahao Chen, Yipeng Qin, Lingjie Liu, Jiangbo Lu, Guanbin Li", + "authors": [ + { + "first_name": "Jiahao", + "last_name": "Chen" + }, + { + "first_name": "Yipeng", + "last_name": "Qin" + }, + { + "first_name": "Lingjie", + "last_name": "Liu" + }, + { + "first_name": "Jiangbo", + "last_name": "Lu" + }, + { + "first_name": "Guanbin", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Addressing Background Context Bias in Few-Shot Segmentation through Iterative Modulation", - "authors": "Lanyun Zhu, Tianrun Chen, Jianxiong Yin, Simon See, Jun Liu", + "authors": [ + { + "first_name": "Lanyun", + "last_name": "Zhu" + }, + { + "first_name": "Tianrun", + "last_name": "Chen" + }, + { + "first_name": "Jianxiong", + "last_name": "Yin" + }, + { + "first_name": "Simon", + "last_name": "See" + }, + { + "first_name": "Jun", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Open-Vocabulary Video Anomaly Detection", - "authors": "Peng Wu, Xuerong Zhou, Guansong Pang, Yujia Sun, Jing Liu, Peng Wang, Yanning Zhang", + "authors": [ + { + "first_name": "Peng", + "last_name": "Wu" + }, + { + "first_name": "Xuerong", + "last_name": "Zhou" + }, + { + "first_name": "Guansong", + "last_name": "Pang" + }, + { + "first_name": "Yujia", + "last_name": "Sun" + }, + { + "first_name": "Jing", + "last_name": "Liu" + }, + { + "first_name": "Peng", + "last_name": "Wang" + }, + { + "first_name": "Yanning", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ODM: A Text-Image Further Alignment Pre-training Approach for Scene Text Detection and Spotting", - "authors": "Chen Duan, Pei Fu, Shan Guo, Qianyi Jiang, Xiaoming Wei", + "authors": [ + { + "first_name": "Chen", + "last_name": "Duan" + }, + { + "first_name": "Pei", + "last_name": "Fu" + }, + { + "first_name": "Shan", + "last_name": "Guo" + }, + { + "first_name": "Qianyi", + "last_name": "Jiang" + }, + { + "first_name": "Xiaoming", + "last_name": "Wei" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "TiNO-Edit: Timestep and Noise Optimization for Robust Diffusion-Based Image Editing", - "authors": "Sherry X Chen, Yaron Vaxman, Elad Ben Baruch, David Asulin, Aviad Moreshet, Kuo-Chin Lien, Misha Sra, Pradeep Sen", + "authors": [ + { + "first_name": "Sherry", + "last_name": "X Chen" + }, + { + "first_name": "Yaron", + "last_name": "Vaxman" + }, + { + "first_name": "Elad", + "last_name": "Ben Baruch" + }, + { + "first_name": "David", + "last_name": "Asulin" + }, + { + "first_name": "Aviad", + "last_name": "Moreshet" + }, + { + "first_name": "Kuo-Chin", + "last_name": "Lien" + }, + { + "first_name": "Misha", + "last_name": "Sra" + }, + { + "first_name": "Pradeep", + "last_name": "Sen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Epistemic Uncertainty Quantification For Pre-Trained Neural Networks", - "authors": "Hanjing Wang, Qiang Ji", + "authors": [ + { + "first_name": "Hanjing", + "last_name": "Wang" + }, + { + "first_name": "Qiang", + "last_name": "Ji" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Diffusion-ES: Gradient-free Planning with Diffusion for Autonomous and Instruction-guided Driving", - "authors": "Brian Yang, Huangyuan Su, Nikolaos Gkanatsios, Tsung-Wei Ke, Ayush Jain, Jeff Schneider, Katerina Fragkiadaki", + "authors": [ + { + "first_name": "Brian", + "last_name": "Yang" + }, + { + "first_name": "Huangyuan", + "last_name": "Su" + }, + { + "first_name": "Nikolaos", + "last_name": "Gkanatsios" + }, + { + "first_name": "Tsung-Wei", + "last_name": "Ke" + }, + { + "first_name": "Ayush", + "last_name": "Jain" + }, + { + "first_name": "Jeff", + "last_name": "Schneider" + }, + { + "first_name": "Katerina", + "last_name": "Fragkiadaki" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "AdaShift: Learning Discriminative Self-Gated Neural Feature Activation With an Adaptive Shift Factor", - "authors": "Sudong Cai", + "authors": [ + { + "first_name": "Sudong", + "last_name": "Cai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SCEdit: Efficient and Controllable Image Diffusion Generation via Skip Connection Editing", - "authors": "Zeyinzi Jiang, Chaojie Mao, Yulin Pan, Zhen Han, Jingfeng Zhang", + "authors": [ + { + "first_name": "Zeyinzi", + "last_name": "Jiang" + }, + { + "first_name": "Chaojie", + "last_name": "Mao" + }, + { + "first_name": "Yulin", + "last_name": "Pan" + }, + { + "first_name": "Zhen", + "last_name": "Han" + }, + { + "first_name": "Jingfeng", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MRC-Net: 6-DoF Pose Estimation with MultiScale Residual Correlation", - "authors": "Yuelong Li, Yafei Mao, Raja Bala, Sunil Hadap", + "authors": [ + { + "first_name": "Yuelong", + "last_name": "Li" + }, + { + "first_name": "Yafei", + "last_name": "Mao" + }, + { + "first_name": "Raja", + "last_name": "Bala" + }, + { + "first_name": "Sunil", + "last_name": "Hadap" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MonoCD: Monocular 3D Object Detection with Complementary Depths", - "authors": "Longfei Yan, Pei Yan, Shengzhou Xiong, Xuanyu Xiang, Yihua Tan", + "authors": [ + { + "first_name": "Longfei", + "last_name": "Yan" + }, + { + "first_name": "Pei", + "last_name": "Yan" + }, + { + "first_name": "Shengzhou", + "last_name": "Xiong" + }, + { + "first_name": "Xuanyu", + "last_name": "Xiang" + }, + { + "first_name": "Yihua", + "last_name": "Tan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ImageNet-D: Benchmarking Neural Network Robustness on Diffusion Synthetic Object", - "authors": "Chenshuang Zhang, Fei Pan, Junmo Kim, In So Kweon, Chengzhi Mao", + "authors": [ + { + "first_name": "Chenshuang", + "last_name": "Zhang" + }, + { + "first_name": "Fei", + "last_name": "Pan" + }, + { + "first_name": "Junmo", + "last_name": "Kim" + }, + { + "first_name": "In", + "last_name": "So Kweon" + }, + { + "first_name": "Chengzhi", + "last_name": "Mao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Consistent3D: Towards Consistent High-Fidelity Text-to-3D Generation with Deterministic Sampling Prior", - "authors": "Zike Wu, Pan Zhou, Xuanyu Yi, Xiaoding Yuan, Hanwang Zhang", + "authors": [ + { + "first_name": "Zike", + "last_name": "Wu" + }, + { + "first_name": "Pan", + "last_name": "Zhou" + }, + { + "first_name": "Xuanyu", + "last_name": "Yi" + }, + { + "first_name": "Xiaoding", + "last_name": "Yuan" + }, + { + "first_name": "Hanwang", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulation", - "authors": "Xiaoqi Li, Mingxu Zhang, Yiran Geng, Haoran Geng, Yuxing Long, Yan Shen, Renrui Zhang, Jiaming Liu, Hao Dong", + "authors": [ + { + "first_name": "Xiaoqi", + "last_name": "Li" + }, + { + "first_name": "Mingxu", + "last_name": "Zhang" + }, + { + "first_name": "Yiran", + "last_name": "Geng" + }, + { + "first_name": "Haoran", + "last_name": "Geng" + }, + { + "first_name": "Yuxing", + "last_name": "Long" + }, + { + "first_name": "Yan", + "last_name": "Shen" + }, + { + "first_name": "Renrui", + "last_name": "Zhang" + }, + { + "first_name": "Jiaming", + "last_name": "Liu" + }, + { + "first_name": "Hao", + "last_name": "Dong" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "BA-SAM: Scalable Bias-Mode Attention Mask for Segment Anything Model", - "authors": "Yiran Song, Qianyu Zhou, Xiangtai Li, Deng-Ping Fan, Xuequan Lu, Lizhuang Ma", + "authors": [ + { + "first_name": "Yiran", + "last_name": "Song" + }, + { + "first_name": "Qianyu", + "last_name": "Zhou" + }, + { + "first_name": "Xiangtai", + "last_name": "Li" + }, + { + "first_name": "Deng-Ping", + "last_name": "Fan" + }, + { + "first_name": "Xuequan", + "last_name": "Lu" + }, + { + "first_name": "Lizhuang", + "last_name": "Ma" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Text-Enhanced Data-free Approach for Federated Class-Incremental Learning", - "authors": "Minh-Tuan Tran, Trung Le, Xuan-May Le, Mehrtash Harandi, Dinh Phung", + "authors": [ + { + "first_name": "Minh-Tuan", + "last_name": "Tran" + }, + { + "first_name": "Trung", + "last_name": "Le" + }, + { + "first_name": "Xuan-May", + "last_name": "Le" + }, + { + "first_name": "Mehrtash", + "last_name": "Harandi" + }, + { + "first_name": "Dinh", + "last_name": "Phung" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Deciphering 'What' and 'Where' Visual Pathways from Spectral Clustering of Layer-Distributed Neural Representations", - "authors": "Xiao Zhang, David Yunis, Michael Maire", + "authors": [ + { + "first_name": "Xiao", + "last_name": "Zhang" + }, + { + "first_name": "David", + "last_name": "Yunis" + }, + { + "first_name": "Michael", + "last_name": "Maire" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GLaMM: Pixel Grounding Large Multimodal Model", - "authors": "Hanoona Rasheed, Muhammad Maaz, Sahal Shaji, Abdelrahman Shaker, Salman Khan, Hisham Cholakkal, Rao M. Anwer, Eric Xing, Ming-Hsuan Yang, Fahad S. Khan", + "authors": [ + { + "first_name": "Hanoona", + "last_name": "Rasheed" + }, + { + "first_name": "Muhammad", + "last_name": "Maaz" + }, + { + "first_name": "Sahal", + "last_name": "Shaji" + }, + { + "first_name": "Abdelrahman", + "last_name": "Shaker" + }, + { + "first_name": "Salman", + "last_name": "Khan" + }, + { + "first_name": "Hisham", + "last_name": "Cholakkal" + }, + { + "first_name": "Rao", + "last_name": "M. Anwer" + }, + { + "first_name": "Eric", + "last_name": "Xing" + }, + { + "first_name": "Ming-Hsuan", + "last_name": "Yang" + }, + { + "first_name": "Fahad", + "last_name": "S. Khan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Incremental Residual Concept Bottleneck Models", - "authors": "Chenming Shang, Shiji Zhou, Hengyuan Zhang, Xinzhe Ni, Yujiu Yang, Yuwang Wang", + "authors": [ + { + "first_name": "Chenming", + "last_name": "Shang" + }, + { + "first_name": "Shiji", + "last_name": "Zhou" + }, + { + "first_name": "Hengyuan", + "last_name": "Zhang" + }, + { + "first_name": "Xinzhe", + "last_name": "Ni" + }, + { + "first_name": "Yujiu", + "last_name": "Yang" + }, + { + "first_name": "Yuwang", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SPOC: Imitating Shortest Paths in Simulation Enables Effective Navigation and Manipulation in the Real World", - "authors": "Kiana Ehsani, Tanmay Gupta, Rose Hendrix, Jordi Salvador, Luca Weihs, Kuo-Hao Zeng, Kunal Pratap Singh, Yejin Kim, Winson Han, Alvaro Herrasti, Ranjay Krishna, Dustin Schwenk, Eli VanderBilt, Aniruddha Kembhavi", + "authors": [ + { + "first_name": "Kiana", + "last_name": "Ehsani" + }, + { + "first_name": "Tanmay", + "last_name": "Gupta" + }, + { + "first_name": "Rose", + "last_name": "Hendrix" + }, + { + "first_name": "Jordi", + "last_name": "Salvador" + }, + { + "first_name": "Luca", + "last_name": "Weihs" + }, + { + "first_name": "Kuo-Hao", + "last_name": "Zeng" + }, + { + "first_name": "Kunal", + "last_name": "Pratap Singh" + }, + { + "first_name": "Yejin", + "last_name": "Kim" + }, + { + "first_name": "Winson", + "last_name": "Han" + }, + { + "first_name": "Alvaro", + "last_name": "Herrasti" + }, + { + "first_name": "Ranjay", + "last_name": "Krishna" + }, + { + "first_name": "Dustin", + "last_name": "Schwenk" + }, + { + "first_name": "Eli", + "last_name": "VanderBilt" + }, + { + "first_name": "Aniruddha", + "last_name": "Kembhavi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Real-Time Exposure Correction via Collaborative Transformations and Adaptive Sampling", - "authors": "Ziwen Li, Feng Zhang, Meng Cao, Jinpu Zhang, Yuanjie Shao, Yuehuan Wang, Nong Sang", + "authors": [ + { + "first_name": "Ziwen", + "last_name": "Li" + }, + { + "first_name": "Feng", + "last_name": "Zhang" + }, + { + "first_name": "Meng", + "last_name": "Cao" + }, + { + "first_name": "Jinpu", + "last_name": "Zhang" + }, + { + "first_name": "Yuanjie", + "last_name": "Shao" + }, + { + "first_name": "Yuehuan", + "last_name": "Wang" + }, + { + "first_name": "Nong", + "last_name": "Sang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Lodge: A Coarse to Fine Diffusion Network for Long Dance Generation Guided by the Characteristic Dance Primitives", - "authors": "Ronghui Li, YuXiang Zhang, Yachao Zhang, Hongwen Zhang, Jie Guo, Yan Zhang, Yebin Liu, Xiu Li", + "authors": [ + { + "first_name": "Ronghui", + "last_name": "Li" + }, + { + "first_name": "YuXiang", + "last_name": "Zhang" + }, + { + "first_name": "Yachao", + "last_name": "Zhang" + }, + { + "first_name": "Hongwen", + "last_name": "Zhang" + }, + { + "first_name": "Jie", + "last_name": "Guo" + }, + { + "first_name": "Yan", + "last_name": "Zhang" + }, + { + "first_name": "Yebin", + "last_name": "Liu" + }, + { + "first_name": "Xiu", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "UDiFF: Generating Conditional Unsigned Distance Fields with Optimal Wavelet Diffusion", - "authors": "Junsheng Zhou, Weiqi Zhang, Baorui Ma, Kanle Shi, Yu-Shen Liu, Zhizhong Han", + "authors": [ + { + "first_name": "Junsheng", + "last_name": "Zhou" + }, + { + "first_name": "Weiqi", + "last_name": "Zhang" + }, + { + "first_name": "Baorui", + "last_name": "Ma" + }, + { + "first_name": "Kanle", + "last_name": "Shi" + }, + { + "first_name": "Yu-Shen", + "last_name": "Liu" + }, + { + "first_name": "Zhizhong", + "last_name": "Han" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LoCoNet: Long-Short Context Network for Active Speaker Detection", - "authors": "Xizi Wang, Feng Cheng, Gedas Bertasius", + "authors": [ + { + "first_name": "Xizi", + "last_name": "Wang" + }, + { + "first_name": "Feng", + "last_name": "Cheng" + }, + { + "first_name": "Gedas", + "last_name": "Bertasius" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "D3still: Decoupled Differential Distillation for Asymmetric Image Retrieval", - "authors": "Yi Xie, Yihong Lin, Wenjie Cai, Xuemiao Xu, Huaidong Zhang, Yong Du, Shengfeng He", + "authors": [ + { + "first_name": "Yi", + "last_name": "Xie" + }, + { + "first_name": "Yihong", + "last_name": "Lin" + }, + { + "first_name": "Wenjie", + "last_name": "Cai" + }, + { + "first_name": "Xuemiao", + "last_name": "Xu" + }, + { + "first_name": "Huaidong", + "last_name": "Zhang" + }, + { + "first_name": "Yong", + "last_name": "Du" + }, + { + "first_name": "Shengfeng", + "last_name": "He" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Transcending Forgery Specificity with Latent Space Augmentation for Generalizable Deepfake Detection", - "authors": "Zhiyuan Yan, Yuhao Luo, Siwei Lyu, Qingshan Liu, Baoyuan Wu", + "authors": [ + { + "first_name": "Zhiyuan", + "last_name": "Yan" + }, + { + "first_name": "Yuhao", + "last_name": "Luo" + }, + { + "first_name": "Siwei", + "last_name": "Lyu" + }, + { + "first_name": "Qingshan", + "last_name": "Liu" + }, + { + "first_name": "Baoyuan", + "last_name": "Wu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Scaling Laws of Synthetic Images for Model Training ... for Now", - "authors": "Lijie Fan, Kaifeng Chen, Dilip Krishnan, Dina Katabi, Phillip Isola, Yonglong Tian", + "authors": [ + { + "first_name": "Lijie", + "last_name": "Fan" + }, + { + "first_name": "Kaifeng", + "last_name": "Chen" + }, + { + "first_name": "Dilip", + "last_name": "Krishnan" + }, + { + "first_name": "Dina", + "last_name": "Katabi" + }, + { + "first_name": "Phillip", + "last_name": "Isola" + }, + { + "first_name": "Yonglong", + "last_name": "Tian" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training", - "authors": "Xiaoyang Wu, Zhuotao Tian, Xin Wen, Bohao Peng, Xihui Liu, Kaicheng Yu, Hengshuang Zhao", + "authors": [ + { + "first_name": "Xiaoyang", + "last_name": "Wu" + }, + { + "first_name": "Zhuotao", + "last_name": "Tian" + }, + { + "first_name": "Xin", + "last_name": "Wen" + }, + { + "first_name": "Bohao", + "last_name": "Peng" + }, + { + "first_name": "Xihui", + "last_name": "Liu" + }, + { + "first_name": "Kaicheng", + "last_name": "Yu" + }, + { + "first_name": "Hengshuang", + "last_name": "Zhao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning Triangular Distribution in Visual World", - "authors": "Ping Chen, Xingpeng Zhang, Chengtao Zhou, Dichao Fan, Peng Tu, Le Zhang, Yanlin Qian", + "authors": [ + { + "first_name": "Ping", + "last_name": "Chen" + }, + { + "first_name": "Xingpeng", + "last_name": "Zhang" + }, + { + "first_name": "Chengtao", + "last_name": "Zhou" + }, + { + "first_name": "Dichao", + "last_name": "Fan" + }, + { + "first_name": "Peng", + "last_name": "Tu" + }, + { + "first_name": "Le", + "last_name": "Zhang" + }, + { + "first_name": "Yanlin", + "last_name": "Qian" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "State Space Models for Event Cameras", - "authors": "Nikola Zubic, Mathias Gehrig, Davide Scaramuzza", + "authors": [ + { + "first_name": "Nikola", + "last_name": "Zubic" + }, + { + "first_name": "Mathias", + "last_name": "Gehrig" + }, + { + "first_name": "Davide", + "last_name": "Scaramuzza" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI", - "authors": "Tai Wang, Xiaohan Mao, Chenming Zhu, Runsen Xu, Ruiyuan Lyu, Peisen Li, Xiao Chen, Wenwei Zhang, Kai Chen, Tianfan Xue, Xihui Liu, Cewu Lu, Dahua Lin, Jiangmiao Pang", + "authors": [ + { + "first_name": "Tai", + "last_name": "Wang" + }, + { + "first_name": "Xiaohan", + "last_name": "Mao" + }, + { + "first_name": "Chenming", + "last_name": "Zhu" + }, + { + "first_name": "Runsen", + "last_name": "Xu" + }, + { + "first_name": "Ruiyuan", + "last_name": "Lyu" + }, + { + "first_name": "Peisen", + "last_name": "Li" + }, + { + "first_name": "Xiao", + "last_name": "Chen" + }, + { + "first_name": "Wenwei", + "last_name": "Zhang" + }, + { + "first_name": "Kai", + "last_name": "Chen" + }, + { + "first_name": "Tianfan", + "last_name": "Xue" + }, + { + "first_name": "Xihui", + "last_name": "Liu" + }, + { + "first_name": "Cewu", + "last_name": "Lu" + }, + { + "first_name": "Dahua", + "last_name": "Lin" + }, + { + "first_name": "Jiangmiao", + "last_name": "Pang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SHINOBI: Shape and Illumination using Neural Object Decomposition via BRDF Optimization In-the-wild", - "authors": "Andreas Engelhardt, Amit Raj, Mark Boss, Yunzhi Zhang, Abhishek Kar, Yuanzhen Li, Deqing Sun, Ricardo Martin Brualla, Jonathan T. Barron, Hendrik P. A. Lensch, Varun Jampani", + "authors": [ + { + "first_name": "Andreas", + "last_name": "Engelhardt" + }, + { + "first_name": "Amit", + "last_name": "Raj" + }, + { + "first_name": "Mark", + "last_name": "Boss" + }, + { + "first_name": "Yunzhi", + "last_name": "Zhang" + }, + { + "first_name": "Abhishek", + "last_name": "Kar" + }, + { + "first_name": "Yuanzhen", + "last_name": "Li" + }, + { + "first_name": "Deqing", + "last_name": "Sun" + }, + { + "first_name": "Ricardo", + "last_name": "Martin Brualla" + }, + { + "first_name": "Jonathan", + "last_name": "T. Barron" + }, + { + "first_name": "Hendrik", + "last_name": "P. A. Lensch" + }, + { + "first_name": "Varun", + "last_name": "Jampani" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ES3: Evolving Self-Supervised Learning of Robust Audio-Visual Speech Representations", - "authors": "Yuanhang Zhang, Shuang Yang, Shiguang Shan, Xilin Chen", + "authors": [ + { + "first_name": "Yuanhang", + "last_name": "Zhang" + }, + { + "first_name": "Shuang", + "last_name": "Yang" + }, + { + "first_name": "Shiguang", + "last_name": "Shan" + }, + { + "first_name": "Xilin", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "TeTriRF: Temporal Tri-Plane Radiance Fields for Efficient Free-Viewpoint Video", - "authors": "Minye Wu, Zehao Wang, Georgios Kouros, Tinne Tuytelaars", + "authors": [ + { + "first_name": "Minye", + "last_name": "Wu" + }, + { + "first_name": "Zehao", + "last_name": "Wang" + }, + { + "first_name": "Georgios", + "last_name": "Kouros" + }, + { + "first_name": "Tinne", + "last_name": "Tuytelaars" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Motion2VecSets: 4D Latent Vector Set Diffusion for Non-rigid Shape Reconstruction and Tracking", - "authors": "Wei Cao, Chang Luo, Biao Zhang, Matthias Nießner, Jiapeng Tang", + "authors": [ + { + "first_name": "Wei", + "last_name": "Cao" + }, + { + "first_name": "Chang", + "last_name": "Luo" + }, + { + "first_name": "Biao", + "last_name": "Zhang" + }, + { + "first_name": "Matthias", + "last_name": "Nießner" + }, + { + "first_name": "Jiapeng", + "last_name": "Tang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DiaLoc: An Iterative Approach to Embodied Dialog Localization", - "authors": "Chao Zhang, Mohan Li, Ignas Budvytis, Stephan Liwicki", + "authors": [ + { + "first_name": "Chao", + "last_name": "Zhang" + }, + { + "first_name": "Mohan", + "last_name": "Li" + }, + { + "first_name": "Ignas", + "last_name": "Budvytis" + }, + { + "first_name": "Stephan", + "last_name": "Liwicki" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Self-Training Large Language Models for Improved Visual Program Synthesis With Visual Reinforcement", - "authors": "Zaid Khan, Vijay Kumar BG, Samuel Schulter, Yun Fu, Manmohan Chandraker", + "authors": [ + { + "first_name": "Zaid", + "last_name": "Khan" + }, + { + "first_name": "Vijay", + "last_name": "Kumar BG" + }, + { + "first_name": "Samuel", + "last_name": "Schulter" + }, + { + "first_name": "Yun", + "last_name": "Fu" + }, + { + "first_name": "Manmohan", + "last_name": "Chandraker" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "A2XP: Towards Private Domain Generalization", - "authors": "Geunhyeok Yu, Hyoseok Hwang", + "authors": [ + { + "first_name": "Geunhyeok", + "last_name": "Yu" + }, + { + "first_name": "Hyoseok", + "last_name": "Hwang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Event-assisted Low-Light Video Object Segmentation", - "authors": "Hebei Li, Jin Wang, Jiahui Yuan, Yue Li, Wenming Weng, Yansong Peng, Yueyi Zhang, Zhiwei Xiong, Xiaoyan Sun", + "authors": [ + { + "first_name": "Hebei", + "last_name": "Li" + }, + { + "first_name": "Jin", + "last_name": "Wang" + }, + { + "first_name": "Jiahui", + "last_name": "Yuan" + }, + { + "first_name": "Yue", + "last_name": "Li" + }, + { + "first_name": "Wenming", + "last_name": "Weng" + }, + { + "first_name": "Yansong", + "last_name": "Peng" + }, + { + "first_name": "Yueyi", + "last_name": "Zhang" + }, + { + "first_name": "Zhiwei", + "last_name": "Xiong" + }, + { + "first_name": "Xiaoyan", + "last_name": "Sun" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Active Domain Adaptation with False Negative Prediction for Object Detection", - "authors": "Yuzuru Nakamura, Yasunori Ishii, Takayoshi Yamashita", + "authors": [ + { + "first_name": "Yuzuru", + "last_name": "Nakamura" + }, + { + "first_name": "Yasunori", + "last_name": "Ishii" + }, + { + "first_name": "Takayoshi", + "last_name": "Yamashita" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MLIP: Enhancing Medical Visual Representation with Divergence Encoder and Knowledge-guided Contrastive Learning", - "authors": "Zhe Li, Laurence T. Yang, Bocheng Ren, Xin Nie, Zhangyang Gao, Cheng Tan, Stan Z. Li", + "authors": [ + { + "first_name": "Zhe", + "last_name": "Li" + }, + { + "first_name": "Laurence", + "last_name": "T. Yang" + }, + { + "first_name": "Bocheng", + "last_name": "Ren" + }, + { + "first_name": "Xin", + "last_name": "Nie" + }, + { + "first_name": "Zhangyang", + "last_name": "Gao" + }, + { + "first_name": "Cheng", + "last_name": "Tan" + }, + { + "first_name": "Stan", + "last_name": "Z. Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Generative 3D Part Assembly via Part-Whole-Hierarchy Message Passing", - "authors": "Bi'an Du, Xiang Gao, Wei Hu, Renjie Liao", + "authors": [ + { + "first_name": "Bi'an", + "last_name": "Du" + }, + { + "first_name": "Xiang", + "last_name": "Gao" + }, + { + "first_name": "Wei", + "last_name": "Hu" + }, + { + "first_name": "Renjie", + "last_name": "Liao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "VidToMe: Video Token Merging for Zero-Shot Video Editing", - "authors": "Xirui Li, Chao Ma, Xiaokang Yang, Ming-Hsuan Yang", + "authors": [ + { + "first_name": "Xirui", + "last_name": "Li" + }, + { + "first_name": "Chao", + "last_name": "Ma" + }, + { + "first_name": "Xiaokang", + "last_name": "Yang" + }, + { + "first_name": "Ming-Hsuan", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FaceChain-SuDe: Building Derived Class to Inherit Category Attributes for One-shot Subject-Driven Generation", - "authors": "Pengchong Qiao, Lei Shang, Chang Liu, Baigui Sun, Xiangyang Ji, Jie Chen", + "authors": [ + { + "first_name": "Pengchong", + "last_name": "Qiao" + }, + { + "first_name": "Lei", + "last_name": "Shang" + }, + { + "first_name": "Chang", + "last_name": "Liu" + }, + { + "first_name": "Baigui", + "last_name": "Sun" + }, + { + "first_name": "Xiangyang", + "last_name": "Ji" + }, + { + "first_name": "Jie", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Benchmarking Segmentation Models with Mask-Preserved Attribute Editing", - "authors": "Zijin Yin, Kongming Liang, Bing Li, Zhanyu Ma, Jun Guo", + "authors": [ + { + "first_name": "Zijin", + "last_name": "Yin" + }, + { + "first_name": "Kongming", + "last_name": "Liang" + }, + { + "first_name": "Bing", + "last_name": "Li" + }, + { + "first_name": "Zhanyu", + "last_name": "Ma" + }, + { + "first_name": "Jun", + "last_name": "Guo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Analyzing and Improving the Training Dynamics of Diffusion Models", - "authors": "Tero Karras, Miika Aittala, Jaakko Lehtinen, Janne Hellsten, Timo Aila, Samuli Laine", + "authors": [ + { + "first_name": "Tero", + "last_name": "Karras" + }, + { + "first_name": "Miika", + "last_name": "Aittala" + }, + { + "first_name": "Jaakko", + "last_name": "Lehtinen" + }, + { + "first_name": "Janne", + "last_name": "Hellsten" + }, + { + "first_name": "Timo", + "last_name": "Aila" + }, + { + "first_name": "Samuli", + "last_name": "Laine" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Hierarchical Correlation Clustering and Tree Preserving Embedding", - "authors": "Morteza Haghir Chehreghani, Mostafa Haghir Chehreghani", + "authors": [ + { + "first_name": "Morteza", + "last_name": "Haghir Chehreghani" + }, + { + "first_name": "Mostafa", + "last_name": "Haghir Chehreghani" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On", - "authors": "Jeongho Kim, Guojung Gu, Minho Park, Sunghyun Park, Jaegul Choo", + "authors": [ + { + "first_name": "Jeongho", + "last_name": "Kim" + }, + { + "first_name": "Guojung", + "last_name": "Gu" + }, + { + "first_name": "Minho", + "last_name": "Park" + }, + { + "first_name": "Sunghyun", + "last_name": "Park" + }, + { + "first_name": "Jaegul", + "last_name": "Choo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion?", - "authors": "Zhengyue Zhao, Jinhao Duan, Kaidi Xu, Chenan Wang, Rui Zhang, Zidong Du, Qi Guo, Xing Hu", + "authors": [ + { + "first_name": "Zhengyue", + "last_name": "Zhao" + }, + { + "first_name": "Jinhao", + "last_name": "Duan" + }, + { + "first_name": "Kaidi", + "last_name": "Xu" + }, + { + "first_name": "Chenan", + "last_name": "Wang" + }, + { + "first_name": "Rui", + "last_name": "Zhang" + }, + { + "first_name": "Zidong", + "last_name": "Du" + }, + { + "first_name": "Qi", + "last_name": "Guo" + }, + { + "first_name": "Xing", + "last_name": "Hu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Make-Your-Anchor: A Diffusion-based 2D Avatar Generation Framework", - "authors": "Ziyao Huang, Fan Tang, Yong Zhang, Xiaodong Cun, Juan Cao, Jintao Li, Tong-Yee Lee", + "authors": [ + { + "first_name": "Ziyao", + "last_name": "Huang" + }, + { + "first_name": "Fan", + "last_name": "Tang" + }, + { + "first_name": "Yong", + "last_name": "Zhang" + }, + { + "first_name": "Xiaodong", + "last_name": "Cun" + }, + { + "first_name": "Juan", + "last_name": "Cao" + }, + { + "first_name": "Jintao", + "last_name": "Li" + }, + { + "first_name": "Tong-Yee", + "last_name": "Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MultiPLY: A Multisensory Object-Centric Embodied Large Language Model in 3D World", - "authors": "Yining Hong, Zishuo Zheng, Peihao Chen, Yian Wang, Junyan Li, Chuang Gan", + "authors": [ + { + "first_name": "Yining", + "last_name": "Hong" + }, + { + "first_name": "Zishuo", + "last_name": "Zheng" + }, + { + "first_name": "Peihao", + "last_name": "Chen" + }, + { + "first_name": "Yian", + "last_name": "Wang" + }, + { + "first_name": "Junyan", + "last_name": "Li" + }, + { + "first_name": "Chuang", + "last_name": "Gan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning to Visually Localize Sound Sources from Mixtures without Prior Source Knowledge", - "authors": "Dongjin Kim, Sung Jin Um, Sangmin Lee, Jung Uk Kim", + "authors": [ + { + "first_name": "Dongjin", + "last_name": "Kim" + }, + { + "first_name": "Sung", + "last_name": "Jin Um" + }, + { + "first_name": "Sangmin", + "last_name": "Lee" + }, + { + "first_name": "Jung", + "last_name": "Uk Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning Dynamic Tetrahedra for High-Quality Talking Head Synthesis", - "authors": "Zicheng Zhang, Ruobing Zheng, Bonan Li, Congying Han, Tianqi Li, Meng Wang, Tiande Guo, Jingdong Chen, Ziwen Liu, Ming Yang", + "authors": [ + { + "first_name": "Zicheng", + "last_name": "Zhang" + }, + { + "first_name": "Ruobing", + "last_name": "Zheng" + }, + { + "first_name": "Bonan", + "last_name": "Li" + }, + { + "first_name": "Congying", + "last_name": "Han" + }, + { + "first_name": "Tianqi", + "last_name": "Li" + }, + { + "first_name": "Meng", + "last_name": "Wang" + }, + { + "first_name": "Tiande", + "last_name": "Guo" + }, + { + "first_name": "Jingdong", + "last_name": "Chen" + }, + { + "first_name": "Ziwen", + "last_name": "Liu" + }, + { + "first_name": "Ming", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Collaborative Learning of Anomalies with Privacy (CLAP) for Unsupervised Video Anomaly Detection: A New Baseline", - "authors": "Anas Al-lahham, Muhammad Zaigham Zaheer, Nurbek Tastan, Karthik Nandakumar", + "authors": [ + { + "first_name": "Anas", + "last_name": "Al-lahham" + }, + { + "first_name": "Muhammad", + "last_name": "Zaigham Zaheer" + }, + { + "first_name": "Nurbek", + "last_name": "Tastan" + }, + { + "first_name": "Karthik", + "last_name": "Nandakumar" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Regressor-Segmenter Mutual Prompt Learning for Crowd Counting", - "authors": "Mingyue Guo, Li Yuan, Zhaoyi Yan, Binghui Chen, Yaowei Wang, Qixiang Ye", + "authors": [ + { + "first_name": "Mingyue", + "last_name": "Guo" + }, + { + "first_name": "Li", + "last_name": "Yuan" + }, + { + "first_name": "Zhaoyi", + "last_name": "Yan" + }, + { + "first_name": "Binghui", + "last_name": "Chen" + }, + { + "first_name": "Yaowei", + "last_name": "Wang" + }, + { + "first_name": "Qixiang", + "last_name": "Ye" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Instantaneous Perception of Moving Objects in 3D", - "authors": "Di Liu, Bingbing Zhuang, Dimitris N. Metaxas, Manmohan Chandraker", + "authors": [ + { + "first_name": "Di", + "last_name": "Liu" + }, + { + "first_name": "Bingbing", + "last_name": "Zhuang" + }, + { + "first_name": "Dimitris", + "last_name": "N. Metaxas" + }, + { + "first_name": "Manmohan", + "last_name": "Chandraker" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CORE-MPI: Consistency Object Removal with Embedding MultiPlane Image", - "authors": "Donggeun Yoon, Donghyeon Cho", + "authors": [ + { + "first_name": "Donggeun", + "last_name": "Yoon" + }, + { + "first_name": "Donghyeon", + "last_name": "Cho" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "3D Geometry-Aware Deformable Gaussian Splatting for Dynamic View Synthesis", - "authors": "Zhicheng Lu, Xiang Guo, Le Hui, Tianrui Chen, Min Yang, Xiao Tang, Feng Zhu, Yuchao Dai", + "authors": [ + { + "first_name": "Zhicheng", + "last_name": "Lu" + }, + { + "first_name": "Xiang", + "last_name": "Guo" + }, + { + "first_name": "Le", + "last_name": "Hui" + }, + { + "first_name": "Tianrui", + "last_name": "Chen" + }, + { + "first_name": "Min", + "last_name": "Yang" + }, + { + "first_name": "Xiao", + "last_name": "Tang" + }, + { + "first_name": "Feng", + "last_name": "Zhu" + }, + { + "first_name": "Yuchao", + "last_name": "Dai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Person-in-WiFi 3D: End-to-End Multi-Person 3D Pose Estimation with Wi-Fi", - "authors": "Kangwei Yan, Fei Wang, Bo Qian, Han Ding, Jinsong Han, Xing Wei", + "authors": [ + { + "first_name": "Kangwei", + "last_name": "Yan" + }, + { + "first_name": "Fei", + "last_name": "Wang" + }, + { + "first_name": "Bo", + "last_name": "Qian" + }, + { + "first_name": "Han", + "last_name": "Ding" + }, + { + "first_name": "Jinsong", + "last_name": "Han" + }, + { + "first_name": "Xing", + "last_name": "Wei" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Backpropagation-free Network for 3D Test-time Adaptation", - "authors": "Yanshuo Wang, Ali Cheraghian, Zeeshan Hayder, Jie Hong, Sameera Ramasinghe, Shafin Rahman, David Ahmedt-Aristizabal, Xuesong Li, Lars Petersson, Mehrtash Harandi", + "authors": [ + { + "first_name": "Yanshuo", + "last_name": "Wang" + }, + { + "first_name": "Ali", + "last_name": "Cheraghian" + }, + { + "first_name": "Zeeshan", + "last_name": "Hayder" + }, + { + "first_name": "Jie", + "last_name": "Hong" + }, + { + "first_name": "Sameera", + "last_name": "Ramasinghe" + }, + { + "first_name": "Shafin", + "last_name": "Rahman" + }, + { + "first_name": "David", + "last_name": "Ahmedt-Aristizabal" + }, + { + "first_name": "Xuesong", + "last_name": "Li" + }, + { + "first_name": "Lars", + "last_name": "Petersson" + }, + { + "first_name": "Mehrtash", + "last_name": "Harandi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Resource-Efficient Transformer Pruning for Finetuning of Large Models", - "authors": "Fatih Ilhan, Gong Su, Selim Furkan Tekin, Tiansheng Huang, Sihao Hu, Ling Liu", + "authors": [ + { + "first_name": "Fatih", + "last_name": "Ilhan" + }, + { + "first_name": "Gong", + "last_name": "Su" + }, + { + "first_name": "Selim", + "last_name": "Furkan Tekin" + }, + { + "first_name": "Tiansheng", + "last_name": "Huang" + }, + { + "first_name": "Sihao", + "last_name": "Hu" + }, + { + "first_name": "Ling", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ParamISP: Learned Forward and Inverse ISPs using Camera Parameters", - "authors": "Woohyeok Kim, Geonu Kim, Junyong Lee, Seungyong Lee, Seung-Hwan Baek, Sunghyun Cho", + "authors": [ + { + "first_name": "Woohyeok", + "last_name": "Kim" + }, + { + "first_name": "Geonu", + "last_name": "Kim" + }, + { + "first_name": "Junyong", + "last_name": "Lee" + }, + { + "first_name": "Seungyong", + "last_name": "Lee" + }, + { + "first_name": "Seung-Hwan", + "last_name": "Baek" + }, + { + "first_name": "Sunghyun", + "last_name": "Cho" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Perturbing Attention Gives You More Bang for the Buck: Subtle Imaging Perturbations That Efficiently Fool Customized Diffusion Models", - "authors": "Jingyao Xu, Yuetong Lu, Yandong Li, Siyang Lu, Dongdong Wang, Xiang Wei", + "authors": [ + { + "first_name": "Jingyao", + "last_name": "Xu" + }, + { + "first_name": "Yuetong", + "last_name": "Lu" + }, + { + "first_name": "Yandong", + "last_name": "Li" + }, + { + "first_name": "Siyang", + "last_name": "Lu" + }, + { + "first_name": "Dongdong", + "last_name": "Wang" + }, + { + "first_name": "Xiang", + "last_name": "Wei" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Fairy: Fast Parallelized Instruction-Guided Video-to-Video Synthesis", - "authors": "Bichen Wu, Ching-Yao Chuang, Xiaoyan Wang, Yichen Jia, Kapil Krishnakumar, Tong Xiao, Feng Liang, Licheng Yu, Peter Vajda", + "authors": [ + { + "first_name": "Bichen", + "last_name": "Wu" + }, + { + "first_name": "Ching-Yao", + "last_name": "Chuang" + }, + { + "first_name": "Xiaoyan", + "last_name": "Wang" + }, + { + "first_name": "Yichen", + "last_name": "Jia" + }, + { + "first_name": "Kapil", + "last_name": "Krishnakumar" + }, + { + "first_name": "Tong", + "last_name": "Xiao" + }, + { + "first_name": "Feng", + "last_name": "Liang" + }, + { + "first_name": "Licheng", + "last_name": "Yu" + }, + { + "first_name": "Peter", + "last_name": "Vajda" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models", - "authors": "Yuzhou Huang, Liangbin Xie, Xintao Wang, Ziyang Yuan, Xiaodong Cun, Yixiao Ge, Jiantao Zhou, Chao Dong, Rui Huang, Ruimao Zhang, Ying Shan", + "authors": [ + { + "first_name": "Yuzhou", + "last_name": "Huang" + }, + { + "first_name": "Liangbin", + "last_name": "Xie" + }, + { + "first_name": "Xintao", + "last_name": "Wang" + }, + { + "first_name": "Ziyang", + "last_name": "Yuan" + }, + { + "first_name": "Xiaodong", + "last_name": "Cun" + }, + { + "first_name": "Yixiao", + "last_name": "Ge" + }, + { + "first_name": "Jiantao", + "last_name": "Zhou" + }, + { + "first_name": "Chao", + "last_name": "Dong" + }, + { + "first_name": "Rui", + "last_name": "Huang" + }, + { + "first_name": "Ruimao", + "last_name": "Zhang" + }, + { + "first_name": "Ying", + "last_name": "Shan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SeNM-VAE: Semi-Supervised Noise Modeling with Hierarchical Variational Autoencoder", - "authors": "Dihan Zheng, Yihang Zou, Xiaowen Zhang, Chenglong Bao", + "authors": [ + { + "first_name": "Dihan", + "last_name": "Zheng" + }, + { + "first_name": "Yihang", + "last_name": "Zou" + }, + { + "first_name": "Xiaowen", + "last_name": "Zhang" + }, + { + "first_name": "Chenglong", + "last_name": "Bao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Multimodal Industrial Anomaly Detection by Crossmodal Feature Mapping", - "authors": "Alex Costanzino, Pierluigi Zama Ramirez, Giuseppe Lisanti, Luigi Di Stefano", + "authors": [ + { + "first_name": "Alex", + "last_name": "Costanzino" + }, + { + "first_name": "Pierluigi", + "last_name": "Zama Ramirez" + }, + { + "first_name": "Giuseppe", + "last_name": "Lisanti" + }, + { + "first_name": "Luigi", + "last_name": "Di Stefano" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FFF: Fixing Flawed Foundations in Contrastive Pre-Training Results in Very Strong Vision-Language Models", - "authors": "Adrian Bulat, Yassine Ouali, Georgios Tzimiropoulos", + "authors": [ + { + "first_name": "Adrian", + "last_name": "Bulat" + }, + { + "first_name": "Yassine", + "last_name": "Ouali" + }, + { + "first_name": "Georgios", + "last_name": "Tzimiropoulos" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Anchor-based Robust Finetuning of Vision-Language Models", - "authors": "Jinwei Han, Zhiwen Lin, Zhongyisun Sun, Yingguo Gao, Ke Yan, Shouhong Ding, Yuan Gao, Gui-Song Xia", + "authors": [ + { + "first_name": "Jinwei", + "last_name": "Han" + }, + { + "first_name": "Zhiwen", + "last_name": "Lin" + }, + { + "first_name": "Zhongyisun", + "last_name": "Sun" + }, + { + "first_name": "Yingguo", + "last_name": "Gao" + }, + { + "first_name": "Ke", + "last_name": "Yan" + }, + { + "first_name": "Shouhong", + "last_name": "Ding" + }, + { + "first_name": "Yuan", + "last_name": "Gao" + }, + { + "first_name": "Gui-Song", + "last_name": "Xia" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Low-power Continuous Remote Behavioral Localization with Event Cameras", - "authors": "Friedhelm Hamann, Suman Ghosh, Ignacio Juarez Martinez, Tom Hart, Alex Kacelnik, Guillermo Gallego", + "authors": [ + { + "first_name": "Friedhelm", + "last_name": "Hamann" + }, + { + "first_name": "Suman", + "last_name": "Ghosh" + }, + { + "first_name": "Ignacio", + "last_name": "Juarez Martinez" + }, + { + "first_name": "Tom", + "last_name": "Hart" + }, + { + "first_name": "Alex", + "last_name": "Kacelnik" + }, + { + "first_name": "Guillermo", + "last_name": "Gallego" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SportsHHI: A Dataset for Human-Human Interaction Detection in Sports Videos", - "authors": "Tao Wu, Runyu He, Gangshan Wu, Limin Wang", + "authors": [ + { + "first_name": "Tao", + "last_name": "Wu" + }, + { + "first_name": "Runyu", + "last_name": "He" + }, + { + "first_name": "Gangshan", + "last_name": "Wu" + }, + { + "first_name": "Limin", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DiSR-NeRF: Diffusion-Guided View-Consistent Super-Resolution NeRF", - "authors": "Jie Long Lee, Chen Li, Gim Hee Lee", + "authors": [ + { + "first_name": "Jie", + "last_name": "Long Lee" + }, + { + "first_name": "Chen", + "last_name": "Li" + }, + { + "first_name": "Gim", + "last_name": "Hee Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Dispersed Structured Light for Hyperspectral 3D Imaging", - "authors": "Suhyun Shin, Seokjun Choi, Felix Heide, Seung-Hwan Baek", + "authors": [ + { + "first_name": "Suhyun", + "last_name": "Shin" + }, + { + "first_name": "Seokjun", + "last_name": "Choi" + }, + { + "first_name": "Felix", + "last_name": "Heide" + }, + { + "first_name": "Seung-Hwan", + "last_name": "Baek" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CrowdDiff: Multi-hypothesis Crowd Density Estimation using Diffusion Models", - "authors": "Yasiru Ranasinghe, Nithin Gopalakrishnan Nair, Wele Gedara Chaminda Bandara, Vishal M. Patel", + "authors": [ + { + "first_name": "Yasiru", + "last_name": "Ranasinghe" + }, + { + "first_name": "Nithin", + "last_name": "Gopalakrishnan Nair" + }, + { + "first_name": "Wele", + "last_name": "Gedara Chaminda Bandara" + }, + { + "first_name": "Vishal", + "last_name": "M. Patel" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "It's All About Your Sketch: Democratising Sketch Control in Diffusion Models", - "authors": "Subhadeep Koley, Ayan Kumar Bhunia, Deeptanshu Sekhri, Aneeshan Sain, Pinaki Nath Chowdhury, Tao Xiang, Yi-Zhe Song", + "authors": [ + { + "first_name": "Subhadeep", + "last_name": "Koley" + }, + { + "first_name": "Ayan", + "last_name": "Kumar Bhunia" + }, + { + "first_name": "Deeptanshu", + "last_name": "Sekhri" + }, + { + "first_name": "Aneeshan", + "last_name": "Sain" + }, + { + "first_name": "Pinaki", + "last_name": "Nath Chowdhury" + }, + { + "first_name": "Tao", + "last_name": "Xiang" + }, + { + "first_name": "Yi-Zhe", + "last_name": "Song" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GLID: Pre-training a Generalist Encoder-Decoder Vision Model", - "authors": "Jihao Liu, Jinliang Zheng, Yu Liu, Hongsheng Li", + "authors": [ + { + "first_name": "Jihao", + "last_name": "Liu" + }, + { + "first_name": "Jinliang", + "last_name": "Zheng" + }, + { + "first_name": "Yu", + "last_name": "Liu" + }, + { + "first_name": "Hongsheng", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Diffusion-FOF: Single-View Clothed Human Reconstruction via Diffusion-Based Fourier Occupancy Field", - "authors": "Yuanzhen Li, Fei Luo, Chunxia Xiao", + "authors": [ + { + "first_name": "Yuanzhen", + "last_name": "Li" + }, + { + "first_name": "Fei", + "last_name": "Luo" + }, + { + "first_name": "Chunxia", + "last_name": "Xiao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "When StyleGAN Meets Stable Diffusion: a W+ Adapter for Personalized Image Generation", - "authors": "Xiaoming Li, Xinyu Hou, Chen Change Loy", + "authors": [ + { + "first_name": "Xiaoming", + "last_name": "Li" + }, + { + "first_name": "Xinyu", + "last_name": "Hou" + }, + { + "first_name": "Chen", + "last_name": "Change Loy" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ToNNO: Tomographic Reconstruction of a Neural Network's Output for Weakly Supervised Segmentation of 3D Medical Images", - "authors": "Marius Schmidt-Mengin, Alexis Benichoux, Shibeshih Belachew, Nikos Komodakis, Nikos Paragios", + "authors": [ + { + "first_name": "Marius", + "last_name": "Schmidt-Mengin" + }, + { + "first_name": "Alexis", + "last_name": "Benichoux" + }, + { + "first_name": "Shibeshih", + "last_name": "Belachew" + }, + { + "first_name": "Nikos", + "last_name": "Komodakis" + }, + { + "first_name": "Nikos", + "last_name": "Paragios" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning to Navigate Efficiently and Precisely in Real Environments", - "authors": "Guillaume Bono, Hervé Poirier, Leonid Antsfeld, Gianluca Monaci, Boris Chidlovskii, Christian Wolf", + "authors": [ + { + "first_name": "Guillaume", + "last_name": "Bono" + }, + { + "first_name": "Hervé", + "last_name": "Poirier" + }, + { + "first_name": "Leonid", + "last_name": "Antsfeld" + }, + { + "first_name": "Gianluca", + "last_name": "Monaci" + }, + { + "first_name": "Boris", + "last_name": "Chidlovskii" + }, + { + "first_name": "Christian", + "last_name": "Wolf" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CAM Back Again: Large Kernel CNNs from a Weakly Supervised Object Localization Perspective", - "authors": "Shunsuke Yasuki, Masato Taki", + "authors": [ + { + "first_name": "Shunsuke", + "last_name": "Yasuki" + }, + { + "first_name": "Masato", + "last_name": "Taki" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "VkD: Improving Knowledge Distillation using Orthogonal Projections", - "authors": "Roy Miles, Ismail Elezi, Jiankang Deng", + "authors": [ + { + "first_name": "Roy", + "last_name": "Miles" + }, + { + "first_name": "Ismail", + "last_name": "Elezi" + }, + { + "first_name": "Jiankang", + "last_name": "Deng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Putting the Object Back into Video Object Segmentation", - "authors": "Ho Kei Cheng, Seoung Wug Oh, Brian Price, Joon-Young Lee, Alexander Schwing", + "authors": [ + { + "first_name": "Ho", + "last_name": "Kei Cheng" + }, + { + "first_name": "Seoung", + "last_name": "Wug Oh" + }, + { + "first_name": "Brian", + "last_name": "Price" + }, + { + "first_name": "Joon-Young", + "last_name": "Lee" + }, + { + "first_name": "Alexander", + "last_name": "Schwing" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Concept Weaver: Enabling Multi-Concept Fusion in Text-to-Image Models", - "authors": "Gihyun Kwon, Simon Jenni, Dingzeyu Li, Joon-Young Lee, Jong Chul Ye, Fabian Caba Heilbron", + "authors": [ + { + "first_name": "Gihyun", + "last_name": "Kwon" + }, + { + "first_name": "Simon", + "last_name": "Jenni" + }, + { + "first_name": "Dingzeyu", + "last_name": "Li" + }, + { + "first_name": "Joon-Young", + "last_name": "Lee" + }, + { + "first_name": "Jong", + "last_name": "Chul Ye" + }, + { + "first_name": "Fabian", + "last_name": "Caba Heilbron" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PKU-DyMVHumans: A Multi-View Video Benchmark for High-Fidelity Dynamic Human Modeling", - "authors": "Xiaoyun Zheng, Liwei Liao, Xufeng Li, Jianbo Jiao, Rongjie Wang, Feng Gao, Shiqi Wang, Ronggang Wang", + "authors": [ + { + "first_name": "Xiaoyun", + "last_name": "Zheng" + }, + { + "first_name": "Liwei", + "last_name": "Liao" + }, + { + "first_name": "Xufeng", + "last_name": "Li" + }, + { + "first_name": "Jianbo", + "last_name": "Jiao" + }, + { + "first_name": "Rongjie", + "last_name": "Wang" + }, + { + "first_name": "Feng", + "last_name": "Gao" + }, + { + "first_name": "Shiqi", + "last_name": "Wang" + }, + { + "first_name": "Ronggang", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Cross-Domain Few-Shot Segmentation via Iterative Support-Query Correspondence Mining", - "authors": "Jiahao Nie, Yun Xing, Gongjie Zhang, Pei Yan, Aoran Xiao, Yap-Peng Tan, Alex C. Kot, Shijian Lu", + "authors": [ + { + "first_name": "Jiahao", + "last_name": "Nie" + }, + { + "first_name": "Yun", + "last_name": "Xing" + }, + { + "first_name": "Gongjie", + "last_name": "Zhang" + }, + { + "first_name": "Pei", + "last_name": "Yan" + }, + { + "first_name": "Aoran", + "last_name": "Xiao" + }, + { + "first_name": "Yap-Peng", + "last_name": "Tan" + }, + { + "first_name": "Alex", + "last_name": "C. Kot" + }, + { + "first_name": "Shijian", + "last_name": "Lu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CausalPC: Improving the Robustness of Point Cloud Classification by Causal Effect Identification", - "authors": "Yuanmin Huang, Mi Zhang, Daizong Ding, Erling Jiang, Zhaoxiang Wang, Min Yang", + "authors": [ + { + "first_name": "Yuanmin", + "last_name": "Huang" + }, + { + "first_name": "Mi", + "last_name": "Zhang" + }, + { + "first_name": "Daizong", + "last_name": "Ding" + }, + { + "first_name": "Erling", + "last_name": "Jiang" + }, + { + "first_name": "Zhaoxiang", + "last_name": "Wang" + }, + { + "first_name": "Min", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LASA: Instance Reconstruction from Real Scans using A Large-scale Aligned Shape Annotation Dataset", - "authors": "Haolin Liu, Chongjie Ye, Yinyu Nie, Yingfan He, Xiaoguang Han", + "authors": [ + { + "first_name": "Haolin", + "last_name": "Liu" + }, + { + "first_name": "Chongjie", + "last_name": "Ye" + }, + { + "first_name": "Yinyu", + "last_name": "Nie" + }, + { + "first_name": "Yingfan", + "last_name": "He" + }, + { + "first_name": "Xiaoguang", + "last_name": "Han" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LaRE^2: Latent Reconstruction Error Based Method for Diffusion-Generated Image Detection", - "authors": "Yunpeng Luo, Junlong Du, Ke Yan, Shouhong Ding", + "authors": [ + { + "first_name": "Yunpeng", + "last_name": "Luo" + }, + { + "first_name": "Junlong", + "last_name": "Du" + }, + { + "first_name": "Ke", + "last_name": "Yan" + }, + { + "first_name": "Shouhong", + "last_name": "Ding" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DiffSCI: Zero-Shot Snapshot Compressive Imaging via Iterative Spectral Diffusion Model", - "authors": "Zhenghao Pan, Haijin Zeng, Jiezhang Cao, Kai Zhang, Yongyong Chen", + "authors": [ + { + "first_name": "Zhenghao", + "last_name": "Pan" + }, + { + "first_name": "Haijin", + "last_name": "Zeng" + }, + { + "first_name": "Jiezhang", + "last_name": "Cao" + }, + { + "first_name": "Kai", + "last_name": "Zhang" + }, + { + "first_name": "Yongyong", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation", - "authors": "Junming Chen, Yunfei Liu, Jianan Wang, Ailing Zeng, Yu Li, Qifeng Chen", + "authors": [ + { + "first_name": "Junming", + "last_name": "Chen" + }, + { + "first_name": "Yunfei", + "last_name": "Liu" + }, + { + "first_name": "Jianan", + "last_name": "Wang" + }, + { + "first_name": "Ailing", + "last_name": "Zeng" + }, + { + "first_name": "Yu", + "last_name": "Li" + }, + { + "first_name": "Qifeng", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MeLFusion: Synthesizing Music from Image and Language Cues using Diffusion Models", - "authors": "Sanjoy Chowdhury, Sayan Nag, K J Joseph, Balaji Vasan Srinivasan, Dinesh Manocha", + "authors": [ + { + "first_name": "Sanjoy", + "last_name": "Chowdhury" + }, + { + "first_name": "Sayan", + "last_name": "Nag" + }, + { + "first_name": "K", + "last_name": "J Joseph" + }, + { + "first_name": "Balaji", + "last_name": "Vasan Srinivasan" + }, + { + "first_name": "Dinesh", + "last_name": "Manocha" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "T4P: Test-Time Training of Trajectory Prediction via Masked Autoencoder and Actor-specific Token Memory", - "authors": "Daehee Park, Jaeseok Jeong, Sung-Hoon Yoon, Jaewoo Jeong, Kuk-Jin Yoon", + "authors": [ + { + "first_name": "Daehee", + "last_name": "Park" + }, + { + "first_name": "Jaeseok", + "last_name": "Jeong" + }, + { + "first_name": "Sung-Hoon", + "last_name": "Yoon" + }, + { + "first_name": "Jaewoo", + "last_name": "Jeong" + }, + { + "first_name": "Kuk-Jin", + "last_name": "Yoon" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Noisy-Correspondence Learning for Text-to-Image Person Re-identification", - "authors": "Yang Qin, Yingke Chen, Dezhong Peng, Xi Peng, Joey Tianyi Zhou, Peng Hu", + "authors": [ + { + "first_name": "Yang", + "last_name": "Qin" + }, + { + "first_name": "Yingke", + "last_name": "Chen" + }, + { + "first_name": "Dezhong", + "last_name": "Peng" + }, + { + "first_name": "Xi", + "last_name": "Peng" + }, + { + "first_name": "Joey", + "last_name": "Tianyi Zhou" + }, + { + "first_name": "Peng", + "last_name": "Hu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "InstaGen: Enhancing Object Detection by Training on Synthetic Dataset", - "authors": "Chengjian Feng, Yujie Zhong, Zequn Jie, Weidi Xie, Lin Ma", + "authors": [ + { + "first_name": "Chengjian", + "last_name": "Feng" + }, + { + "first_name": "Yujie", + "last_name": "Zhong" + }, + { + "first_name": "Zequn", + "last_name": "Jie" + }, + { + "first_name": "Weidi", + "last_name": "Xie" + }, + { + "first_name": "Lin", + "last_name": "Ma" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PanoRecon: Real-Time Panoptic 3D Reconstruction from Monocular Video", - "authors": "Dong Wu, Zike Yan, Hongbin Zha", + "authors": [ + { + "first_name": "Dong", + "last_name": "Wu" + }, + { + "first_name": "Zike", + "last_name": "Yan" + }, + { + "first_name": "Hongbin", + "last_name": "Zha" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Animating General Image with Large Visual Motion Model", - "authors": "Dengsheng Chen, Xiaoming Wei, Xiaolin Wei", + "authors": [ + { + "first_name": "Dengsheng", + "last_name": "Chen" + }, + { + "first_name": "Xiaoming", + "last_name": "Wei" + }, + { + "first_name": "Xiaolin", + "last_name": "Wei" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Visual Point Cloud Forecasting enables Scalable Autonomous Driving", - "authors": "Zetong Yang, Li Chen, Yanan Sun, Hongyang Li", + "authors": [ + { + "first_name": "Zetong", + "last_name": "Yang" + }, + { + "first_name": "Li", + "last_name": "Chen" + }, + { + "first_name": "Yanan", + "last_name": "Sun" + }, + { + "first_name": "Hongyang", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards Transferable Targeted 3D Adversarial Attack in the Physical World", - "authors": "Yao Huang, Yinpeng Dong, Shouwei Ruan, Xiao Yang, Hang Su, Xingxing Wei", + "authors": [ + { + "first_name": "Yao", + "last_name": "Huang" + }, + { + "first_name": "Yinpeng", + "last_name": "Dong" + }, + { + "first_name": "Shouwei", + "last_name": "Ruan" + }, + { + "first_name": "Xiao", + "last_name": "Yang" + }, + { + "first_name": "Hang", + "last_name": "Su" + }, + { + "first_name": "Xingxing", + "last_name": "Wei" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SwitchLight: Co-design of Physics-driven Architecture and Pre-training Framework for Human Portrait Relighting", - "authors": "Hoon Kim, Minje Jang, Wonjun Yoon, Jisoo Lee, Donghyun Na, Sanghyun Woo", + "authors": [ + { + "first_name": "Hoon", + "last_name": "Kim" + }, + { + "first_name": "Minje", + "last_name": "Jang" + }, + { + "first_name": "Wonjun", + "last_name": "Yoon" + }, + { + "first_name": "Jisoo", + "last_name": "Lee" + }, + { + "first_name": "Donghyun", + "last_name": "Na" + }, + { + "first_name": "Sanghyun", + "last_name": "Woo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DIRECT-3D: Learning Direct Text-to-3D Generation on Massive Noisy 3D Data", - "authors": "Qihao Liu, Yi Zhang, Song Bai, Adam Kortylewski, Alan Yuille", + "authors": [ + { + "first_name": "Qihao", + "last_name": "Liu" + }, + { + "first_name": "Yi", + "last_name": "Zhang" + }, + { + "first_name": "Song", + "last_name": "Bai" + }, + { + "first_name": "Adam", + "last_name": "Kortylewski" + }, + { + "first_name": "Alan", + "last_name": "Yuille" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Synthesize Step-by-Step: Tools Templates and LLMs as Data Generators for Reasoning-Based Chart VQA", - "authors": "Zhuowan Li, Bhavan Jasani, Peng Tang, Shabnam Ghadar", + "authors": [ + { + "first_name": "Zhuowan", + "last_name": "Li" + }, + { + "first_name": "Bhavan", + "last_name": "Jasani" + }, + { + "first_name": "Peng", + "last_name": "Tang" + }, + { + "first_name": "Shabnam", + "last_name": "Ghadar" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understanding", - "authors": "Chuwei Luo, Yufan Shen, Zhaoqing Zhu, Qi Zheng, Zhi Yu, Cong Yao", + "authors": [ + { + "first_name": "Chuwei", + "last_name": "Luo" + }, + { + "first_name": "Yufan", + "last_name": "Shen" + }, + { + "first_name": "Zhaoqing", + "last_name": "Zhu" + }, + { + "first_name": "Qi", + "last_name": "Zheng" + }, + { + "first_name": "Zhi", + "last_name": "Yu" + }, + { + "first_name": "Cong", + "last_name": "Yao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ProTeCt: Prompt Tuning for Taxonomic Open Set Classification", - "authors": "Tz-Ying Wu, Chih-Hui Ho, Nuno Vasconcelos", + "authors": [ + { + "first_name": "Tz-Ying", + "last_name": "Wu" + }, + { + "first_name": "Chih-Hui", + "last_name": "Ho" + }, + { + "first_name": "Nuno", + "last_name": "Vasconcelos" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Adapters Strike Back", - "authors": "Jan-Martin O. Steitz, Stefan Roth", + "authors": [ + { + "first_name": "Jan-Martin", + "last_name": "O. Steitz" + }, + { + "first_name": "Stefan", + "last_name": "Roth" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Masked Autoencoders for Microscopy are Scalable Learners of Cellular Biology", - "authors": "Oren Kraus, Kian Kenyon-Dean, Saber Saberian, Maryam Fallah, Peter McLean, Jess Leung, Vasudev Sharma, Ayla Khan, Jia Balakrishnan, Safiye Celik, Dominique Beaini, Maciej Sypetkowski, Chi Vicky Cheng, Kristen Morse, Maureen Makes, Ben Mabey, Berton Earnshaw", + "authors": [ + { + "first_name": "Oren", + "last_name": "Kraus" + }, + { + "first_name": "Kian", + "last_name": "Kenyon-Dean" + }, + { + "first_name": "Saber", + "last_name": "Saberian" + }, + { + "first_name": "Maryam", + "last_name": "Fallah" + }, + { + "first_name": "Peter", + "last_name": "McLean" + }, + { + "first_name": "Jess", + "last_name": "Leung" + }, + { + "first_name": "Vasudev", + "last_name": "Sharma" + }, + { + "first_name": "Ayla", + "last_name": "Khan" + }, + { + "first_name": "Jia", + "last_name": "Balakrishnan" + }, + { + "first_name": "Safiye", + "last_name": "Celik" + }, + { + "first_name": "Dominique", + "last_name": "Beaini" + }, + { + "first_name": "Maciej", + "last_name": "Sypetkowski" + }, + { + "first_name": "Chi", + "last_name": "Vicky Cheng" + }, + { + "first_name": "Kristen", + "last_name": "Morse" + }, + { + "first_name": "Maureen", + "last_name": "Makes" + }, + { + "first_name": "Ben", + "last_name": "Mabey" + }, + { + "first_name": "Berton", + "last_name": "Earnshaw" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "OHTA: One-shot Hand Avatar via Data-driven Implicit Priors", - "authors": "Xiaozheng Zheng, Chao Wen, Zhuo Su, Zeran Xu, Zhaohu Li, Yang Zhao, Zhou Xue", + "authors": [ + { + "first_name": "Xiaozheng", + "last_name": "Zheng" + }, + { + "first_name": "Chao", + "last_name": "Wen" + }, + { + "first_name": "Zhuo", + "last_name": "Su" + }, + { + "first_name": "Zeran", + "last_name": "Xu" + }, + { + "first_name": "Zhaohu", + "last_name": "Li" + }, + { + "first_name": "Yang", + "last_name": "Zhao" + }, + { + "first_name": "Zhou", + "last_name": "Xue" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Segment and Caption Anything", - "authors": "Xiaoke Huang, Jianfeng Wang, Yansong Tang, Zheng Zhang, Han Hu, Jiwen Lu, Lijuan Wang, Zicheng Liu", + "authors": [ + { + "first_name": "Xiaoke", + "last_name": "Huang" + }, + { + "first_name": "Jianfeng", + "last_name": "Wang" + }, + { + "first_name": "Yansong", + "last_name": "Tang" + }, + { + "first_name": "Zheng", + "last_name": "Zhang" + }, + { + "first_name": "Han", + "last_name": "Hu" + }, + { + "first_name": "Jiwen", + "last_name": "Lu" + }, + { + "first_name": "Lijuan", + "last_name": "Wang" + }, + { + "first_name": "Zicheng", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Human Motion Prediction Under Unexpected Perturbation", - "authors": "Jiangbei Yue, Baiyi Li, Julien Pettré, Armin Seyfried, He Wang", + "authors": [ + { + "first_name": "Jiangbei", + "last_name": "Yue" + }, + { + "first_name": "Baiyi", + "last_name": "Li" + }, + { + "first_name": "Julien", + "last_name": "Pettré" + }, + { + "first_name": "Armin", + "last_name": "Seyfried" + }, + { + "first_name": "He", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Text-to-3D Generation with Bidirectional Diffusion using both 2D and 3D priors", - "authors": "Lihe Ding, Shaocong Dong, Zhanpeng Huang, Zibin Wang, Yiyuan Zhang, Kaixiong Gong, Dan Xu, Tianfan Xue", + "authors": [ + { + "first_name": "Lihe", + "last_name": "Ding" + }, + { + "first_name": "Shaocong", + "last_name": "Dong" + }, + { + "first_name": "Zhanpeng", + "last_name": "Huang" + }, + { + "first_name": "Zibin", + "last_name": "Wang" + }, + { + "first_name": "Yiyuan", + "last_name": "Zhang" + }, + { + "first_name": "Kaixiong", + "last_name": "Gong" + }, + { + "first_name": "Dan", + "last_name": "Xu" + }, + { + "first_name": "Tianfan", + "last_name": "Xue" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CLIP-Driven Open-Vocabulary 3D Scene Graph Generation via Cross-Modality Contrastive Learning", - "authors": "Lianggangxu Chen, Xuejiao Wang, Jiale Lu, Shaohui Lin, Changbo Wang, Gaoqi He", + "authors": [ + { + "first_name": "Lianggangxu", + "last_name": "Chen" + }, + { + "first_name": "Xuejiao", + "last_name": "Wang" + }, + { + "first_name": "Jiale", + "last_name": "Lu" + }, + { + "first_name": "Shaohui", + "last_name": "Lin" + }, + { + "first_name": "Changbo", + "last_name": "Wang" + }, + { + "first_name": "Gaoqi", + "last_name": "He" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Adversarial Backdoor Attack by Naturalistic Data Poisoning on Trajectory Prediction in Autonomous Driving", - "authors": "Mozhgan Pourkeshavarz, Mohammad Sabokrou, Amir Rasouli", + "authors": [ + { + "first_name": "Mozhgan", + "last_name": "Pourkeshavarz" + }, + { + "first_name": "Mohammad", + "last_name": "Sabokrou" + }, + { + "first_name": "Amir", + "last_name": "Rasouli" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Make-It-Vivid: Dressing Your Animatable Biped Cartoon Characters from Text", - "authors": "Junshu Tang, Yanhong Zeng, Ke Fan, Xuheng Wang, Bo Dai, Kai Chen, Lizhuang Ma", + "authors": [ + { + "first_name": "Junshu", + "last_name": "Tang" + }, + { + "first_name": "Yanhong", + "last_name": "Zeng" + }, + { + "first_name": "Ke", + "last_name": "Fan" + }, + { + "first_name": "Xuheng", + "last_name": "Wang" + }, + { + "first_name": "Bo", + "last_name": "Dai" + }, + { + "first_name": "Kai", + "last_name": "Chen" + }, + { + "first_name": "Lizhuang", + "last_name": "Ma" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "StraightPCF: Straight Point Cloud Filtering", - "authors": "Dasith de Silva Edirimuni, Xuequan Lu, Gang Li, Lei Wei, Antonio Robles-Kelly, Hongdong Li", + "authors": [ + { + "first_name": "Dasith", + "last_name": "de Silva Edirimuni" + }, + { + "first_name": "Xuequan", + "last_name": "Lu" + }, + { + "first_name": "Gang", + "last_name": "Li" + }, + { + "first_name": "Lei", + "last_name": "Wei" + }, + { + "first_name": "Antonio", + "last_name": "Robles-Kelly" + }, + { + "first_name": "Hongdong", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Mirasol3B: A Multimodal Autoregressive Model for Time-Aligned and Contextual Modalities", - "authors": "AJ Piergiovanni, Isaac Noble, Dahun Kim, Michael S. Ryoo, Victor Gomes, Anelia Angelova", + "authors": [ + { + "first_name": "AJ", + "last_name": "Piergiovanni" + }, + { + "first_name": "Isaac", + "last_name": "Noble" + }, + { + "first_name": "Dahun", + "last_name": "Kim" + }, + { + "first_name": "Michael", + "last_name": "S. Ryoo" + }, + { + "first_name": "Victor", + "last_name": "Gomes" + }, + { + "first_name": "Anelia", + "last_name": "Angelova" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Neural Sign Actors: A Diffusion Model for 3D Sign Language Production from Text", - "authors": "Vasileios Baltatzis, Rolandos Alexandros Potamias, Evangelos Ververas, Guanxiong Sun, Jiankang Deng, Stefanos Zafeiriou", + "authors": [ + { + "first_name": "Vasileios", + "last_name": "Baltatzis" + }, + { + "first_name": "Rolandos", + "last_name": "Alexandros Potamias" + }, + { + "first_name": "Evangelos", + "last_name": "Ververas" + }, + { + "first_name": "Guanxiong", + "last_name": "Sun" + }, + { + "first_name": "Jiankang", + "last_name": "Deng" + }, + { + "first_name": "Stefanos", + "last_name": "Zafeiriou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation Paradigm", - "authors": "Peng Sun, Bei Shi, Daiwei Yu, Tao Lin", + "authors": [ + { + "first_name": "Peng", + "last_name": "Sun" + }, + { + "first_name": "Bei", + "last_name": "Shi" + }, + { + "first_name": "Daiwei", + "last_name": "Yu" + }, + { + "first_name": "Tao", + "last_name": "Lin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Semantics-aware Motion Retargeting with Vision-Language Models", - "authors": "Haodong Zhang, Zhike Chen, Haocheng Xu, Lei Hao, Xiaofei Wu, Songcen Xu, Zhensong Zhang, Yue Wang, Rong Xiong", + "authors": [ + { + "first_name": "Haodong", + "last_name": "Zhang" + }, + { + "first_name": "Zhike", + "last_name": "Chen" + }, + { + "first_name": "Haocheng", + "last_name": "Xu" + }, + { + "first_name": "Lei", + "last_name": "Hao" + }, + { + "first_name": "Xiaofei", + "last_name": "Wu" + }, + { + "first_name": "Songcen", + "last_name": "Xu" + }, + { + "first_name": "Zhensong", + "last_name": "Zhang" + }, + { + "first_name": "Yue", + "last_name": "Wang" + }, + { + "first_name": "Rong", + "last_name": "Xiong" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Semantically-Shifted Incremental Adapter-Tuning is A Continual ViTransformer", - "authors": "Yuwen Tan, Qinhao Zhou, Xiang Xiang, Ke Wang, Yuchuan Wu, Yongbin Li", + "authors": [ + { + "first_name": "Yuwen", + "last_name": "Tan" + }, + { + "first_name": "Qinhao", + "last_name": "Zhou" + }, + { + "first_name": "Xiang", + "last_name": "Xiang" + }, + { + "first_name": "Ke", + "last_name": "Wang" + }, + { + "first_name": "Yuchuan", + "last_name": "Wu" + }, + { + "first_name": "Yongbin", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Low-Rank Approximation for Sparse Attention in Multi-Modal LLMs", - "authors": "Lin Song, Yukang Chen, Shuai Yang, Xiaohan Ding, Yixiao Ge, Ying-Cong Chen, Ying Shan", + "authors": [ + { + "first_name": "Lin", + "last_name": "Song" + }, + { + "first_name": "Yukang", + "last_name": "Chen" + }, + { + "first_name": "Shuai", + "last_name": "Yang" + }, + { + "first_name": "Xiaohan", + "last_name": "Ding" + }, + { + "first_name": "Yixiao", + "last_name": "Ge" + }, + { + "first_name": "Ying-Cong", + "last_name": "Chen" + }, + { + "first_name": "Ying", + "last_name": "Shan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "TASeg: Temporal Aggregation Network for LiDAR Semantic Segmentation", - "authors": "Xiaopei Wu, Yuenan Hou, Xiaoshui Huang, Binbin Lin, Tong He, Xinge Zhu, Yuexin Ma, Boxi Wu, Haifeng Liu, Deng Cai, Wanli Ouyang", + "authors": [ + { + "first_name": "Xiaopei", + "last_name": "Wu" + }, + { + "first_name": "Yuenan", + "last_name": "Hou" + }, + { + "first_name": "Xiaoshui", + "last_name": "Huang" + }, + { + "first_name": "Binbin", + "last_name": "Lin" + }, + { + "first_name": "Tong", + "last_name": "He" + }, + { + "first_name": "Xinge", + "last_name": "Zhu" + }, + { + "first_name": "Yuexin", + "last_name": "Ma" + }, + { + "first_name": "Boxi", + "last_name": "Wu" + }, + { + "first_name": "Haifeng", + "last_name": "Liu" + }, + { + "first_name": "Deng", + "last_name": "Cai" + }, + { + "first_name": "Wanli", + "last_name": "Ouyang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Bootstrapping SparseFormers from Vision Foundation Models", - "authors": "Ziteng Gao, Zhan Tong, Kevin Qinghong Lin, Joya Chen, Mike Zheng Shou", + "authors": [ + { + "first_name": "Ziteng", + "last_name": "Gao" + }, + { + "first_name": "Zhan", + "last_name": "Tong" + }, + { + "first_name": "Kevin", + "last_name": "Qinghong Lin" + }, + { + "first_name": "Joya", + "last_name": "Chen" + }, + { + "first_name": "Mike", + "last_name": "Zheng Shou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "EventPS: Real-Time Photometric Stereo Using an Event Camera", - "authors": "Bohan Yu, Jieji Ren, Jin Han, Feishi Wang, Jinxiu Liang, Boxin Shi", + "authors": [ + { + "first_name": "Bohan", + "last_name": "Yu" + }, + { + "first_name": "Jieji", + "last_name": "Ren" + }, + { + "first_name": "Jin", + "last_name": "Han" + }, + { + "first_name": "Feishi", + "last_name": "Wang" + }, + { + "first_name": "Jinxiu", + "last_name": "Liang" + }, + { + "first_name": "Boxin", + "last_name": "Shi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Unsupervised Semantic Segmentation Through Depth-Guided Feature Correlation and Sampling", - "authors": "Leon Sick, Dominik Engel, Pedro Hermosilla, Timo Ropinski", + "authors": [ + { + "first_name": "Leon", + "last_name": "Sick" + }, + { + "first_name": "Dominik", + "last_name": "Engel" + }, + { + "first_name": "Pedro", + "last_name": "Hermosilla" + }, + { + "first_name": "Timo", + "last_name": "Ropinski" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "On the Road to Portability: Compressing End-to-End Motion Planner for Autonomous Driving", - "authors": "Kaituo Feng, Changsheng Li, Dongchun Ren, Ye Yuan, Guoren Wang", + "authors": [ + { + "first_name": "Kaituo", + "last_name": "Feng" + }, + { + "first_name": "Changsheng", + "last_name": "Li" + }, + { + "first_name": "Dongchun", + "last_name": "Ren" + }, + { + "first_name": "Ye", + "last_name": "Yuan" + }, + { + "first_name": "Guoren", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "RAVE: Randomized Noise Shuffling for Fast and Consistent Video Editing with Diffusion Models", - "authors": "Ozgur Kara, Bariscan Kurtkaya, Hidir Yesiltepe, James M. Rehg, Pinar Yanardag", + "authors": [ + { + "first_name": "Ozgur", + "last_name": "Kara" + }, + { + "first_name": "Bariscan", + "last_name": "Kurtkaya" + }, + { + "first_name": "Hidir", + "last_name": "Yesiltepe" + }, + { + "first_name": "James", + "last_name": "M. Rehg" + }, + { + "first_name": "Pinar", + "last_name": "Yanardag" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PredToken: Predicting Unknown Tokens and Beyond with Coarse-to-Fine Iterative Decoding", - "authors": "Xuesong Nie, Haoyuan Jin, Yunfeng Yan, Xi Chen, Zhihang Zhu, Donglian Qi", + "authors": [ + { + "first_name": "Xuesong", + "last_name": "Nie" + }, + { + "first_name": "Haoyuan", + "last_name": "Jin" + }, + { + "first_name": "Yunfeng", + "last_name": "Yan" + }, + { + "first_name": "Xi", + "last_name": "Chen" + }, + { + "first_name": "Zhihang", + "last_name": "Zhu" + }, + { + "first_name": "Donglian", + "last_name": "Qi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Video-Based Human Pose Regression via Decoupled Space-Time Aggregation", - "authors": "Jijie He, Wenwu Yang", + "authors": [ + { + "first_name": "Jijie", + "last_name": "He" + }, + { + "first_name": "Wenwu", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "L-MAGIC: Language Model Assisted Generation of Images with Coherence", - "authors": "Zhipeng Cai, Matthias Mueller, Reiner Birkl, Diana Wofk, Shao-Yen Tseng, Junda Cheng, Gabriela Ben-Melech Stan, Vasudev Lai, Michael Paulitsch", + "authors": [ + { + "first_name": "Zhipeng", + "last_name": "Cai" + }, + { + "first_name": "Matthias", + "last_name": "Mueller" + }, + { + "first_name": "Reiner", + "last_name": "Birkl" + }, + { + "first_name": "Diana", + "last_name": "Wofk" + }, + { + "first_name": "Shao-Yen", + "last_name": "Tseng" + }, + { + "first_name": "Junda", + "last_name": "Cheng" + }, + { + "first_name": "Gabriela", + "last_name": "Ben-Melech Stan" + }, + { + "first_name": "Vasudev", + "last_name": "Lai" + }, + { + "first_name": "Michael", + "last_name": "Paulitsch" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "3D Face Tracking from 2D Video through Iterative Dense UV to Image Flow", - "authors": "Felix Taubner, Prashant Raina, Mathieu Tuli, Eu Wern Teh, Chul Lee, Jinmiao Huang", + "authors": [ + { + "first_name": "Felix", + "last_name": "Taubner" + }, + { + "first_name": "Prashant", + "last_name": "Raina" + }, + { + "first_name": "Mathieu", + "last_name": "Tuli" + }, + { + "first_name": "Eu", + "last_name": "Wern Teh" + }, + { + "first_name": "Chul", + "last_name": "Lee" + }, + { + "first_name": "Jinmiao", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Carve3D: Improving Multi-view Reconstruction Consistency for Diffusion Models with RL Finetuning", - "authors": "Desai Xie, Jiahao Li, Hao Tan, Xin Sun, Zhixin Shu, Yi Zhou, Sai Bi, Sören Pirk, Arie E. Kaufman", + "authors": [ + { + "first_name": "Desai", + "last_name": "Xie" + }, + { + "first_name": "Jiahao", + "last_name": "Li" + }, + { + "first_name": "Hao", + "last_name": "Tan" + }, + { + "first_name": "Xin", + "last_name": "Sun" + }, + { + "first_name": "Zhixin", + "last_name": "Shu" + }, + { + "first_name": "Yi", + "last_name": "Zhou" + }, + { + "first_name": "Sai", + "last_name": "Bi" + }, + { + "first_name": "Sören", + "last_name": "Pirk" + }, + { + "first_name": "Arie", + "last_name": "E. Kaufman" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Random Entangled Tokens for Adversarially Robust Vision Transformer", - "authors": "Huihui Gong, Minjing Dong, Siqi Ma, Seyit Camtepe, Surya Nepal, Chang Xu", + "authors": [ + { + "first_name": "Huihui", + "last_name": "Gong" + }, + { + "first_name": "Minjing", + "last_name": "Dong" + }, + { + "first_name": "Siqi", + "last_name": "Ma" + }, + { + "first_name": "Seyit", + "last_name": "Camtepe" + }, + { + "first_name": "Surya", + "last_name": "Nepal" + }, + { + "first_name": "Chang", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Shadow Generation for Composite Image Using Diffusion Model", - "authors": "Qingyang Liu, Junqi You, Jianting Wang, Xinhao Tao, Bo Zhang, Li Niu", + "authors": [ + { + "first_name": "Qingyang", + "last_name": "Liu" + }, + { + "first_name": "Junqi", + "last_name": "You" + }, + { + "first_name": "Jianting", + "last_name": "Wang" + }, + { + "first_name": "Xinhao", + "last_name": "Tao" + }, + { + "first_name": "Bo", + "last_name": "Zhang" + }, + { + "first_name": "Li", + "last_name": "Niu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DisCo: Disentangled Control for Realistic Human Dance Generation", - "authors": "Tan Wang, Linjie Li, Kevin Lin, Yuanhao Zhai, Chung-Ching Lin, Zhengyuan Yang, Hanwang Zhang, Zicheng Liu, Lijuan Wang", + "authors": [ + { + "first_name": "Tan", + "last_name": "Wang" + }, + { + "first_name": "Linjie", + "last_name": "Li" + }, + { + "first_name": "Kevin", + "last_name": "Lin" + }, + { + "first_name": "Yuanhao", + "last_name": "Zhai" + }, + { + "first_name": "Chung-Ching", + "last_name": "Lin" + }, + { + "first_name": "Zhengyuan", + "last_name": "Yang" + }, + { + "first_name": "Hanwang", + "last_name": "Zhang" + }, + { + "first_name": "Zicheng", + "last_name": "Liu" + }, + { + "first_name": "Lijuan", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "L2B: Learning to Bootstrap Robust Models for Combating Label Noise", - "authors": "Yuyin Zhou, Xianhang Li, Fengze Liu, Qingyue Wei, Xuxi Chen, Lequan Yu, Cihang Xie, Matthew P. Lungren, Lei Xing", + "authors": [ + { + "first_name": "Yuyin", + "last_name": "Zhou" + }, + { + "first_name": "Xianhang", + "last_name": "Li" + }, + { + "first_name": "Fengze", + "last_name": "Liu" + }, + { + "first_name": "Qingyue", + "last_name": "Wei" + }, + { + "first_name": "Xuxi", + "last_name": "Chen" + }, + { + "first_name": "Lequan", + "last_name": "Yu" + }, + { + "first_name": "Cihang", + "last_name": "Xie" + }, + { + "first_name": "Matthew", + "last_name": "P. Lungren" + }, + { + "first_name": "Lei", + "last_name": "Xing" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GaussianShader: 3D Gaussian Splatting with Shading Functions for Reflective Surfaces", - "authors": "Yingwenqi Jiang, Jiadong Tu, Yuan Liu, Xifeng Gao, Xiaoxiao Long, Wenping Wang, Yuexin Ma", + "authors": [ + { + "first_name": "Yingwenqi", + "last_name": "Jiang" + }, + { + "first_name": "Jiadong", + "last_name": "Tu" + }, + { + "first_name": "Yuan", + "last_name": "Liu" + }, + { + "first_name": "Xifeng", + "last_name": "Gao" + }, + { + "first_name": "Xiaoxiao", + "last_name": "Long" + }, + { + "first_name": "Wenping", + "last_name": "Wang" + }, + { + "first_name": "Yuexin", + "last_name": "Ma" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Tactile-Augmented Radiance Fields", - "authors": "Yiming Dou, Fengyu Yang, Yi Liu, Antonio Loquercio, Andrew Owens", + "authors": [ + { + "first_name": "Yiming", + "last_name": "Dou" + }, + { + "first_name": "Fengyu", + "last_name": "Yang" + }, + { + "first_name": "Yi", + "last_name": "Liu" + }, + { + "first_name": "Antonio", + "last_name": "Loquercio" + }, + { + "first_name": "Andrew", + "last_name": "Owens" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Intensity-Robust Autofocus for Spike Camera", - "authors": "Changqing Su, Zhiyuan Ye, Yongsheng Xiao, You Zhou, Zhen Cheng, Bo Xiong, Zhaofei Yu, Tiejun Huang", + "authors": [ + { + "first_name": "Changqing", + "last_name": "Su" + }, + { + "first_name": "Zhiyuan", + "last_name": "Ye" + }, + { + "first_name": "Yongsheng", + "last_name": "Xiao" + }, + { + "first_name": "You", + "last_name": "Zhou" + }, + { + "first_name": "Zhen", + "last_name": "Cheng" + }, + { + "first_name": "Bo", + "last_name": "Xiong" + }, + { + "first_name": "Zhaofei", + "last_name": "Yu" + }, + { + "first_name": "Tiejun", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FairCLIP: Harnessing Fairness in Vision-Language Learning", - "authors": "Yan Luo, Min Shi, Muhammad Osama Khan, Muhammad Muneeb Afzal, Hao Huang, Shuaihang Yuan, Yu Tian, Luo Song, Ava Kouhana, Tobias Elze, Yi Fang, Mengyu Wang", + "authors": [ + { + "first_name": "Yan", + "last_name": "Luo" + }, + { + "first_name": "Min", + "last_name": "Shi" + }, + { + "first_name": "Muhammad", + "last_name": "Osama Khan" + }, + { + "first_name": "Muhammad", + "last_name": "Muneeb Afzal" + }, + { + "first_name": "Hao", + "last_name": "Huang" + }, + { + "first_name": "Shuaihang", + "last_name": "Yuan" + }, + { + "first_name": "Yu", + "last_name": "Tian" + }, + { + "first_name": "Luo", + "last_name": "Song" + }, + { + "first_name": "Ava", + "last_name": "Kouhana" + }, + { + "first_name": "Tobias", + "last_name": "Elze" + }, + { + "first_name": "Yi", + "last_name": "Fang" + }, + { + "first_name": "Mengyu", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "StreamingFlow: Streaming Occupancy Forecasting with Asynchronous Multi-modal Data Streams via Neural Ordinary Differential Equation", - "authors": "Yining Shi, Kun Jiang, Ke Wang, Jiusi Li, Yunlong Wang, Mengmeng Yang, Diange Yang", + "authors": [ + { + "first_name": "Yining", + "last_name": "Shi" + }, + { + "first_name": "Kun", + "last_name": "Jiang" + }, + { + "first_name": "Ke", + "last_name": "Wang" + }, + { + "first_name": "Jiusi", + "last_name": "Li" + }, + { + "first_name": "Yunlong", + "last_name": "Wang" + }, + { + "first_name": "Mengmeng", + "last_name": "Yang" + }, + { + "first_name": "Diange", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "pix2gestalt: Amodal Segmentation by Synthesizing Wholes", - "authors": "Ege Ozguroglu, Ruoshi Liu, Dídac Surís, Dian Chen, Achal Dave, Pavel Tokmakov, Carl Vondrick", + "authors": [ + { + "first_name": "Ege", + "last_name": "Ozguroglu" + }, + { + "first_name": "Ruoshi", + "last_name": "Liu" + }, + { + "first_name": "Dídac", + "last_name": "Surís" + }, + { + "first_name": "Dian", + "last_name": "Chen" + }, + { + "first_name": "Achal", + "last_name": "Dave" + }, + { + "first_name": "Pavel", + "last_name": "Tokmakov" + }, + { + "first_name": "Carl", + "last_name": "Vondrick" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Weakly Supervised Point Cloud Semantic Segmentation via Artificial Oracle", - "authors": "Hyeokjun Kweon, Jihun Kim, Kuk-Jin Yoon", + "authors": [ + { + "first_name": "Hyeokjun", + "last_name": "Kweon" + }, + { + "first_name": "Jihun", + "last_name": "Kim" + }, + { + "first_name": "Kuk-Jin", + "last_name": "Yoon" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Language Model Guided Interpretable Video Action Reasoning", - "authors": "Ning Wang, Guangming Zhu, HS Li, Liang Zhang, Syed Afaq Ali Shah, Mohammed Bennamoun", + "authors": [ + { + "first_name": "Ning", + "last_name": "Wang" + }, + { + "first_name": "Guangming", + "last_name": "Zhu" + }, + { + "first_name": "HS", + "last_name": "Li" + }, + { + "first_name": "Liang", + "last_name": "Zhang" + }, + { + "first_name": "Syed", + "last_name": "Afaq Ali Shah" + }, + { + "first_name": "Mohammed", + "last_name": "Bennamoun" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Forecasting of 3D Whole-body Human Poses with Grasping Objects", - "authors": "Haitao Yan, Qiongjie Cui, Jiexin Xie, Shijie Guo", + "authors": [ + { + "first_name": "Haitao", + "last_name": "Yan" + }, + { + "first_name": "Qiongjie", + "last_name": "Cui" + }, + { + "first_name": "Jiexin", + "last_name": "Xie" + }, + { + "first_name": "Shijie", + "last_name": "Guo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Prediction", - "authors": "Qihang Ma, Xin Tan, Yanyun Qu, Lizhuang Ma, Zhizhong Zhang, Yuan Xie", + "authors": [ + { + "first_name": "Qihang", + "last_name": "Ma" + }, + { + "first_name": "Xin", + "last_name": "Tan" + }, + { + "first_name": "Yanyun", + "last_name": "Qu" + }, + { + "first_name": "Lizhuang", + "last_name": "Ma" + }, + { + "first_name": "Zhizhong", + "last_name": "Zhang" + }, + { + "first_name": "Yuan", + "last_name": "Xie" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Accelerating Diffusion Sampling with Optimized Time Steps", - "authors": "Shuchen Xue, Zhaoqiang Liu, Fei Chen, Shifeng Zhang, Tianyang Hu, Enze Xie, Zhenguo Li", + "authors": [ + { + "first_name": "Shuchen", + "last_name": "Xue" + }, + { + "first_name": "Zhaoqiang", + "last_name": "Liu" + }, + { + "first_name": "Fei", + "last_name": "Chen" + }, + { + "first_name": "Shifeng", + "last_name": "Zhang" + }, + { + "first_name": "Tianyang", + "last_name": "Hu" + }, + { + "first_name": "Enze", + "last_name": "Xie" + }, + { + "first_name": "Zhenguo", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "See Say and Segment: Teaching LMMs to Overcome False Premises", - "authors": "Tsung-Han Wu, Giscard Biamby, David Chan, Lisa Dunlap, Ritwik Gupta, Xudong Wang, Joseph E. Gonzalez, Trevor Darrell", + "authors": [ + { + "first_name": "Tsung-Han", + "last_name": "Wu" + }, + { + "first_name": "Giscard", + "last_name": "Biamby" + }, + { + "first_name": "David", + "last_name": "Chan" + }, + { + "first_name": "Lisa", + "last_name": "Dunlap" + }, + { + "first_name": "Ritwik", + "last_name": "Gupta" + }, + { + "first_name": "Xudong", + "last_name": "Wang" + }, + { + "first_name": "Joseph", + "last_name": "E. Gonzalez" + }, + { + "first_name": "Trevor", + "last_name": "Darrell" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Is Ego Status All You Need for Open-Loop End-to-End Autonomous Driving?", - "authors": "Zhiqi Li, Zhiding Yu, Shiyi Lan, Jiahan Li, Jan Kautz, Tong Lu, Jose M. Alvarez", + "authors": [ + { + "first_name": "Zhiqi", + "last_name": "Li" + }, + { + "first_name": "Zhiding", + "last_name": "Yu" + }, + { + "first_name": "Shiyi", + "last_name": "Lan" + }, + { + "first_name": "Jiahan", + "last_name": "Li" + }, + { + "first_name": "Jan", + "last_name": "Kautz" + }, + { + "first_name": "Tong", + "last_name": "Lu" + }, + { + "first_name": "Jose", + "last_name": "M. Alvarez" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Unsupervised Template-assisted Point Cloud Shape Correspondence Network", - "authors": "Jiacheng Deng, Jiahao Lu, Tianzhu Zhang", + "authors": [ + { + "first_name": "Jiacheng", + "last_name": "Deng" + }, + { + "first_name": "Jiahao", + "last_name": "Lu" + }, + { + "first_name": "Tianzhu", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CGI-DM: Digital Copyright Authentication for Diffusion Models via Contrasting Gradient Inversion", - "authors": "Xiaoyu Wu, Yang Hua, Chumeng Liang, Jiaru Zhang, Hao Wang, Tao Song, Haibing Guan", + "authors": [ + { + "first_name": "Xiaoyu", + "last_name": "Wu" + }, + { + "first_name": "Yang", + "last_name": "Hua" + }, + { + "first_name": "Chumeng", + "last_name": "Liang" + }, + { + "first_name": "Jiaru", + "last_name": "Zhang" + }, + { + "first_name": "Hao", + "last_name": "Wang" + }, + { + "first_name": "Tao", + "last_name": "Song" + }, + { + "first_name": "Haibing", + "last_name": "Guan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Making Visual Sense of Oracle Bones for You and Me", - "authors": "Runqi Qiao, Lan Yang, Kaiyue Pang, Honggang Zhang", + "authors": [ + { + "first_name": "Runqi", + "last_name": "Qiao" + }, + { + "first_name": "Lan", + "last_name": "Yang" + }, + { + "first_name": "Kaiyue", + "last_name": "Pang" + }, + { + "first_name": "Honggang", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Finsler-Laplace-Beltrami Operators with Application to Shape Analysis", - "authors": "Simon Weber, Thomas Dagès, Maolin Gao, Daniel Cremers", + "authors": [ + { + "first_name": "Simon", + "last_name": "Weber" + }, + { + "first_name": "Thomas", + "last_name": "Dagès" + }, + { + "first_name": "Maolin", + "last_name": "Gao" + }, + { + "first_name": "Daniel", + "last_name": "Cremers" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Minimal Perspective Autocalibration", - "authors": "Andrea Porfiri Dal Cin, Timothy Duff, Luca Magri, Tomas Pajdla", + "authors": [ + { + "first_name": "Andrea", + "last_name": "Porfiri Dal Cin" + }, + { + "first_name": "Timothy", + "last_name": "Duff" + }, + { + "first_name": "Luca", + "last_name": "Magri" + }, + { + "first_name": "Tomas", + "last_name": "Pajdla" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MOHO: Learning Single-view Hand-held Object Reconstruction with Multi-view Occlusion-Aware Supervision", - "authors": "Chenyangguang Zhang, Guanlong Jiao, Yan Di, Gu Wang, Ziqin Huang, Ruida Zhang, Fabian Manhardt, Bowen Fu, Federico Tombari, Xiangyang Ji", + "authors": [ + { + "first_name": "Chenyangguang", + "last_name": "Zhang" + }, + { + "first_name": "Guanlong", + "last_name": "Jiao" + }, + { + "first_name": "Yan", + "last_name": "Di" + }, + { + "first_name": "Gu", + "last_name": "Wang" + }, + { + "first_name": "Ziqin", + "last_name": "Huang" + }, + { + "first_name": "Ruida", + "last_name": "Zhang" + }, + { + "first_name": "Fabian", + "last_name": "Manhardt" + }, + { + "first_name": "Bowen", + "last_name": "Fu" + }, + { + "first_name": "Federico", + "last_name": "Tombari" + }, + { + "first_name": "Xiangyang", + "last_name": "Ji" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "BANF: Band-Limited Neural Fields for Levels of Detail Reconstruction", - "authors": "Akhmedkhan Shabanov, Shrisudhan Govindarajan, Cody Reading, Lily Goli, Daniel Rebain, Kwang Moo Yi, Andrea Tagliasacchi", + "authors": [ + { + "first_name": "Akhmedkhan", + "last_name": "Shabanov" + }, + { + "first_name": "Shrisudhan", + "last_name": "Govindarajan" + }, + { + "first_name": "Cody", + "last_name": "Reading" + }, + { + "first_name": "Lily", + "last_name": "Goli" + }, + { + "first_name": "Daniel", + "last_name": "Rebain" + }, + { + "first_name": "Kwang", + "last_name": "Moo Yi" + }, + { + "first_name": "Andrea", + "last_name": "Tagliasacchi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Time- Memory- and Parameter-Efficient Visual Adaptation", - "authors": "Otniel-Bogdan Mercea, Alexey Gritsenko, Cordelia Schmid, Anurag Arnab", + "authors": [ + { + "first_name": "Otniel-Bogdan", + "last_name": "Mercea" + }, + { + "first_name": "Alexey", + "last_name": "Gritsenko" + }, + { + "first_name": "Cordelia", + "last_name": "Schmid" + }, + { + "first_name": "Anurag", + "last_name": "Arnab" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SecondPose: SE(3)-Consistent Dual-Stream Feature Fusion for Category-Level Pose Estimation", - "authors": "Yamei Chen, Yan Di, Guangyao Zhai, Fabian Manhardt, Chenyangguang Zhang, Ruida Zhang, Federico Tombari, Nassir Navab, Benjamin Busam", + "authors": [ + { + "first_name": "Yamei", + "last_name": "Chen" + }, + { + "first_name": "Yan", + "last_name": "Di" + }, + { + "first_name": "Guangyao", + "last_name": "Zhai" + }, + { + "first_name": "Fabian", + "last_name": "Manhardt" + }, + { + "first_name": "Chenyangguang", + "last_name": "Zhang" + }, + { + "first_name": "Ruida", + "last_name": "Zhang" + }, + { + "first_name": "Federico", + "last_name": "Tombari" + }, + { + "first_name": "Nassir", + "last_name": "Navab" + }, + { + "first_name": "Benjamin", + "last_name": "Busam" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Physical Property Understanding from Language-Embedded Feature Fields", - "authors": "Albert J. Zhai, Yuan Shen, Emily Y. Chen, Gloria X. Wang, Xinlei Wang, Sheng Wang, Kaiyu Guan, Shenlong Wang", + "authors": [ + { + "first_name": "Albert", + "last_name": "J. Zhai" + }, + { + "first_name": "Yuan", + "last_name": "Shen" + }, + { + "first_name": "Emily", + "last_name": "Y. Chen" + }, + { + "first_name": "Gloria", + "last_name": "X. Wang" + }, + { + "first_name": "Xinlei", + "last_name": "Wang" + }, + { + "first_name": "Sheng", + "last_name": "Wang" + }, + { + "first_name": "Kaiyu", + "last_name": "Guan" + }, + { + "first_name": "Shenlong", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "EgoGen: An Egocentric Synthetic Data Generator", - "authors": "Gen Li, Kaifeng Zhao, Siwei Zhang, Xiaozhong Lyu, Mihai Dusmanu, Yan Zhang, Marc Pollefeys, Siyu Tang", + "authors": [ + { + "first_name": "Gen", + "last_name": "Li" + }, + { + "first_name": "Kaifeng", + "last_name": "Zhao" + }, + { + "first_name": "Siwei", + "last_name": "Zhang" + }, + { + "first_name": "Xiaozhong", + "last_name": "Lyu" + }, + { + "first_name": "Mihai", + "last_name": "Dusmanu" + }, + { + "first_name": "Yan", + "last_name": "Zhang" + }, + { + "first_name": "Marc", + "last_name": "Pollefeys" + }, + { + "first_name": "Siyu", + "last_name": "Tang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Suppress and Rebalance: Towards Generalized Multi-Modal Face Anti-Spoofing", - "authors": "Xun Lin, Shuai Wang, Rizhao Cai, Yizhong Liu, Ying Fu, Wenzhong Tang, Zitong Yu, Alex Kot", + "authors": [ + { + "first_name": "Xun", + "last_name": "Lin" + }, + { + "first_name": "Shuai", + "last_name": "Wang" + }, + { + "first_name": "Rizhao", + "last_name": "Cai" + }, + { + "first_name": "Yizhong", + "last_name": "Liu" + }, + { + "first_name": "Ying", + "last_name": "Fu" + }, + { + "first_name": "Wenzhong", + "last_name": "Tang" + }, + { + "first_name": "Zitong", + "last_name": "Yu" + }, + { + "first_name": "Alex", + "last_name": "Kot" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LEAD: Exploring Logit Space Evolution for Model Selection", - "authors": "Zixuan Hu, Xiaotong Li, Shixiang Tang, Jun Liu, Yichun Hu, Ling-Yu Duan", + "authors": [ + { + "first_name": "Zixuan", + "last_name": "Hu" + }, + { + "first_name": "Xiaotong", + "last_name": "Li" + }, + { + "first_name": "Shixiang", + "last_name": "Tang" + }, + { + "first_name": "Jun", + "last_name": "Liu" + }, + { + "first_name": "Yichun", + "last_name": "Hu" + }, + { + "first_name": "Ling-Yu", + "last_name": "Duan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Video ReCap: Recursive Captioning of Hour-Long Videos", - "authors": "Md Mohaiminul Islam, Ngan Ho, Xitong Yang, Tushar Nagarajan, Lorenzo Torresani, Gedas Bertasius", + "authors": [ + { + "first_name": "Md", + "last_name": "Mohaiminul Islam" + }, + { + "first_name": "Ngan", + "last_name": "Ho" + }, + { + "first_name": "Xitong", + "last_name": "Yang" + }, + { + "first_name": "Tushar", + "last_name": "Nagarajan" + }, + { + "first_name": "Lorenzo", + "last_name": "Torresani" + }, + { + "first_name": "Gedas", + "last_name": "Bertasius" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards Realistic Scene Generation with LiDAR Diffusion Models", - "authors": "Haoxi Ran, Vitor Guizilini, Yue Wang", + "authors": [ + { + "first_name": "Haoxi", + "last_name": "Ran" + }, + { + "first_name": "Vitor", + "last_name": "Guizilini" + }, + { + "first_name": "Yue", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Diffusion Reflectance Map: Single-Image Stochastic Inverse Rendering of Illumination and Reflectance", - "authors": "Yuto Enyo, Ko Nishino", + "authors": [ + { + "first_name": "Yuto", + "last_name": "Enyo" + }, + { + "first_name": "Ko", + "last_name": "Nishino" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Universal Segmentation at Arbitrary Granularity with Language Instruction", - "authors": "Yong Liu, Cairong Zhang, Yitong Wang, Jiahao Wang, Yujiu Yang, Yansong Tang", + "authors": [ + { + "first_name": "Yong", + "last_name": "Liu" + }, + { + "first_name": "Cairong", + "last_name": "Zhang" + }, + { + "first_name": "Yitong", + "last_name": "Wang" + }, + { + "first_name": "Jiahao", + "last_name": "Wang" + }, + { + "first_name": "Yujiu", + "last_name": "Yang" + }, + { + "first_name": "Yansong", + "last_name": "Tang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians", - "authors": "Shenhan Qian, Tobias Kirschstein, Liam Schoneveld, Davide Davoli, Simon Giebenhain, Matthias Nießner", + "authors": [ + { + "first_name": "Shenhan", + "last_name": "Qian" + }, + { + "first_name": "Tobias", + "last_name": "Kirschstein" + }, + { + "first_name": "Liam", + "last_name": "Schoneveld" + }, + { + "first_name": "Davide", + "last_name": "Davoli" + }, + { + "first_name": "Simon", + "last_name": "Giebenhain" + }, + { + "first_name": "Matthias", + "last_name": "Nießner" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI", - "authors": "Xiang Yue, Yuansheng Ni, Kai Zhang, Tianyu Zheng, Ruoqi Liu, Ge Zhang, Samuel Stevens, Dongfu Jiang, Weiming Ren, Yuxuan Sun, Cong Wei, Botao Yu, Ruibin Yuan, Renliang Sun, Ming Yin, Boyuan Zheng, Zhenzhu Yang, Yibo Liu, Wenhao Huang, Huan Sun, Yu Su, Wenhu Chen", + "authors": [ + { + "first_name": "Xiang", + "last_name": "Yue" + }, + { + "first_name": "Yuansheng", + "last_name": "Ni" + }, + { + "first_name": "Kai", + "last_name": "Zhang" + }, + { + "first_name": "Tianyu", + "last_name": "Zheng" + }, + { + "first_name": "Ruoqi", + "last_name": "Liu" + }, + { + "first_name": "Ge", + "last_name": "Zhang" + }, + { + "first_name": "Samuel", + "last_name": "Stevens" + }, + { + "first_name": "Dongfu", + "last_name": "Jiang" + }, + { + "first_name": "Weiming", + "last_name": "Ren" + }, + { + "first_name": "Yuxuan", + "last_name": "Sun" + }, + { + "first_name": "Cong", + "last_name": "Wei" + }, + { + "first_name": "Botao", + "last_name": "Yu" + }, + { + "first_name": "Ruibin", + "last_name": "Yuan" + }, + { + "first_name": "Renliang", + "last_name": "Sun" + }, + { + "first_name": "Ming", + "last_name": "Yin" + }, + { + "first_name": "Boyuan", + "last_name": "Zheng" + }, + { + "first_name": "Zhenzhu", + "last_name": "Yang" + }, + { + "first_name": "Yibo", + "last_name": "Liu" + }, + { + "first_name": "Wenhao", + "last_name": "Huang" + }, + { + "first_name": "Huan", + "last_name": "Sun" + }, + { + "first_name": "Yu", + "last_name": "Su" + }, + { + "first_name": "Wenhu", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Layout-Agnostic Scene Text Image Synthesis with Diffusion Models", - "authors": "Qilong Zhangli, Jindong Jiang, Di Liu, Licheng Yu, Xiaoliang Dai, Ankit Ramchandani, Guan Pang, Dimitris N. Metaxas, Praveen Krishnan", + "authors": [ + { + "first_name": "Qilong", + "last_name": "Zhangli" + }, + { + "first_name": "Jindong", + "last_name": "Jiang" + }, + { + "first_name": "Di", + "last_name": "Liu" + }, + { + "first_name": "Licheng", + "last_name": "Yu" + }, + { + "first_name": "Xiaoliang", + "last_name": "Dai" + }, + { + "first_name": "Ankit", + "last_name": "Ramchandani" + }, + { + "first_name": "Guan", + "last_name": "Pang" + }, + { + "first_name": "Dimitris", + "last_name": "N. Metaxas" + }, + { + "first_name": "Praveen", + "last_name": "Krishnan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "EarthLoc: Astronaut Photography Localization by Indexing Earth from Space", - "authors": "Gabriele Berton, Alex Stoken, Barbara Caputo, Carlo Masone", + "authors": [ + { + "first_name": "Gabriele", + "last_name": "Berton" + }, + { + "first_name": "Alex", + "last_name": "Stoken" + }, + { + "first_name": "Barbara", + "last_name": "Caputo" + }, + { + "first_name": "Carlo", + "last_name": "Masone" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SmartMask: Context Aware High-Fidelity Mask Generation for Fine-grained Object Insertion and Layout Control", - "authors": "Jaskirat Singh, Jianming Zhang, Qing Liu, Cameron Smith, Zhe Lin, Liang Zheng", + "authors": [ + { + "first_name": "Jaskirat", + "last_name": "Singh" + }, + { + "first_name": "Jianming", + "last_name": "Zhang" + }, + { + "first_name": "Qing", + "last_name": "Liu" + }, + { + "first_name": "Cameron", + "last_name": "Smith" + }, + { + "first_name": "Zhe", + "last_name": "Lin" + }, + { + "first_name": "Liang", + "last_name": "Zheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Text-Image Alignment for Diffusion-Based Perception", - "authors": "Neehar Kondapaneni, Markus Marks, Manuel Knott, Rogerio Guimaraes, Pietro Perona", + "authors": [ + { + "first_name": "Neehar", + "last_name": "Kondapaneni" + }, + { + "first_name": "Markus", + "last_name": "Marks" + }, + { + "first_name": "Manuel", + "last_name": "Knott" + }, + { + "first_name": "Rogerio", + "last_name": "Guimaraes" + }, + { + "first_name": "Pietro", + "last_name": "Perona" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Customization Assistant for Text-to-Image Generation", - "authors": "Yufan Zhou, Ruiyi Zhang, Jiuxiang Gu, Tong Sun", + "authors": [ + { + "first_name": "Yufan", + "last_name": "Zhou" + }, + { + "first_name": "Ruiyi", + "last_name": "Zhang" + }, + { + "first_name": "Jiuxiang", + "last_name": "Gu" + }, + { + "first_name": "Tong", + "last_name": "Sun" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GaussianEditor: Editing 3D Gaussians Delicately with Text Instructions", - "authors": "Junjie Wang, Jiemin Fang, Xiaopeng Zhang, Lingxi Xie, Qi Tian", + "authors": [ + { + "first_name": "Junjie", + "last_name": "Wang" + }, + { + "first_name": "Jiemin", + "last_name": "Fang" + }, + { + "first_name": "Xiaopeng", + "last_name": "Zhang" + }, + { + "first_name": "Lingxi", + "last_name": "Xie" + }, + { + "first_name": "Qi", + "last_name": "Tian" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MemFlow: Optical Flow Estimation and Prediction with Memory", - "authors": "Qiaole Dong, Yanwei Fu", + "authors": [ + { + "first_name": "Qiaole", + "last_name": "Dong" + }, + { + "first_name": "Yanwei", + "last_name": "Fu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Novel Class Discovery for Ultra-Fine-Grained Visual Categorization", - "authors": "Yu Liu, Yaqi Cai, Qi Jia, Binglin Qiu, Weimin Wang, Nan Pu", + "authors": [ + { + "first_name": "Yu", + "last_name": "Liu" + }, + { + "first_name": "Yaqi", + "last_name": "Cai" + }, + { + "first_name": "Qi", + "last_name": "Jia" + }, + { + "first_name": "Binglin", + "last_name": "Qiu" + }, + { + "first_name": "Weimin", + "last_name": "Wang" + }, + { + "first_name": "Nan", + "last_name": "Pu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GenHowTo: Learning to Generate Actions and State Transformations from Instructional Videos", - "authors": "Tomáš Souček, Dima Damen, Michael Wray, Ivan Laptev, Josef Sivic", + "authors": [ + { + "first_name": "Tomáš", + "last_name": "Souček" + }, + { + "first_name": "Dima", + "last_name": "Damen" + }, + { + "first_name": "Michael", + "last_name": "Wray" + }, + { + "first_name": "Ivan", + "last_name": "Laptev" + }, + { + "first_name": "Josef", + "last_name": "Sivic" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Paint-it: Text-to-Texture Synthesis via Deep Convolutional Texture Map Optimization and Physically-Based Rendering", - "authors": "Kim Youwang, Tae-Hyun Oh, Gerard Pons-Moll", + "authors": [ + { + "first_name": "Kim", + "last_name": "Youwang" + }, + { + "first_name": "Tae-Hyun", + "last_name": "Oh" + }, + { + "first_name": "Gerard", + "last_name": "Pons-Moll" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HiKER-SGG: Hierarchical Knowledge Enhanced Robust Scene Graph Generation", - "authors": "Ce Zhang, Simon Stepputtis, Joseph Campbell, Katia Sycara, Yaqi Xie", + "authors": [ + { + "first_name": "Ce", + "last_name": "Zhang" + }, + { + "first_name": "Simon", + "last_name": "Stepputtis" + }, + { + "first_name": "Joseph", + "last_name": "Campbell" + }, + { + "first_name": "Katia", + "last_name": "Sycara" + }, + { + "first_name": "Yaqi", + "last_name": "Xie" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DiffusionGAN3D: Boosting Text-guided 3D Generation and Domain Adaptation by Combining 3D GANs and Diffusion Priors", - "authors": "Biwen Lei, Kai Yu, Mengyang Feng, Miaomiao Cui, Xuansong Xie", + "authors": [ + { + "first_name": "Biwen", + "last_name": "Lei" + }, + { + "first_name": "Kai", + "last_name": "Yu" + }, + { + "first_name": "Mengyang", + "last_name": "Feng" + }, + { + "first_name": "Miaomiao", + "last_name": "Cui" + }, + { + "first_name": "Xuansong", + "last_name": "Xie" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Physics-Aware Hand-Object Interaction Denoising", - "authors": "Haowen Luo, Yunze Liu, Li Yi", + "authors": [ + { + "first_name": "Haowen", + "last_name": "Luo" + }, + { + "first_name": "Yunze", + "last_name": "Liu" + }, + { + "first_name": "Li", + "last_name": "Yi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "VastGaussian: Vast 3D Gaussians for Large Scene Reconstruction", - "authors": "Jiaqi Lin, Zhihao Li, Xiao Tang, Jianzhuang Liu, Shiyong Liu, Jiayue Liu, Yangdi Lu, Xiaofei Wu, Songcen Xu, Youliang Yan, Wenming Yang", + "authors": [ + { + "first_name": "Jiaqi", + "last_name": "Lin" + }, + { + "first_name": "Zhihao", + "last_name": "Li" + }, + { + "first_name": "Xiao", + "last_name": "Tang" + }, + { + "first_name": "Jianzhuang", + "last_name": "Liu" + }, + { + "first_name": "Shiyong", + "last_name": "Liu" + }, + { + "first_name": "Jiayue", + "last_name": "Liu" + }, + { + "first_name": "Yangdi", + "last_name": "Lu" + }, + { + "first_name": "Xiaofei", + "last_name": "Wu" + }, + { + "first_name": "Songcen", + "last_name": "Xu" + }, + { + "first_name": "Youliang", + "last_name": "Yan" + }, + { + "first_name": "Wenming", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Edit One for All: Interactive Batch Image Editing", - "authors": "Thao Nguyen, Utkarsh Ojha, Yuheng Li, Haotian Liu, Yong Jae Lee", + "authors": [ + { + "first_name": "Thao", + "last_name": "Nguyen" + }, + { + "first_name": "Utkarsh", + "last_name": "Ojha" + }, + { + "first_name": "Yuheng", + "last_name": "Li" + }, + { + "first_name": "Haotian", + "last_name": "Liu" + }, + { + "first_name": "Yong", + "last_name": "Jae Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Rethinking Boundary Discontinuity Problem for Oriented Object Detection", - "authors": "Hang Xu, Xinyuan Liu, Haonan Xu, Yike Ma, Zunjie Zhu, Chenggang Yan, Feng Dai", + "authors": [ + { + "first_name": "Hang", + "last_name": "Xu" + }, + { + "first_name": "Xinyuan", + "last_name": "Liu" + }, + { + "first_name": "Haonan", + "last_name": "Xu" + }, + { + "first_name": "Yike", + "last_name": "Ma" + }, + { + "first_name": "Zunjie", + "last_name": "Zhu" + }, + { + "first_name": "Chenggang", + "last_name": "Yan" + }, + { + "first_name": "Feng", + "last_name": "Dai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Deformable One-shot Face Stylization via DINO Semantic Guidance", - "authors": "Yang Zhou, Zichong Chen, Hui Huang", + "authors": [ + { + "first_name": "Yang", + "last_name": "Zhou" + }, + { + "first_name": "Zichong", + "last_name": "Chen" + }, + { + "first_name": "Hui", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SleepVST: Sleep Staging from Near-Infrared Video Signals using Pre-Trained Transformers", - "authors": "Jonathan F. Carter, João Jorge, Oliver Gibson, Lionel Tarassenko", + "authors": [ + { + "first_name": "Jonathan", + "last_name": "F. Carter" + }, + { + "first_name": "João", + "last_name": "Jorge" + }, + { + "first_name": "Oliver", + "last_name": "Gibson" + }, + { + "first_name": "Lionel", + "last_name": "Tarassenko" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesis", - "authors": "Yanzuo Lu, Manlin Zhang, Andy J Ma, Xiaohua Xie, Jianhuang Lai", + "authors": [ + { + "first_name": "Yanzuo", + "last_name": "Lu" + }, + { + "first_name": "Manlin", + "last_name": "Zhang" + }, + { + "first_name": "Andy", + "last_name": "J Ma" + }, + { + "first_name": "Xiaohua", + "last_name": "Xie" + }, + { + "first_name": "Jianhuang", + "last_name": "Lai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Watermark-embedded Adversarial Examples for Copyright Protection against Diffusion Models", - "authors": "Peifei Zhu, Tsubasa Takahashi, Hirokatsu Kataoka", + "authors": [ + { + "first_name": "Peifei", + "last_name": "Zhu" + }, + { + "first_name": "Tsubasa", + "last_name": "Takahashi" + }, + { + "first_name": "Hirokatsu", + "last_name": "Kataoka" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "TCP:Textual-based Class-aware Prompt tuning for Visual-Language Model", - "authors": "Hantao Yao, Rui Zhang, Changsheng Xu", + "authors": [ + { + "first_name": "Hantao", + "last_name": "Yao" + }, + { + "first_name": "Rui", + "last_name": "Zhang" + }, + { + "first_name": "Changsheng", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "OMG: Towards Open-vocabulary Motion Generation via Mixture of Controllers", - "authors": "Han Liang, Jiacheng Bao, Ruichi Zhang, Sihan Ren, Yuecheng Xu, Sibei Yang, Xin Chen, Jingyi Yu, Lan Xu", + "authors": [ + { + "first_name": "Han", + "last_name": "Liang" + }, + { + "first_name": "Jiacheng", + "last_name": "Bao" + }, + { + "first_name": "Ruichi", + "last_name": "Zhang" + }, + { + "first_name": "Sihan", + "last_name": "Ren" + }, + { + "first_name": "Yuecheng", + "last_name": "Xu" + }, + { + "first_name": "Sibei", + "last_name": "Yang" + }, + { + "first_name": "Xin", + "last_name": "Chen" + }, + { + "first_name": "Jingyi", + "last_name": "Yu" + }, + { + "first_name": "Lan", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding", - "authors": "Shuhuai Ren, Linli Yao, Shicheng Li, Xu Sun, Lu Hou", + "authors": [ + { + "first_name": "Shuhuai", + "last_name": "Ren" + }, + { + "first_name": "Linli", + "last_name": "Yao" + }, + { + "first_name": "Shicheng", + "last_name": "Li" + }, + { + "first_name": "Xu", + "last_name": "Sun" + }, + { + "first_name": "Lu", + "last_name": "Hou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models", - "authors": "Huan Ling, Seung Wook Kim, Antonio Torralba, Sanja Fidler, Karsten Kreis", + "authors": [ + { + "first_name": "Huan", + "last_name": "Ling" + }, + { + "first_name": "Seung", + "last_name": "Wook Kim" + }, + { + "first_name": "Antonio", + "last_name": "Torralba" + }, + { + "first_name": "Sanja", + "last_name": "Fidler" + }, + { + "first_name": "Karsten", + "last_name": "Kreis" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PDF: A Probability-Driven Framework for Open World 3D Point Cloud Semantic Segmentation", - "authors": "Jinfeng Xu, Siyuan Yang, Xianzhi Li, Yuan Tang, Yixue Hao, Long Hu, Min Chen", + "authors": [ + { + "first_name": "Jinfeng", + "last_name": "Xu" + }, + { + "first_name": "Siyuan", + "last_name": "Yang" + }, + { + "first_name": "Xianzhi", + "last_name": "Li" + }, + { + "first_name": "Yuan", + "last_name": "Tang" + }, + { + "first_name": "Yixue", + "last_name": "Hao" + }, + { + "first_name": "Long", + "last_name": "Hu" + }, + { + "first_name": "Min", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Test-Time Domain Generalization for Face Anti-Spoofing", - "authors": "Qianyu Zhou, Ke-Yue Zhang, Taiping Yao, Xuequan Lu, Shouhong Ding, Lizhuang Ma", + "authors": [ + { + "first_name": "Qianyu", + "last_name": "Zhou" + }, + { + "first_name": "Ke-Yue", + "last_name": "Zhang" + }, + { + "first_name": "Taiping", + "last_name": "Yao" + }, + { + "first_name": "Xuequan", + "last_name": "Lu" + }, + { + "first_name": "Shouhong", + "last_name": "Ding" + }, + { + "first_name": "Lizhuang", + "last_name": "Ma" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DiffusionMTL: Learning Multi-Task Denoising Diffusion Model from Partially Annotated Data", - "authors": "Hanrong Ye, Dan Xu", + "authors": [ + { + "first_name": "Hanrong", + "last_name": "Ye" + }, + { + "first_name": "Dan", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Spike-guided Motion Deblurring with Unknown Modal Spatiotemporal Alignment", - "authors": "Jiyuan Zhang, Shiyan Chen, Yajing Zheng, Zhaofei Yu, Tiejun Huang", + "authors": [ + { + "first_name": "Jiyuan", + "last_name": "Zhang" + }, + { + "first_name": "Shiyan", + "last_name": "Chen" + }, + { + "first_name": "Yajing", + "last_name": "Zheng" + }, + { + "first_name": "Zhaofei", + "last_name": "Yu" + }, + { + "first_name": "Tiejun", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "VRP-SAM: SAM with Visual Reference Prompt", - "authors": "Yanpeng Sun, Jiahui Chen, Shan Zhang, Xinyu Zhang, Qiang Chen, Gang Zhang, Errui Ding, Jingdong Wang, Zechao Li", + "authors": [ + { + "first_name": "Yanpeng", + "last_name": "Sun" + }, + { + "first_name": "Jiahui", + "last_name": "Chen" + }, + { + "first_name": "Shan", + "last_name": "Zhang" + }, + { + "first_name": "Xinyu", + "last_name": "Zhang" + }, + { + "first_name": "Qiang", + "last_name": "Chen" + }, + { + "first_name": "Gang", + "last_name": "Zhang" + }, + { + "first_name": "Errui", + "last_name": "Ding" + }, + { + "first_name": "Jingdong", + "last_name": "Wang" + }, + { + "first_name": "Zechao", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Discriminability-Driven Channel Selection for Out-of-Distribution Detection", - "authors": "Yue Yuan, Rundong He, Yicong Dong, Zhongyi Han, Yilong Yin", + "authors": [ + { + "first_name": "Yue", + "last_name": "Yuan" + }, + { + "first_name": "Rundong", + "last_name": "He" + }, + { + "first_name": "Yicong", + "last_name": "Dong" + }, + { + "first_name": "Zhongyi", + "last_name": "Han" + }, + { + "first_name": "Yilong", + "last_name": "Yin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ManiFPT: Defining and Analyzing Fingerprints of Generative Models", - "authors": "Hae Jin Song, Mahyar Khayatkhoei, Wael AbdAlmageed", + "authors": [ + { + "first_name": "Hae", + "last_name": "Jin Song" + }, + { + "first_name": "Mahyar", + "last_name": "Khayatkhoei" + }, + { + "first_name": "Wael", + "last_name": "AbdAlmageed" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Real-time 3D-aware Portrait Video Relighting", - "authors": "Ziqi Cai, Kaiwen Jiang, Shu-Yu Chen, Yu-Kun Lai, Hongbo Fu, Boxin Shi, Lin Gao", + "authors": [ + { + "first_name": "Ziqi", + "last_name": "Cai" + }, + { + "first_name": "Kaiwen", + "last_name": "Jiang" + }, + { + "first_name": "Shu-Yu", + "last_name": "Chen" + }, + { + "first_name": "Yu-Kun", + "last_name": "Lai" + }, + { + "first_name": "Hongbo", + "last_name": "Fu" + }, + { + "first_name": "Boxin", + "last_name": "Shi" + }, + { + "first_name": "Lin", + "last_name": "Gao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting", - "authors": "Zhiyin Qian, Shaofei Wang, Marko Mihajlovic, Andreas Geiger, Siyu Tang", + "authors": [ + { + "first_name": "Zhiyin", + "last_name": "Qian" + }, + { + "first_name": "Shaofei", + "last_name": "Wang" + }, + { + "first_name": "Marko", + "last_name": "Mihajlovic" + }, + { + "first_name": "Andreas", + "last_name": "Geiger" + }, + { + "first_name": "Siyu", + "last_name": "Tang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Quilt-LLaVA: Visual Instruction Tuning by Extracting Localized Narratives from Open-Source Histopathology Videos", - "authors": "Mehmet Saygin Seyfioglu, Wisdom O. Ikezogwo, Fatemeh Ghezloo, Ranjay Krishna, Linda Shapiro", + "authors": [ + { + "first_name": "Mehmet", + "last_name": "Saygin Seyfioglu" + }, + { + "first_name": "Wisdom", + "last_name": "O. Ikezogwo" + }, + { + "first_name": "Fatemeh", + "last_name": "Ghezloo" + }, + { + "first_name": "Ranjay", + "last_name": "Krishna" + }, + { + "first_name": "Linda", + "last_name": "Shapiro" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Traffic Scene Parsing through the TSP6K Dataset", - "authors": "Peng-Tao Jiang, Yuqi Yang, Yang Cao, Qibin Hou, Ming-Ming Cheng, Chunhua Shen", + "authors": [ + { + "first_name": "Peng-Tao", + "last_name": "Jiang" + }, + { + "first_name": "Yuqi", + "last_name": "Yang" + }, + { + "first_name": "Yang", + "last_name": "Cao" + }, + { + "first_name": "Qibin", + "last_name": "Hou" + }, + { + "first_name": "Ming-Ming", + "last_name": "Cheng" + }, + { + "first_name": "Chunhua", + "last_name": "Shen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Style Aligned Image Generation via Shared Attention", - "authors": "Amir Hertz, Andrey Voynov, Shlomi Fruchter, Daniel Cohen-Or", + "authors": [ + { + "first_name": "Amir", + "last_name": "Hertz" + }, + { + "first_name": "Andrey", + "last_name": "Voynov" + }, + { + "first_name": "Shlomi", + "last_name": "Fruchter" + }, + { + "first_name": "Daniel", + "last_name": "Cohen-Or" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "E-GPS: Explainable Geometry Problem Solving via Top-Down Solver and Bottom-Up Generator", - "authors": "Wenjun Wu, Lingling Zhang, Jun Liu, Xi Tang, Yaxian Wang, Shaowei Wang, Qianying Wang", + "authors": [ + { + "first_name": "Wenjun", + "last_name": "Wu" + }, + { + "first_name": "Lingling", + "last_name": "Zhang" + }, + { + "first_name": "Jun", + "last_name": "Liu" + }, + { + "first_name": "Xi", + "last_name": "Tang" + }, + { + "first_name": "Yaxian", + "last_name": "Wang" + }, + { + "first_name": "Shaowei", + "last_name": "Wang" + }, + { + "first_name": "Qianying", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Back to 3D: Few-Shot 3D Keypoint Detection with Back-Projected 2D Features", - "authors": "Thomas Wimmer, Peter Wonka, Maks Ovsjanikov", + "authors": [ + { + "first_name": "Thomas", + "last_name": "Wimmer" + }, + { + "first_name": "Peter", + "last_name": "Wonka" + }, + { + "first_name": "Maks", + "last_name": "Ovsjanikov" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Fourier Priors-Guided Diffusion for Zero-Shot Joint Low-Light Enhancement and Deblurring", - "authors": "Xiaoqian Lv, Shengping Zhang, Chenyang Wang, Yichen Zheng, Bineng Zhong, Chongyi Li, Liqiang Nie", + "authors": [ + { + "first_name": "Xiaoqian", + "last_name": "Lv" + }, + { + "first_name": "Shengping", + "last_name": "Zhang" + }, + { + "first_name": "Chenyang", + "last_name": "Wang" + }, + { + "first_name": "Yichen", + "last_name": "Zheng" + }, + { + "first_name": "Bineng", + "last_name": "Zhong" + }, + { + "first_name": "Chongyi", + "last_name": "Li" + }, + { + "first_name": "Liqiang", + "last_name": "Nie" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Neural Markov Random Field for Stereo Matching", - "authors": "Tongfan Guan, Chen Wang, Yun-Hui Liu", + "authors": [ + { + "first_name": "Tongfan", + "last_name": "Guan" + }, + { + "first_name": "Chen", + "last_name": "Wang" + }, + { + "first_name": "Yun-Hui", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving", - "authors": "Yuqi Wang, Jiawei He, Lue Fan, Hongxin Li, Yuntao Chen, Zhaoxiang Zhang", + "authors": [ + { + "first_name": "Yuqi", + "last_name": "Wang" + }, + { + "first_name": "Jiawei", + "last_name": "He" + }, + { + "first_name": "Lue", + "last_name": "Fan" + }, + { + "first_name": "Hongxin", + "last_name": "Li" + }, + { + "first_name": "Yuntao", + "last_name": "Chen" + }, + { + "first_name": "Zhaoxiang", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "OpenESS: Event-based Semantic Scene Understanding with Open Vocabularies", - "authors": "Lingdong Kong, Youquan Liu, Lai Xing Ng, Benoit R. Cottereau, Wei Tsang Ooi", + "authors": [ + { + "first_name": "Lingdong", + "last_name": "Kong" + }, + { + "first_name": "Youquan", + "last_name": "Liu" + }, + { + "first_name": "Lai", + "last_name": "Xing Ng" + }, + { + "first_name": "Benoit", + "last_name": "R. Cottereau" + }, + { + "first_name": "Wei", + "last_name": "Tsang Ooi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Do Vision and Language Encoders Represent the World Similarly?", - "authors": "Mayug Maniparambil, Raiymbek Akshulakov, Yasser Abdelaziz Dahou Djilali, Mohamed El Amine Seddik, Sanath Narayan, Karttikeya Mangalam, Noel E. O'Connor", + "authors": [ + { + "first_name": "Mayug", + "last_name": "Maniparambil" + }, + { + "first_name": "Raiymbek", + "last_name": "Akshulakov" + }, + { + "first_name": "Yasser", + "last_name": "Abdelaziz Dahou Djilali" + }, + { + "first_name": "Mohamed", + "last_name": "El Amine Seddik" + }, + { + "first_name": "Sanath", + "last_name": "Narayan" + }, + { + "first_name": "Karttikeya", + "last_name": "Mangalam" + }, + { + "first_name": "Noel", + "last_name": "E. O'Connor" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MGMap: Mask-Guided Learning for Online Vectorized HD Map Construction", - "authors": "Xiaolu Liu, Song Wang, Wentong Li, Ruizi Yang, Junbo Chen, Jianke Zhu", + "authors": [ + { + "first_name": "Xiaolu", + "last_name": "Liu" + }, + { + "first_name": "Song", + "last_name": "Wang" + }, + { + "first_name": "Wentong", + "last_name": "Li" + }, + { + "first_name": "Ruizi", + "last_name": "Yang" + }, + { + "first_name": "Junbo", + "last_name": "Chen" + }, + { + "first_name": "Jianke", + "last_name": "Zhu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild", - "authors": "Fanghua Yu, Jinjin Gu, Zheyuan Li, Jinfan Hu, Xiangtao Kong, Xintao Wang, Jingwen He, Yu Qiao, Chao Dong", + "authors": [ + { + "first_name": "Fanghua", + "last_name": "Yu" + }, + { + "first_name": "Jinjin", + "last_name": "Gu" + }, + { + "first_name": "Zheyuan", + "last_name": "Li" + }, + { + "first_name": "Jinfan", + "last_name": "Hu" + }, + { + "first_name": "Xiangtao", + "last_name": "Kong" + }, + { + "first_name": "Xintao", + "last_name": "Wang" + }, + { + "first_name": "Jingwen", + "last_name": "He" + }, + { + "first_name": "Yu", + "last_name": "Qiao" + }, + { + "first_name": "Chao", + "last_name": "Dong" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models", - "authors": "Haoning Wu, Zicheng Zhang, Erli Zhang, Chaofeng Chen, Liang Liao, Annan Wang, Kaixin Xu, Chunyi Li, Jingwen Hou, Guangtao Zhai, Geng Xue, Wenxiu Sun, Qiong Yan, Weisi Lin", + "authors": [ + { + "first_name": "Haoning", + "last_name": "Wu" + }, + { + "first_name": "Zicheng", + "last_name": "Zhang" + }, + { + "first_name": "Erli", + "last_name": "Zhang" + }, + { + "first_name": "Chaofeng", + "last_name": "Chen" + }, + { + "first_name": "Liang", + "last_name": "Liao" + }, + { + "first_name": "Annan", + "last_name": "Wang" + }, + { + "first_name": "Kaixin", + "last_name": "Xu" + }, + { + "first_name": "Chunyi", + "last_name": "Li" + }, + { + "first_name": "Jingwen", + "last_name": "Hou" + }, + { + "first_name": "Guangtao", + "last_name": "Zhai" + }, + { + "first_name": "Geng", + "last_name": "Xue" + }, + { + "first_name": "Wenxiu", + "last_name": "Sun" + }, + { + "first_name": "Qiong", + "last_name": "Yan" + }, + { + "first_name": "Weisi", + "last_name": "Lin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PoseIRM: Enhance 3D Human Pose Estimation on Unseen Camera Settings via Invariant Risk Minimization", - "authors": "Yanlu Cai, Weizhong Zhang, Yuan Wu, Cheng Jin", + "authors": [ + { + "first_name": "Yanlu", + "last_name": "Cai" + }, + { + "first_name": "Weizhong", + "last_name": "Zhang" + }, + { + "first_name": "Yuan", + "last_name": "Wu" + }, + { + "first_name": "Cheng", + "last_name": "Jin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Zero-Shot Structure-Preserving Diffusion Model for High Dynamic Range Tone Mapping", - "authors": "Ruoxi Zhu, Shusong Xu, Peiye Liu, Sicheng Li, Yanheng Lu, Dimin Niu, Zihao Liu, Zihao Meng, Zhiyong Li, Xinhua Chen, Yibo Fan", + "authors": [ + { + "first_name": "Ruoxi", + "last_name": "Zhu" + }, + { + "first_name": "Shusong", + "last_name": "Xu" + }, + { + "first_name": "Peiye", + "last_name": "Liu" + }, + { + "first_name": "Sicheng", + "last_name": "Li" + }, + { + "first_name": "Yanheng", + "last_name": "Lu" + }, + { + "first_name": "Dimin", + "last_name": "Niu" + }, + { + "first_name": "Zihao", + "last_name": "Liu" + }, + { + "first_name": "Zihao", + "last_name": "Meng" + }, + { + "first_name": "Zhiyong", + "last_name": "Li" + }, + { + "first_name": "Xinhua", + "last_name": "Chen" + }, + { + "first_name": "Yibo", + "last_name": "Fan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "VidLA: Video-Language Alignment at Scale", - "authors": "Mamshad Nayeem Rizve, Fan Fei, Jayakrishnan Unnikrishnan, Son Tran, Benjamin Z. Yao, Belinda Zeng, Mubarak Shah, Trishul Chilimbi", + "authors": [ + { + "first_name": "Mamshad", + "last_name": "Nayeem Rizve" + }, + { + "first_name": "Fan", + "last_name": "Fei" + }, + { + "first_name": "Jayakrishnan", + "last_name": "Unnikrishnan" + }, + { + "first_name": "Son", + "last_name": "Tran" + }, + { + "first_name": "Benjamin", + "last_name": "Z. Yao" + }, + { + "first_name": "Belinda", + "last_name": "Zeng" + }, + { + "first_name": "Mubarak", + "last_name": "Shah" + }, + { + "first_name": "Trishul", + "last_name": "Chilimbi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "VoCo: A Simple-yet-Effective Volume Contrastive Learning Framework for 3D Medical Image Analysis", - "authors": "Linshan Wu, Jiaxin Zhuang, Hao Chen", + "authors": [ + { + "first_name": "Linshan", + "last_name": "Wu" + }, + { + "first_name": "Jiaxin", + "last_name": "Zhuang" + }, + { + "first_name": "Hao", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CCEdit: Creative and Controllable Video Editing via Diffusion Models", - "authors": "Ruoyu Feng, Wenming Weng, Yanhui Wang, Yuhui Yuan, Jianmin Bao, Chong Luo, Zhibo Chen, Baining Guo", + "authors": [ + { + "first_name": "Ruoyu", + "last_name": "Feng" + }, + { + "first_name": "Wenming", + "last_name": "Weng" + }, + { + "first_name": "Yanhui", + "last_name": "Wang" + }, + { + "first_name": "Yuhui", + "last_name": "Yuan" + }, + { + "first_name": "Jianmin", + "last_name": "Bao" + }, + { + "first_name": "Chong", + "last_name": "Luo" + }, + { + "first_name": "Zhibo", + "last_name": "Chen" + }, + { + "first_name": "Baining", + "last_name": "Guo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "IPoD: Implicit Field Learning with Point Diffusion for Generalizable 3D Object Reconstruction from Single RGB-D Images", - "authors": "Yushuang Wu, Luyue Shi, Junhao Cai, Weihao Yuan, Lingteng Qiu, Zilong Dong, Liefeng Bo, Shuguang Cui, Xiaoguang Han", + "authors": [ + { + "first_name": "Yushuang", + "last_name": "Wu" + }, + { + "first_name": "Luyue", + "last_name": "Shi" + }, + { + "first_name": "Junhao", + "last_name": "Cai" + }, + { + "first_name": "Weihao", + "last_name": "Yuan" + }, + { + "first_name": "Lingteng", + "last_name": "Qiu" + }, + { + "first_name": "Zilong", + "last_name": "Dong" + }, + { + "first_name": "Liefeng", + "last_name": "Bo" + }, + { + "first_name": "Shuguang", + "last_name": "Cui" + }, + { + "first_name": "Xiaoguang", + "last_name": "Han" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HAVE-FUN: Human Avatar Reconstruction from Few-Shot Unconstrained Images", - "authors": "Xihe Yang, Xingyu Chen, Daiheng Gao, Shaohui Wang, Xiaoguang Han, Baoyuan Wang", + "authors": [ + { + "first_name": "Xihe", + "last_name": "Yang" + }, + { + "first_name": "Xingyu", + "last_name": "Chen" + }, + { + "first_name": "Daiheng", + "last_name": "Gao" + }, + { + "first_name": "Shaohui", + "last_name": "Wang" + }, + { + "first_name": "Xiaoguang", + "last_name": "Han" + }, + { + "first_name": "Baoyuan", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ERMVP: Communication-Efficient and Collaboration-Robust Multi-Vehicle Perception in Challenging Environments", - "authors": "Jingyu Zhang, Kun Yang, Yilei Wang, Hanqi Wang, Peng Sun, Liang Song", + "authors": [ + { + "first_name": "Jingyu", + "last_name": "Zhang" + }, + { + "first_name": "Kun", + "last_name": "Yang" + }, + { + "first_name": "Yilei", + "last_name": "Wang" + }, + { + "first_name": "Hanqi", + "last_name": "Wang" + }, + { + "first_name": "Peng", + "last_name": "Sun" + }, + { + "first_name": "Liang", + "last_name": "Song" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DiffMorpher: Unleashing the Capability of Diffusion Models for Image Morphing", - "authors": "Kaiwen Zhang, Yifan Zhou, Xudong Xu, Bo Dai, Xingang Pan", + "authors": [ + { + "first_name": "Kaiwen", + "last_name": "Zhang" + }, + { + "first_name": "Yifan", + "last_name": "Zhou" + }, + { + "first_name": "Xudong", + "last_name": "Xu" + }, + { + "first_name": "Bo", + "last_name": "Dai" + }, + { + "first_name": "Xingang", + "last_name": "Pan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards Real-World HDR Video Reconstruction: A Large-Scale Benchmark Dataset and A Two-Stage Alignment Network", - "authors": "Yong Shu, Liquan Shen, Xiangyu Hu, Mengyao Li, Zihao Zhou", + "authors": [ + { + "first_name": "Yong", + "last_name": "Shu" + }, + { + "first_name": "Liquan", + "last_name": "Shen" + }, + { + "first_name": "Xiangyu", + "last_name": "Hu" + }, + { + "first_name": "Mengyao", + "last_name": "Li" + }, + { + "first_name": "Zihao", + "last_name": "Zhou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Efficient 3D Implicit Head Avatar with Mesh-anchored Hash Table Blendshapes", - "authors": "Ziqian Bai, Feitong Tan, Sean Fanello, Rohit Pandey, Mingsong Dou, Shichen Liu, Ping Tan, Yinda Zhang", + "authors": [ + { + "first_name": "Ziqian", + "last_name": "Bai" + }, + { + "first_name": "Feitong", + "last_name": "Tan" + }, + { + "first_name": "Sean", + "last_name": "Fanello" + }, + { + "first_name": "Rohit", + "last_name": "Pandey" + }, + { + "first_name": "Mingsong", + "last_name": "Dou" + }, + { + "first_name": "Shichen", + "last_name": "Liu" + }, + { + "first_name": "Ping", + "last_name": "Tan" + }, + { + "first_name": "Yinda", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PikeLPN: Mitigating Overlooked Inefficiencies of Low-Precision Neural Networks", - "authors": "Marina Neseem, Conor McCullough, Randy Hsin, Chas Leichner, Shan Li, In Suk Chong, Andrew Howard, Lukasz Lew, Sherief Reda, Ville-Mikko Rautio, Daniele Moro", + "authors": [ + { + "first_name": "Marina", + "last_name": "Neseem" + }, + { + "first_name": "Conor", + "last_name": "McCullough" + }, + { + "first_name": "Randy", + "last_name": "Hsin" + }, + { + "first_name": "Chas", + "last_name": "Leichner" + }, + { + "first_name": "Shan", + "last_name": "Li" + }, + { + "first_name": "In", + "last_name": "Suk Chong" + }, + { + "first_name": "Andrew", + "last_name": "Howard" + }, + { + "first_name": "Lukasz", + "last_name": "Lew" + }, + { + "first_name": "Sherief", + "last_name": "Reda" + }, + { + "first_name": "Ville-Mikko", + "last_name": "Rautio" + }, + { + "first_name": "Daniele", + "last_name": "Moro" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CurveCloudNet: Processing Point Clouds with 1D Structure", - "authors": "Colton Stearns, Alex Fu, Jiateng Liu, Jeong Joon Park, Davis Rempe, Despoina Paschalidou, Leonidas J. Guibas", + "authors": [ + { + "first_name": "Colton", + "last_name": "Stearns" + }, + { + "first_name": "Alex", + "last_name": "Fu" + }, + { + "first_name": "Jiateng", + "last_name": "Liu" + }, + { + "first_name": "Jeong", + "last_name": "Joon Park" + }, + { + "first_name": "Davis", + "last_name": "Rempe" + }, + { + "first_name": "Despoina", + "last_name": "Paschalidou" + }, + { + "first_name": "Leonidas", + "last_name": "J. Guibas" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CAGE: Controllable Articulation GEneration", - "authors": "Jiayi Liu, Hou In Ivan Tam, Ali Mahdavi-Amiri, Manolis Savva", + "authors": [ + { + "first_name": "Jiayi", + "last_name": "Liu" + }, + { + "first_name": "Hou", + "last_name": "In Ivan Tam" + }, + { + "first_name": "Ali", + "last_name": "Mahdavi-Amiri" + }, + { + "first_name": "Manolis", + "last_name": "Savva" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "No Time to Train: Empowering Non-Parametric Networks for Few-shot 3D Scene Segmentation", - "authors": "Xiangyang Zhu, Renrui Zhang, Bowei He, Ziyu Guo, Jiaming Liu, Han Xiao, Chaoyou Fu, Hao Dong, Peng Gao", + "authors": [ + { + "first_name": "Xiangyang", + "last_name": "Zhu" + }, + { + "first_name": "Renrui", + "last_name": "Zhang" + }, + { + "first_name": "Bowei", + "last_name": "He" + }, + { + "first_name": "Ziyu", + "last_name": "Guo" + }, + { + "first_name": "Jiaming", + "last_name": "Liu" + }, + { + "first_name": "Han", + "last_name": "Xiao" + }, + { + "first_name": "Chaoyou", + "last_name": "Fu" + }, + { + "first_name": "Hao", + "last_name": "Dong" + }, + { + "first_name": "Peng", + "last_name": "Gao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics", - "authors": "Tianyi Xie, Zeshun Zong, Yuxing Qiu, Xuan Li, Yutao Feng, Yin Yang, Chenfanfu Jiang", + "authors": [ + { + "first_name": "Tianyi", + "last_name": "Xie" + }, + { + "first_name": "Zeshun", + "last_name": "Zong" + }, + { + "first_name": "Yuxing", + "last_name": "Qiu" + }, + { + "first_name": "Xuan", + "last_name": "Li" + }, + { + "first_name": "Yutao", + "last_name": "Feng" + }, + { + "first_name": "Yin", + "last_name": "Yang" + }, + { + "first_name": "Chenfanfu", + "last_name": "Jiang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Spatio-Temporal Turbulence Mitigation: A Translational Perspective", - "authors": "Xingguang Zhang, Nicholas Chimitt, Yiheng Chi, Zhiyuan Mao, Stanley H. Chan", + "authors": [ + { + "first_name": "Xingguang", + "last_name": "Zhang" + }, + { + "first_name": "Nicholas", + "last_name": "Chimitt" + }, + { + "first_name": "Yiheng", + "last_name": "Chi" + }, + { + "first_name": "Zhiyuan", + "last_name": "Mao" + }, + { + "first_name": "Stanley", + "last_name": "H. Chan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FocusMAE: Gallbladder Cancer Detection from Ultrasound Videos with Focused Masked Autoencoders", - "authors": "Soumen Basu, Mayuna Gupta, Chetan Madan, Pankaj Gupta, Chetan Arora", + "authors": [ + { + "first_name": "Soumen", + "last_name": "Basu" + }, + { + "first_name": "Mayuna", + "last_name": "Gupta" + }, + { + "first_name": "Chetan", + "last_name": "Madan" + }, + { + "first_name": "Pankaj", + "last_name": "Gupta" + }, + { + "first_name": "Chetan", + "last_name": "Arora" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Grounded Text-to-Image Synthesis with Attention Refocusing", - "authors": "Quynh Phung, Songwei Ge, Jia-Bin Huang", + "authors": [ + { + "first_name": "Quynh", + "last_name": "Phung" + }, + { + "first_name": "Songwei", + "last_name": "Ge" + }, + { + "first_name": "Jia-Bin", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "OpenStreetView-5M: The Many Roads to Global Visual Geolocation", - "authors": "Guillaume Astruc, Nicolas Dufour, Ioannis Siglidis, Constantin Aronssohn, Nacim Bouia, Stephanie Fu, Romain Loiseau, Van Nguyen Nguyen, Charles Raude, Elliot Vincent, Lintao Xu, Hongyu Zhou, Loic Landrieu", + "authors": [ + { + "first_name": "Guillaume", + "last_name": "Astruc" + }, + { + "first_name": "Nicolas", + "last_name": "Dufour" + }, + { + "first_name": "Ioannis", + "last_name": "Siglidis" + }, + { + "first_name": "Constantin", + "last_name": "Aronssohn" + }, + { + "first_name": "Nacim", + "last_name": "Bouia" + }, + { + "first_name": "Stephanie", + "last_name": "Fu" + }, + { + "first_name": "Romain", + "last_name": "Loiseau" + }, + { + "first_name": "Van", + "last_name": "Nguyen Nguyen" + }, + { + "first_name": "Charles", + "last_name": "Raude" + }, + { + "first_name": "Elliot", + "last_name": "Vincent" + }, + { + "first_name": "Lintao", + "last_name": "Xu" + }, + { + "first_name": "Hongyu", + "last_name": "Zhou" + }, + { + "first_name": "Loic", + "last_name": "Landrieu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Visual Concept Connectome (VCC): Open World Concept Discovery and their Interlayer Connections in Deep Models", - "authors": "Matthew Kowal, Richard P. Wildes, Konstantinos G. Derpanis", + "authors": [ + { + "first_name": "Matthew", + "last_name": "Kowal" + }, + { + "first_name": "Richard", + "last_name": "P. Wildes" + }, + { + "first_name": "Konstantinos", + "last_name": "G. Derpanis" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "IReNe: Instant Recoloring of Neural Radiance Fields", - "authors": "Alessio Mazzucchelli, Adrian Garcia-Garcia, Elena Garces, Fernando Rivas-Manzaneque, Francesc Moreno-Noguer, Adrian Penate-Sanchez", + "authors": [ + { + "first_name": "Alessio", + "last_name": "Mazzucchelli" + }, + { + "first_name": "Adrian", + "last_name": "Garcia-Garcia" + }, + { + "first_name": "Elena", + "last_name": "Garces" + }, + { + "first_name": "Fernando", + "last_name": "Rivas-Manzaneque" + }, + { + "first_name": "Francesc", + "last_name": "Moreno-Noguer" + }, + { + "first_name": "Adrian", + "last_name": "Penate-Sanchez" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Class Tokens Infusion for Weakly Supervised Semantic Segmentation", - "authors": "Sung-Hoon Yoon, Hoyong Kwon, Hyeonseong Kim, Kuk-Jin Yoon", + "authors": [ + { + "first_name": "Sung-Hoon", + "last_name": "Yoon" + }, + { + "first_name": "Hoyong", + "last_name": "Kwon" + }, + { + "first_name": "Hyeonseong", + "last_name": "Kim" + }, + { + "first_name": "Kuk-Jin", + "last_name": "Yoon" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FedHCA2: Towards Hetero-Client Federated Multi-Task Learning", - "authors": "Yuxiang Lu, Suizhi Huang, Yuwen Yang, Shalayiding Sirejiding, Yue Ding, Hongtao Lu", + "authors": [ + { + "first_name": "Yuxiang", + "last_name": "Lu" + }, + { + "first_name": "Suizhi", + "last_name": "Huang" + }, + { + "first_name": "Yuwen", + "last_name": "Yang" + }, + { + "first_name": "Shalayiding", + "last_name": "Sirejiding" + }, + { + "first_name": "Yue", + "last_name": "Ding" + }, + { + "first_name": "Hongtao", + "last_name": "Lu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Text-IF: Leveraging Semantic Text Guidance for Degradation-Aware and Interactive Image Fusion", - "authors": "Xunpeng Yi, Han Xu, Hao Zhang, Linfeng Tang, Jiayi Ma", + "authors": [ + { + "first_name": "Xunpeng", + "last_name": "Yi" + }, + { + "first_name": "Han", + "last_name": "Xu" + }, + { + "first_name": "Hao", + "last_name": "Zhang" + }, + { + "first_name": "Linfeng", + "last_name": "Tang" + }, + { + "first_name": "Jiayi", + "last_name": "Ma" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GRAM: Global Reasoning for Multi-Page VQA", - "authors": "Tsachi Blau, Sharon Fogel, Roi Ronen, Alona Golts, Roy Ganz, Elad Ben Avraham, Aviad Aberdam, Shahar Tsiper, Ron Litman", + "authors": [ + { + "first_name": "Tsachi", + "last_name": "Blau" + }, + { + "first_name": "Sharon", + "last_name": "Fogel" + }, + { + "first_name": "Roi", + "last_name": "Ronen" + }, + { + "first_name": "Alona", + "last_name": "Golts" + }, + { + "first_name": "Roy", + "last_name": "Ganz" + }, + { + "first_name": "Elad", + "last_name": "Ben Avraham" + }, + { + "first_name": "Aviad", + "last_name": "Aberdam" + }, + { + "first_name": "Shahar", + "last_name": "Tsiper" + }, + { + "first_name": "Ron", + "last_name": "Litman" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MS-DETR: Efficient DETR Training with Mixed Supervision", - "authors": "Chuyang Zhao, Yifan Sun, Wenhao Wang, Qiang Chen, Errui Ding, Yi Yang, Jingdong Wang", + "authors": [ + { + "first_name": "Chuyang", + "last_name": "Zhao" + }, + { + "first_name": "Yifan", + "last_name": "Sun" + }, + { + "first_name": "Wenhao", + "last_name": "Wang" + }, + { + "first_name": "Qiang", + "last_name": "Chen" + }, + { + "first_name": "Errui", + "last_name": "Ding" + }, + { + "first_name": "Yi", + "last_name": "Yang" + }, + { + "first_name": "Jingdong", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning to Produce Semi-dense Correspondences for Visual Localization", - "authors": "Khang Truong Giang, Soohwan Song, Sungho Jo", + "authors": [ + { + "first_name": "Khang", + "last_name": "Truong Giang" + }, + { + "first_name": "Soohwan", + "last_name": "Song" + }, + { + "first_name": "Sungho", + "last_name": "Jo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Amodal Ground Truth and Completion in the Wild", - "authors": "Guanqi Zhan, Chuanxia Zheng, Weidi Xie, Andrew Zisserman", + "authors": [ + { + "first_name": "Guanqi", + "last_name": "Zhan" + }, + { + "first_name": "Chuanxia", + "last_name": "Zheng" + }, + { + "first_name": "Weidi", + "last_name": "Xie" + }, + { + "first_name": "Andrew", + "last_name": "Zisserman" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Motion Diversification Networks", - "authors": "Hee Jae Kim, Eshed Ohn-Bar", + "authors": [ + { + "first_name": "Hee", + "last_name": "Jae Kim" + }, + { + "first_name": "Eshed", + "last_name": "Ohn-Bar" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence", - "authors": "Junyi Zhang, Charles Herrmann, Junhwa Hur, Eric Chen, Varun Jampani, Deqing Sun, Ming-Hsuan Yang", + "authors": [ + { + "first_name": "Junyi", + "last_name": "Zhang" + }, + { + "first_name": "Charles", + "last_name": "Herrmann" + }, + { + "first_name": "Junhwa", + "last_name": "Hur" + }, + { + "first_name": "Eric", + "last_name": "Chen" + }, + { + "first_name": "Varun", + "last_name": "Jampani" + }, + { + "first_name": "Deqing", + "last_name": "Sun" + }, + { + "first_name": "Ming-Hsuan", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "NECA: Neural Customizable Human Avatar", - "authors": "Junjin Xiao, Qing Zhang, Zhan Xu, Wei-Shi Zheng", + "authors": [ + { + "first_name": "Junjin", + "last_name": "Xiao" + }, + { + "first_name": "Qing", + "last_name": "Zhang" + }, + { + "first_name": "Zhan", + "last_name": "Xu" + }, + { + "first_name": "Wei-Shi", + "last_name": "Zheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "BEVSpread: Spread Voxel Pooling for Bird's-Eye-View Representation in Vision-based Roadside 3D Object Detection", - "authors": "Wenjie Wang, Yehao Lu, Guangcong Zheng, Shuigen Zhan, Xiaoqing Ye, Zichang Tan, Jingdong Wang, Gaoang Wang, Xi Li", + "authors": [ + { + "first_name": "Wenjie", + "last_name": "Wang" + }, + { + "first_name": "Yehao", + "last_name": "Lu" + }, + { + "first_name": "Guangcong", + "last_name": "Zheng" + }, + { + "first_name": "Shuigen", + "last_name": "Zhan" + }, + { + "first_name": "Xiaoqing", + "last_name": "Ye" + }, + { + "first_name": "Zichang", + "last_name": "Tan" + }, + { + "first_name": "Jingdong", + "last_name": "Wang" + }, + { + "first_name": "Gaoang", + "last_name": "Wang" + }, + { + "first_name": "Xi", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detection", - "authors": "Chengjie Wang, Wenbing Zhu, Bin-Bin Gao, Zhenye Gan, Jiangning Zhang, Zhihao Gu, Shuguang Qian, Mingang Chen, Lizhuang Ma", + "authors": [ + { + "first_name": "Chengjie", + "last_name": "Wang" + }, + { + "first_name": "Wenbing", + "last_name": "Zhu" + }, + { + "first_name": "Bin-Bin", + "last_name": "Gao" + }, + { + "first_name": "Zhenye", + "last_name": "Gan" + }, + { + "first_name": "Jiangning", + "last_name": "Zhang" + }, + { + "first_name": "Zhihao", + "last_name": "Gu" + }, + { + "first_name": "Shuguang", + "last_name": "Qian" + }, + { + "first_name": "Mingang", + "last_name": "Chen" + }, + { + "first_name": "Lizhuang", + "last_name": "Ma" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PAIR Diffusion: A Comprehensive Multimodal Object-Level Image Editor", - "authors": "Vidit Goel, Elia Peruzzo, Yifan Jiang, Dejia Xu, Xingqian Xu, Nicu Sebe, Trevor Darrell, Zhangyang Wang, Humphrey Shi", + "authors": [ + { + "first_name": "Vidit", + "last_name": "Goel" + }, + { + "first_name": "Elia", + "last_name": "Peruzzo" + }, + { + "first_name": "Yifan", + "last_name": "Jiang" + }, + { + "first_name": "Dejia", + "last_name": "Xu" + }, + { + "first_name": "Xingqian", + "last_name": "Xu" + }, + { + "first_name": "Nicu", + "last_name": "Sebe" + }, + { + "first_name": "Trevor", + "last_name": "Darrell" + }, + { + "first_name": "Zhangyang", + "last_name": "Wang" + }, + { + "first_name": "Humphrey", + "last_name": "Shi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Boosting Adversarial Transferability by Block Shuffle and Rotation", - "authors": "Kunyu Wang, Xuanran He, Wenxuan Wang, Xiaosen Wang", + "authors": [ + { + "first_name": "Kunyu", + "last_name": "Wang" + }, + { + "first_name": "Xuanran", + "last_name": "He" + }, + { + "first_name": "Wenxuan", + "last_name": "Wang" + }, + { + "first_name": "Xiaosen", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DriveWorld: 4D Pre-trained Scene Understanding via World Models for Autonomous Driving", - "authors": "Chen Min, Dawei Zhao, Liang Xiao, Jian Zhao, Xinli Xu, Zheng Zhu, Lei Jin, Jianshu Li, Yulan Guo, Junliang Xing, Liping Jing, Yiming Nie, Bin Dai", + "authors": [ + { + "first_name": "Chen", + "last_name": "Min" + }, + { + "first_name": "Dawei", + "last_name": "Zhao" + }, + { + "first_name": "Liang", + "last_name": "Xiao" + }, + { + "first_name": "Jian", + "last_name": "Zhao" + }, + { + "first_name": "Xinli", + "last_name": "Xu" + }, + { + "first_name": "Zheng", + "last_name": "Zhu" + }, + { + "first_name": "Lei", + "last_name": "Jin" + }, + { + "first_name": "Jianshu", + "last_name": "Li" + }, + { + "first_name": "Yulan", + "last_name": "Guo" + }, + { + "first_name": "Junliang", + "last_name": "Xing" + }, + { + "first_name": "Liping", + "last_name": "Jing" + }, + { + "first_name": "Yiming", + "last_name": "Nie" + }, + { + "first_name": "Bin", + "last_name": "Dai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Bridging the Gap Between End-to-End and Two-Step Text Spotting", - "authors": "Mingxin Huang, Hongliang Li, Yuliang Liu, Xiang Bai, Lianwen Jin", + "authors": [ + { + "first_name": "Mingxin", + "last_name": "Huang" + }, + { + "first_name": "Hongliang", + "last_name": "Li" + }, + { + "first_name": "Yuliang", + "last_name": "Liu" + }, + { + "first_name": "Xiang", + "last_name": "Bai" + }, + { + "first_name": "Lianwen", + "last_name": "Jin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "TokenCompose: Text-to-Image Diffusion with Token-level Supervision", - "authors": "Zirui Wang, Zhizhou Sha, Zheng Ding, Yilin Wang, Zhuowen Tu", + "authors": [ + { + "first_name": "Zirui", + "last_name": "Wang" + }, + { + "first_name": "Zhizhou", + "last_name": "Sha" + }, + { + "first_name": "Zheng", + "last_name": "Ding" + }, + { + "first_name": "Yilin", + "last_name": "Wang" + }, + { + "first_name": "Zhuowen", + "last_name": "Tu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SUGAR: Pre-training 3D Visual Representations for Robotics", - "authors": "Shizhe Chen, Ricardo Garcia, Ivan Laptev, Cordelia Schmid", + "authors": [ + { + "first_name": "Shizhe", + "last_name": "Chen" + }, + { + "first_name": "Ricardo", + "last_name": "Garcia" + }, + { + "first_name": "Ivan", + "last_name": "Laptev" + }, + { + "first_name": "Cordelia", + "last_name": "Schmid" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LidaRF: Delving into Lidar for Neural Radiance Field on Street Scenes", - "authors": "Shanlin Sun, Bingbing Zhuang, Ziyu Jiang, Buyu Liu, Xiaohui Xie, Manmohan Chandraker", + "authors": [ + { + "first_name": "Shanlin", + "last_name": "Sun" + }, + { + "first_name": "Bingbing", + "last_name": "Zhuang" + }, + { + "first_name": "Ziyu", + "last_name": "Jiang" + }, + { + "first_name": "Buyu", + "last_name": "Liu" + }, + { + "first_name": "Xiaohui", + "last_name": "Xie" + }, + { + "first_name": "Manmohan", + "last_name": "Chandraker" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PairAug: What Can Augmented Image-Text Pairs Do for Radiology?", - "authors": "Yutong Xie, Qi Chen, Sinuo Wang, Minh-Son To, Iris Lee, Ee Win Khoo, Kerolos Hendy, Daniel Koh, Yong Xia, Qi Wu", + "authors": [ + { + "first_name": "Yutong", + "last_name": "Xie" + }, + { + "first_name": "Qi", + "last_name": "Chen" + }, + { + "first_name": "Sinuo", + "last_name": "Wang" + }, + { + "first_name": "Minh-Son", + "last_name": "To" + }, + { + "first_name": "Iris", + "last_name": "Lee" + }, + { + "first_name": "Ee", + "last_name": "Win Khoo" + }, + { + "first_name": "Kerolos", + "last_name": "Hendy" + }, + { + "first_name": "Daniel", + "last_name": "Koh" + }, + { + "first_name": "Yong", + "last_name": "Xia" + }, + { + "first_name": "Qi", + "last_name": "Wu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FINER: Flexible Spectral-bias Tuning in Implicit NEural Representation by Variable-periodic Activation Functions", - "authors": "Zhen Liu, Hao Zhu, Qi Zhang, Jingde Fu, Weibing Deng, Zhan Ma, Yanwen Guo, Xun Cao", + "authors": [ + { + "first_name": "Zhen", + "last_name": "Liu" + }, + { + "first_name": "Hao", + "last_name": "Zhu" + }, + { + "first_name": "Qi", + "last_name": "Zhang" + }, + { + "first_name": "Jingde", + "last_name": "Fu" + }, + { + "first_name": "Weibing", + "last_name": "Deng" + }, + { + "first_name": "Zhan", + "last_name": "Ma" + }, + { + "first_name": "Yanwen", + "last_name": "Guo" + }, + { + "first_name": "Xun", + "last_name": "Cao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Harnessing Large Language Models for Training-free Video Anomaly Detection", - "authors": "Luca Zanella, Willi Menapace, Massimiliano Mancini, Yiming Wang, Elisa Ricci", + "authors": [ + { + "first_name": "Luca", + "last_name": "Zanella" + }, + { + "first_name": "Willi", + "last_name": "Menapace" + }, + { + "first_name": "Massimiliano", + "last_name": "Mancini" + }, + { + "first_name": "Yiming", + "last_name": "Wang" + }, + { + "first_name": "Elisa", + "last_name": "Ricci" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "TextCraftor: Your Text Encoder Can be Image Quality Controller", - "authors": "Yanyu Li, Xian Liu, Anil Kag, Ju Hu, Yerlan Idelbayev, Dhritiman Sagar, Yanzhi Wang, Sergey Tulyakov, Jian Ren", + "authors": [ + { + "first_name": "Yanyu", + "last_name": "Li" + }, + { + "first_name": "Xian", + "last_name": "Liu" + }, + { + "first_name": "Anil", + "last_name": "Kag" + }, + { + "first_name": "Ju", + "last_name": "Hu" + }, + { + "first_name": "Yerlan", + "last_name": "Idelbayev" + }, + { + "first_name": "Dhritiman", + "last_name": "Sagar" + }, + { + "first_name": "Yanzhi", + "last_name": "Wang" + }, + { + "first_name": "Sergey", + "last_name": "Tulyakov" + }, + { + "first_name": "Jian", + "last_name": "Ren" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FineParser: A Fine-grained Spatio-temporal Action Parser for Human-centric Action Quality Assessment", - "authors": "Jinglin Xu, Sibo Yin, Guohao Zhao, Zishuo Wang, Yuxin Peng", + "authors": [ + { + "first_name": "Jinglin", + "last_name": "Xu" + }, + { + "first_name": "Sibo", + "last_name": "Yin" + }, + { + "first_name": "Guohao", + "last_name": "Zhao" + }, + { + "first_name": "Zishuo", + "last_name": "Wang" + }, + { + "first_name": "Yuxin", + "last_name": "Peng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Video Recognition in Portrait Mode", - "authors": "Mingfei Han, Linjie Yang, Xiaojie Jin, Jiashi Feng, Xiaojun Chang, Heng Wang", + "authors": [ + { + "first_name": "Mingfei", + "last_name": "Han" + }, + { + "first_name": "Linjie", + "last_name": "Yang" + }, + { + "first_name": "Xiaojie", + "last_name": "Jin" + }, + { + "first_name": "Jiashi", + "last_name": "Feng" + }, + { + "first_name": "Xiaojun", + "last_name": "Chang" + }, + { + "first_name": "Heng", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Selective Hourglass Mapping for Universal Image Restoration Based on Diffusion Model", - "authors": "Dian Zheng, Xiao-Ming Wu, Shuzhou Yang, Jian Zhang, Jian-Fang Hu, Wei-Shi Zheng", + "authors": [ + { + "first_name": "Dian", + "last_name": "Zheng" + }, + { + "first_name": "Xiao-Ming", + "last_name": "Wu" + }, + { + "first_name": "Shuzhou", + "last_name": "Yang" + }, + { + "first_name": "Jian", + "last_name": "Zhang" + }, + { + "first_name": "Jian-Fang", + "last_name": "Hu" + }, + { + "first_name": "Wei-Shi", + "last_name": "Zheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Language Models as Black-Box Optimizers for Vision-Language Models", - "authors": "Shihong Liu, Samuel Yu, Zhiqiu Lin, Deepak Pathak, Deva Ramanan", + "authors": [ + { + "first_name": "Shihong", + "last_name": "Liu" + }, + { + "first_name": "Samuel", + "last_name": "Yu" + }, + { + "first_name": "Zhiqiu", + "last_name": "Lin" + }, + { + "first_name": "Deepak", + "last_name": "Pathak" + }, + { + "first_name": "Deva", + "last_name": "Ramanan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Exploring Orthogonality in Open World Object Detection", - "authors": "Zhicheng Sun, Jinghan Li, Yadong Mu", + "authors": [ + { + "first_name": "Zhicheng", + "last_name": "Sun" + }, + { + "first_name": "Jinghan", + "last_name": "Li" + }, + { + "first_name": "Yadong", + "last_name": "Mu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding", - "authors": "Sicong Leng, Hang Zhang, Guanzheng Chen, Xin Li, Shijian Lu, Chunyan Miao, Lidong Bing", + "authors": [ + { + "first_name": "Sicong", + "last_name": "Leng" + }, + { + "first_name": "Hang", + "last_name": "Zhang" + }, + { + "first_name": "Guanzheng", + "last_name": "Chen" + }, + { + "first_name": "Xin", + "last_name": "Li" + }, + { + "first_name": "Shijian", + "last_name": "Lu" + }, + { + "first_name": "Chunyan", + "last_name": "Miao" + }, + { + "first_name": "Lidong", + "last_name": "Bing" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "IMPRINT: Generative Object Compositing by Learning Identity-Preserving Representation", - "authors": "Yizhi Song, Zhifei Zhang, Zhe Lin, Scott Cohen, Brian Price, Jianming Zhang, Soo Ye Kim, He Zhang, Wei Xiong, Daniel Aliaga", + "authors": [ + { + "first_name": "Yizhi", + "last_name": "Song" + }, + { + "first_name": "Zhifei", + "last_name": "Zhang" + }, + { + "first_name": "Zhe", + "last_name": "Lin" + }, + { + "first_name": "Scott", + "last_name": "Cohen" + }, + { + "first_name": "Brian", + "last_name": "Price" + }, + { + "first_name": "Jianming", + "last_name": "Zhang" + }, + { + "first_name": "Soo", + "last_name": "Ye Kim" + }, + { + "first_name": "He", + "last_name": "Zhang" + }, + { + "first_name": "Wei", + "last_name": "Xiong" + }, + { + "first_name": "Daniel", + "last_name": "Aliaga" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Audio-Visual Segmentation via Unlabeled Frame Exploitation", - "authors": "Jinxiang Liu, Yikun Liu, Fei Zhang, Chen Ju, Ya Zhang, Yanfeng Wang", + "authors": [ + { + "first_name": "Jinxiang", + "last_name": "Liu" + }, + { + "first_name": "Yikun", + "last_name": "Liu" + }, + { + "first_name": "Fei", + "last_name": "Zhang" + }, + { + "first_name": "Chen", + "last_name": "Ju" + }, + { + "first_name": "Ya", + "last_name": "Zhang" + }, + { + "first_name": "Yanfeng", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DriveTrack: A Benchmark for Long-Range Point Tracking in Real-World Videos", - "authors": "Arjun Balasingam, Joseph Chandler, Chenning Li, Zhoutong Zhang, Hari Balakrishnan", + "authors": [ + { + "first_name": "Arjun", + "last_name": "Balasingam" + }, + { + "first_name": "Joseph", + "last_name": "Chandler" + }, + { + "first_name": "Chenning", + "last_name": "Li" + }, + { + "first_name": "Zhoutong", + "last_name": "Zhang" + }, + { + "first_name": "Hari", + "last_name": "Balakrishnan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Infrared Adversarial Car Stickers", - "authors": "Xiaopei Zhu, Yuqiu Liu, Zhanhao Hu, Jianmin Li, Xiaolin Hu", + "authors": [ + { + "first_name": "Xiaopei", + "last_name": "Zhu" + }, + { + "first_name": "Yuqiu", + "last_name": "Liu" + }, + { + "first_name": "Zhanhao", + "last_name": "Hu" + }, + { + "first_name": "Jianmin", + "last_name": "Li" + }, + { + "first_name": "Xiaolin", + "last_name": "Hu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Sculpt3D: Multi-View Consistent Text-to-3D Generation with Sparse 3D Prior", - "authors": "Cheng Chen, Xiaofeng Yang, Fan Yang, Chengzeng Feng, Zhoujie Fu, Chuan-Sheng Foo, Guosheng Lin, Fayao Liu", + "authors": [ + { + "first_name": "Cheng", + "last_name": "Chen" + }, + { + "first_name": "Xiaofeng", + "last_name": "Yang" + }, + { + "first_name": "Fan", + "last_name": "Yang" + }, + { + "first_name": "Chengzeng", + "last_name": "Feng" + }, + { + "first_name": "Zhoujie", + "last_name": "Fu" + }, + { + "first_name": "Chuan-Sheng", + "last_name": "Foo" + }, + { + "first_name": "Guosheng", + "last_name": "Lin" + }, + { + "first_name": "Fayao", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FreeMan: Towards Benchmarking 3D Human Pose Estimation under Real-World Conditions", - "authors": "Jiong Wang, Fengyu Yang, Bingliang Li, Wenbo Gou, Danqi Yan, Ailing Zeng, Yijun Gao, Junle Wang, Yanqing Jing, Ruimao Zhang", + "authors": [ + { + "first_name": "Jiong", + "last_name": "Wang" + }, + { + "first_name": "Fengyu", + "last_name": "Yang" + }, + { + "first_name": "Bingliang", + "last_name": "Li" + }, + { + "first_name": "Wenbo", + "last_name": "Gou" + }, + { + "first_name": "Danqi", + "last_name": "Yan" + }, + { + "first_name": "Ailing", + "last_name": "Zeng" + }, + { + "first_name": "Yijun", + "last_name": "Gao" + }, + { + "first_name": "Junle", + "last_name": "Wang" + }, + { + "first_name": "Yanqing", + "last_name": "Jing" + }, + { + "first_name": "Ruimao", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ScanFormer: Referring Expression Comprehension by Iteratively Scanning", - "authors": "Wei Su, Peihan Miao, Huanzhang Dou, Xi Li", + "authors": [ + { + "first_name": "Wei", + "last_name": "Su" + }, + { + "first_name": "Peihan", + "last_name": "Miao" + }, + { + "first_name": "Huanzhang", + "last_name": "Dou" + }, + { + "first_name": "Xi", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Model Inversion Robustness: Can Transfer Learning Help?", - "authors": "Sy-Tuyen Ho, Koh Jun Hao, Keshigeyan Chandrasegaran, Ngoc-Bao Nguyen, Ngai-Man Cheung", + "authors": [ + { + "first_name": "Sy-Tuyen", + "last_name": "Ho" + }, + { + "first_name": "Koh", + "last_name": "Jun Hao" + }, + { + "first_name": "Keshigeyan", + "last_name": "Chandrasegaran" + }, + { + "first_name": "Ngoc-Bao", + "last_name": "Nguyen" + }, + { + "first_name": "Ngai-Man", + "last_name": "Cheung" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Portrait4D: Learning One-Shot 4D Head Avatar Synthesis using Synthetic Data", - "authors": "Yu Deng, Duomin Wang, Xiaohang Ren, Xingyu Chen, Baoyuan Wang", + "authors": [ + { + "first_name": "Yu", + "last_name": "Deng" + }, + { + "first_name": "Duomin", + "last_name": "Wang" + }, + { + "first_name": "Xiaohang", + "last_name": "Ren" + }, + { + "first_name": "Xingyu", + "last_name": "Chen" + }, + { + "first_name": "Baoyuan", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GP-NeRF: Generalized Perception NeRF for Context-Aware 3D Scene Understanding", - "authors": "Hao Li, Dingwen Zhang, Yalun Dai, Nian Liu, Lechao Cheng, Jingfeng Li, Jingdong Wang, Junwei Han", + "authors": [ + { + "first_name": "Hao", + "last_name": "Li" + }, + { + "first_name": "Dingwen", + "last_name": "Zhang" + }, + { + "first_name": "Yalun", + "last_name": "Dai" + }, + { + "first_name": "Nian", + "last_name": "Liu" + }, + { + "first_name": "Lechao", + "last_name": "Cheng" + }, + { + "first_name": "Jingfeng", + "last_name": "Li" + }, + { + "first_name": "Jingdong", + "last_name": "Wang" + }, + { + "first_name": "Junwei", + "last_name": "Han" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Polarization Wavefront Lidar: Learning Large Scene Reconstruction from Polarized Wavefronts", - "authors": "Dominik Scheuble, Chenyang Lei, Seung-Hwan Baek, Mario Bijelic, Felix Heide", + "authors": [ + { + "first_name": "Dominik", + "last_name": "Scheuble" + }, + { + "first_name": "Chenyang", + "last_name": "Lei" + }, + { + "first_name": "Seung-Hwan", + "last_name": "Baek" + }, + { + "first_name": "Mario", + "last_name": "Bijelic" + }, + { + "first_name": "Felix", + "last_name": "Heide" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GDA: Generalized Diffusion for Robust Test-time Adaptation", - "authors": "Yun-Yun Tsai, Fu-Chen Chen, Albert Y. C. Chen, Junfeng Yang, Che-Chun Su, Min Sun, Cheng-Hao Kuo", + "authors": [ + { + "first_name": "Yun-Yun", + "last_name": "Tsai" + }, + { + "first_name": "Fu-Chen", + "last_name": "Chen" + }, + { + "first_name": "Albert", + "last_name": "Y. C. Chen" + }, + { + "first_name": "Junfeng", + "last_name": "Yang" + }, + { + "first_name": "Che-Chun", + "last_name": "Su" + }, + { + "first_name": "Min", + "last_name": "Sun" + }, + { + "first_name": "Cheng-Hao", + "last_name": "Kuo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ConvoFusion: Multi-Modal Conversational Diffusion for Co-Speech Gesture Synthesis", - "authors": "Muhammad Hamza Mughal, Rishabh Dabral, Ikhsanul Habibie, Lucia Donatelli, Marc Habermann, Christian Theobalt", + "authors": [ + { + "first_name": "Muhammad", + "last_name": "Hamza Mughal" + }, + { + "first_name": "Rishabh", + "last_name": "Dabral" + }, + { + "first_name": "Ikhsanul", + "last_name": "Habibie" + }, + { + "first_name": "Lucia", + "last_name": "Donatelli" + }, + { + "first_name": "Marc", + "last_name": "Habermann" + }, + { + "first_name": "Christian", + "last_name": "Theobalt" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback", - "authors": "Tianyu Yu, Yuan Yao, Haoye Zhang, Taiwen He, Yifeng Han, Ganqu Cui, Jinyi Hu, Zhiyuan Liu, Hai-Tao Zheng, Maosong Sun, Tat-Seng Chua", + "authors": [ + { + "first_name": "Tianyu", + "last_name": "Yu" + }, + { + "first_name": "Yuan", + "last_name": "Yao" + }, + { + "first_name": "Haoye", + "last_name": "Zhang" + }, + { + "first_name": "Taiwen", + "last_name": "He" + }, + { + "first_name": "Yifeng", + "last_name": "Han" + }, + { + "first_name": "Ganqu", + "last_name": "Cui" + }, + { + "first_name": "Jinyi", + "last_name": "Hu" + }, + { + "first_name": "Zhiyuan", + "last_name": "Liu" + }, + { + "first_name": "Hai-Tao", + "last_name": "Zheng" + }, + { + "first_name": "Maosong", + "last_name": "Sun" + }, + { + "first_name": "Tat-Seng", + "last_name": "Chua" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ZeroShape: Regression-based Zero-shot Shape Reconstruction", - "authors": "Zixuan Huang, Stefan Stojanov, Anh Thai, Varun Jampani, James M. Rehg", + "authors": [ + { + "first_name": "Zixuan", + "last_name": "Huang" + }, + { + "first_name": "Stefan", + "last_name": "Stojanov" + }, + { + "first_name": "Anh", + "last_name": "Thai" + }, + { + "first_name": "Varun", + "last_name": "Jampani" + }, + { + "first_name": "James", + "last_name": "M. Rehg" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Continual-MAE: Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptation", - "authors": "Jiaming Liu, Ran Xu, Senqiao Yang, Renrui Zhang, Qizhe Zhang, Zehui Chen, Yandong Guo, Shanghang Zhang", + "authors": [ + { + "first_name": "Jiaming", + "last_name": "Liu" + }, + { + "first_name": "Ran", + "last_name": "Xu" + }, + { + "first_name": "Senqiao", + "last_name": "Yang" + }, + { + "first_name": "Renrui", + "last_name": "Zhang" + }, + { + "first_name": "Qizhe", + "last_name": "Zhang" + }, + { + "first_name": "Zehui", + "last_name": "Chen" + }, + { + "first_name": "Yandong", + "last_name": "Guo" + }, + { + "first_name": "Shanghang", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "The STVchrono Dataset: Towards Continuous Change Recognition in Time", - "authors": "Yanjun Sun, Yue Qiu, Mariia Khan, Fumiya Matsuzawa, Kenji Iwata", + "authors": [ + { + "first_name": "Yanjun", + "last_name": "Sun" + }, + { + "first_name": "Yue", + "last_name": "Qiu" + }, + { + "first_name": "Mariia", + "last_name": "Khan" + }, + { + "first_name": "Fumiya", + "last_name": "Matsuzawa" + }, + { + "first_name": "Kenji", + "last_name": "Iwata" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SocialCircle: Learning the Angle-based Social Interaction Representation for Pedestrian Trajectory Prediction", - "authors": "Conghao Wong, Beihao Xia, Ziqian Zou, Yulong Wang, Xinge You", + "authors": [ + { + "first_name": "Conghao", + "last_name": "Wong" + }, + { + "first_name": "Beihao", + "last_name": "Xia" + }, + { + "first_name": "Ziqian", + "last_name": "Zou" + }, + { + "first_name": "Yulong", + "last_name": "Wang" + }, + { + "first_name": "Xinge", + "last_name": "You" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Boosting Neural Representations for Videos with a Conditional Decoder", - "authors": "Xinjie Zhang, Ren Yang, Dailan He, Xingtong Ge, Tongda Xu, Yan Wang, Hongwei Qin, Jun Zhang", + "authors": [ + { + "first_name": "Xinjie", + "last_name": "Zhang" + }, + { + "first_name": "Ren", + "last_name": "Yang" + }, + { + "first_name": "Dailan", + "last_name": "He" + }, + { + "first_name": "Xingtong", + "last_name": "Ge" + }, + { + "first_name": "Tongda", + "last_name": "Xu" + }, + { + "first_name": "Yan", + "last_name": "Wang" + }, + { + "first_name": "Hongwei", + "last_name": "Qin" + }, + { + "first_name": "Jun", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Dual-Enhanced Coreset Selection with Class-wise Collaboration for Online Blurry Class Incremental Learning", - "authors": "Yutian Luo, Shiqi Zhao, Haoran Wu, Zhiwu Lu", + "authors": [ + { + "first_name": "Yutian", + "last_name": "Luo" + }, + { + "first_name": "Shiqi", + "last_name": "Zhao" + }, + { + "first_name": "Haoran", + "last_name": "Wu" + }, + { + "first_name": "Zhiwu", + "last_name": "Lu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "From Audio to Photoreal Embodiment: Synthesizing Humans in Conversations", - "authors": "Evonne Ng, Javier Romero, Timur Bagautdinov, Shaojie Bai, Trevor Darrell, Angjoo Kanazawa, Alexander Richard", + "authors": [ + { + "first_name": "Evonne", + "last_name": "Ng" + }, + { + "first_name": "Javier", + "last_name": "Romero" + }, + { + "first_name": "Timur", + "last_name": "Bagautdinov" + }, + { + "first_name": "Shaojie", + "last_name": "Bai" + }, + { + "first_name": "Trevor", + "last_name": "Darrell" + }, + { + "first_name": "Angjoo", + "last_name": "Kanazawa" + }, + { + "first_name": "Alexander", + "last_name": "Richard" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Single-View Scene Point Cloud Human Grasp Generation", - "authors": "Yan-Kang Wang, Chengyi Xing, Yi-Lin Wei, Xiao-Ming Wu, Wei-Shi Zheng", + "authors": [ + { + "first_name": "Yan-Kang", + "last_name": "Wang" + }, + { + "first_name": "Chengyi", + "last_name": "Xing" + }, + { + "first_name": "Yi-Lin", + "last_name": "Wei" + }, + { + "first_name": "Xiao-Ming", + "last_name": "Wu" + }, + { + "first_name": "Wei-Shi", + "last_name": "Zheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "One-step Diffusion with Distribution Matching Distillation", - "authors": "Tianwei Yin, Michaël Gharbi, Richard Zhang, Eli Shechtman, Frédo Durand, William T. Freeman, Taesung Park", + "authors": [ + { + "first_name": "Tianwei", + "last_name": "Yin" + }, + { + "first_name": "Michaël", + "last_name": "Gharbi" + }, + { + "first_name": "Richard", + "last_name": "Zhang" + }, + { + "first_name": "Eli", + "last_name": "Shechtman" + }, + { + "first_name": "Frédo", + "last_name": "Durand" + }, + { + "first_name": "William", + "last_name": "T. Freeman" + }, + { + "first_name": "Taesung", + "last_name": "Park" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Cyclic Learning for Binaural Audio Generation and Localization", - "authors": "Zhaojian Li, Bin Zhao, Yuan Yuan", + "authors": [ + { + "first_name": "Zhaojian", + "last_name": "Li" + }, + { + "first_name": "Bin", + "last_name": "Zhao" + }, + { + "first_name": "Yuan", + "last_name": "Yuan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Neighbor Relations Matter in Video Scene Detection", - "authors": "Jiawei Tan, Hongxing Wang, Jiaxin Li, Zhilong Ou, Zhangbin Qian", + "authors": [ + { + "first_name": "Jiawei", + "last_name": "Tan" + }, + { + "first_name": "Hongxing", + "last_name": "Wang" + }, + { + "first_name": "Jiaxin", + "last_name": "Li" + }, + { + "first_name": "Zhilong", + "last_name": "Ou" + }, + { + "first_name": "Zhangbin", + "last_name": "Qian" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Rethinking Human Motion Prediction with Symplectic Integral", - "authors": "Haipeng Chen, Kedi Lyu, Zhenguang Liu, Yifang Yin, Xun Yang, Yingda Lyu", + "authors": [ + { + "first_name": "Haipeng", + "last_name": "Chen" + }, + { + "first_name": "Kedi", + "last_name": "Lyu" + }, + { + "first_name": "Zhenguang", + "last_name": "Liu" + }, + { + "first_name": "Yifang", + "last_name": "Yin" + }, + { + "first_name": "Xun", + "last_name": "Yang" + }, + { + "first_name": "Yingda", + "last_name": "Lyu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Text-to-Image Diffusion Models are Great Sketch-Photo Matchmakers", - "authors": "Subhadeep Koley, Ayan Kumar Bhunia, Aneeshan Sain, Pinaki Nath Chowdhury, Tao Xiang, Yi-Zhe Song", + "authors": [ + { + "first_name": "Subhadeep", + "last_name": "Koley" + }, + { + "first_name": "Ayan", + "last_name": "Kumar Bhunia" + }, + { + "first_name": "Aneeshan", + "last_name": "Sain" + }, + { + "first_name": "Pinaki", + "last_name": "Nath Chowdhury" + }, + { + "first_name": "Tao", + "last_name": "Xiang" + }, + { + "first_name": "Yi-Zhe", + "last_name": "Song" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Mudslide: A Universal Nuclear Instance Segmentation Method", - "authors": "Jun Wang", + "authors": [ + { + "first_name": "Jun", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CPGA: Coding Priors-Guided Aggregation Network for Compressed Video Quality Enhancement", - "authors": "Qiang Zhu, Jinhua Hao, Yukang Ding, Yu Liu, Qiao Mo, Ming Sun, Chao Zhou, Shuyuan Zhu", + "authors": [ + { + "first_name": "Qiang", + "last_name": "Zhu" + }, + { + "first_name": "Jinhua", + "last_name": "Hao" + }, + { + "first_name": "Yukang", + "last_name": "Ding" + }, + { + "first_name": "Yu", + "last_name": "Liu" + }, + { + "first_name": "Qiao", + "last_name": "Mo" + }, + { + "first_name": "Ming", + "last_name": "Sun" + }, + { + "first_name": "Chao", + "last_name": "Zhou" + }, + { + "first_name": "Shuyuan", + "last_name": "Zhu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MicroCinema: A Divide-and-Conquer Approach for Text-to-Video Generation", - "authors": "Yanhui Wang, Jianmin Bao, Wenming Weng, Ruoyu Feng, Dacheng Yin, Tao Yang, Jingxu Zhang, Qi Dai, Zhiyuan Zhao, Chunyu Wang, Kai Qiu, Yuhui Yuan, Xiaoyan Sun, Chong Luo, Baining Guo", + "authors": [ + { + "first_name": "Yanhui", + "last_name": "Wang" + }, + { + "first_name": "Jianmin", + "last_name": "Bao" + }, + { + "first_name": "Wenming", + "last_name": "Weng" + }, + { + "first_name": "Ruoyu", + "last_name": "Feng" + }, + { + "first_name": "Dacheng", + "last_name": "Yin" + }, + { + "first_name": "Tao", + "last_name": "Yang" + }, + { + "first_name": "Jingxu", + "last_name": "Zhang" + }, + { + "first_name": "Qi", + "last_name": "Dai" + }, + { + "first_name": "Zhiyuan", + "last_name": "Zhao" + }, + { + "first_name": "Chunyu", + "last_name": "Wang" + }, + { + "first_name": "Kai", + "last_name": "Qiu" + }, + { + "first_name": "Yuhui", + "last_name": "Yuan" + }, + { + "first_name": "Xiaoyan", + "last_name": "Sun" + }, + { + "first_name": "Chong", + "last_name": "Luo" + }, + { + "first_name": "Baining", + "last_name": "Guo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning Instance-Aware Correspondences for Robust Multi-Instance Point Cloud Registration in Cluttered Scenes", - "authors": "Zhiyuan Yu, Zheng Qin, Lintao Zheng, Kai Xu", + "authors": [ + { + "first_name": "Zhiyuan", + "last_name": "Yu" + }, + { + "first_name": "Zheng", + "last_name": "Qin" + }, + { + "first_name": "Lintao", + "last_name": "Zheng" + }, + { + "first_name": "Kai", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Structure Matters: Tackling the Semantic Discrepancy in Diffusion Models for Image Inpainting", - "authors": "Haipeng Liu, Yang Wang, Biao Qian, Meng Wang, Yong Rui", + "authors": [ + { + "first_name": "Haipeng", + "last_name": "Liu" + }, + { + "first_name": "Yang", + "last_name": "Wang" + }, + { + "first_name": "Biao", + "last_name": "Qian" + }, + { + "first_name": "Meng", + "last_name": "Wang" + }, + { + "first_name": "Yong", + "last_name": "Rui" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Modeling Multimodal Social Interactions: New Challenges and Baselines with Densely Aligned Representations", - "authors": "Sangmin Lee, Bolin Lai, Fiona Ryan, Bikram Boote, James M. Rehg", + "authors": [ + { + "first_name": "Sangmin", + "last_name": "Lee" + }, + { + "first_name": "Bolin", + "last_name": "Lai" + }, + { + "first_name": "Fiona", + "last_name": "Ryan" + }, + { + "first_name": "Bikram", + "last_name": "Boote" + }, + { + "first_name": "James", + "last_name": "M. Rehg" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "COCONut: Modernizing COCO Segmentation", - "authors": "Xueqing Deng, Qihang Yu, Peng Wang, Xiaohui Shen, Liang-Chieh Chen", + "authors": [ + { + "first_name": "Xueqing", + "last_name": "Deng" + }, + { + "first_name": "Qihang", + "last_name": "Yu" + }, + { + "first_name": "Peng", + "last_name": "Wang" + }, + { + "first_name": "Xiaohui", + "last_name": "Shen" + }, + { + "first_name": "Liang-Chieh", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Semantic Line Combination Detector", - "authors": "Jinwon Ko, Dongkwon Jin, Chang-Su Kim", + "authors": [ + { + "first_name": "Jinwon", + "last_name": "Ko" + }, + { + "first_name": "Dongkwon", + "last_name": "Jin" + }, + { + "first_name": "Chang-Su", + "last_name": "Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Prompt-Driven Dynamic Object-Centric Learning for Single Domain Generalization", - "authors": "Deng Li, Aming Wu, Yaowei Wang, Yahong Han", + "authors": [ + { + "first_name": "Deng", + "last_name": "Li" + }, + { + "first_name": "Aming", + "last_name": "Wu" + }, + { + "first_name": "Yaowei", + "last_name": "Wang" + }, + { + "first_name": "Yahong", + "last_name": "Han" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Dual Pose-invariant Embeddings: Learning Category and Object-specific Discriminative Representations for Recognition and Retrieval", - "authors": "Rohan Sarkar, Avinash Kak", + "authors": [ + { + "first_name": "Rohan", + "last_name": "Sarkar" + }, + { + "first_name": "Avinash", + "last_name": "Kak" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "vid-TLDR: Training Free Token Merging for Light-weight Video Transformer", - "authors": "Joonmyung Choi, Sanghyeok Lee, Jaewon Chu, Minhyuk Choi, Hyunwoo J. Kim", + "authors": [ + { + "first_name": "Joonmyung", + "last_name": "Choi" + }, + { + "first_name": "Sanghyeok", + "last_name": "Lee" + }, + { + "first_name": "Jaewon", + "last_name": "Chu" + }, + { + "first_name": "Minhyuk", + "last_name": "Choi" + }, + { + "first_name": "Hyunwoo", + "last_name": "J. Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DRESS: Instructing Large Vision-Language Models to Align and Interact with Humans via Natural Language Feedback", - "authors": "Yangyi Chen, Karan Sikka, Michael Cogswell, Heng Ji, Ajay Divakaran", + "authors": [ + { + "first_name": "Yangyi", + "last_name": "Chen" + }, + { + "first_name": "Karan", + "last_name": "Sikka" + }, + { + "first_name": "Michael", + "last_name": "Cogswell" + }, + { + "first_name": "Heng", + "last_name": "Ji" + }, + { + "first_name": "Ajay", + "last_name": "Divakaran" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Makeup Prior Models for 3D Facial Makeup Estimation and Applications", - "authors": "Xingchao Yang, Takafumi Taketomi, Yuki Endo, Yoshihiro Kanamori", + "authors": [ + { + "first_name": "Xingchao", + "last_name": "Yang" + }, + { + "first_name": "Takafumi", + "last_name": "Taketomi" + }, + { + "first_name": "Yuki", + "last_name": "Endo" + }, + { + "first_name": "Yoshihiro", + "last_name": "Kanamori" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinement", - "authors": "Xiuquan Hou, Meiqin Liu, Senlin Zhang, Ping Wei, Badong Chen", + "authors": [ + { + "first_name": "Xiuquan", + "last_name": "Hou" + }, + { + "first_name": "Meiqin", + "last_name": "Liu" + }, + { + "first_name": "Senlin", + "last_name": "Zhang" + }, + { + "first_name": "Ping", + "last_name": "Wei" + }, + { + "first_name": "Badong", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards More Unified In-context Visual Understanding", - "authors": "Dianmo Sheng, Dongdong Chen, Zhentao Tan, Qiankun Liu, Qi Chu, Jianmin Bao, Tao Gong, Bin Liu, Shengwei Xu, Nenghai Yu", + "authors": [ + { + "first_name": "Dianmo", + "last_name": "Sheng" + }, + { + "first_name": "Dongdong", + "last_name": "Chen" + }, + { + "first_name": "Zhentao", + "last_name": "Tan" + }, + { + "first_name": "Qiankun", + "last_name": "Liu" + }, + { + "first_name": "Qi", + "last_name": "Chu" + }, + { + "first_name": "Jianmin", + "last_name": "Bao" + }, + { + "first_name": "Tao", + "last_name": "Gong" + }, + { + "first_name": "Bin", + "last_name": "Liu" + }, + { + "first_name": "Shengwei", + "last_name": "Xu" + }, + { + "first_name": "Nenghai", + "last_name": "Yu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "F3Loc: Fusion and Filtering for Floorplan Localization", - "authors": "Changan Chen, Rui Wang, Christoph Vogel, Marc Pollefeys", + "authors": [ + { + "first_name": "Changan", + "last_name": "Chen" + }, + { + "first_name": "Rui", + "last_name": "Wang" + }, + { + "first_name": "Christoph", + "last_name": "Vogel" + }, + { + "first_name": "Marc", + "last_name": "Pollefeys" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ReconFusion: 3D Reconstruction with Diffusion Priors", - "authors": "Rundi Wu, Ben Mildenhall, Philipp Henzler, Keunhong Park, Ruiqi Gao, Daniel Watson, Pratul P. Srinivasan, Dor Verbin, Jonathan T. Barron, Ben Poole, Aleksander Ho?y?ski", + "authors": [ + { + "first_name": "Rundi", + "last_name": "Wu" + }, + { + "first_name": "Ben", + "last_name": "Mildenhall" + }, + { + "first_name": "Philipp", + "last_name": "Henzler" + }, + { + "first_name": "Keunhong", + "last_name": "Park" + }, + { + "first_name": "Ruiqi", + "last_name": "Gao" + }, + { + "first_name": "Daniel", + "last_name": "Watson" + }, + { + "first_name": "Pratul", + "last_name": "P. Srinivasan" + }, + { + "first_name": "Dor", + "last_name": "Verbin" + }, + { + "first_name": "Jonathan", + "last_name": "T. Barron" + }, + { + "first_name": "Ben", + "last_name": "Poole" + }, + { + "first_name": "Aleksander", + "last_name": "Ho?y?ski" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "I'M HOI: Inertia-aware Monocular Capture of 3D Human-Object Interactions", - "authors": "Chengfeng Zhao, Juze Zhang, Jiashen Du, Ziwei Shan, Junye Wang, Jingyi Yu, Jingya Wang, Lan Xu", + "authors": [ + { + "first_name": "Chengfeng", + "last_name": "Zhao" + }, + { + "first_name": "Juze", + "last_name": "Zhang" + }, + { + "first_name": "Jiashen", + "last_name": "Du" + }, + { + "first_name": "Ziwei", + "last_name": "Shan" + }, + { + "first_name": "Junye", + "last_name": "Wang" + }, + { + "first_name": "Jingyi", + "last_name": "Yu" + }, + { + "first_name": "Jingya", + "last_name": "Wang" + }, + { + "first_name": "Lan", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Dynamic Policy-Driven Adaptive Multi-Instance Learning for Whole Slide Image Classification", - "authors": "Tingting Zheng, Kui Jiang, Hongxun Yao", + "authors": [ + { + "first_name": "Tingting", + "last_name": "Zheng" + }, + { + "first_name": "Kui", + "last_name": "Jiang" + }, + { + "first_name": "Hongxun", + "last_name": "Yao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks", - "authors": "Zhe Chen, Jiannan Wu, Wenhai Wang, Weijie Su, Guo Chen, Sen Xing, Muyan Zhong, Qinglong Zhang, Xizhou Zhu, Lewei Lu, Bin Li, Ping Luo, Tong Lu, Yu Qiao, Jifeng Dai", + "authors": [ + { + "first_name": "Zhe", + "last_name": "Chen" + }, + { + "first_name": "Jiannan", + "last_name": "Wu" + }, + { + "first_name": "Wenhai", + "last_name": "Wang" + }, + { + "first_name": "Weijie", + "last_name": "Su" + }, + { + "first_name": "Guo", + "last_name": "Chen" + }, + { + "first_name": "Sen", + "last_name": "Xing" + }, + { + "first_name": "Muyan", + "last_name": "Zhong" + }, + { + "first_name": "Qinglong", + "last_name": "Zhang" + }, + { + "first_name": "Xizhou", + "last_name": "Zhu" + }, + { + "first_name": "Lewei", + "last_name": "Lu" + }, + { + "first_name": "Bin", + "last_name": "Li" + }, + { + "first_name": "Ping", + "last_name": "Luo" + }, + { + "first_name": "Tong", + "last_name": "Lu" + }, + { + "first_name": "Yu", + "last_name": "Qiao" + }, + { + "first_name": "Jifeng", + "last_name": "Dai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Multi-View Attentive Contextualization for Multi-View 3D Object Detection", - "authors": "Xianpeng Liu, Ce Zheng, Ming Qian, Nan Xue, Chen Chen, Zhebin Zhang, Chen Li, Tianfu Wu", + "authors": [ + { + "first_name": "Xianpeng", + "last_name": "Liu" + }, + { + "first_name": "Ce", + "last_name": "Zheng" + }, + { + "first_name": "Ming", + "last_name": "Qian" + }, + { + "first_name": "Nan", + "last_name": "Xue" + }, + { + "first_name": "Chen", + "last_name": "Chen" + }, + { + "first_name": "Zhebin", + "last_name": "Zhang" + }, + { + "first_name": "Chen", + "last_name": "Li" + }, + { + "first_name": "Tianfu", + "last_name": "Wu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MemSAM: Taming Segment Anything Model for Echocardiography Video Segmentation", - "authors": "Xiaolong Deng, Huisi Wu, Runhao Zeng, Jing Qin", + "authors": [ + { + "first_name": "Xiaolong", + "last_name": "Deng" + }, + { + "first_name": "Huisi", + "last_name": "Wu" + }, + { + "first_name": "Runhao", + "last_name": "Zeng" + }, + { + "first_name": "Jing", + "last_name": "Qin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LiDAR4D: Dynamic Neural Fields for Novel Space-time View LiDAR Synthesis", - "authors": "Zehan Zheng, Fan Lu, Weiyi Xue, Guang Chen, Changjun Jiang", + "authors": [ + { + "first_name": "Zehan", + "last_name": "Zheng" + }, + { + "first_name": "Fan", + "last_name": "Lu" + }, + { + "first_name": "Weiyi", + "last_name": "Xue" + }, + { + "first_name": "Guang", + "last_name": "Chen" + }, + { + "first_name": "Changjun", + "last_name": "Jiang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Exploiting Diffusion Prior for Generalizable Dense Prediction", - "authors": "Hsin-Ying Lee, Hung-Yu Tseng, Hsin-Ying Lee, Ming-Hsuan Yang", + "authors": [ + { + "first_name": "Hsin-Ying", + "last_name": "Lee" + }, + { + "first_name": "Hung-Yu", + "last_name": "Tseng" + }, + { + "first_name": "Hsin-Ying", + "last_name": "Lee" + }, + { + "first_name": "Ming-Hsuan", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PI3D: Efficient Text-to-3D Generation with Pseudo-Image Diffusion", - "authors": "Ying-Tian Liu, Yuan-Chen Guo, Guan Luo, Heyi Sun, Wei Yin, Song-Hai Zhang", + "authors": [ + { + "first_name": "Ying-Tian", + "last_name": "Liu" + }, + { + "first_name": "Yuan-Chen", + "last_name": "Guo" + }, + { + "first_name": "Guan", + "last_name": "Luo" + }, + { + "first_name": "Heyi", + "last_name": "Sun" + }, + { + "first_name": "Wei", + "last_name": "Yin" + }, + { + "first_name": "Song-Hai", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Orthogonal Adaptation for Modular Customization of Diffusion Models", - "authors": "Ryan Po, Guandao Yang, Kfir Aberman, Gordon Wetzstein", + "authors": [ + { + "first_name": "Ryan", + "last_name": "Po" + }, + { + "first_name": "Guandao", + "last_name": "Yang" + }, + { + "first_name": "Kfir", + "last_name": "Aberman" + }, + { + "first_name": "Gordon", + "last_name": "Wetzstein" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction", - "authors": "David Charatan, Sizhe Lester Li, Andrea Tagliasacchi, Vincent Sitzmann", + "authors": [ + { + "first_name": "David", + "last_name": "Charatan" + }, + { + "first_name": "Sizhe", + "last_name": "Lester Li" + }, + { + "first_name": "Andrea", + "last_name": "Tagliasacchi" + }, + { + "first_name": "Vincent", + "last_name": "Sitzmann" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "VBench: Comprehensive Benchmark Suite for Video Generative Models", - "authors": "Ziqi Huang, Yinan He, Jiashuo Yu, Fan Zhang, Chenyang Si, Yuming Jiang, Yuanhan Zhang, Tianxing Wu, Qingyang Jin, Nattapol Chanpaisit, Yaohui Wang, Xinyuan Chen, Limin Wang, Dahua Lin, Yu Qiao, Ziwei Liu", + "authors": [ + { + "first_name": "Ziqi", + "last_name": "Huang" + }, + { + "first_name": "Yinan", + "last_name": "He" + }, + { + "first_name": "Jiashuo", + "last_name": "Yu" + }, + { + "first_name": "Fan", + "last_name": "Zhang" + }, + { + "first_name": "Chenyang", + "last_name": "Si" + }, + { + "first_name": "Yuming", + "last_name": "Jiang" + }, + { + "first_name": "Yuanhan", + "last_name": "Zhang" + }, + { + "first_name": "Tianxing", + "last_name": "Wu" + }, + { + "first_name": "Qingyang", + "last_name": "Jin" + }, + { + "first_name": "Nattapol", + "last_name": "Chanpaisit" + }, + { + "first_name": "Yaohui", + "last_name": "Wang" + }, + { + "first_name": "Xinyuan", + "last_name": "Chen" + }, + { + "first_name": "Limin", + "last_name": "Wang" + }, + { + "first_name": "Dahua", + "last_name": "Lin" + }, + { + "first_name": "Yu", + "last_name": "Qiao" + }, + { + "first_name": "Ziwei", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Language-conditioned Detection Transformer", - "authors": "Jang Hyun Cho, Philipp Krähenbühl", + "authors": [ + { + "first_name": "Jang", + "last_name": "Hyun Cho" + }, + { + "first_name": "Philipp", + "last_name": "Krähenbühl" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Optimizing Diffusion Noise Can Serve As Universal Motion Priors", - "authors": "Korrawe Karunratanakul, Konpat Preechakul, Emre Aksan, Thabo Beeler, Supasorn Suwajanakorn, Siyu Tang", + "authors": [ + { + "first_name": "Korrawe", + "last_name": "Karunratanakul" + }, + { + "first_name": "Konpat", + "last_name": "Preechakul" + }, + { + "first_name": "Emre", + "last_name": "Aksan" + }, + { + "first_name": "Thabo", + "last_name": "Beeler" + }, + { + "first_name": "Supasorn", + "last_name": "Suwajanakorn" + }, + { + "first_name": "Siyu", + "last_name": "Tang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MAP: MAsk-Pruning for Source-Free Model Intellectual Property Protection", - "authors": "Boyang Peng, Sanqing Qu, Yong Wu, Tianpei Zou, Lianghua He, Alois Knoll, Guang Chen, Changjun Jiang", + "authors": [ + { + "first_name": "Boyang", + "last_name": "Peng" + }, + { + "first_name": "Sanqing", + "last_name": "Qu" + }, + { + "first_name": "Yong", + "last_name": "Wu" + }, + { + "first_name": "Tianpei", + "last_name": "Zou" + }, + { + "first_name": "Lianghua", + "last_name": "He" + }, + { + "first_name": "Alois", + "last_name": "Knoll" + }, + { + "first_name": "Guang", + "last_name": "Chen" + }, + { + "first_name": "Changjun", + "last_name": "Jiang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Improving Single Domain-Generalized Object Detection: A Focus on Diversification and Alignment", - "authors": "Muhammad Sohail Danish, Muhammad Haris Khan, Muhammad Akhtar Munir, M. Saquib Sarfraz, Mohsen Ali", + "authors": [ + { + "first_name": "Muhammad", + "last_name": "Sohail Danish" + }, + { + "first_name": "Muhammad", + "last_name": "Haris Khan" + }, + { + "first_name": "Muhammad", + "last_name": "Akhtar Munir" + }, + { + "first_name": "M.", + "last_name": "Saquib Sarfraz" + }, + { + "first_name": "Mohsen", + "last_name": "Ali" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "OVFoodSeg: Elevating Open-Vocabulary Food Image Segmentation via Image-Informed Textual Representation", - "authors": "Xiongwei Wu, Sicheng Yu, Ee-Peng Lim, Chong-Wah Ngo", + "authors": [ + { + "first_name": "Xiongwei", + "last_name": "Wu" + }, + { + "first_name": "Sicheng", + "last_name": "Yu" + }, + { + "first_name": "Ee-Peng", + "last_name": "Lim" + }, + { + "first_name": "Chong-Wah", + "last_name": "Ngo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "XFeat: Accelerated Features for Lightweight Image Matching", - "authors": "Guilherme Potje, Felipe Cadar, André Araujo, Renato Martins, Erickson R. Nascimento", + "authors": [ + { + "first_name": "Guilherme", + "last_name": "Potje" + }, + { + "first_name": "Felipe", + "last_name": "Cadar" + }, + { + "first_name": "André", + "last_name": "Araujo" + }, + { + "first_name": "Renato", + "last_name": "Martins" + }, + { + "first_name": "Erickson", + "last_name": "R. Nascimento" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Visual Prompting for Generalized Few-shot Segmentation: A Multi-scale Approach", - "authors": "Mir Rayat Imtiaz Hossain, Mennatullah Siam, Leonid Sigal, James J. Little", + "authors": [ + { + "first_name": "Mir", + "last_name": "Rayat Imtiaz Hossain" + }, + { + "first_name": "Mennatullah", + "last_name": "Siam" + }, + { + "first_name": "Leonid", + "last_name": "Sigal" + }, + { + "first_name": "James", + "last_name": "J. Little" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ARTrackV2: Prompting Autoregressive Tracker Where to Look and How to Describe", - "authors": "Yifan Bai, Zeyang Zhao, Yihong Gong, Xing Wei", + "authors": [ + { + "first_name": "Yifan", + "last_name": "Bai" + }, + { + "first_name": "Zeyang", + "last_name": "Zhao" + }, + { + "first_name": "Yihong", + "last_name": "Gong" + }, + { + "first_name": "Xing", + "last_name": "Wei" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "A Vision Check-up for Language Models", - "authors": "Pratyusha Sharma, Tamar Rott Shaham, Manel Baradad, Stephanie Fu, Adrian Rodriguez-Munoz, Shivam Duggal, Phillip Isola, Antonio Torralba", + "authors": [ + { + "first_name": "Pratyusha", + "last_name": "Sharma" + }, + { + "first_name": "Tamar", + "last_name": "Rott Shaham" + }, + { + "first_name": "Manel", + "last_name": "Baradad" + }, + { + "first_name": "Stephanie", + "last_name": "Fu" + }, + { + "first_name": "Adrian", + "last_name": "Rodriguez-Munoz" + }, + { + "first_name": "Shivam", + "last_name": "Duggal" + }, + { + "first_name": "Phillip", + "last_name": "Isola" + }, + { + "first_name": "Antonio", + "last_name": "Torralba" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Memory-based Adapters for Online 3D Scene Perception", - "authors": "Xiuwei Xu, Chong Xia, Ziwei Wang, Linqing Zhao, Yueqi Duan, Jie Zhou, Jiwen Lu", + "authors": [ + { + "first_name": "Xiuwei", + "last_name": "Xu" + }, + { + "first_name": "Chong", + "last_name": "Xia" + }, + { + "first_name": "Ziwei", + "last_name": "Wang" + }, + { + "first_name": "Linqing", + "last_name": "Zhao" + }, + { + "first_name": "Yueqi", + "last_name": "Duan" + }, + { + "first_name": "Jie", + "last_name": "Zhou" + }, + { + "first_name": "Jiwen", + "last_name": "Lu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SyncMask: Synchronized Attentional Masking for Fashion-centric Vision-Language Pretraining", - "authors": "Chull Hwan Song, Taebaek Hwang, Jooyoung Yoon, Shunghyun Choi, Yeong Hyeon Gu", + "authors": [ + { + "first_name": "Chull", + "last_name": "Hwan Song" + }, + { + "first_name": "Taebaek", + "last_name": "Hwang" + }, + { + "first_name": "Jooyoung", + "last_name": "Yoon" + }, + { + "first_name": "Shunghyun", + "last_name": "Choi" + }, + { + "first_name": "Yeong", + "last_name": "Hyeon Gu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "A Study of Dropout-Induced Modality Bias on Robustness to Missing Video Frames for Audio-Visual Speech Recognition", - "authors": "Yusheng Dai, Hang Chen, Jun Du, Ruoyu Wang, Shihao Chen, Haotian Wang, Chin-Hui Lee", + "authors": [ + { + "first_name": "Yusheng", + "last_name": "Dai" + }, + { + "first_name": "Hang", + "last_name": "Chen" + }, + { + "first_name": "Jun", + "last_name": "Du" + }, + { + "first_name": "Ruoyu", + "last_name": "Wang" + }, + { + "first_name": "Shihao", + "last_name": "Chen" + }, + { + "first_name": "Haotian", + "last_name": "Wang" + }, + { + "first_name": "Chin-Hui", + "last_name": "Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "A Conditional Denoising Diffusion Probabilistic Model for Point Cloud Upsampling", - "authors": "Wentao Qu, Yuantian Shao, Lingwu Meng, Xiaoshui Huang, Liang Xiao", + "authors": [ + { + "first_name": "Wentao", + "last_name": "Qu" + }, + { + "first_name": "Yuantian", + "last_name": "Shao" + }, + { + "first_name": "Lingwu", + "last_name": "Meng" + }, + { + "first_name": "Xiaoshui", + "last_name": "Huang" + }, + { + "first_name": "Liang", + "last_name": "Xiao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "VideoRF: Rendering Dynamic Radiance Fields as 2D Feature Video Streams", - "authors": "Liao Wang, Kaixin Yao, Chengcheng Guo, Zhirui Zhang, Qiang Hu, Jingyi Yu, Lan Xu, Minye Wu", + "authors": [ + { + "first_name": "Liao", + "last_name": "Wang" + }, + { + "first_name": "Kaixin", + "last_name": "Yao" + }, + { + "first_name": "Chengcheng", + "last_name": "Guo" + }, + { + "first_name": "Zhirui", + "last_name": "Zhang" + }, + { + "first_name": "Qiang", + "last_name": "Hu" + }, + { + "first_name": "Jingyi", + "last_name": "Yu" + }, + { + "first_name": "Lan", + "last_name": "Xu" + }, + { + "first_name": "Minye", + "last_name": "Wu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DPHMs: Diffusion Parametric Head Models for Depth-based Tracking", - "authors": "Jiapeng Tang, Angela Dai, Yinyu Nie, Lev Markhasin, Justus Thies, Matthias Nießner", + "authors": [ + { + "first_name": "Jiapeng", + "last_name": "Tang" + }, + { + "first_name": "Angela", + "last_name": "Dai" + }, + { + "first_name": "Yinyu", + "last_name": "Nie" + }, + { + "first_name": "Lev", + "last_name": "Markhasin" + }, + { + "first_name": "Justus", + "last_name": "Thies" + }, + { + "first_name": "Matthias", + "last_name": "Nießner" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DetDiffusion: Synergizing Generative and Perceptive Models for Enhanced Data Generation and Perception", - "authors": "Yibo Wang, Ruiyuan Gao, Kai Chen, Kaiqiang Zhou, Yingjie Cai, Lanqing Hong, Zhenguo Li, Lihui Jiang, Dit-Yan Yeung, Qiang Xu, Kai Zhang", + "authors": [ + { + "first_name": "Yibo", + "last_name": "Wang" + }, + { + "first_name": "Ruiyuan", + "last_name": "Gao" + }, + { + "first_name": "Kai", + "last_name": "Chen" + }, + { + "first_name": "Kaiqiang", + "last_name": "Zhou" + }, + { + "first_name": "Yingjie", + "last_name": "Cai" + }, + { + "first_name": "Lanqing", + "last_name": "Hong" + }, + { + "first_name": "Zhenguo", + "last_name": "Li" + }, + { + "first_name": "Lihui", + "last_name": "Jiang" + }, + { + "first_name": "Dit-Yan", + "last_name": "Yeung" + }, + { + "first_name": "Qiang", + "last_name": "Xu" + }, + { + "first_name": "Kai", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GAFusion: Adaptive Fusing LiDAR and Camera with Multiple Guidance for 3D Object Detection", - "authors": "Xiaotian Li, Baojie Fan, Jiandong Tian, Huijie Fan", + "authors": [ + { + "first_name": "Xiaotian", + "last_name": "Li" + }, + { + "first_name": "Baojie", + "last_name": "Fan" + }, + { + "first_name": "Jiandong", + "last_name": "Tian" + }, + { + "first_name": "Huijie", + "last_name": "Fan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Perception-Oriented Video Frame Interpolation via Asymmetric Blending", - "authors": "Guangyang Wu, Xin Tao, Changlin Li, Wenyi Wang, Xiaohong Liu, Qingqing Zheng", + "authors": [ + { + "first_name": "Guangyang", + "last_name": "Wu" + }, + { + "first_name": "Xin", + "last_name": "Tao" + }, + { + "first_name": "Changlin", + "last_name": "Li" + }, + { + "first_name": "Wenyi", + "last_name": "Wang" + }, + { + "first_name": "Xiaohong", + "last_name": "Liu" + }, + { + "first_name": "Qingqing", + "last_name": "Zheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Countering Personalized Text-to-Image Generation with Influence Watermarks", - "authors": "Hanwen Liu, Zhicheng Sun, Yadong Mu", + "authors": [ + { + "first_name": "Hanwen", + "last_name": "Liu" + }, + { + "first_name": "Zhicheng", + "last_name": "Sun" + }, + { + "first_name": "Yadong", + "last_name": "Mu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DUDF: Differentiable Unsigned Distance Fields with Hyperbolic Scaling", - "authors": "Miguel Fainstein, Viviana Siless, Emmanuel Iarussi", + "authors": [ + { + "first_name": "Miguel", + "last_name": "Fainstein" + }, + { + "first_name": "Viviana", + "last_name": "Siless" + }, + { + "first_name": "Emmanuel", + "last_name": "Iarussi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection", - "authors": "Xiaofan Li, Zhizhong Zhang, Xin Tan, Chengwei Chen, Yanyun Qu, Yuan Xie, Lizhuang Ma", + "authors": [ + { + "first_name": "Xiaofan", + "last_name": "Li" + }, + { + "first_name": "Zhizhong", + "last_name": "Zhang" + }, + { + "first_name": "Xin", + "last_name": "Tan" + }, + { + "first_name": "Chengwei", + "last_name": "Chen" + }, + { + "first_name": "Yanyun", + "last_name": "Qu" + }, + { + "first_name": "Yuan", + "last_name": "Xie" + }, + { + "first_name": "Lizhuang", + "last_name": "Ma" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Improving Graph Contrastive Learning via Adaptive Positive Sampling", - "authors": "Jiaming Zhuo, Feiyang Qin, Can Cui, Kun Fu, Bingxin Niu, Mengzhu Wang, Yuanfang Guo, Chuan Wang, Zhen Wang, Xiaochun Cao, Liang Yang", + "authors": [ + { + "first_name": "Jiaming", + "last_name": "Zhuo" + }, + { + "first_name": "Feiyang", + "last_name": "Qin" + }, + { + "first_name": "Can", + "last_name": "Cui" + }, + { + "first_name": "Kun", + "last_name": "Fu" + }, + { + "first_name": "Bingxin", + "last_name": "Niu" + }, + { + "first_name": "Mengzhu", + "last_name": "Wang" + }, + { + "first_name": "Yuanfang", + "last_name": "Guo" + }, + { + "first_name": "Chuan", + "last_name": "Wang" + }, + { + "first_name": "Zhen", + "last_name": "Wang" + }, + { + "first_name": "Xiaochun", + "last_name": "Cao" + }, + { + "first_name": "Liang", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "UFC-Net: Unrolling Fixed-point Continuous Network for Deep Compressive Sensing", - "authors": "Xiaoyang Wang, Hongping Gan", + "authors": [ + { + "first_name": "Xiaoyang", + "last_name": "Wang" + }, + { + "first_name": "Hongping", + "last_name": "Gan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation", - "authors": "Suraj Patni, Aradhye Agarwal, Chetan Arora", + "authors": [ + { + "first_name": "Suraj", + "last_name": "Patni" + }, + { + "first_name": "Aradhye", + "last_name": "Agarwal" + }, + { + "first_name": "Chetan", + "last_name": "Arora" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision", - "authors": "Lu Ling, Yichen Sheng, Zhi Tu, Wentian Zhao, Cheng Xin, Kun Wan, Lantao Yu, Qianyu Guo, Zixun Yu, Yawen Lu, Xuanmao Li, Xingpeng Sun, Rohan Ashok, Aniruddha Mukherjee, Hao Kang, Xiangrui Kong, Gang Hua, Tianyi Zhang, Bedrich Benes, Aniket Bera", + "authors": [ + { + "first_name": "Lu", + "last_name": "Ling" + }, + { + "first_name": "Yichen", + "last_name": "Sheng" + }, + { + "first_name": "Zhi", + "last_name": "Tu" + }, + { + "first_name": "Wentian", + "last_name": "Zhao" + }, + { + "first_name": "Cheng", + "last_name": "Xin" + }, + { + "first_name": "Kun", + "last_name": "Wan" + }, + { + "first_name": "Lantao", + "last_name": "Yu" + }, + { + "first_name": "Qianyu", + "last_name": "Guo" + }, + { + "first_name": "Zixun", + "last_name": "Yu" + }, + { + "first_name": "Yawen", + "last_name": "Lu" + }, + { + "first_name": "Xuanmao", + "last_name": "Li" + }, + { + "first_name": "Xingpeng", + "last_name": "Sun" + }, + { + "first_name": "Rohan", + "last_name": "Ashok" + }, + { + "first_name": "Aniruddha", + "last_name": "Mukherjee" + }, + { + "first_name": "Hao", + "last_name": "Kang" + }, + { + "first_name": "Xiangrui", + "last_name": "Kong" + }, + { + "first_name": "Gang", + "last_name": "Hua" + }, + { + "first_name": "Tianyi", + "last_name": "Zhang" + }, + { + "first_name": "Bedrich", + "last_name": "Benes" + }, + { + "first_name": "Aniket", + "last_name": "Bera" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "2S-UDF: A Novel Two-stage UDF Learning Method for Robust Non-watertight Model Reconstruction from Multi-view Images", - "authors": "Junkai Deng, Fei Hou, Xuhui Chen, Wencheng Wang, Ying He", + "authors": [ + { + "first_name": "Junkai", + "last_name": "Deng" + }, + { + "first_name": "Fei", + "last_name": "Hou" + }, + { + "first_name": "Xuhui", + "last_name": "Chen" + }, + { + "first_name": "Wencheng", + "last_name": "Wang" + }, + { + "first_name": "Ying", + "last_name": "He" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DETRs Beat YOLOs on Real-time Object Detection", - "authors": "Yian Zhao, Wenyu Lv, Shangliang Xu, Jinman Wei, Guanzhong Wang, Qingqing Dang, Yi Liu, Jie Chen", + "authors": [ + { + "first_name": "Yian", + "last_name": "Zhao" + }, + { + "first_name": "Wenyu", + "last_name": "Lv" + }, + { + "first_name": "Shangliang", + "last_name": "Xu" + }, + { + "first_name": "Jinman", + "last_name": "Wei" + }, + { + "first_name": "Guanzhong", + "last_name": "Wang" + }, + { + "first_name": "Qingqing", + "last_name": "Dang" + }, + { + "first_name": "Yi", + "last_name": "Liu" + }, + { + "first_name": "Jie", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "UniVS: Unified and Universal Video Segmentation with Prompts as Queries", - "authors": "Minghan Li, Shuai Li, Xindong Zhang, Lei Zhang", + "authors": [ + { + "first_name": "Minghan", + "last_name": "Li" + }, + { + "first_name": "Shuai", + "last_name": "Li" + }, + { + "first_name": "Xindong", + "last_name": "Zhang" + }, + { + "first_name": "Lei", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Bilateral Adaptation for Human-Object Interaction Detection with Occlusion-Robustness", - "authors": "Guangzhi Wang, Yangyang Guo, Ziwei Xu, Mohan Kankanhalli", + "authors": [ + { + "first_name": "Guangzhi", + "last_name": "Wang" + }, + { + "first_name": "Yangyang", + "last_name": "Guo" + }, + { + "first_name": "Ziwei", + "last_name": "Xu" + }, + { + "first_name": "Mohan", + "last_name": "Kankanhalli" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "An Asymmetric Augmented Self-Supervised Learning Method for Unsupervised Fine-Grained Image Hashing", - "authors": "Feiran Hu, Chenlin Zhang, Jiangliang Guo, Xiu-Shen Wei, Lin Zhao, Anqi Xu, Lingyan Gao", + "authors": [ + { + "first_name": "Feiran", + "last_name": "Hu" + }, + { + "first_name": "Chenlin", + "last_name": "Zhang" + }, + { + "first_name": "Jiangliang", + "last_name": "Guo" + }, + { + "first_name": "Xiu-Shen", + "last_name": "Wei" + }, + { + "first_name": "Lin", + "last_name": "Zhao" + }, + { + "first_name": "Anqi", + "last_name": "Xu" + }, + { + "first_name": "Lingyan", + "last_name": "Gao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Efficiently Assemble Normalization Layers and Regularization for Federated Domain Generalization", - "authors": "Khiem Le, Long Ho, Cuong Do, Danh Le-Phuoc, Kok-Seng Wong", + "authors": [ + { + "first_name": "Khiem", + "last_name": "Le" + }, + { + "first_name": "Long", + "last_name": "Ho" + }, + { + "first_name": "Cuong", + "last_name": "Do" + }, + { + "first_name": "Danh", + "last_name": "Le-Phuoc" + }, + { + "first_name": "Kok-Seng", + "last_name": "Wong" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Exploring Pose-Aware Human-Object Interaction via Hybrid Learning", - "authors": "Eastman Z Y Wu, Yali Li, Yuan Wang, Shengjin Wang", + "authors": [ + { + "first_name": "Eastman", + "last_name": "Z Y Wu" + }, + { + "first_name": "Yali", + "last_name": "Li" + }, + { + "first_name": "Yuan", + "last_name": "Wang" + }, + { + "first_name": "Shengjin", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Depth Information Assisted Collaborative Mutual Promotion Network for Single Image Dehazing", - "authors": "Yafei Zhang, Shen Zhou, Huafeng Li", + "authors": [ + { + "first_name": "Yafei", + "last_name": "Zhang" + }, + { + "first_name": "Shen", + "last_name": "Zhou" + }, + { + "first_name": "Huafeng", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Density-Adaptive Model Based on Motif Matrix for Multi-Agent Trajectory Prediction", - "authors": "Di Wen, Haoran Xu, Zhaocheng He, Zhe Wu, Guang Tan, Peixi Peng", + "authors": [ + { + "first_name": "Di", + "last_name": "Wen" + }, + { + "first_name": "Haoran", + "last_name": "Xu" + }, + { + "first_name": "Zhaocheng", + "last_name": "He" + }, + { + "first_name": "Zhe", + "last_name": "Wu" + }, + { + "first_name": "Guang", + "last_name": "Tan" + }, + { + "first_name": "Peixi", + "last_name": "Peng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Contrastive Learning for DeepFake Classification and Localization via Multi-Label Ranking", - "authors": "Cheng-Yao Hong, Yen-Chi Hsu, Tyng-Luh Liu", + "authors": [ + { + "first_name": "Cheng-Yao", + "last_name": "Hong" + }, + { + "first_name": "Yen-Chi", + "last_name": "Hsu" + }, + { + "first_name": "Tyng-Luh", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Unlocking the Potential of Pre-trained Vision Transformers for Few-Shot Semantic Segmentation through Relationship Descriptors", - "authors": "Ziqin Zhou, Hai-Ming Xu, Yangyang Shu, Lingqiao Liu", + "authors": [ + { + "first_name": "Ziqin", + "last_name": "Zhou" + }, + { + "first_name": "Hai-Ming", + "last_name": "Xu" + }, + { + "first_name": "Yangyang", + "last_name": "Shu" + }, + { + "first_name": "Lingqiao", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CustomListener: Text-guided Responsive Interaction for User-friendly Listening Head Generation", - "authors": "Xi Liu, Ying Guo, Cheng Zhen, Tong Li, Yingying Ao, Pengfei Yan", + "authors": [ + { + "first_name": "Xi", + "last_name": "Liu" + }, + { + "first_name": "Ying", + "last_name": "Guo" + }, + { + "first_name": "Cheng", + "last_name": "Zhen" + }, + { + "first_name": "Tong", + "last_name": "Li" + }, + { + "first_name": "Yingying", + "last_name": "Ao" + }, + { + "first_name": "Pengfei", + "last_name": "Yan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Projecting Trackable Thermal Patterns for Dynamic Computer Vision", - "authors": "Mark Sheinin, Aswin C. Sankaranarayanan, Srinivasa G. Narasimhan", + "authors": [ + { + "first_name": "Mark", + "last_name": "Sheinin" + }, + { + "first_name": "Aswin", + "last_name": "C. Sankaranarayanan" + }, + { + "first_name": "Srinivasa", + "last_name": "G. Narasimhan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SG-PGM: Partial Graph Matching Network with Semantic Geometric Fusion for 3D Scene Graph Alignment and Its Downstream Tasks", - "authors": "Yaxu Xie, Alain Pagani, Didier Stricker", + "authors": [ + { + "first_name": "Yaxu", + "last_name": "Xie" + }, + { + "first_name": "Alain", + "last_name": "Pagani" + }, + { + "first_name": "Didier", + "last_name": "Stricker" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Fun with Flags: Robust Principal Directions via Flag Manifolds", - "authors": "Nathan Mankovich, Gustau Camps-Valls, Tolga Birdal", + "authors": [ + { + "first_name": "Nathan", + "last_name": "Mankovich" + }, + { + "first_name": "Gustau", + "last_name": "Camps-Valls" + }, + { + "first_name": "Tolga", + "last_name": "Birdal" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Generating Non-Stationary Textures using Self-Rectification", - "authors": "Yang Zhou, Rongjun Xiao, Dani Lischinski, Daniel Cohen-Or, Hui Huang", + "authors": [ + { + "first_name": "Yang", + "last_name": "Zhou" + }, + { + "first_name": "Rongjun", + "last_name": "Xiao" + }, + { + "first_name": "Dani", + "last_name": "Lischinski" + }, + { + "first_name": "Daniel", + "last_name": "Cohen-Or" + }, + { + "first_name": "Hui", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SPU-PMD: Self-Supervised Point Cloud Upsampling via Progressive Mesh Deformation", - "authors": "Yanzhe Liu, Rong Chen, Yushi Li, Yixi Li, Xuehou Tan", + "authors": [ + { + "first_name": "Yanzhe", + "last_name": "Liu" + }, + { + "first_name": "Rong", + "last_name": "Chen" + }, + { + "first_name": "Yushi", + "last_name": "Li" + }, + { + "first_name": "Yixi", + "last_name": "Li" + }, + { + "first_name": "Xuehou", + "last_name": "Tan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Advancing Saliency Ranking with Human Fixations: Dataset Models and Benchmarks", - "authors": "Bowen Deng, Siyang Song, Andrew P. French, Denis Schluppeck, Michael P. Pound", + "authors": [ + { + "first_name": "Bowen", + "last_name": "Deng" + }, + { + "first_name": "Siyang", + "last_name": "Song" + }, + { + "first_name": "Andrew", + "last_name": "P. French" + }, + { + "first_name": "Denis", + "last_name": "Schluppeck" + }, + { + "first_name": "Michael", + "last_name": "P. Pound" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis", - "authors": "Willi Menapace, Aliaksandr Siarohin, Ivan Skorokhodov, Ekaterina Deyneka, Tsai-Shien Chen, Anil Kag, Yuwei Fang, Aleksei Stoliar, Elisa Ricci, Jian Ren, Sergey Tulyakov", + "authors": [ + { + "first_name": "Willi", + "last_name": "Menapace" + }, + { + "first_name": "Aliaksandr", + "last_name": "Siarohin" + }, + { + "first_name": "Ivan", + "last_name": "Skorokhodov" + }, + { + "first_name": "Ekaterina", + "last_name": "Deyneka" + }, + { + "first_name": "Tsai-Shien", + "last_name": "Chen" + }, + { + "first_name": "Anil", + "last_name": "Kag" + }, + { + "first_name": "Yuwei", + "last_name": "Fang" + }, + { + "first_name": "Aleksei", + "last_name": "Stoliar" + }, + { + "first_name": "Elisa", + "last_name": "Ricci" + }, + { + "first_name": "Jian", + "last_name": "Ren" + }, + { + "first_name": "Sergey", + "last_name": "Tulyakov" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Unsupervised Deep Unrolling Networks for Phase Unwrapping", - "authors": "Zhile Chen, Yuhui Quan, Hui Ji", + "authors": [ + { + "first_name": "Zhile", + "last_name": "Chen" + }, + { + "first_name": "Yuhui", + "last_name": "Quan" + }, + { + "first_name": "Hui", + "last_name": "Ji" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Federated Generalized Category Discovery", - "authors": "Nan Pu, Wenjing Li, Xingyuan Ji, Yalan Qin, Nicu Sebe, Zhun Zhong", + "authors": [ + { + "first_name": "Nan", + "last_name": "Pu" + }, + { + "first_name": "Wenjing", + "last_name": "Li" + }, + { + "first_name": "Xingyuan", + "last_name": "Ji" + }, + { + "first_name": "Yalan", + "last_name": "Qin" + }, + { + "first_name": "Nicu", + "last_name": "Sebe" + }, + { + "first_name": "Zhun", + "last_name": "Zhong" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "JointSQ: Joint Sparsification-Quantization for Distributed Learning", - "authors": "Weiying Xie, Haowei Li, Jitao Ma, Yunsong Li, Jie Lei, Donglai Liu, Leyuan Fang", + "authors": [ + { + "first_name": "Weiying", + "last_name": "Xie" + }, + { + "first_name": "Haowei", + "last_name": "Li" + }, + { + "first_name": "Jitao", + "last_name": "Ma" + }, + { + "first_name": "Yunsong", + "last_name": "Li" + }, + { + "first_name": "Jie", + "last_name": "Lei" + }, + { + "first_name": "Donglai", + "last_name": "Liu" + }, + { + "first_name": "Leyuan", + "last_name": "Fang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "A Unified Framework for Human-centric Point Cloud Video Understanding", - "authors": "Yiteng Xu, Kecheng Ye, Xiao Han, Yiming Ren, Xinge Zhu, Yuexin Ma", + "authors": [ + { + "first_name": "Yiteng", + "last_name": "Xu" + }, + { + "first_name": "Kecheng", + "last_name": "Ye" + }, + { + "first_name": "Xiao", + "last_name": "Han" + }, + { + "first_name": "Yiming", + "last_name": "Ren" + }, + { + "first_name": "Xinge", + "last_name": "Zhu" + }, + { + "first_name": "Yuexin", + "last_name": "Ma" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Edge-Aware 3D Instance Segmentation Network with Intelligent Semantic Prior", - "authors": "Wonseok Roh, Hwanhee Jung, Giljoo Nam, Jinseop Yeom, Hyunje Park, Sang Ho Yoon, Sangpil Kim", + "authors": [ + { + "first_name": "Wonseok", + "last_name": "Roh" + }, + { + "first_name": "Hwanhee", + "last_name": "Jung" + }, + { + "first_name": "Giljoo", + "last_name": "Nam" + }, + { + "first_name": "Jinseop", + "last_name": "Yeom" + }, + { + "first_name": "Hyunje", + "last_name": "Park" + }, + { + "first_name": "Sang", + "last_name": "Ho Yoon" + }, + { + "first_name": "Sangpil", + "last_name": "Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Coherence As Texture - Passive Textureless 3D Reconstruction by Self-interference", - "authors": "Wei-Yu Chen, Aswin C. Sankaranarayanan, Anat Levin, Matthew O'Toole", + "authors": [ + { + "first_name": "Wei-Yu", + "last_name": "Chen" + }, + { + "first_name": "Aswin", + "last_name": "C. Sankaranarayanan" + }, + { + "first_name": "Anat", + "last_name": "Levin" + }, + { + "first_name": "Matthew", + "last_name": "O'Toole" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Enhancing the Power of OOD Detection via Sample-Aware Model Selection", - "authors": "Feng Xue, Zi He, Yuan Zhang, Chuanlong Xie, Zhenguo Li, Falong Tan", + "authors": [ + { + "first_name": "Feng", + "last_name": "Xue" + }, + { + "first_name": "Zi", + "last_name": "He" + }, + { + "first_name": "Yuan", + "last_name": "Zhang" + }, + { + "first_name": "Chuanlong", + "last_name": "Xie" + }, + { + "first_name": "Zhenguo", + "last_name": "Li" + }, + { + "first_name": "Falong", + "last_name": "Tan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Collaborative Semantic Occupancy Prediction with Hybrid Feature Fusion in Connected Automated Vehicles", - "authors": "Rui Song, Chenwei Liang, Hu Cao, Zhiran Yan, Walter Zimmer, Markus Gross, Andreas Festag, Alois Knoll", + "authors": [ + { + "first_name": "Rui", + "last_name": "Song" + }, + { + "first_name": "Chenwei", + "last_name": "Liang" + }, + { + "first_name": "Hu", + "last_name": "Cao" + }, + { + "first_name": "Zhiran", + "last_name": "Yan" + }, + { + "first_name": "Walter", + "last_name": "Zimmer" + }, + { + "first_name": "Markus", + "last_name": "Gross" + }, + { + "first_name": "Andreas", + "last_name": "Festag" + }, + { + "first_name": "Alois", + "last_name": "Knoll" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Generative Multi-modal Models are Good Class Incremental Learners", - "authors": "Xusheng Cao, Haori Lu, Linlan Huang, Xialei Liu, Ming-Ming Cheng", + "authors": [ + { + "first_name": "Xusheng", + "last_name": "Cao" + }, + { + "first_name": "Haori", + "last_name": "Lu" + }, + { + "first_name": "Linlan", + "last_name": "Huang" + }, + { + "first_name": "Xialei", + "last_name": "Liu" + }, + { + "first_name": "Ming-Ming", + "last_name": "Cheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Low-Resource Vision Challenges for Foundation Models", - "authors": "Yunhua Zhang, Hazel Doughty, Cees G. M. Snoek", + "authors": [ + { + "first_name": "Yunhua", + "last_name": "Zhang" + }, + { + "first_name": "Hazel", + "last_name": "Doughty" + }, + { + "first_name": "Cees", + "last_name": "G. M. Snoek" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videos", - "authors": "Hongchi Xia, Yang Fu, Sifei Liu, Xiaolong Wang", + "authors": [ + { + "first_name": "Hongchi", + "last_name": "Xia" + }, + { + "first_name": "Yang", + "last_name": "Fu" + }, + { + "first_name": "Sifei", + "last_name": "Liu" + }, + { + "first_name": "Xiaolong", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Shadow-Enlightened Image Outpainting", - "authors": "Hang Yu, Ruilin Li, Shaorong Xie, Jiayan Qiu", + "authors": [ + { + "first_name": "Hang", + "last_name": "Yu" + }, + { + "first_name": "Ruilin", + "last_name": "Li" + }, + { + "first_name": "Shaorong", + "last_name": "Xie" + }, + { + "first_name": "Jiayan", + "last_name": "Qiu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards Generalizable Tumor Synthesis", - "authors": "Qi Chen, Xiaoxi Chen, Haorui Song, Zhiwei Xiong, Alan Yuille, Chen Wei, Zongwei Zhou", + "authors": [ + { + "first_name": "Qi", + "last_name": "Chen" + }, + { + "first_name": "Xiaoxi", + "last_name": "Chen" + }, + { + "first_name": "Haorui", + "last_name": "Song" + }, + { + "first_name": "Zhiwei", + "last_name": "Xiong" + }, + { + "first_name": "Alan", + "last_name": "Yuille" + }, + { + "first_name": "Chen", + "last_name": "Wei" + }, + { + "first_name": "Zongwei", + "last_name": "Zhou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learning", - "authors": "Haoyu Chen, Wenbo Li, Jinjin Gu, Jingjing Ren, Haoze Sun, Xueyi Zou, Zhensong Zhang, Youliang Yan, Lei Zhu", + "authors": [ + { + "first_name": "Haoyu", + "last_name": "Chen" + }, + { + "first_name": "Wenbo", + "last_name": "Li" + }, + { + "first_name": "Jinjin", + "last_name": "Gu" + }, + { + "first_name": "Jingjing", + "last_name": "Ren" + }, + { + "first_name": "Haoze", + "last_name": "Sun" + }, + { + "first_name": "Xueyi", + "last_name": "Zou" + }, + { + "first_name": "Zhensong", + "last_name": "Zhang" + }, + { + "first_name": "Youliang", + "last_name": "Yan" + }, + { + "first_name": "Lei", + "last_name": "Zhu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "BOTH2Hands: Inferring 3D Hands from Both Text Prompts and Body Dynamics", - "authors": "Wenqian Zhang, Molin Huang, Yuxuan Zhou, Juze Zhang, Jingyi Yu, Jingya Wang, Lan Xu", + "authors": [ + { + "first_name": "Wenqian", + "last_name": "Zhang" + }, + { + "first_name": "Molin", + "last_name": "Huang" + }, + { + "first_name": "Yuxuan", + "last_name": "Zhou" + }, + { + "first_name": "Juze", + "last_name": "Zhang" + }, + { + "first_name": "Jingyi", + "last_name": "Yu" + }, + { + "first_name": "Jingya", + "last_name": "Wang" + }, + { + "first_name": "Lan", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "EpiDiff: Enhancing Multi-View Synthesis via Localized Epipolar-Constrained Diffusion", - "authors": "Zehuan Huang, Hao Wen, Junting Dong, Yaohui Wang, Yangguang Li, Xinyuan Chen, Yan-Pei Cao, Ding Liang, Yu Qiao, Bo Dai, Lu Sheng", + "authors": [ + { + "first_name": "Zehuan", + "last_name": "Huang" + }, + { + "first_name": "Hao", + "last_name": "Wen" + }, + { + "first_name": "Junting", + "last_name": "Dong" + }, + { + "first_name": "Yaohui", + "last_name": "Wang" + }, + { + "first_name": "Yangguang", + "last_name": "Li" + }, + { + "first_name": "Xinyuan", + "last_name": "Chen" + }, + { + "first_name": "Yan-Pei", + "last_name": "Cao" + }, + { + "first_name": "Ding", + "last_name": "Liang" + }, + { + "first_name": "Yu", + "last_name": "Qiao" + }, + { + "first_name": "Bo", + "last_name": "Dai" + }, + { + "first_name": "Lu", + "last_name": "Sheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "On the Faithfulness of Vision Transformer Explanations", - "authors": "Junyi Wu, Weitai Kang, Hao Tang, Yuan Hong, Yan Yan", + "authors": [ + { + "first_name": "Junyi", + "last_name": "Wu" + }, + { + "first_name": "Weitai", + "last_name": "Kang" + }, + { + "first_name": "Hao", + "last_name": "Tang" + }, + { + "first_name": "Yuan", + "last_name": "Hong" + }, + { + "first_name": "Yan", + "last_name": "Yan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Pixel-level Semantic Correspondence through Layout-aware Representation Learning and Multi-scale Matching Integration", - "authors": "Yixuan Sun, Zhangyue Yin, Haibo Wang, Yan Wang, Xipeng Qiu, Weifeng Ge, Wenqiang Zhang", + "authors": [ + { + "first_name": "Yixuan", + "last_name": "Sun" + }, + { + "first_name": "Zhangyue", + "last_name": "Yin" + }, + { + "first_name": "Haibo", + "last_name": "Wang" + }, + { + "first_name": "Yan", + "last_name": "Wang" + }, + { + "first_name": "Xipeng", + "last_name": "Qiu" + }, + { + "first_name": "Weifeng", + "last_name": "Ge" + }, + { + "first_name": "Wenqiang", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning Spatial Features from Audio-Visual Correspondence in Egocentric Videos", - "authors": "Sagnik Majumder, Ziad Al-Halah, Kristen Grauman", + "authors": [ + { + "first_name": "Sagnik", + "last_name": "Majumder" + }, + { + "first_name": "Ziad", + "last_name": "Al-Halah" + }, + { + "first_name": "Kristen", + "last_name": "Grauman" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Models", - "authors": "Yukang Cao, Yan-Pei Cao, Kai Han, Ying Shan, Kwan-Yee K. Wong", + "authors": [ + { + "first_name": "Yukang", + "last_name": "Cao" + }, + { + "first_name": "Yan-Pei", + "last_name": "Cao" + }, + { + "first_name": "Kai", + "last_name": "Han" + }, + { + "first_name": "Ying", + "last_name": "Shan" + }, + { + "first_name": "Kwan-Yee", + "last_name": "K. Wong" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Dynamic Graph Representation with Knowledge-aware Attention for Histopathology Whole Slide Image Analysis", - "authors": "Jiawen Li, Yuxuan Chen, Hongbo Chu, Qiehe Sun, Tian Guan, Anjia Han, Yonghong He", + "authors": [ + { + "first_name": "Jiawen", + "last_name": "Li" + }, + { + "first_name": "Yuxuan", + "last_name": "Chen" + }, + { + "first_name": "Hongbo", + "last_name": "Chu" + }, + { + "first_name": "Qiehe", + "last_name": "Sun" + }, + { + "first_name": "Tian", + "last_name": "Guan" + }, + { + "first_name": "Anjia", + "last_name": "Han" + }, + { + "first_name": "Yonghong", + "last_name": "He" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Brain Decodes Deep Nets", - "authors": "Huzheng Yang, James Gee, Jianbo Shi", + "authors": [ + { + "first_name": "Huzheng", + "last_name": "Yang" + }, + { + "first_name": "James", + "last_name": "Gee" + }, + { + "first_name": "Jianbo", + "last_name": "Shi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Semantics Distortion and Style Matter: Towards Source-free UDA for Panoramic Segmentation", - "authors": "Xu Zheng, Pengyuan Zhou, Athanasios V. Vasilakos, Lin Wang", + "authors": [ + { + "first_name": "Xu", + "last_name": "Zheng" + }, + { + "first_name": "Pengyuan", + "last_name": "Zhou" + }, + { + "first_name": "Athanasios", + "last_name": "V. Vasilakos" + }, + { + "first_name": "Lin", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Bidirectional Autoregessive Diffusion Model for Dance Generation", - "authors": "Canyu Zhang, Youbao Tang, Ning Zhang, Ruei-Sung Lin, Mei Han, Jing Xiao, Song Wang", + "authors": [ + { + "first_name": "Canyu", + "last_name": "Zhang" + }, + { + "first_name": "Youbao", + "last_name": "Tang" + }, + { + "first_name": "Ning", + "last_name": "Zhang" + }, + { + "first_name": "Ruei-Sung", + "last_name": "Lin" + }, + { + "first_name": "Mei", + "last_name": "Han" + }, + { + "first_name": "Jing", + "last_name": "Xiao" + }, + { + "first_name": "Song", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Align Before Adapt: Leveraging Entity-to-Region Alignments for Generalizable Video Action Recognition", - "authors": "Yifei Chen, Dapeng Chen, Ruijin Liu, Sai Zhou, Wenyuan Xue, Wei Peng", + "authors": [ + { + "first_name": "Yifei", + "last_name": "Chen" + }, + { + "first_name": "Dapeng", + "last_name": "Chen" + }, + { + "first_name": "Ruijin", + "last_name": "Liu" + }, + { + "first_name": "Sai", + "last_name": "Zhou" + }, + { + "first_name": "Wenyuan", + "last_name": "Xue" + }, + { + "first_name": "Wei", + "last_name": "Peng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GOV-NeSF: Generalizable Open-Vocabulary Neural Semantic Fields", - "authors": "Yunsong Wang, Hanlin Chen, Gim Hee Lee", + "authors": [ + { + "first_name": "Yunsong", + "last_name": "Wang" + }, + { + "first_name": "Hanlin", + "last_name": "Chen" + }, + { + "first_name": "Gim", + "last_name": "Hee Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FRESCO: Spatial-Temporal Correspondence for Zero-Shot Video Translation", - "authors": "Shuai Yang, Yifan Zhou, Ziwei Liu, Chen Change Loy", + "authors": [ + { + "first_name": "Shuai", + "last_name": "Yang" + }, + { + "first_name": "Yifan", + "last_name": "Zhou" + }, + { + "first_name": "Ziwei", + "last_name": "Liu" + }, + { + "first_name": "Chen", + "last_name": "Change Loy" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Dual-Scale Transformer for Large-Scale Single-Pixel Imaging", - "authors": "Gang Qu, Ping Wang, Xin Yuan", + "authors": [ + { + "first_name": "Gang", + "last_name": "Qu" + }, + { + "first_name": "Ping", + "last_name": "Wang" + }, + { + "first_name": "Xin", + "last_name": "Yuan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards Robust 3D Object Detection with LiDAR and 4D Radar Fusion in Various Weather Conditions", - "authors": "Yujeong Chae, Hyeonseong Kim, Kuk-Jin Yoon", + "authors": [ + { + "first_name": "Yujeong", + "last_name": "Chae" + }, + { + "first_name": "Hyeonseong", + "last_name": "Kim" + }, + { + "first_name": "Kuk-Jin", + "last_name": "Yoon" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Enhancing 3D Fidelity of Text-to-3D using Cross-View Correspondences", - "authors": "Seungwook Kim, Kejie Li, Xueqing Deng, Yichun Shi, Minsu Cho, Peng Wang", + "authors": [ + { + "first_name": "Seungwook", + "last_name": "Kim" + }, + { + "first_name": "Kejie", + "last_name": "Li" + }, + { + "first_name": "Xueqing", + "last_name": "Deng" + }, + { + "first_name": "Yichun", + "last_name": "Shi" + }, + { + "first_name": "Minsu", + "last_name": "Cho" + }, + { + "first_name": "Peng", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Bezier Everywhere All at Once: Learning Drivable Lanes as Bezier Graphs", - "authors": "Hugh Blayney, Hanlin Tian, Hamish Scott, Nils Goldbeck, Chess Stetson, Panagiotis Angeloudis", + "authors": [ + { + "first_name": "Hugh", + "last_name": "Blayney" + }, + { + "first_name": "Hanlin", + "last_name": "Tian" + }, + { + "first_name": "Hamish", + "last_name": "Scott" + }, + { + "first_name": "Nils", + "last_name": "Goldbeck" + }, + { + "first_name": "Chess", + "last_name": "Stetson" + }, + { + "first_name": "Panagiotis", + "last_name": "Angeloudis" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting", - "authors": "Zhijing Shao, Zhaolong Wang, Zhuang Li, Duotun Wang, Xiangru Lin, Yu Zhang, Mingming Fan, Zeyu Wang", + "authors": [ + { + "first_name": "Zhijing", + "last_name": "Shao" + }, + { + "first_name": "Zhaolong", + "last_name": "Wang" + }, + { + "first_name": "Zhuang", + "last_name": "Li" + }, + { + "first_name": "Duotun", + "last_name": "Wang" + }, + { + "first_name": "Xiangru", + "last_name": "Lin" + }, + { + "first_name": "Yu", + "last_name": "Zhang" + }, + { + "first_name": "Mingming", + "last_name": "Fan" + }, + { + "first_name": "Zeyu", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MoSAR: Monocular Semi-Supervised Model for Avatar Reconstruction using Differentiable Shading", - "authors": "Abdallah Dib, Luiz Gustavo Hafemann, Emeline Got, Trevor Anderson, Amin Fadaeinejad, Rafael M. O. Cruz, Marc-André Carbonneau", + "authors": [ + { + "first_name": "Abdallah", + "last_name": "Dib" + }, + { + "first_name": "Luiz", + "last_name": "Gustavo Hafemann" + }, + { + "first_name": "Emeline", + "last_name": "Got" + }, + { + "first_name": "Trevor", + "last_name": "Anderson" + }, + { + "first_name": "Amin", + "last_name": "Fadaeinejad" + }, + { + "first_name": "Rafael", + "last_name": "M. O. Cruz" + }, + { + "first_name": "Marc-André", + "last_name": "Carbonneau" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Bridging Remote Sensors with Multisensor Geospatial Foundation Models", - "authors": "Boran Han, Shuai Zhang, Xingjian Shi, Markus Reichstein", + "authors": [ + { + "first_name": "Boran", + "last_name": "Han" + }, + { + "first_name": "Shuai", + "last_name": "Zhang" + }, + { + "first_name": "Xingjian", + "last_name": "Shi" + }, + { + "first_name": "Markus", + "last_name": "Reichstein" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Can I Trust Your Answer? Visually Grounded Video Question Answering", - "authors": "Junbin Xiao, Angela Yao, Yicong Li, Tat-Seng Chua", + "authors": [ + { + "first_name": "Junbin", + "last_name": "Xiao" + }, + { + "first_name": "Angela", + "last_name": "Yao" + }, + { + "first_name": "Yicong", + "last_name": "Li" + }, + { + "first_name": "Tat-Seng", + "last_name": "Chua" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "RankED: Addressing Imbalance and Uncertainty in Edge Detection Using Ranking-based Losses", - "authors": "Bedrettin Cetinkaya, Sinan Kalkan, Emre Akbas", + "authors": [ + { + "first_name": "Bedrettin", + "last_name": "Cetinkaya" + }, + { + "first_name": "Sinan", + "last_name": "Kalkan" + }, + { + "first_name": "Emre", + "last_name": "Akbas" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DiffHuman: Probabilistic Photorealistic 3D Reconstruction of Humans", - "authors": "Akash Sengupta, Thiemo Alldieck, Nikos Kolotouros, Enric Corona, Andrei Zanfir, Cristian Sminchisescu", + "authors": [ + { + "first_name": "Akash", + "last_name": "Sengupta" + }, + { + "first_name": "Thiemo", + "last_name": "Alldieck" + }, + { + "first_name": "Nikos", + "last_name": "Kolotouros" + }, + { + "first_name": "Enric", + "last_name": "Corona" + }, + { + "first_name": "Andrei", + "last_name": "Zanfir" + }, + { + "first_name": "Cristian", + "last_name": "Sminchisescu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution", - "authors": "Rongyuan Wu, Tao Yang, Lingchen Sun, Zhengqiang Zhang, Shuai Li, Lei Zhang", + "authors": [ + { + "first_name": "Rongyuan", + "last_name": "Wu" + }, + { + "first_name": "Tao", + "last_name": "Yang" + }, + { + "first_name": "Lingchen", + "last_name": "Sun" + }, + { + "first_name": "Zhengqiang", + "last_name": "Zhang" + }, + { + "first_name": "Shuai", + "last_name": "Li" + }, + { + "first_name": "Lei", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Permutation Equivariance of Transformers and Its Applications", - "authors": "Hengyuan Xu, Liyao Xiang, Hangyu Ye, Dixi Yao, Pengzhi Chu, Baochun Li", + "authors": [ + { + "first_name": "Hengyuan", + "last_name": "Xu" + }, + { + "first_name": "Liyao", + "last_name": "Xiang" + }, + { + "first_name": "Hangyu", + "last_name": "Ye" + }, + { + "first_name": "Dixi", + "last_name": "Yao" + }, + { + "first_name": "Pengzhi", + "last_name": "Chu" + }, + { + "first_name": "Baochun", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Polos: Multimodal Metric Learning from Human Feedback for Image Captioning", - "authors": "Yuiga Wada, Kanta Kaneda, Daichi Saito, Komei Sugiura", + "authors": [ + { + "first_name": "Yuiga", + "last_name": "Wada" + }, + { + "first_name": "Kanta", + "last_name": "Kaneda" + }, + { + "first_name": "Daichi", + "last_name": "Saito" + }, + { + "first_name": "Komei", + "last_name": "Sugiura" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Detours for Navigating Instructional Videos", - "authors": "Kumar Ashutosh, Zihui Xue, Tushar Nagarajan, Kristen Grauman", + "authors": [ + { + "first_name": "Kumar", + "last_name": "Ashutosh" + }, + { + "first_name": "Zihui", + "last_name": "Xue" + }, + { + "first_name": "Tushar", + "last_name": "Nagarajan" + }, + { + "first_name": "Kristen", + "last_name": "Grauman" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Discontinuity-preserving Normal Integration with Auxiliary Edges", - "authors": "Hyomin Kim, Yucheol Jung, Seungyong Lee", + "authors": [ + { + "first_name": "Hyomin", + "last_name": "Kim" + }, + { + "first_name": "Yucheol", + "last_name": "Jung" + }, + { + "first_name": "Seungyong", + "last_name": "Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes", - "authors": "Xiaoyu Zhou, Zhiwei Lin, Xiaojun Shan, Yongtao Wang, Deqing Sun, Ming-Hsuan Yang", + "authors": [ + { + "first_name": "Xiaoyu", + "last_name": "Zhou" + }, + { + "first_name": "Zhiwei", + "last_name": "Lin" + }, + { + "first_name": "Xiaojun", + "last_name": "Shan" + }, + { + "first_name": "Yongtao", + "last_name": "Wang" + }, + { + "first_name": "Deqing", + "last_name": "Sun" + }, + { + "first_name": "Ming-Hsuan", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Self-Supervised Multi-Object Tracking with Path Consistency", - "authors": "Zijia Lu, Bing Shuai, Yanbei Chen, Zhenlin Xu, Davide Modolo", + "authors": [ + { + "first_name": "Zijia", + "last_name": "Lu" + }, + { + "first_name": "Bing", + "last_name": "Shuai" + }, + { + "first_name": "Yanbei", + "last_name": "Chen" + }, + { + "first_name": "Zhenlin", + "last_name": "Xu" + }, + { + "first_name": "Davide", + "last_name": "Modolo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Unsupervised Keypoints from Pretrained Diffusion Models", - "authors": "Eric Hedlin, Gopal Sharma, Shweta Mahajan, Xingzhe He, Hossam Isack, Abhishek Kar, Helge Rhodin, Andrea Tagliasacchi, Kwang Moo Yi", + "authors": [ + { + "first_name": "Eric", + "last_name": "Hedlin" + }, + { + "first_name": "Gopal", + "last_name": "Sharma" + }, + { + "first_name": "Shweta", + "last_name": "Mahajan" + }, + { + "first_name": "Xingzhe", + "last_name": "He" + }, + { + "first_name": "Hossam", + "last_name": "Isack" + }, + { + "first_name": "Abhishek", + "last_name": "Kar" + }, + { + "first_name": "Helge", + "last_name": "Rhodin" + }, + { + "first_name": "Andrea", + "last_name": "Tagliasacchi" + }, + { + "first_name": "Kwang", + "last_name": "Moo Yi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Resolution Limit of Single-Photon LiDAR", - "authors": "Stanley H. Chan, Hashan K. Weerasooriya, Weijian Zhang, Pamela Abshire, Istvan Gyongy, Robert K. Henderson", + "authors": [ + { + "first_name": "Stanley", + "last_name": "H. Chan" + }, + { + "first_name": "Hashan", + "last_name": "K. Weerasooriya" + }, + { + "first_name": "Weijian", + "last_name": "Zhang" + }, + { + "first_name": "Pamela", + "last_name": "Abshire" + }, + { + "first_name": "Istvan", + "last_name": "Gyongy" + }, + { + "first_name": "Robert", + "last_name": "K. Henderson" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Flatten Long-Range Loss Landscapes for Cross-Domain Few-Shot Learning", - "authors": "Yixiong Zou, Yicong Liu, Yiman Hu, Yuhua Li, Ruixuan Li", + "authors": [ + { + "first_name": "Yixiong", + "last_name": "Zou" + }, + { + "first_name": "Yicong", + "last_name": "Liu" + }, + { + "first_name": "Yiman", + "last_name": "Hu" + }, + { + "first_name": "Yuhua", + "last_name": "Li" + }, + { + "first_name": "Ruixuan", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Improving Distant 3D Object Detection Using 2D Box Supervision", - "authors": "Zetong Yang, Zhiding Yu, Chris Choy, Renhao Wang, Anima Anandkumar, Jose M. Alvarez", + "authors": [ + { + "first_name": "Zetong", + "last_name": "Yang" + }, + { + "first_name": "Zhiding", + "last_name": "Yu" + }, + { + "first_name": "Chris", + "last_name": "Choy" + }, + { + "first_name": "Renhao", + "last_name": "Wang" + }, + { + "first_name": "Anima", + "last_name": "Anandkumar" + }, + { + "first_name": "Jose", + "last_name": "M. Alvarez" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HDQMF: Holographic Feature Decomposition Using Quantum Algorithms", - "authors": "Prathyush Prasanth Poduval, Zhuowen Zou, Mohsen Imani", + "authors": [ + { + "first_name": "Prathyush", + "last_name": "Prasanth Poduval" + }, + { + "first_name": "Zhuowen", + "last_name": "Zou" + }, + { + "first_name": "Mohsen", + "last_name": "Imani" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Diffusion-based Blind Text Image Super-Resolution", - "authors": "Yuzhe Zhang, Jiawei Zhang, Hao Li, Zhouxia Wang, Luwei Hou, Dongqing Zou, Liheng Bian", + "authors": [ + { + "first_name": "Yuzhe", + "last_name": "Zhang" + }, + { + "first_name": "Jiawei", + "last_name": "Zhang" + }, + { + "first_name": "Hao", + "last_name": "Li" + }, + { + "first_name": "Zhouxia", + "last_name": "Wang" + }, + { + "first_name": "Luwei", + "last_name": "Hou" + }, + { + "first_name": "Dongqing", + "last_name": "Zou" + }, + { + "first_name": "Liheng", + "last_name": "Bian" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Consistent Prompting for Rehearsal-Free Continual Learning", - "authors": "Zhanxin Gao, Jun Cen, Xiaobin Chang", + "authors": [ + { + "first_name": "Zhanxin", + "last_name": "Gao" + }, + { + "first_name": "Jun", + "last_name": "Cen" + }, + { + "first_name": "Xiaobin", + "last_name": "Chang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "UniPAD: A Universal Pre-training Paradigm for Autonomous Driving", - "authors": "Honghui Yang, Sha Zhang, Di Huang, Xiaoyang Wu, Haoyi Zhu, Tong He, Shixiang Tang, Hengshuang Zhao, Qibo Qiu, Binbin Lin, Xiaofei He, Wanli Ouyang", + "authors": [ + { + "first_name": "Honghui", + "last_name": "Yang" + }, + { + "first_name": "Sha", + "last_name": "Zhang" + }, + { + "first_name": "Di", + "last_name": "Huang" + }, + { + "first_name": "Xiaoyang", + "last_name": "Wu" + }, + { + "first_name": "Haoyi", + "last_name": "Zhu" + }, + { + "first_name": "Tong", + "last_name": "He" + }, + { + "first_name": "Shixiang", + "last_name": "Tang" + }, + { + "first_name": "Hengshuang", + "last_name": "Zhao" + }, + { + "first_name": "Qibo", + "last_name": "Qiu" + }, + { + "first_name": "Binbin", + "last_name": "Lin" + }, + { + "first_name": "Xiaofei", + "last_name": "He" + }, + { + "first_name": "Wanli", + "last_name": "Ouyang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SeD: Semantic-Aware Discriminator for Image Super-Resolution", - "authors": "Bingchen Li, Xin Li, Hanxin Zhu, Yeying Jin, Ruoyu Feng, Zhizheng Zhang, Zhibo Chen", + "authors": [ + { + "first_name": "Bingchen", + "last_name": "Li" + }, + { + "first_name": "Xin", + "last_name": "Li" + }, + { + "first_name": "Hanxin", + "last_name": "Zhu" + }, + { + "first_name": "Yeying", + "last_name": "Jin" + }, + { + "first_name": "Ruoyu", + "last_name": "Feng" + }, + { + "first_name": "Zhizheng", + "last_name": "Zhang" + }, + { + "first_name": "Zhibo", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SocialCounterfactuals: Probing and Mitigating Intersectional Social Biases in Vision-Language Models with Counterfactual Examples", - "authors": "Phillip Howard, Avinash Madasu, Tiep Le, Gustavo Lujan Moreno, Anahita Bhiwandiwalla, Vasudev Lal", + "authors": [ + { + "first_name": "Phillip", + "last_name": "Howard" + }, + { + "first_name": "Avinash", + "last_name": "Madasu" + }, + { + "first_name": "Tiep", + "last_name": "Le" + }, + { + "first_name": "Gustavo", + "last_name": "Lujan Moreno" + }, + { + "first_name": "Anahita", + "last_name": "Bhiwandiwalla" + }, + { + "first_name": "Vasudev", + "last_name": "Lal" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SVDTree: Semantic Voxel Diffusion for Single Image Tree Reconstruction", - "authors": "Yuan Li, Zhihao Liu, Bedrich Benes, Xiaopeng Zhang, Jianwei Guo", + "authors": [ + { + "first_name": "Yuan", + "last_name": "Li" + }, + { + "first_name": "Zhihao", + "last_name": "Liu" + }, + { + "first_name": "Bedrich", + "last_name": "Benes" + }, + { + "first_name": "Xiaopeng", + "last_name": "Zhang" + }, + { + "first_name": "Jianwei", + "last_name": "Guo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Rethinking FID: Towards a Better Evaluation Metric for Image Generation", - "authors": "Sadeep Jayasumana, Srikumar Ramalingam, Andreas Veit, Daniel Glasner, Ayan Chakrabarti, Sanjiv Kumar", + "authors": [ + { + "first_name": "Sadeep", + "last_name": "Jayasumana" + }, + { + "first_name": "Srikumar", + "last_name": "Ramalingam" + }, + { + "first_name": "Andreas", + "last_name": "Veit" + }, + { + "first_name": "Daniel", + "last_name": "Glasner" + }, + { + "first_name": "Ayan", + "last_name": "Chakrabarti" + }, + { + "first_name": "Sanjiv", + "last_name": "Kumar" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Efficient Privacy-Preserving Visual Localization Using 3D Ray Clouds", - "authors": "Heejoon Moon, Chunghwan Lee, Je Hyeong Hong", + "authors": [ + { + "first_name": "Heejoon", + "last_name": "Moon" + }, + { + "first_name": "Chunghwan", + "last_name": "Lee" + }, + { + "first_name": "Je", + "last_name": "Hyeong Hong" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SuperPrimitive: Scene Reconstruction at a Primitive Level", - "authors": "Kirill Mazur, Gwangbin Bae, Andrew J. Davison", + "authors": [ + { + "first_name": "Kirill", + "last_name": "Mazur" + }, + { + "first_name": "Gwangbin", + "last_name": "Bae" + }, + { + "first_name": "Andrew", + "last_name": "J. Davison" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ReCoRe: Regularized Contrastive Representation Learning of World Model", - "authors": "Rudra P.K. Poudel, Harit Pandya, Stephan Liwicki, Roberto Cipolla", + "authors": [ + { + "first_name": "Rudra", + "last_name": "P.K. Poudel" + }, + { + "first_name": "Harit", + "last_name": "Pandya" + }, + { + "first_name": "Stephan", + "last_name": "Liwicki" + }, + { + "first_name": "Roberto", + "last_name": "Cipolla" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models", - "authors": "Yushi Huang, Ruihao Gong, Jing Liu, Tianlong Chen, Xianglong Liu", + "authors": [ + { + "first_name": "Yushi", + "last_name": "Huang" + }, + { + "first_name": "Ruihao", + "last_name": "Gong" + }, + { + "first_name": "Jing", + "last_name": "Liu" + }, + { + "first_name": "Tianlong", + "last_name": "Chen" + }, + { + "first_name": "Xianglong", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CNC-Net: Self-Supervised Learning for CNC Machining Operations", - "authors": "Mohsen Yavartanoo, Sangmin Hong, Reyhaneh Neshatavar, Kyoung Mu Lee", + "authors": [ + { + "first_name": "Mohsen", + "last_name": "Yavartanoo" + }, + { + "first_name": "Sangmin", + "last_name": "Hong" + }, + { + "first_name": "Reyhaneh", + "last_name": "Neshatavar" + }, + { + "first_name": "Kyoung", + "last_name": "Mu Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "JRDB-PanoTrack: An Open-world Panoptic Segmentation and Tracking Robotic Dataset in Crowded Human Environments", - "authors": "Duy Tho Le, Chenhui Gou, Stavya Datta, Hengcan Shi, Ian Reid, Jianfei Cai, Hamid Rezatofighi", + "authors": [ + { + "first_name": "Duy", + "last_name": "Tho Le" + }, + { + "first_name": "Chenhui", + "last_name": "Gou" + }, + { + "first_name": "Stavya", + "last_name": "Datta" + }, + { + "first_name": "Hengcan", + "last_name": "Shi" + }, + { + "first_name": "Ian", + "last_name": "Reid" + }, + { + "first_name": "Jianfei", + "last_name": "Cai" + }, + { + "first_name": "Hamid", + "last_name": "Rezatofighi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CONFORM: Contrast is All You Need for High-Fidelity Text-to-Image Diffusion Models", - "authors": "Tuna Han Salih Meral, Enis Simsar, Federico Tombari, Pinar Yanardag", + "authors": [ + { + "first_name": "Tuna", + "last_name": "Han Salih Meral" + }, + { + "first_name": "Enis", + "last_name": "Simsar" + }, + { + "first_name": "Federico", + "last_name": "Tombari" + }, + { + "first_name": "Pinar", + "last_name": "Yanardag" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Self-Supervised Facial Representation Learning with Facial Region Awareness", - "authors": "Zheng Gao, Ioannis Patras", + "authors": [ + { + "first_name": "Zheng", + "last_name": "Gao" + }, + { + "first_name": "Ioannis", + "last_name": "Patras" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models", - "authors": "Taoran Yi, Jiemin Fang, Junjie Wang, Guanjun Wu, Lingxi Xie, Xiaopeng Zhang, Wenyu Liu, Qi Tian, Xinggang Wang", + "authors": [ + { + "first_name": "Taoran", + "last_name": "Yi" + }, + { + "first_name": "Jiemin", + "last_name": "Fang" + }, + { + "first_name": "Junjie", + "last_name": "Wang" + }, + { + "first_name": "Guanjun", + "last_name": "Wu" + }, + { + "first_name": "Lingxi", + "last_name": "Xie" + }, + { + "first_name": "Xiaopeng", + "last_name": "Zhang" + }, + { + "first_name": "Wenyu", + "last_name": "Liu" + }, + { + "first_name": "Qi", + "last_name": "Tian" + }, + { + "first_name": "Xinggang", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Open-Vocabulary Attention Maps with Token Optimization for Semantic Segmentation in Diffusion Models", - "authors": "Pablo Marcos-Manchón, Roberto Alcover-Couso, Juan C. SanMiguel, José M. Martínez", + "authors": [ + { + "first_name": "Pablo", + "last_name": "Marcos-Manchón" + }, + { + "first_name": "Roberto", + "last_name": "Alcover-Couso" + }, + { + "first_name": "Juan", + "last_name": "C. SanMiguel" + }, + { + "first_name": "José", + "last_name": "M. Martínez" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation", - "authors": "Qidong Huang, Xiaoyi Dong, Pan Zhang, Bin Wang, Conghui He, Jiaqi Wang, Dahua Lin, Weiming Zhang, Nenghai Yu", + "authors": [ + { + "first_name": "Qidong", + "last_name": "Huang" + }, + { + "first_name": "Xiaoyi", + "last_name": "Dong" + }, + { + "first_name": "Pan", + "last_name": "Zhang" + }, + { + "first_name": "Bin", + "last_name": "Wang" + }, + { + "first_name": "Conghui", + "last_name": "He" + }, + { + "first_name": "Jiaqi", + "last_name": "Wang" + }, + { + "first_name": "Dahua", + "last_name": "Lin" + }, + { + "first_name": "Weiming", + "last_name": "Zhang" + }, + { + "first_name": "Nenghai", + "last_name": "Yu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Volumetric Environment Representation for Vision-Language Navigation", - "authors": "Rui Liu, Wenguan Wang, Yi Yang", + "authors": [ + { + "first_name": "Rui", + "last_name": "Liu" + }, + { + "first_name": "Wenguan", + "last_name": "Wang" + }, + { + "first_name": "Yi", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DreamComposer: Controllable 3D Object Generation via Multi-View Conditions", - "authors": "Yunhan Yang, Yukun Huang, Xiaoyang Wu, Yuan-Chen Guo, Song-Hai Zhang, Hengshuang Zhao, Tong He, Xihui Liu", + "authors": [ + { + "first_name": "Yunhan", + "last_name": "Yang" + }, + { + "first_name": "Yukun", + "last_name": "Huang" + }, + { + "first_name": "Xiaoyang", + "last_name": "Wu" + }, + { + "first_name": "Yuan-Chen", + "last_name": "Guo" + }, + { + "first_name": "Song-Hai", + "last_name": "Zhang" + }, + { + "first_name": "Hengshuang", + "last_name": "Zhao" + }, + { + "first_name": "Tong", + "last_name": "He" + }, + { + "first_name": "Xihui", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Self-Calibrating Vicinal Risk Minimisation for Model Calibration", - "authors": "Jiawei Liu, Changkun Ye, Ruikai Cui, Nick Barnes", + "authors": [ + { + "first_name": "Jiawei", + "last_name": "Liu" + }, + { + "first_name": "Changkun", + "last_name": "Ye" + }, + { + "first_name": "Ruikai", + "last_name": "Cui" + }, + { + "first_name": "Nick", + "last_name": "Barnes" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "NeRFDeformer: NeRF Transformation from a Single View via 3D Scene Flows", - "authors": "Zhenggang Tang, Zhongzheng Ren, Xiaoming Zhao, Bowen Wen, Jonathan Tremblay, Stan Birchfield, Alexander Schwing", + "authors": [ + { + "first_name": "Zhenggang", + "last_name": "Tang" + }, + { + "first_name": "Zhongzheng", + "last_name": "Ren" + }, + { + "first_name": "Xiaoming", + "last_name": "Zhao" + }, + { + "first_name": "Bowen", + "last_name": "Wen" + }, + { + "first_name": "Jonathan", + "last_name": "Tremblay" + }, + { + "first_name": "Stan", + "last_name": "Birchfield" + }, + { + "first_name": "Alexander", + "last_name": "Schwing" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LPSNet: End-to-End Human Pose and Shape Estimation with Lensless Imaging", - "authors": "Haoyang Ge, Qiao Feng, Hailong Jia, Xiongzheng Li, Xiangjun Yin, You Zhou, Jingyu Yang, Kun Li", + "authors": [ + { + "first_name": "Haoyang", + "last_name": "Ge" + }, + { + "first_name": "Qiao", + "last_name": "Feng" + }, + { + "first_name": "Hailong", + "last_name": "Jia" + }, + { + "first_name": "Xiongzheng", + "last_name": "Li" + }, + { + "first_name": "Xiangjun", + "last_name": "Yin" + }, + { + "first_name": "You", + "last_name": "Zhou" + }, + { + "first_name": "Jingyu", + "last_name": "Yang" + }, + { + "first_name": "Kun", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Embracing Unimodal Aleatoric Uncertainty for Robust Multimodal Fusion", - "authors": "Zixian Gao, Xun Jiang, Xing Xu, Fumin Shen, Yujie Li, Heng Tao Shen", + "authors": [ + { + "first_name": "Zixian", + "last_name": "Gao" + }, + { + "first_name": "Xun", + "last_name": "Jiang" + }, + { + "first_name": "Xing", + "last_name": "Xu" + }, + { + "first_name": "Fumin", + "last_name": "Shen" + }, + { + "first_name": "Yujie", + "last_name": "Li" + }, + { + "first_name": "Heng", + "last_name": "Tao Shen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Unifying Correspondence Pose and NeRF for Generalized Pose-Free Novel View Synthesis", - "authors": "Sunghwan Hong, Jaewoo Jung, Heeseong Shin, Jiaolong Yang, Seungryong Kim, Chong Luo", + "authors": [ + { + "first_name": "Sunghwan", + "last_name": "Hong" + }, + { + "first_name": "Jaewoo", + "last_name": "Jung" + }, + { + "first_name": "Heeseong", + "last_name": "Shin" + }, + { + "first_name": "Jiaolong", + "last_name": "Yang" + }, + { + "first_name": "Seungryong", + "last_name": "Kim" + }, + { + "first_name": "Chong", + "last_name": "Luo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Draw Step by Step: Reconstructing CAD Construction Sequences from Point Clouds via Multimodal Diffusion.", - "authors": "Weijian Ma, Shuaiqi Chen, Yunzhong Lou, Xueyang Li, Xiangdong Zhou", + "authors": [ + { + "first_name": "Weijian", + "last_name": "Ma" + }, + { + "first_name": "Shuaiqi", + "last_name": "Chen" + }, + { + "first_name": "Yunzhong", + "last_name": "Lou" + }, + { + "first_name": "Xueyang", + "last_name": "Li" + }, + { + "first_name": "Xiangdong", + "last_name": "Zhou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DiffusionTrack: Point Set Diffusion Model for Visual Object Tracking", - "authors": "Fei Xie, Zhongdao Wang, Chao Ma", + "authors": [ + { + "first_name": "Fei", + "last_name": "Xie" + }, + { + "first_name": "Zhongdao", + "last_name": "Wang" + }, + { + "first_name": "Chao", + "last_name": "Ma" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards a Simultaneous and Granular Identity-Expression Control in Personalized Face Generation", - "authors": "Renshuai Liu, Bowen Ma, Wei Zhang, Zhipeng Hu, Changjie Fan, Tangjie Lv, Yu Ding, Xuan Cheng", + "authors": [ + { + "first_name": "Renshuai", + "last_name": "Liu" + }, + { + "first_name": "Bowen", + "last_name": "Ma" + }, + { + "first_name": "Wei", + "last_name": "Zhang" + }, + { + "first_name": "Zhipeng", + "last_name": "Hu" + }, + { + "first_name": "Changjie", + "last_name": "Fan" + }, + { + "first_name": "Tangjie", + "last_name": "Lv" + }, + { + "first_name": "Yu", + "last_name": "Ding" + }, + { + "first_name": "Xuan", + "last_name": "Cheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PEEKABOO: Interactive Video Generation via Masked-Diffusion", - "authors": "Yash Jain, Anshul Nasery, Vibhav Vineet, Harkirat Behl", + "authors": [ + { + "first_name": "Yash", + "last_name": "Jain" + }, + { + "first_name": "Anshul", + "last_name": "Nasery" + }, + { + "first_name": "Vibhav", + "last_name": "Vineet" + }, + { + "first_name": "Harkirat", + "last_name": "Behl" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Scaling Diffusion Models to Real-World 3D LiDAR Scene Completion", - "authors": "Lucas Nunes, Rodrigo Marcuzzi, Benedikt Mersch, Jens Behley, Cyrill Stachniss", + "authors": [ + { + "first_name": "Lucas", + "last_name": "Nunes" + }, + { + "first_name": "Rodrigo", + "last_name": "Marcuzzi" + }, + { + "first_name": "Benedikt", + "last_name": "Mersch" + }, + { + "first_name": "Jens", + "last_name": "Behley" + }, + { + "first_name": "Cyrill", + "last_name": "Stachniss" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Discriminative Pattern Calibration Mechanism for Source-Free Domain Adaptation", - "authors": "Haifeng Xia, Siyu Xia, Zhengming Ding", + "authors": [ + { + "first_name": "Haifeng", + "last_name": "Xia" + }, + { + "first_name": "Siyu", + "last_name": "Xia" + }, + { + "first_name": "Zhengming", + "last_name": "Ding" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Deep Generative Model based Rate-Distortion for Image Downscaling Assessment", - "authors": "Yuanbang Liang, Bhavesh Garg, Paul Rosin, Yipeng Qin", + "authors": [ + { + "first_name": "Yuanbang", + "last_name": "Liang" + }, + { + "first_name": "Bhavesh", + "last_name": "Garg" + }, + { + "first_name": "Paul", + "last_name": "Rosin" + }, + { + "first_name": "Yipeng", + "last_name": "Qin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Physical Backdoor: Towards Temperature-based Backdoor Attacks in the Physical World", - "authors": "Wen Yin, Jian Lou, Pan Zhou, Yulai Xie, Dan Feng, Yuhua Sun, Tailai Zhang, Lichao Sun", + "authors": [ + { + "first_name": "Wen", + "last_name": "Yin" + }, + { + "first_name": "Jian", + "last_name": "Lou" + }, + { + "first_name": "Pan", + "last_name": "Zhou" + }, + { + "first_name": "Yulai", + "last_name": "Xie" + }, + { + "first_name": "Dan", + "last_name": "Feng" + }, + { + "first_name": "Yuhua", + "last_name": "Sun" + }, + { + "first_name": "Tailai", + "last_name": "Zhang" + }, + { + "first_name": "Lichao", + "last_name": "Sun" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Make Me a BNN: A Simple Strategy for Estimating Bayesian Uncertainty from Pre-trained Models", - "authors": "Gianni Franchi, Olivier Laurent, Maxence Leguery, Andrei Bursuc, Andrea Pilzer, Angela Yao", + "authors": [ + { + "first_name": "Gianni", + "last_name": "Franchi" + }, + { + "first_name": "Olivier", + "last_name": "Laurent" + }, + { + "first_name": "Maxence", + "last_name": "Leguery" + }, + { + "first_name": "Andrei", + "last_name": "Bursuc" + }, + { + "first_name": "Andrea", + "last_name": "Pilzer" + }, + { + "first_name": "Angela", + "last_name": "Yao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Language-only Training of Zero-shot Composed Image Retrieval", - "authors": "Geonmo Gu, Sanghyuk Chun, Wonjae Kim, Yoohoon Kang, Sangdoo Yun", + "authors": [ + { + "first_name": "Geonmo", + "last_name": "Gu" + }, + { + "first_name": "Sanghyuk", + "last_name": "Chun" + }, + { + "first_name": "Wonjae", + "last_name": "Kim" + }, + { + "first_name": "Yoohoon", + "last_name": "Kang" + }, + { + "first_name": "Sangdoo", + "last_name": "Yun" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "EFHQ: Multi-purpose ExtremePose-Face-HQ dataset", - "authors": "Trung Tuan Dao, Duc Hong Vu, Cuong Pham, Anh Tran", + "authors": [ + { + "first_name": "Trung", + "last_name": "Tuan Dao" + }, + { + "first_name": "Duc", + "last_name": "Hong Vu" + }, + { + "first_name": "Cuong", + "last_name": "Pham" + }, + { + "first_name": "Anh", + "last_name": "Tran" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Dynamic Cues-Assisted Transformer for Robust Point Cloud Registration", - "authors": "Hong Chen, Pei Yan, Sihe Xiang, Yihua Tan", + "authors": [ + { + "first_name": "Hong", + "last_name": "Chen" + }, + { + "first_name": "Pei", + "last_name": "Yan" + }, + { + "first_name": "Sihe", + "last_name": "Xiang" + }, + { + "first_name": "Yihua", + "last_name": "Tan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Patch2Self2: Self-supervised Denoising on Coresets via Matrix Sketching", - "authors": "Shreyas Fadnavis, Agniva Chowdhury, Joshua Batson, Petros Drineas, Eleftherios Garyfallidis", + "authors": [ + { + "first_name": "Shreyas", + "last_name": "Fadnavis" + }, + { + "first_name": "Agniva", + "last_name": "Chowdhury" + }, + { + "first_name": "Joshua", + "last_name": "Batson" + }, + { + "first_name": "Petros", + "last_name": "Drineas" + }, + { + "first_name": "Eleftherios", + "last_name": "Garyfallidis" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "High-fidelity Person-centric Subject-to-Image Synthesis", - "authors": "Yibin Wang, Weizhong Zhang, Jianwei Zheng, Cheng Jin", + "authors": [ + { + "first_name": "Yibin", + "last_name": "Wang" + }, + { + "first_name": "Weizhong", + "last_name": "Zhang" + }, + { + "first_name": "Jianwei", + "last_name": "Zheng" + }, + { + "first_name": "Cheng", + "last_name": "Jin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "The Devil is in the Fine-Grained Details: Evaluating Open-Vocabulary Object Detectors for Fine-Grained Understanding", - "authors": "Lorenzo Bianchi, Fabio Carrara, Nicola Messina, Claudio Gennaro, Fabrizio Falchi", + "authors": [ + { + "first_name": "Lorenzo", + "last_name": "Bianchi" + }, + { + "first_name": "Fabio", + "last_name": "Carrara" + }, + { + "first_name": "Nicola", + "last_name": "Messina" + }, + { + "first_name": "Claudio", + "last_name": "Gennaro" + }, + { + "first_name": "Fabrizio", + "last_name": "Falchi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Efficient and Effective Weakly-Supervised Action Segmentation via Action-Transition-Aware Boundary Alignment", - "authors": "Angchi Xu, Wei-Shi Zheng", + "authors": [ + { + "first_name": "Angchi", + "last_name": "Xu" + }, + { + "first_name": "Wei-Shi", + "last_name": "Zheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Link-Context Learning for Multimodal LLMs", - "authors": "Yan Tai, Weichen Fan, Zhao Zhang, Ziwei Liu", + "authors": [ + { + "first_name": "Yan", + "last_name": "Tai" + }, + { + "first_name": "Weichen", + "last_name": "Fan" + }, + { + "first_name": "Zhao", + "last_name": "Zhang" + }, + { + "first_name": "Ziwei", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Pixel-Aligned Language Model", - "authors": "Jiarui Xu, Xingyi Zhou, Shen Yan, Xiuye Gu, Anurag Arnab, Chen Sun, Xiaolong Wang, Cordelia Schmid", + "authors": [ + { + "first_name": "Jiarui", + "last_name": "Xu" + }, + { + "first_name": "Xingyi", + "last_name": "Zhou" + }, + { + "first_name": "Shen", + "last_name": "Yan" + }, + { + "first_name": "Xiuye", + "last_name": "Gu" + }, + { + "first_name": "Anurag", + "last_name": "Arnab" + }, + { + "first_name": "Chen", + "last_name": "Sun" + }, + { + "first_name": "Xiaolong", + "last_name": "Wang" + }, + { + "first_name": "Cordelia", + "last_name": "Schmid" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "JeDi: Joint-Image Diffusion Models for Finetuning-Free Personalized Text-to-Image Generation", - "authors": "Yu Zeng, Vishal M. Patel, Haochen Wang, Xun Huang, Ting-Chun Wang, Ming-Yu Liu, Yogesh Balaji", + "authors": [ + { + "first_name": "Yu", + "last_name": "Zeng" + }, + { + "first_name": "Vishal", + "last_name": "M. Patel" + }, + { + "first_name": "Haochen", + "last_name": "Wang" + }, + { + "first_name": "Xun", + "last_name": "Huang" + }, + { + "first_name": "Ting-Chun", + "last_name": "Wang" + }, + { + "first_name": "Ming-Yu", + "last_name": "Liu" + }, + { + "first_name": "Yogesh", + "last_name": "Balaji" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ConsistDreamer: 3D-Consistent 2D Diffusion for High-Fidelity Scene Editing", - "authors": "Jun-Kun Chen, Samuel Rota Bulò, Norman Müller, Lorenzo Porzi, Peter Kontschieder, Yu-Xiong Wang", + "authors": [ + { + "first_name": "Jun-Kun", + "last_name": "Chen" + }, + { + "first_name": "Samuel", + "last_name": "Rota Bulò" + }, + { + "first_name": "Norman", + "last_name": "Müller" + }, + { + "first_name": "Lorenzo", + "last_name": "Porzi" + }, + { + "first_name": "Peter", + "last_name": "Kontschieder" + }, + { + "first_name": "Yu-Xiong", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HandDiff: 3D Hand Pose Estimation with Diffusion on Image-Point Cloud", - "authors": "Wencan Cheng, Hao Tang, Luc Van Gool, Jong Hwan Ko", + "authors": [ + { + "first_name": "Wencan", + "last_name": "Cheng" + }, + { + "first_name": "Hao", + "last_name": "Tang" + }, + { + "first_name": "Luc", + "last_name": "Van Gool" + }, + { + "first_name": "Jong", + "last_name": "Hwan Ko" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SNIDA: Unlocking Few-Shot Object Detection with Non-linear Semantic Decoupling Augmentation", - "authors": "Yanjie Wang, Xu Zou, Luxin Yan, Sheng Zhong, Jiahuan Zhou", + "authors": [ + { + "first_name": "Yanjie", + "last_name": "Wang" + }, + { + "first_name": "Xu", + "last_name": "Zou" + }, + { + "first_name": "Luxin", + "last_name": "Yan" + }, + { + "first_name": "Sheng", + "last_name": "Zhong" + }, + { + "first_name": "Jiahuan", + "last_name": "Zhou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "On the Robustness of Large Multimodal Models Against Image Adversarial Attacks", - "authors": "Xuanming Cui, Alejandro Aparcedo, Young Kyun Jang, Ser-Nam Lim", + "authors": [ + { + "first_name": "Xuanming", + "last_name": "Cui" + }, + { + "first_name": "Alejandro", + "last_name": "Aparcedo" + }, + { + "first_name": "Young", + "last_name": "Kyun Jang" + }, + { + "first_name": "Ser-Nam", + "last_name": "Lim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SoundingActions: Learning How Actions Sound from Narrated Egocentric Videos", - "authors": "Changan Chen, Kumar Ashutosh, Rohit Girdhar, David Harwath, Kristen Grauman", + "authors": [ + { + "first_name": "Changan", + "last_name": "Chen" + }, + { + "first_name": "Kumar", + "last_name": "Ashutosh" + }, + { + "first_name": "Rohit", + "last_name": "Girdhar" + }, + { + "first_name": "David", + "last_name": "Harwath" + }, + { + "first_name": "Kristen", + "last_name": "Grauman" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Not All Voxels Are Equal: Hardness-Aware Semantic Scene Completion with Self-Distillation", - "authors": "Song Wang, Jiawei Yu, Wentong Li, Wenyu Liu, Xiaolu Liu, Junbo Chen, Jianke Zhu", + "authors": [ + { + "first_name": "Song", + "last_name": "Wang" + }, + { + "first_name": "Jiawei", + "last_name": "Yu" + }, + { + "first_name": "Wentong", + "last_name": "Li" + }, + { + "first_name": "Wenyu", + "last_name": "Liu" + }, + { + "first_name": "Xiaolu", + "last_name": "Liu" + }, + { + "first_name": "Junbo", + "last_name": "Chen" + }, + { + "first_name": "Jianke", + "last_name": "Zhu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "3D-LFM: Lifting Foundation Model", - "authors": "Mosam Dabhi, László A. Jeni, Simon Lucey", + "authors": [ + { + "first_name": "Mosam", + "last_name": "Dabhi" + }, + { + "first_name": "László", + "last_name": "A. Jeni" + }, + { + "first_name": "Simon", + "last_name": "Lucey" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "VP3D: Unleashing 2D Visual Prompt for Text-to-3D Generation", - "authors": "Yang Chen, Yingwei Pan, Haibo Yang, Ting Yao, Tao Mei", + "authors": [ + { + "first_name": "Yang", + "last_name": "Chen" + }, + { + "first_name": "Yingwei", + "last_name": "Pan" + }, + { + "first_name": "Haibo", + "last_name": "Yang" + }, + { + "first_name": "Ting", + "last_name": "Yao" + }, + { + "first_name": "Tao", + "last_name": "Mei" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MonoHair: High-Fidelity Hair Modeling from a Monocular Video", - "authors": "Keyu Wu, Lingchen Yang, Zhiyi Kuang, Yao Feng, Xutao Han, Yuefan Shen, Hongbo Fu, Kun Zhou, Youyi Zheng", + "authors": [ + { + "first_name": "Keyu", + "last_name": "Wu" + }, + { + "first_name": "Lingchen", + "last_name": "Yang" + }, + { + "first_name": "Zhiyi", + "last_name": "Kuang" + }, + { + "first_name": "Yao", + "last_name": "Feng" + }, + { + "first_name": "Xutao", + "last_name": "Han" + }, + { + "first_name": "Yuefan", + "last_name": "Shen" + }, + { + "first_name": "Hongbo", + "last_name": "Fu" + }, + { + "first_name": "Kun", + "last_name": "Zhou" + }, + { + "first_name": "Youyi", + "last_name": "Zheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Content-Style Decoupling for Unsupervised Makeup Transfer without Generating Pseudo Ground Truth", - "authors": "Zhaoyang Sun, Shengwu Xiong, Yaxiong Chen, Yi Rong", + "authors": [ + { + "first_name": "Zhaoyang", + "last_name": "Sun" + }, + { + "first_name": "Shengwu", + "last_name": "Xiong" + }, + { + "first_name": "Yaxiong", + "last_name": "Chen" + }, + { + "first_name": "Yi", + "last_name": "Rong" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models", - "authors": "Lin Li, Haoyan Guan, Jianing Qiu, Michael Spratling", + "authors": [ + { + "first_name": "Lin", + "last_name": "Li" + }, + { + "first_name": "Haoyan", + "last_name": "Guan" + }, + { + "first_name": "Jianing", + "last_name": "Qiu" + }, + { + "first_name": "Michael", + "last_name": "Spratling" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "A Versatile Framework for Continual Test-Time Domain Adaptation: Balancing Discriminability and Generalizability", - "authors": "Xu Yang, Xuan Chen, Moqi Li, Kun Wei, Cheng Deng", + "authors": [ + { + "first_name": "Xu", + "last_name": "Yang" + }, + { + "first_name": "Xuan", + "last_name": "Chen" + }, + { + "first_name": "Moqi", + "last_name": "Li" + }, + { + "first_name": "Kun", + "last_name": "Wei" + }, + { + "first_name": "Cheng", + "last_name": "Deng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Quantifying Uncertainty in Motion Prediction with Variational Bayesian Mixture", - "authors": "Juanwu Lu, Can Cui, Yunsheng Ma, Aniket Bera, Ziran Wang", + "authors": [ + { + "first_name": "Juanwu", + "last_name": "Lu" + }, + { + "first_name": "Can", + "last_name": "Cui" + }, + { + "first_name": "Yunsheng", + "last_name": "Ma" + }, + { + "first_name": "Aniket", + "last_name": "Bera" + }, + { + "first_name": "Ziran", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "You Only Need Less Attention at Each Stage in Vision Transformers", - "authors": "Shuoxi Zhang, Hanpeng Liu, Stephen Lin, Kun He", + "authors": [ + { + "first_name": "Shuoxi", + "last_name": "Zhang" + }, + { + "first_name": "Hanpeng", + "last_name": "Liu" + }, + { + "first_name": "Stephen", + "last_name": "Lin" + }, + { + "first_name": "Kun", + "last_name": "He" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Sieve: Multimodal Dataset Pruning using Image Captioning Models", - "authors": "Anas Mahmoud, Mostafa Elhoushi, Amro Abbas, Yu Yang, Newsha Ardalani, Hugh Leather, Ari S. Morcos", + "authors": [ + { + "first_name": "Anas", + "last_name": "Mahmoud" + }, + { + "first_name": "Mostafa", + "last_name": "Elhoushi" + }, + { + "first_name": "Amro", + "last_name": "Abbas" + }, + { + "first_name": "Yu", + "last_name": "Yang" + }, + { + "first_name": "Newsha", + "last_name": "Ardalani" + }, + { + "first_name": "Hugh", + "last_name": "Leather" + }, + { + "first_name": "Ari", + "last_name": "S. Morcos" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Generalizable Novel-View Synthesis using a Stereo Camera", - "authors": "Haechan Lee, Wonjoon Jin, Seung-Hwan Baek, Sunghyun Cho", + "authors": [ + { + "first_name": "Haechan", + "last_name": "Lee" + }, + { + "first_name": "Wonjoon", + "last_name": "Jin" + }, + { + "first_name": "Seung-Hwan", + "last_name": "Baek" + }, + { + "first_name": "Sunghyun", + "last_name": "Cho" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Dynamic LiDAR Re-simulation using Compositional Neural Fields", - "authors": "Hanfeng Wu, Xingxing Zuo, Stefan Leutenegger, Or Litany, Konrad Schindler, Shengyu Huang", + "authors": [ + { + "first_name": "Hanfeng", + "last_name": "Wu" + }, + { + "first_name": "Xingxing", + "last_name": "Zuo" + }, + { + "first_name": "Stefan", + "last_name": "Leutenegger" + }, + { + "first_name": "Or", + "last_name": "Litany" + }, + { + "first_name": "Konrad", + "last_name": "Schindler" + }, + { + "first_name": "Shengyu", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Explaining CLIP's Performance Disparities on Data from Blind/Low Vision Users", - "authors": "Daniela Massiceti, Camilla Longden, Agnieszka Slowik, Samuel Wills, Martin Grayson, Cecily Morrison", + "authors": [ + { + "first_name": "Daniela", + "last_name": "Massiceti" + }, + { + "first_name": "Camilla", + "last_name": "Longden" + }, + { + "first_name": "Agnieszka", + "last_name": "Slowik" + }, + { + "first_name": "Samuel", + "last_name": "Wills" + }, + { + "first_name": "Martin", + "last_name": "Grayson" + }, + { + "first_name": "Cecily", + "last_name": "Morrison" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "AETTA: Label-Free Accuracy Estimation for Test-Time Adaptation", - "authors": "Taeckyung Lee, Sorn Chottananurak, Taesik Gong, Sung-Ju Lee", + "authors": [ + { + "first_name": "Taeckyung", + "last_name": "Lee" + }, + { + "first_name": "Sorn", + "last_name": "Chottananurak" + }, + { + "first_name": "Taesik", + "last_name": "Gong" + }, + { + "first_name": "Sung-Ju", + "last_name": "Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Digital Life Project: Autonomous 3D Characters with Social Intelligence", - "authors": "Zhongang Cai, Jianping Jiang, Zhongfei Qing, Xinying Guo, Mingyuan Zhang, Zhengyu Lin, Haiyi Mei, Chen Wei, Ruisi Wang, Wanqi Yin, Liang Pan, Xiangyu Fan, Han Du, Peng Gao, Zhitao Yang, Yang Gao, Jiaqi Li, Tianxiang Ren, Yukun Wei, Xiaogang Wang, Chen Change Loy, Lei Yang, Ziwei Liu", + "authors": [ + { + "first_name": "Zhongang", + "last_name": "Cai" + }, + { + "first_name": "Jianping", + "last_name": "Jiang" + }, + { + "first_name": "Zhongfei", + "last_name": "Qing" + }, + { + "first_name": "Xinying", + "last_name": "Guo" + }, + { + "first_name": "Mingyuan", + "last_name": "Zhang" + }, + { + "first_name": "Zhengyu", + "last_name": "Lin" + }, + { + "first_name": "Haiyi", + "last_name": "Mei" + }, + { + "first_name": "Chen", + "last_name": "Wei" + }, + { + "first_name": "Ruisi", + "last_name": "Wang" + }, + { + "first_name": "Wanqi", + "last_name": "Yin" + }, + { + "first_name": "Liang", + "last_name": "Pan" + }, + { + "first_name": "Xiangyu", + "last_name": "Fan" + }, + { + "first_name": "Han", + "last_name": "Du" + }, + { + "first_name": "Peng", + "last_name": "Gao" + }, + { + "first_name": "Zhitao", + "last_name": "Yang" + }, + { + "first_name": "Yang", + "last_name": "Gao" + }, + { + "first_name": "Jiaqi", + "last_name": "Li" + }, + { + "first_name": "Tianxiang", + "last_name": "Ren" + }, + { + "first_name": "Yukun", + "last_name": "Wei" + }, + { + "first_name": "Xiaogang", + "last_name": "Wang" + }, + { + "first_name": "Chen", + "last_name": "Change Loy" + }, + { + "first_name": "Lei", + "last_name": "Yang" + }, + { + "first_name": "Ziwei", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "An Empirical Study of the Generalization Ability of Lidar 3D Object Detectors to Unseen Domains", - "authors": "George Eskandar", + "authors": [ + { + "first_name": "George", + "last_name": "Eskandar" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Unsupervised Universal Image Segmentation", - "authors": "Dantong Niu, Xudong Wang, Xinyang Han, Long Lian, Roei Herzig, Trevor Darrell", + "authors": [ + { + "first_name": "Dantong", + "last_name": "Niu" + }, + { + "first_name": "Xudong", + "last_name": "Wang" + }, + { + "first_name": "Xinyang", + "last_name": "Han" + }, + { + "first_name": "Long", + "last_name": "Lian" + }, + { + "first_name": "Roei", + "last_name": "Herzig" + }, + { + "first_name": "Trevor", + "last_name": "Darrell" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Rethinking Prior Information Generation with CLIP for Few-Shot Segmentation", - "authors": "Jin Wang, Bingfeng Zhang, Jian Pang, Honglong Chen, Weifeng Liu", + "authors": [ + { + "first_name": "Jin", + "last_name": "Wang" + }, + { + "first_name": "Bingfeng", + "last_name": "Zhang" + }, + { + "first_name": "Jian", + "last_name": "Pang" + }, + { + "first_name": "Honglong", + "last_name": "Chen" + }, + { + "first_name": "Weifeng", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SingularTrajectory: Universal Trajectory Predictor Using Diffusion Model", - "authors": "Inhwan Bae, Young-Jae Park, Hae-Gon Jeon", + "authors": [ + { + "first_name": "Inhwan", + "last_name": "Bae" + }, + { + "first_name": "Young-Jae", + "last_name": "Park" + }, + { + "first_name": "Hae-Gon", + "last_name": "Jeon" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Generating Handwritten Mathematical Expressions From Symbol Graphs: An End-to-End Pipeline", - "authors": "Yu Chen, Fei Gao, Yanguang Zhang, Maoying Qiao, Nannan Wang", + "authors": [ + { + "first_name": "Yu", + "last_name": "Chen" + }, + { + "first_name": "Fei", + "last_name": "Gao" + }, + { + "first_name": "Yanguang", + "last_name": "Zhang" + }, + { + "first_name": "Maoying", + "last_name": "Qiao" + }, + { + "first_name": "Nannan", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "A Closer Look at the Few-Shot Adaptation of Large Vision-Language Models", - "authors": "Julio Silva-Rodríguez, Sina Hajimiri, Ismail Ben Ayed, Jose Dolz", + "authors": [ + { + "first_name": "Julio", + "last_name": "Silva-Rodríguez" + }, + { + "first_name": "Sina", + "last_name": "Hajimiri" + }, + { + "first_name": "Ismail", + "last_name": "Ben Ayed" + }, + { + "first_name": "Jose", + "last_name": "Dolz" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Generative Rendering: Controllable 4D-Guided Video Generation with 2D Diffusion Models", - "authors": "Shengqu Cai, Duygu Ceylan, Matheus Gadelha, Chun-Hao Paul Huang, Tuanfeng Yang Wang, Gordon Wetzstein", + "authors": [ + { + "first_name": "Shengqu", + "last_name": "Cai" + }, + { + "first_name": "Duygu", + "last_name": "Ceylan" + }, + { + "first_name": "Matheus", + "last_name": "Gadelha" + }, + { + "first_name": "Chun-Hao", + "last_name": "Paul Huang" + }, + { + "first_name": "Tuanfeng", + "last_name": "Yang Wang" + }, + { + "first_name": "Gordon", + "last_name": "Wetzstein" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Relightable Gaussian Codec Avatars", - "authors": "Shunsuke Saito, Gabriel Schwartz, Tomas Simon, Junxuan Li, Giljoo Nam", + "authors": [ + { + "first_name": "Shunsuke", + "last_name": "Saito" + }, + { + "first_name": "Gabriel", + "last_name": "Schwartz" + }, + { + "first_name": "Tomas", + "last_name": "Simon" + }, + { + "first_name": "Junxuan", + "last_name": "Li" + }, + { + "first_name": "Giljoo", + "last_name": "Nam" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Why Not Use Your Textbook? Knowledge-Enhanced Procedure Planning of Instructional Videos", - "authors": "Kumaranage Ravindu Yasas Nagasinghe, Honglu Zhou, Malitha Gunawardhana, Martin Renqiang Min, Daniel Harari, Muhammad Haris Khan", + "authors": [ + { + "first_name": "Kumaranage", + "last_name": "Ravindu Yasas Nagasinghe" + }, + { + "first_name": "Honglu", + "last_name": "Zhou" + }, + { + "first_name": "Malitha", + "last_name": "Gunawardhana" + }, + { + "first_name": "Martin", + "last_name": "Renqiang Min" + }, + { + "first_name": "Daniel", + "last_name": "Harari" + }, + { + "first_name": "Muhammad", + "last_name": "Haris Khan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Global and Hierarchical Geometry Consistency Priors for Few-shot NeRFs in Indoor Scenes", - "authors": "Xiaotian Sun, Qingshan Xu, Xinjie Yang, Yu Zang, Cheng Wang", + "authors": [ + { + "first_name": "Xiaotian", + "last_name": "Sun" + }, + { + "first_name": "Qingshan", + "last_name": "Xu" + }, + { + "first_name": "Xinjie", + "last_name": "Yang" + }, + { + "first_name": "Yu", + "last_name": "Zang" + }, + { + "first_name": "Cheng", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FreeKD: Knowledge Distillation via Semantic Frequency Prompt", - "authors": "Yuan Zhang, Tao Huang, Jiaming Liu, Tao Jiang, Kuan Cheng, Shanghang Zhang", + "authors": [ + { + "first_name": "Yuan", + "last_name": "Zhang" + }, + { + "first_name": "Tao", + "last_name": "Huang" + }, + { + "first_name": "Jiaming", + "last_name": "Liu" + }, + { + "first_name": "Tao", + "last_name": "Jiang" + }, + { + "first_name": "Kuan", + "last_name": "Cheng" + }, + { + "first_name": "Shanghang", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Can't Make an Omelette Without Breaking Some Eggs: Plausible Action Anticipation Using Large Video-Language Models", - "authors": "Himangi Mittal, Nakul Agarwal, Shao-Yuan Lo, Kwonjoon Lee", + "authors": [ + { + "first_name": "Himangi", + "last_name": "Mittal" + }, + { + "first_name": "Nakul", + "last_name": "Agarwal" + }, + { + "first_name": "Shao-Yuan", + "last_name": "Lo" + }, + { + "first_name": "Kwonjoon", + "last_name": "Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "On the Estimation of Image-matching Uncertainty in Visual Place Recognition", - "authors": "Mubariz Zaffar, Liangliang Nan, Julian F. P. Kooij", + "authors": [ + { + "first_name": "Mubariz", + "last_name": "Zaffar" + }, + { + "first_name": "Liangliang", + "last_name": "Nan" + }, + { + "first_name": "Julian", + "last_name": "F. P. Kooij" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Mask Grounding for Referring Image Segmentation", - "authors": "Yong Xien Chng, Henry Zheng, Yizeng Han, Xuchong Qiu, Gao Huang", + "authors": [ + { + "first_name": "Yong", + "last_name": "Xien Chng" + }, + { + "first_name": "Henry", + "last_name": "Zheng" + }, + { + "first_name": "Yizeng", + "last_name": "Han" + }, + { + "first_name": "Xuchong", + "last_name": "Qiu" + }, + { + "first_name": "Gao", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Single-to-Dual-View Adaptation for Egocentric 3D Hand Pose Estimation", - "authors": "Ruicong Liu, Takehiko Ohkawa, Mingfang Zhang, Yoichi Sato", + "authors": [ + { + "first_name": "Ruicong", + "last_name": "Liu" + }, + { + "first_name": "Takehiko", + "last_name": "Ohkawa" + }, + { + "first_name": "Mingfang", + "last_name": "Zhang" + }, + { + "first_name": "Yoichi", + "last_name": "Sato" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Time-Efficient Light-Field Acquisition Using Coded Aperture and Events", - "authors": "Shuji Habuchi, Keita Takahashi, Chihiro Tsutake, Toshiaki Fujii, Hajime Nagahara", + "authors": [ + { + "first_name": "Shuji", + "last_name": "Habuchi" + }, + { + "first_name": "Keita", + "last_name": "Takahashi" + }, + { + "first_name": "Chihiro", + "last_name": "Tsutake" + }, + { + "first_name": "Toshiaki", + "last_name": "Fujii" + }, + { + "first_name": "Hajime", + "last_name": "Nagahara" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "EVS-assisted Joint Deblurring Rolling-Shutter Correction and Video Frame Interpolation through Sensor Inverse Modeling", - "authors": "Rui Jiang, Fangwen Tu, Yixuan Long, Aabhaas Vaish, Bowen Zhou, Qinyi Wang, Wei Zhang, Yuntan Fang, Luis Eduardo Garcia Capel, Bo Mu, Tiejun Dai, Andreas Suess", + "authors": [ + { + "first_name": "Rui", + "last_name": "Jiang" + }, + { + "first_name": "Fangwen", + "last_name": "Tu" + }, + { + "first_name": "Yixuan", + "last_name": "Long" + }, + { + "first_name": "Aabhaas", + "last_name": "Vaish" + }, + { + "first_name": "Bowen", + "last_name": "Zhou" + }, + { + "first_name": "Qinyi", + "last_name": "Wang" + }, + { + "first_name": "Wei", + "last_name": "Zhang" + }, + { + "first_name": "Yuntan", + "last_name": "Fang" + }, + { + "first_name": "Luis", + "last_name": "Eduardo Garcia Capel" + }, + { + "first_name": "Bo", + "last_name": "Mu" + }, + { + "first_name": "Tiejun", + "last_name": "Dai" + }, + { + "first_name": "Andreas", + "last_name": "Suess" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Prompt-Enhanced Multiple Instance Learning for Weakly Supervised Video Anomaly Detection", - "authors": "Junxi Chen, Liang Li, Li Su, Zheng-jun Zha, Qingming Huang", + "authors": [ + { + "first_name": "Junxi", + "last_name": "Chen" + }, + { + "first_name": "Liang", + "last_name": "Li" + }, + { + "first_name": "Li", + "last_name": "Su" + }, + { + "first_name": "Zheng-jun", + "last_name": "Zha" + }, + { + "first_name": "Qingming", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation", - "authors": "Li Hu", + "authors": [ + { + "first_name": "Li", + "last_name": "Hu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FreeCustom: Tuning-Free Customized Image Generation for Multi-Concept Composition", - "authors": "Ganggui Ding, Canyu Zhao, Wen Wang, Zhen Yang, Zide Liu, Hao Chen, Chunhua Shen", + "authors": [ + { + "first_name": "Ganggui", + "last_name": "Ding" + }, + { + "first_name": "Canyu", + "last_name": "Zhao" + }, + { + "first_name": "Wen", + "last_name": "Wang" + }, + { + "first_name": "Zhen", + "last_name": "Yang" + }, + { + "first_name": "Zide", + "last_name": "Liu" + }, + { + "first_name": "Hao", + "last_name": "Chen" + }, + { + "first_name": "Chunhua", + "last_name": "Shen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Non-autoregressive Sequence-to-Sequence Vision-Language Models", - "authors": "Kunyu Shi, Qi Dong, Luis Goncalves, Zhuowen Tu, Stefano Soatto", + "authors": [ + { + "first_name": "Kunyu", + "last_name": "Shi" + }, + { + "first_name": "Qi", + "last_name": "Dong" + }, + { + "first_name": "Luis", + "last_name": "Goncalves" + }, + { + "first_name": "Zhuowen", + "last_name": "Tu" + }, + { + "first_name": "Stefano", + "last_name": "Soatto" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MaskINT: Video Editing via Interpolative Non-autoregressive Masked Transformers", - "authors": "Haoyu Ma, Shahin Mahdizadehaghdam, Bichen Wu, Zhipeng Fan, Yuchao Gu, Wenliang Zhao, Lior Shapira, Xiaohui Xie", + "authors": [ + { + "first_name": "Haoyu", + "last_name": "Ma" + }, + { + "first_name": "Shahin", + "last_name": "Mahdizadehaghdam" + }, + { + "first_name": "Bichen", + "last_name": "Wu" + }, + { + "first_name": "Zhipeng", + "last_name": "Fan" + }, + { + "first_name": "Yuchao", + "last_name": "Gu" + }, + { + "first_name": "Wenliang", + "last_name": "Zhao" + }, + { + "first_name": "Lior", + "last_name": "Shapira" + }, + { + "first_name": "Xiaohui", + "last_name": "Xie" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Active Prompt Learning in Vision Language Models", - "authors": "Jihwan Bang, Sumyeong Ahn, Jae-Gil Lee", + "authors": [ + { + "first_name": "Jihwan", + "last_name": "Bang" + }, + { + "first_name": "Sumyeong", + "last_name": "Ahn" + }, + { + "first_name": "Jae-Gil", + "last_name": "Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning Multi-Dimensional Human Preference for Text-to-Image Generation", - "authors": "Sixian Zhang, Bohan Wang, Junqiang Wu, Yan Li, Tingting Gao, Di Zhang, Zhongyuan Wang", + "authors": [ + { + "first_name": "Sixian", + "last_name": "Zhang" + }, + { + "first_name": "Bohan", + "last_name": "Wang" + }, + { + "first_name": "Junqiang", + "last_name": "Wu" + }, + { + "first_name": "Yan", + "last_name": "Li" + }, + { + "first_name": "Tingting", + "last_name": "Gao" + }, + { + "first_name": "Di", + "last_name": "Zhang" + }, + { + "first_name": "Zhongyuan", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ViVid-1-to-3: Novel View Synthesis with Video Diffusion Models", - "authors": "Jeong-gi Kwak, Erqun Dong, Yuhe Jin, Hanseok Ko, Shweta Mahajan, Kwang Moo Yi", + "authors": [ + { + "first_name": "Jeong-gi", + "last_name": "Kwak" + }, + { + "first_name": "Erqun", + "last_name": "Dong" + }, + { + "first_name": "Yuhe", + "last_name": "Jin" + }, + { + "first_name": "Hanseok", + "last_name": "Ko" + }, + { + "first_name": "Shweta", + "last_name": "Mahajan" + }, + { + "first_name": "Kwang", + "last_name": "Moo Yi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Active Object Detection with Knowledge Aggregation and Distillation from Large Models", - "authors": "Dejie Yang, Yang Liu", + "authors": [ + { + "first_name": "Dejie", + "last_name": "Yang" + }, + { + "first_name": "Yang", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "NICE: Neurogenesis Inspired Contextual Encoding for Replay-free Class Incremental Learning", - "authors": "Mustafa Burak Gurbuz, Jean Michael Moorman, Constantine Dovrolis", + "authors": [ + { + "first_name": "Mustafa", + "last_name": "Burak Gurbuz" + }, + { + "first_name": "Jean", + "last_name": "Michael Moorman" + }, + { + "first_name": "Constantine", + "last_name": "Dovrolis" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Generating Human Motion in 3D Scenes from Text Descriptions", - "authors": "Zhi Cen, Huaijin Pi, Sida Peng, Zehong Shen, Minghui Yang, Shuai Zhu, Hujun Bao, Xiaowei Zhou", + "authors": [ + { + "first_name": "Zhi", + "last_name": "Cen" + }, + { + "first_name": "Huaijin", + "last_name": "Pi" + }, + { + "first_name": "Sida", + "last_name": "Peng" + }, + { + "first_name": "Zehong", + "last_name": "Shen" + }, + { + "first_name": "Minghui", + "last_name": "Yang" + }, + { + "first_name": "Shuai", + "last_name": "Zhu" + }, + { + "first_name": "Hujun", + "last_name": "Bao" + }, + { + "first_name": "Xiaowei", + "last_name": "Zhou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Weak-to-Strong 3D Object Detection with X-Ray Distillation", - "authors": "Alexander Gambashidze, Aleksandr Dadukin, Maxim Golyadkin, Maria Razzhivina, Ilya Makarov", + "authors": [ + { + "first_name": "Alexander", + "last_name": "Gambashidze" + }, + { + "first_name": "Aleksandr", + "last_name": "Dadukin" + }, + { + "first_name": "Maxim", + "last_name": "Golyadkin" + }, + { + "first_name": "Maria", + "last_name": "Razzhivina" + }, + { + "first_name": "Ilya", + "last_name": "Makarov" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "QDFormer: Towards Robust Audiovisual Segmentation in Complex Environments with Quantization-based Semantic Decomposition", - "authors": "Xiang Li, Jinglu Wang, Xiaohao Xu, Xiulian Peng, Rita Singh, Yan Lu, Bhiksha Raj", + "authors": [ + { + "first_name": "Xiang", + "last_name": "Li" + }, + { + "first_name": "Jinglu", + "last_name": "Wang" + }, + { + "first_name": "Xiaohao", + "last_name": "Xu" + }, + { + "first_name": "Xiulian", + "last_name": "Peng" + }, + { + "first_name": "Rita", + "last_name": "Singh" + }, + { + "first_name": "Yan", + "last_name": "Lu" + }, + { + "first_name": "Bhiksha", + "last_name": "Raj" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Active Open-Vocabulary Recognition: Let Intelligent Moving Mitigate CLIP Limitations", - "authors": "Lei Fan, Jianxiong Zhou, Xiaoying Xing, Ying Wu", + "authors": [ + { + "first_name": "Lei", + "last_name": "Fan" + }, + { + "first_name": "Jianxiong", + "last_name": "Zhou" + }, + { + "first_name": "Xiaoying", + "last_name": "Xing" + }, + { + "first_name": "Ying", + "last_name": "Wu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Backdoor Defense via Test-Time Detecting and Repairing", - "authors": "Jiyang Guan, Jian Liang, Ran He", + "authors": [ + { + "first_name": "Jiyang", + "last_name": "Guan" + }, + { + "first_name": "Jian", + "last_name": "Liang" + }, + { + "first_name": "Ran", + "last_name": "He" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Fast Adaptation for Human Pose Estimation via Meta-Optimization", - "authors": "Shengxiang Hu, Huaijiang Sun, Bin Li, Dong Wei, Weiqing Li, Jianfeng Lu", + "authors": [ + { + "first_name": "Shengxiang", + "last_name": "Hu" + }, + { + "first_name": "Huaijiang", + "last_name": "Sun" + }, + { + "first_name": "Bin", + "last_name": "Li" + }, + { + "first_name": "Dong", + "last_name": "Wei" + }, + { + "first_name": "Weiqing", + "last_name": "Li" + }, + { + "first_name": "Jianfeng", + "last_name": "Lu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Efficient Meshflow and Optical Flow Estimation from Event Cameras", - "authors": "Xinglong Luo, Ao Luo, Zhengning Wang, Chunyu Lin, Bing Zeng, Shuaicheng Liu", + "authors": [ + { + "first_name": "Xinglong", + "last_name": "Luo" + }, + { + "first_name": "Ao", + "last_name": "Luo" + }, + { + "first_name": "Zhengning", + "last_name": "Wang" + }, + { + "first_name": "Chunyu", + "last_name": "Lin" + }, + { + "first_name": "Bing", + "last_name": "Zeng" + }, + { + "first_name": "Shuaicheng", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models", - "authors": "Yushi Hu, Otilia Stretcu, Chun-Ta Lu, Krishnamurthy Viswanathan, Kenji Hata, Enming Luo, Ranjay Krishna, Ariel Fuxman", + "authors": [ + { + "first_name": "Yushi", + "last_name": "Hu" + }, + { + "first_name": "Otilia", + "last_name": "Stretcu" + }, + { + "first_name": "Chun-Ta", + "last_name": "Lu" + }, + { + "first_name": "Krishnamurthy", + "last_name": "Viswanathan" + }, + { + "first_name": "Kenji", + "last_name": "Hata" + }, + { + "first_name": "Enming", + "last_name": "Luo" + }, + { + "first_name": "Ranjay", + "last_name": "Krishna" + }, + { + "first_name": "Ariel", + "last_name": "Fuxman" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "OneFormer3D: One Transformer for Unified Point Cloud Segmentation", - "authors": "Maxim Kolodiazhnyi, Anna Vorontsova, Anton Konushin, Danila Rukhovich", + "authors": [ + { + "first_name": "Maxim", + "last_name": "Kolodiazhnyi" + }, + { + "first_name": "Anna", + "last_name": "Vorontsova" + }, + { + "first_name": "Anton", + "last_name": "Konushin" + }, + { + "first_name": "Danila", + "last_name": "Rukhovich" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "JRDB-Social: A Multifaceted Robotic Dataset for Understanding of Context and Dynamics of Human Interactions Within Social Groups", - "authors": "Simindokht Jahangard, Zhixi Cai, Shiki Wen, Hamid Rezatofighi", + "authors": [ + { + "first_name": "Simindokht", + "last_name": "Jahangard" + }, + { + "first_name": "Zhixi", + "last_name": "Cai" + }, + { + "first_name": "Shiki", + "last_name": "Wen" + }, + { + "first_name": "Hamid", + "last_name": "Rezatofighi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "A Backpack Full of Skills: Egocentric Video Understanding with Diverse Task Perspectives", - "authors": "Simone Alberto Peirone, Francesca Pistilli, Antonio Alliegro, Giuseppe Averta", + "authors": [ + { + "first_name": "Simone", + "last_name": "Alberto Peirone" + }, + { + "first_name": "Francesca", + "last_name": "Pistilli" + }, + { + "first_name": "Antonio", + "last_name": "Alliegro" + }, + { + "first_name": "Giuseppe", + "last_name": "Averta" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Models", - "authors": "Changhoon Kim, Kyle Min, Maitreya Patel, Sheng Cheng, Yezhou Yang", + "authors": [ + { + "first_name": "Changhoon", + "last_name": "Kim" + }, + { + "first_name": "Kyle", + "last_name": "Min" + }, + { + "first_name": "Maitreya", + "last_name": "Patel" + }, + { + "first_name": "Sheng", + "last_name": "Cheng" + }, + { + "first_name": "Yezhou", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Visual In-Context Prompting", - "authors": "Feng Li, Qing Jiang, Hao Zhang, Tianhe Ren, Shilong Liu, Xueyan Zou, Huaizhe Xu, Hongyang Li, Jianwei Yang, Chunyuan Li, Lei Zhang, Jianfeng Gao", + "authors": [ + { + "first_name": "Feng", + "last_name": "Li" + }, + { + "first_name": "Qing", + "last_name": "Jiang" + }, + { + "first_name": "Hao", + "last_name": "Zhang" + }, + { + "first_name": "Tianhe", + "last_name": "Ren" + }, + { + "first_name": "Shilong", + "last_name": "Liu" + }, + { + "first_name": "Xueyan", + "last_name": "Zou" + }, + { + "first_name": "Huaizhe", + "last_name": "Xu" + }, + { + "first_name": "Hongyang", + "last_name": "Li" + }, + { + "first_name": "Jianwei", + "last_name": "Yang" + }, + { + "first_name": "Chunyuan", + "last_name": "Li" + }, + { + "first_name": "Lei", + "last_name": "Zhang" + }, + { + "first_name": "Jianfeng", + "last_name": "Gao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Text-Conditioned Generative Model of 3D Strand-based Human Hairstyles", - "authors": "Vanessa Sklyarova, Egor Zakharov, Otmar Hilliges, Michael J. Black, Justus Thies", + "authors": [ + { + "first_name": "Vanessa", + "last_name": "Sklyarova" + }, + { + "first_name": "Egor", + "last_name": "Zakharov" + }, + { + "first_name": "Otmar", + "last_name": "Hilliges" + }, + { + "first_name": "Michael", + "last_name": "J. Black" + }, + { + "first_name": "Justus", + "last_name": "Thies" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generation", - "authors": "Tong Wu, Guandao Yang, Zhibing Li, Kai Zhang, Ziwei Liu, Leonidas Guibas, Dahua Lin, Gordon Wetzstein", + "authors": [ + { + "first_name": "Tong", + "last_name": "Wu" + }, + { + "first_name": "Guandao", + "last_name": "Yang" + }, + { + "first_name": "Zhibing", + "last_name": "Li" + }, + { + "first_name": "Kai", + "last_name": "Zhang" + }, + { + "first_name": "Ziwei", + "last_name": "Liu" + }, + { + "first_name": "Leonidas", + "last_name": "Guibas" + }, + { + "first_name": "Dahua", + "last_name": "Lin" + }, + { + "first_name": "Gordon", + "last_name": "Wetzstein" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "NTO3D: Neural Target Object 3D Reconstruction with Segment Anything", - "authors": "Xiaobao Wei, Renrui Zhang, Jiarui Wu, Jiaming Liu, Ming Lu, Yandong Guo, Shanghang Zhang", + "authors": [ + { + "first_name": "Xiaobao", + "last_name": "Wei" + }, + { + "first_name": "Renrui", + "last_name": "Zhang" + }, + { + "first_name": "Jiarui", + "last_name": "Wu" + }, + { + "first_name": "Jiaming", + "last_name": "Liu" + }, + { + "first_name": "Ming", + "last_name": "Lu" + }, + { + "first_name": "Yandong", + "last_name": "Guo" + }, + { + "first_name": "Shanghang", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Instruct-ReID: A Multi-purpose Person Re-identification Task with Instructions", - "authors": "Weizhen He, Yiheng Deng, Shixiang Tang, Qihao Chen, Qingsong Xie, Yizhou Wang, Lei Bai, Feng Zhu, Rui Zhao, Wanli Ouyang, Donglian Qi, Yunfeng Yan", + "authors": [ + { + "first_name": "Weizhen", + "last_name": "He" + }, + { + "first_name": "Yiheng", + "last_name": "Deng" + }, + { + "first_name": "Shixiang", + "last_name": "Tang" + }, + { + "first_name": "Qihao", + "last_name": "Chen" + }, + { + "first_name": "Qingsong", + "last_name": "Xie" + }, + { + "first_name": "Yizhou", + "last_name": "Wang" + }, + { + "first_name": "Lei", + "last_name": "Bai" + }, + { + "first_name": "Feng", + "last_name": "Zhu" + }, + { + "first_name": "Rui", + "last_name": "Zhao" + }, + { + "first_name": "Wanli", + "last_name": "Ouyang" + }, + { + "first_name": "Donglian", + "last_name": "Qi" + }, + { + "first_name": "Yunfeng", + "last_name": "Yan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "OmniMedVQA: A New Large-Scale Comprehensive Evaluation Benchmark for Medical LVLM", - "authors": "Yutao Hu, Tianbin Li, Quanfeng Lu, Wenqi Shao, Junjun He, Yu Qiao, Ping Luo", + "authors": [ + { + "first_name": "Yutao", + "last_name": "Hu" + }, + { + "first_name": "Tianbin", + "last_name": "Li" + }, + { + "first_name": "Quanfeng", + "last_name": "Lu" + }, + { + "first_name": "Wenqi", + "last_name": "Shao" + }, + { + "first_name": "Junjun", + "last_name": "He" + }, + { + "first_name": "Yu", + "last_name": "Qiao" + }, + { + "first_name": "Ping", + "last_name": "Luo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Skeleton-in-Context: Unified Skeleton Sequence Modeling with In-Context Learning", - "authors": "Xinshun Wang, Zhongbin Fang, Xia Li, Xiangtai Li, Chen Chen, Mengyuan Liu", + "authors": [ + { + "first_name": "Xinshun", + "last_name": "Wang" + }, + { + "first_name": "Zhongbin", + "last_name": "Fang" + }, + { + "first_name": "Xia", + "last_name": "Li" + }, + { + "first_name": "Xiangtai", + "last_name": "Li" + }, + { + "first_name": "Chen", + "last_name": "Chen" + }, + { + "first_name": "Mengyuan", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DemoFusion: Democratising High-Resolution Image Generation With No $$$", - "authors": "Ruoyi Du, Dongliang Chang, Timothy Hospedales, Yi-Zhe Song, Zhanyu Ma", + "authors": [ + { + "first_name": "Ruoyi", + "last_name": "Du" + }, + { + "first_name": "Dongliang", + "last_name": "Chang" + }, + { + "first_name": "Timothy", + "last_name": "Hospedales" + }, + { + "first_name": "Yi-Zhe", + "last_name": "Song" + }, + { + "first_name": "Zhanyu", + "last_name": "Ma" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "IBD-SLAM: Learning Image-Based Depth Fusion for Generalizable SLAM", - "authors": "Minghao Yin, Shangzhe Wu, Kai Han", + "authors": [ + { + "first_name": "Minghao", + "last_name": "Yin" + }, + { + "first_name": "Shangzhe", + "last_name": "Wu" + }, + { + "first_name": "Kai", + "last_name": "Han" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CPLIP: Zero-Shot Learning for Histopathology with Comprehensive Vision-Language Alignment", - "authors": "Sajid Javed, Arif Mahmood, Iyyakutti Iyappan Ganapathi, Fayaz Ali Dharejo, Naoufel Werghi, Mohammed Bennamoun", + "authors": [ + { + "first_name": "Sajid", + "last_name": "Javed" + }, + { + "first_name": "Arif", + "last_name": "Mahmood" + }, + { + "first_name": "Iyyakutti", + "last_name": "Iyappan Ganapathi" + }, + { + "first_name": "Fayaz", + "last_name": "Ali Dharejo" + }, + { + "first_name": "Naoufel", + "last_name": "Werghi" + }, + { + "first_name": "Mohammed", + "last_name": "Bennamoun" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Total Selfie: Generating Full-Body Selfies", - "authors": "Bowei Chen, Brian Curless, Ira Kemelmacher-Shlizerman, Steven M. Seitz", + "authors": [ + { + "first_name": "Bowei", + "last_name": "Chen" + }, + { + "first_name": "Brian", + "last_name": "Curless" + }, + { + "first_name": "Ira", + "last_name": "Kemelmacher-Shlizerman" + }, + { + "first_name": "Steven", + "last_name": "M. Seitz" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Visual Programming for Zero-shot Open-Vocabulary 3D Visual Grounding", - "authors": "Zhihao Yuan, Jinke Ren, Chun-Mei Feng, Hengshuang Zhao, Shuguang Cui, Zhen Li", + "authors": [ + { + "first_name": "Zhihao", + "last_name": "Yuan" + }, + { + "first_name": "Jinke", + "last_name": "Ren" + }, + { + "first_name": "Chun-Mei", + "last_name": "Feng" + }, + { + "first_name": "Hengshuang", + "last_name": "Zhao" + }, + { + "first_name": "Shuguang", + "last_name": "Cui" + }, + { + "first_name": "Zhen", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning Structure-from-Motion with Graph Attention Networks", - "authors": "Lucas Brynte, José Pedro Iglesias, Carl Olsson, Fredrik Kahl", + "authors": [ + { + "first_name": "Lucas", + "last_name": "Brynte" + }, + { + "first_name": "José", + "last_name": "Pedro Iglesias" + }, + { + "first_name": "Carl", + "last_name": "Olsson" + }, + { + "first_name": "Fredrik", + "last_name": "Kahl" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Geometry Transfer for Stylizing Radiance Fields", - "authors": "Hyunyoung Jung, Seonghyeon Nam, Nikolaos Sarafianos, Sungjoo Yoo, Alexander Sorkine-Hornung, Rakesh Ranjan", + "authors": [ + { + "first_name": "Hyunyoung", + "last_name": "Jung" + }, + { + "first_name": "Seonghyeon", + "last_name": "Nam" + }, + { + "first_name": "Nikolaos", + "last_name": "Sarafianos" + }, + { + "first_name": "Sungjoo", + "last_name": "Yoo" + }, + { + "first_name": "Alexander", + "last_name": "Sorkine-Hornung" + }, + { + "first_name": "Rakesh", + "last_name": "Ranjan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Holoported Characters: Real-time Free-viewpoint Rendering of Humans from Sparse RGB Cameras", - "authors": "Ashwath Shetty, Marc Habermann, Guoxing Sun, Diogo Luvizon, Vladislav Golyanik, Christian Theobalt", + "authors": [ + { + "first_name": "Ashwath", + "last_name": "Shetty" + }, + { + "first_name": "Marc", + "last_name": "Habermann" + }, + { + "first_name": "Guoxing", + "last_name": "Sun" + }, + { + "first_name": "Diogo", + "last_name": "Luvizon" + }, + { + "first_name": "Vladislav", + "last_name": "Golyanik" + }, + { + "first_name": "Christian", + "last_name": "Theobalt" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SEAS: ShapE-Aligned Supervision for Person Re-Identification", - "authors": "Haidong Zhu, Pranav Budhwant, Zhaoheng Zheng, Ram Nevatia", + "authors": [ + { + "first_name": "Haidong", + "last_name": "Zhu" + }, + { + "first_name": "Pranav", + "last_name": "Budhwant" + }, + { + "first_name": "Zhaoheng", + "last_name": "Zheng" + }, + { + "first_name": "Ram", + "last_name": "Nevatia" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Class Incremental Learning with Multi-Teacher Distillation", - "authors": "Haitao Wen, Lili Pan, Yu Dai, Heqian Qiu, Lanxiao Wang, Qingbo Wu, Hongliang Li", + "authors": [ + { + "first_name": "Haitao", + "last_name": "Wen" + }, + { + "first_name": "Lili", + "last_name": "Pan" + }, + { + "first_name": "Yu", + "last_name": "Dai" + }, + { + "first_name": "Heqian", + "last_name": "Qiu" + }, + { + "first_name": "Lanxiao", + "last_name": "Wang" + }, + { + "first_name": "Qingbo", + "last_name": "Wu" + }, + { + "first_name": "Hongliang", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Reg-PTQ: Regression-specialized Post-training Quantization for Fully Quantized Object Detector", - "authors": "Yifu Ding, Weilun Feng, Chuyan Chen, Jinyang Guo, Xianglong Liu", + "authors": [ + { + "first_name": "Yifu", + "last_name": "Ding" + }, + { + "first_name": "Weilun", + "last_name": "Feng" + }, + { + "first_name": "Chuyan", + "last_name": "Chen" + }, + { + "first_name": "Jinyang", + "last_name": "Guo" + }, + { + "first_name": "Xianglong", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "AMU-Tuning: Effective Logit Bias for CLIP-based Few-shot Learning", - "authors": "Yuwei Tang, Zhenyi Lin, Qilong Wang, Pengfei Zhu, Qinghua Hu", + "authors": [ + { + "first_name": "Yuwei", + "last_name": "Tang" + }, + { + "first_name": "Zhenyi", + "last_name": "Lin" + }, + { + "first_name": "Qilong", + "last_name": "Wang" + }, + { + "first_name": "Pengfei", + "last_name": "Zhu" + }, + { + "first_name": "Qinghua", + "last_name": "Hu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Real-World Mobile Image Denoising Dataset with Efficient Baselines", - "authors": "Roman Flepp, Andrey Ignatov, Radu Timofte, Luc Van Gool", + "authors": [ + { + "first_name": "Roman", + "last_name": "Flepp" + }, + { + "first_name": "Andrey", + "last_name": "Ignatov" + }, + { + "first_name": "Radu", + "last_name": "Timofte" + }, + { + "first_name": "Luc", + "last_name": "Van Gool" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Making Vision Transformers Truly Shift-Equivariant", - "authors": "Renan A. Rojas-Gomez, Teck-Yian Lim, Minh N. Do, Raymond A. Yeh", + "authors": [ + { + "first_name": "Renan", + "last_name": "A. Rojas-Gomez" + }, + { + "first_name": "Teck-Yian", + "last_name": "Lim" + }, + { + "first_name": "Minh", + "last_name": "N. Do" + }, + { + "first_name": "Raymond", + "last_name": "A. Yeh" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SpikeNeRF: Learning Neural Radiance Fields from Continuous Spike Stream", - "authors": "Lin Zhu, Kangmin Jia, Yifan Zhao, Yunshan Qi, Lizhi Wang, Hua Huang", + "authors": [ + { + "first_name": "Lin", + "last_name": "Zhu" + }, + { + "first_name": "Kangmin", + "last_name": "Jia" + }, + { + "first_name": "Yifan", + "last_name": "Zhao" + }, + { + "first_name": "Yunshan", + "last_name": "Qi" + }, + { + "first_name": "Lizhi", + "last_name": "Wang" + }, + { + "first_name": "Hua", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Action Scene Graphs for Long-Form Understanding of Egocentric Videos", - "authors": "Ivan Rodin, Antonino Furnari, Kyle Min, Subarna Tripathi, Giovanni Maria Farinella", + "authors": [ + { + "first_name": "Ivan", + "last_name": "Rodin" + }, + { + "first_name": "Antonino", + "last_name": "Furnari" + }, + { + "first_name": "Kyle", + "last_name": "Min" + }, + { + "first_name": "Subarna", + "last_name": "Tripathi" + }, + { + "first_name": "Giovanni", + "last_name": "Maria Farinella" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "A Semi-supervised Nighttime Dehazing Baseline with Spatial-Frequency Aware and Realistic Brightness Constraint", - "authors": "Xiaofeng Cong, Jie Gui, Jing Zhang, Junming Hou, Hao Shen", + "authors": [ + { + "first_name": "Xiaofeng", + "last_name": "Cong" + }, + { + "first_name": "Jie", + "last_name": "Gui" + }, + { + "first_name": "Jing", + "last_name": "Zhang" + }, + { + "first_name": "Junming", + "last_name": "Hou" + }, + { + "first_name": "Hao", + "last_name": "Shen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "De-confounded Data-free Knowledge Distillation for Handling Distribution Shifts", - "authors": "Yuzheng Wang, Dingkang Yang, Zhaoyu Chen, Yang Liu, Siao Liu, Wenqiang Zhang, Lihua Zhang, Lizhe Qi", + "authors": [ + { + "first_name": "Yuzheng", + "last_name": "Wang" + }, + { + "first_name": "Dingkang", + "last_name": "Yang" + }, + { + "first_name": "Zhaoyu", + "last_name": "Chen" + }, + { + "first_name": "Yang", + "last_name": "Liu" + }, + { + "first_name": "Siao", + "last_name": "Liu" + }, + { + "first_name": "Wenqiang", + "last_name": "Zhang" + }, + { + "first_name": "Lihua", + "last_name": "Zhang" + }, + { + "first_name": "Lizhe", + "last_name": "Qi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Fine-Grained Bipartite Concept Factorization for Clustering", - "authors": "Chong Peng, Pengfei Zhang, Yongyong Chen, Zhao Kang, Chenglizhao Chen, Qiang Cheng", + "authors": [ + { + "first_name": "Chong", + "last_name": "Peng" + }, + { + "first_name": "Pengfei", + "last_name": "Zhang" + }, + { + "first_name": "Yongyong", + "last_name": "Chen" + }, + { + "first_name": "Zhao", + "last_name": "Kang" + }, + { + "first_name": "Chenglizhao", + "last_name": "Chen" + }, + { + "first_name": "Qiang", + "last_name": "Cheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Siamese Learning with Joint Alignment and Regression for Weakly-Supervised Video Paragraph Grounding", - "authors": "Chaolei Tan, Jianhuang Lai, Wei-Shi Zheng, Jian-Fang Hu", + "authors": [ + { + "first_name": "Chaolei", + "last_name": "Tan" + }, + { + "first_name": "Jianhuang", + "last_name": "Lai" + }, + { + "first_name": "Wei-Shi", + "last_name": "Zheng" + }, + { + "first_name": "Jian-Fang", + "last_name": "Hu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Language-Driven Anchors for Zero-Shot Adversarial Robustness", - "authors": "Xiao Li, Wei Zhang, Yining Liu, Zhanhao Hu, Bo Zhang, Xiaolin Hu", + "authors": [ + { + "first_name": "Xiao", + "last_name": "Li" + }, + { + "first_name": "Wei", + "last_name": "Zhang" + }, + { + "first_name": "Yining", + "last_name": "Liu" + }, + { + "first_name": "Zhanhao", + "last_name": "Hu" + }, + { + "first_name": "Bo", + "last_name": "Zhang" + }, + { + "first_name": "Xiaolin", + "last_name": "Hu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Deep Equilibrium Diffusion Restoration with Parallel Sampling", - "authors": "Jiezhang Cao, Yue Shi, Kai Zhang, Yulun Zhang, Radu Timofte, Luc Van Gool", + "authors": [ + { + "first_name": "Jiezhang", + "last_name": "Cao" + }, + { + "first_name": "Yue", + "last_name": "Shi" + }, + { + "first_name": "Kai", + "last_name": "Zhang" + }, + { + "first_name": "Yulun", + "last_name": "Zhang" + }, + { + "first_name": "Radu", + "last_name": "Timofte" + }, + { + "first_name": "Luc", + "last_name": "Van Gool" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LEOD: Label-Efficient Object Detection for Event Cameras", - "authors": "Ziyi Wu, Mathias Gehrig, Qing Lyu, Xudong Liu, Igor Gilitschenski", + "authors": [ + { + "first_name": "Ziyi", + "last_name": "Wu" + }, + { + "first_name": "Mathias", + "last_name": "Gehrig" + }, + { + "first_name": "Qing", + "last_name": "Lyu" + }, + { + "first_name": "Xudong", + "last_name": "Liu" + }, + { + "first_name": "Igor", + "last_name": "Gilitschenski" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Morphological Prototyping for Unsupervised Slide Representation Learning in Computational Pathology", - "authors": "Andrew H. Song, Richard J. Chen, Tong Ding, Drew F.K. Williamson, Guillaume Jaume, Faisal Mahmood", + "authors": [ + { + "first_name": "Andrew", + "last_name": "H. Song" + }, + { + "first_name": "Richard", + "last_name": "J. Chen" + }, + { + "first_name": "Tong", + "last_name": "Ding" + }, + { + "first_name": "Drew", + "last_name": "F.K. Williamson" + }, + { + "first_name": "Guillaume", + "last_name": "Jaume" + }, + { + "first_name": "Faisal", + "last_name": "Mahmood" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Fooling Polarization-Based Vision using Locally Controllable Polarizing Projection", - "authors": "Zhuoxiao Li, Zhihang Zhong, Shohei Nobuhara, Ko Nishino, Yinqiang Zheng", + "authors": [ + { + "first_name": "Zhuoxiao", + "last_name": "Li" + }, + { + "first_name": "Zhihang", + "last_name": "Zhong" + }, + { + "first_name": "Shohei", + "last_name": "Nobuhara" + }, + { + "first_name": "Ko", + "last_name": "Nishino" + }, + { + "first_name": "Yinqiang", + "last_name": "Zheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Dense Optical Tracking: Connecting the Dots", - "authors": "Guillaume Le Moing, Jean Ponce, Cordelia Schmid", + "authors": [ + { + "first_name": "Guillaume", + "last_name": "Le Moing" + }, + { + "first_name": "Jean", + "last_name": "Ponce" + }, + { + "first_name": "Cordelia", + "last_name": "Schmid" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "A Stealthy Wrongdoer: Feature-Oriented Reconstruction Attack against Split Learning", - "authors": "Xiaoyang Xu, Mengda Yang, Wenzhe Yi, Ziang Li, Juan Wang, Hongxin Hu, Yong Zhuang, Yaxin Liu", + "authors": [ + { + "first_name": "Xiaoyang", + "last_name": "Xu" + }, + { + "first_name": "Mengda", + "last_name": "Yang" + }, + { + "first_name": "Wenzhe", + "last_name": "Yi" + }, + { + "first_name": "Ziang", + "last_name": "Li" + }, + { + "first_name": "Juan", + "last_name": "Wang" + }, + { + "first_name": "Hongxin", + "last_name": "Hu" + }, + { + "first_name": "Yong", + "last_name": "Zhuang" + }, + { + "first_name": "Yaxin", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DiffAM: Diffusion-based Adversarial Makeup Transfer for Facial Privacy Protection", - "authors": "Yuhao Sun, Lingyun Yu, Hongtao Xie, Jiaming Li, Yongdong Zhang", + "authors": [ + { + "first_name": "Yuhao", + "last_name": "Sun" + }, + { + "first_name": "Lingyun", + "last_name": "Yu" + }, + { + "first_name": "Hongtao", + "last_name": "Xie" + }, + { + "first_name": "Jiaming", + "last_name": "Li" + }, + { + "first_name": "Yongdong", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SlowFormer: Adversarial Attack on Compute and Energy Consumption of Efficient Vision Transformers", - "authors": "K L Navaneet, Soroush Abbasi Koohpayegani, Essam Sleiman, Hamed Pirsiavash", + "authors": [ + { + "first_name": "K", + "last_name": "L Navaneet" + }, + { + "first_name": "Soroush", + "last_name": "Abbasi Koohpayegani" + }, + { + "first_name": "Essam", + "last_name": "Sleiman" + }, + { + "first_name": "Hamed", + "last_name": "Pirsiavash" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "TULIP: Transformer for Upsampling of LiDAR Point Clouds", - "authors": "Bin Yang, Patrick Pfreundschuh, Roland Siegwart, Marco Hutter, Peyman Moghadam, Vaishakh Patil", + "authors": [ + { + "first_name": "Bin", + "last_name": "Yang" + }, + { + "first_name": "Patrick", + "last_name": "Pfreundschuh" + }, + { + "first_name": "Roland", + "last_name": "Siegwart" + }, + { + "first_name": "Marco", + "last_name": "Hutter" + }, + { + "first_name": "Peyman", + "last_name": "Moghadam" + }, + { + "first_name": "Vaishakh", + "last_name": "Patil" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "How to Configure Good In-Context Sequence for Visual Question Answering", - "authors": "Li Li, Jiawei Peng, Huiyi Chen, Chongyang Gao, Xu Yang", + "authors": [ + { + "first_name": "Li", + "last_name": "Li" + }, + { + "first_name": "Jiawei", + "last_name": "Peng" + }, + { + "first_name": "Huiyi", + "last_name": "Chen" + }, + { + "first_name": "Chongyang", + "last_name": "Gao" + }, + { + "first_name": "Xu", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Gaussian Shell Maps for Efficient 3D Human Generation", - "authors": "Rameen Abdal, Wang Yifan, Zifan Shi, Yinghao Xu, Ryan Po, Zhengfei Kuang, Qifeng Chen, Dit-Yan Yeung, Gordon Wetzstein", + "authors": [ + { + "first_name": "Rameen", + "last_name": "Abdal" + }, + { + "first_name": "Wang", + "last_name": "Yifan" + }, + { + "first_name": "Zifan", + "last_name": "Shi" + }, + { + "first_name": "Yinghao", + "last_name": "Xu" + }, + { + "first_name": "Ryan", + "last_name": "Po" + }, + { + "first_name": "Zhengfei", + "last_name": "Kuang" + }, + { + "first_name": "Qifeng", + "last_name": "Chen" + }, + { + "first_name": "Dit-Yan", + "last_name": "Yeung" + }, + { + "first_name": "Gordon", + "last_name": "Wetzstein" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Defense Against Adversarial Attacks on No-Reference Image Quality Models with Gradient Norm Regularization", - "authors": "Yujia Liu, Chenxi Yang, Dingquan Li, Jianhao Ding, Tingting Jiang", + "authors": [ + { + "first_name": "Yujia", + "last_name": "Liu" + }, + { + "first_name": "Chenxi", + "last_name": "Yang" + }, + { + "first_name": "Dingquan", + "last_name": "Li" + }, + { + "first_name": "Jianhao", + "last_name": "Ding" + }, + { + "first_name": "Tingting", + "last_name": "Jiang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understanding", - "authors": "Yun Liu, Haolin Yang, Xu Si, Ling Liu, Zipeng Li, Yuxiang Zhang, Yebin Liu, Li Yi", + "authors": [ + { + "first_name": "Yun", + "last_name": "Liu" + }, + { + "first_name": "Haolin", + "last_name": "Yang" + }, + { + "first_name": "Xu", + "last_name": "Si" + }, + { + "first_name": "Ling", + "last_name": "Liu" + }, + { + "first_name": "Zipeng", + "last_name": "Li" + }, + { + "first_name": "Yuxiang", + "last_name": "Zhang" + }, + { + "first_name": "Yebin", + "last_name": "Liu" + }, + { + "first_name": "Li", + "last_name": "Yi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MoST: Motion Style Transformer Between Diverse Action Contents", - "authors": "Boeun Kim, Jungho Kim, Hyung Jin Chang, Jin Young Choi", + "authors": [ + { + "first_name": "Boeun", + "last_name": "Kim" + }, + { + "first_name": "Jungho", + "last_name": "Kim" + }, + { + "first_name": "Hyung", + "last_name": "Jin Chang" + }, + { + "first_name": "Jin", + "last_name": "Young Choi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Prompting Hard or Hardly Prompting: Prompt Inversion for Text-to-Image Diffusion Models", - "authors": "Shweta Mahajan, Tanzila Rahman, Kwang Moo Yi, Leonid Sigal", + "authors": [ + { + "first_name": "Shweta", + "last_name": "Mahajan" + }, + { + "first_name": "Tanzila", + "last_name": "Rahman" + }, + { + "first_name": "Kwang", + "last_name": "Moo Yi" + }, + { + "first_name": "Leonid", + "last_name": "Sigal" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Unmixing Before Fusion: A Generalized Paradigm for Multi-Source-based Hyperspectral Image Synthesis", - "authors": "Yang Yu, Erting Pan, Xinya Wang, Yuheng Wu, Xiaoguang Mei, Jiayi Ma", + "authors": [ + { + "first_name": "Yang", + "last_name": "Yu" + }, + { + "first_name": "Erting", + "last_name": "Pan" + }, + { + "first_name": "Xinya", + "last_name": "Wang" + }, + { + "first_name": "Yuheng", + "last_name": "Wu" + }, + { + "first_name": "Xiaoguang", + "last_name": "Mei" + }, + { + "first_name": "Jiayi", + "last_name": "Ma" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "AlignMiF: Geometry-Aligned Multimodal Implicit Field for LiDAR-Camera Joint Synthesis", - "authors": "Tang Tao, Guangrun Wang, Yixing Lao, Peng Chen, Jie Liu, Liang Lin, Kaicheng Yu, Xiaodan Liang", + "authors": [ + { + "first_name": "Tang", + "last_name": "Tao" + }, + { + "first_name": "Guangrun", + "last_name": "Wang" + }, + { + "first_name": "Yixing", + "last_name": "Lao" + }, + { + "first_name": "Peng", + "last_name": "Chen" + }, + { + "first_name": "Jie", + "last_name": "Liu" + }, + { + "first_name": "Liang", + "last_name": "Lin" + }, + { + "first_name": "Kaicheng", + "last_name": "Yu" + }, + { + "first_name": "Xiaodan", + "last_name": "Liang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CoDi: Conditional Diffusion Distillation for Higher-Fidelity and Faster Image Generation", - "authors": "Kangfu Mei, Mauricio Delbracio, Hossein Talebi, Zhengzhong Tu, Vishal M. Patel, Peyman Milanfar", + "authors": [ + { + "first_name": "Kangfu", + "last_name": "Mei" + }, + { + "first_name": "Mauricio", + "last_name": "Delbracio" + }, + { + "first_name": "Hossein", + "last_name": "Talebi" + }, + { + "first_name": "Zhengzhong", + "last_name": "Tu" + }, + { + "first_name": "Vishal", + "last_name": "M. Patel" + }, + { + "first_name": "Peyman", + "last_name": "Milanfar" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Improving Unsupervised Hierarchical Representation with Reinforcement Learning", - "authors": "Ruyi An, Yewen Li, Xu He, Pengjie Gu, Mengchen Zhao, Dong Li, Jianye Hao, Chaojie Wang, Bo An, Mingyuan Zhou", + "authors": [ + { + "first_name": "Ruyi", + "last_name": "An" + }, + { + "first_name": "Yewen", + "last_name": "Li" + }, + { + "first_name": "Xu", + "last_name": "He" + }, + { + "first_name": "Pengjie", + "last_name": "Gu" + }, + { + "first_name": "Mengchen", + "last_name": "Zhao" + }, + { + "first_name": "Dong", + "last_name": "Li" + }, + { + "first_name": "Jianye", + "last_name": "Hao" + }, + { + "first_name": "Chaojie", + "last_name": "Wang" + }, + { + "first_name": "Bo", + "last_name": "An" + }, + { + "first_name": "Mingyuan", + "last_name": "Zhou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HPL-ESS: Hybrid Pseudo-Labeling for Unsupervised Event-based Semantic Segmentation", - "authors": "Linglin Jing, Yiming Ding, Yunpeng Gao, Zhigang Wang, Xu Yan, Dong Wang, Gerald Schaefer, Hui Fang, Bin Zhao, Xuelong Li", + "authors": [ + { + "first_name": "Linglin", + "last_name": "Jing" + }, + { + "first_name": "Yiming", + "last_name": "Ding" + }, + { + "first_name": "Yunpeng", + "last_name": "Gao" + }, + { + "first_name": "Zhigang", + "last_name": "Wang" + }, + { + "first_name": "Xu", + "last_name": "Yan" + }, + { + "first_name": "Dong", + "last_name": "Wang" + }, + { + "first_name": "Gerald", + "last_name": "Schaefer" + }, + { + "first_name": "Hui", + "last_name": "Fang" + }, + { + "first_name": "Bin", + "last_name": "Zhao" + }, + { + "first_name": "Xuelong", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "X-Adapter: Adding Universal Compatibility of Plugins for Upgraded Diffusion Model", - "authors": "Lingmin Ran, Xiaodong Cun, Jia-Wei Liu, Rui Zhao, Song Zijie, Xintao Wang, Jussi Keppo, Mike Zheng Shou", + "authors": [ + { + "first_name": "Lingmin", + "last_name": "Ran" + }, + { + "first_name": "Xiaodong", + "last_name": "Cun" + }, + { + "first_name": "Jia-Wei", + "last_name": "Liu" + }, + { + "first_name": "Rui", + "last_name": "Zhao" + }, + { + "first_name": "Song", + "last_name": "Zijie" + }, + { + "first_name": "Xintao", + "last_name": "Wang" + }, + { + "first_name": "Jussi", + "last_name": "Keppo" + }, + { + "first_name": "Mike", + "last_name": "Zheng Shou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards General Robustness Verification of MaxPool-based Convolutional Neural Networks via Tightening Linear Approximation", - "authors": "Yuan Xiao, Shiqing Ma, Juan Zhai, Chunrong Fang, Jinyuan Jia, Zhenyu Chen", + "authors": [ + { + "first_name": "Yuan", + "last_name": "Xiao" + }, + { + "first_name": "Shiqing", + "last_name": "Ma" + }, + { + "first_name": "Juan", + "last_name": "Zhai" + }, + { + "first_name": "Chunrong", + "last_name": "Fang" + }, + { + "first_name": "Jinyuan", + "last_name": "Jia" + }, + { + "first_name": "Zhenyu", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning", - "authors": "Ruyang Liu, Chen Li, Yixiao Ge, Thomas H. Li, Ying Shan, Ge Li", + "authors": [ + { + "first_name": "Ruyang", + "last_name": "Liu" + }, + { + "first_name": "Chen", + "last_name": "Li" + }, + { + "first_name": "Yixiao", + "last_name": "Ge" + }, + { + "first_name": "Thomas", + "last_name": "H. Li" + }, + { + "first_name": "Ying", + "last_name": "Shan" + }, + { + "first_name": "Ge", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CADTalk: An Algorithm and Benchmark for Semantic Commenting of CAD Programs", - "authors": "Haocheng Yuan, Jing Xu, Hao Pan, Adrien Bousseau, Niloy J. Mitra, Changjian Li", + "authors": [ + { + "first_name": "Haocheng", + "last_name": "Yuan" + }, + { + "first_name": "Jing", + "last_name": "Xu" + }, + { + "first_name": "Hao", + "last_name": "Pan" + }, + { + "first_name": "Adrien", + "last_name": "Bousseau" + }, + { + "first_name": "Niloy", + "last_name": "J. Mitra" + }, + { + "first_name": "Changjian", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning to Rematch Mismatched Pairs for Robust Cross-Modal Retrieval", - "authors": "Haochen Han, Qinghua Zheng, Guang Dai, Minnan Luo, Jingdong Wang", + "authors": [ + { + "first_name": "Haochen", + "last_name": "Han" + }, + { + "first_name": "Qinghua", + "last_name": "Zheng" + }, + { + "first_name": "Guang", + "last_name": "Dai" + }, + { + "first_name": "Minnan", + "last_name": "Luo" + }, + { + "first_name": "Jingdong", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Generate Subgoal Images before Act: Unlocking the Chain-of-Thought Reasoning in Diffusion Model for Robot Manipulation with Multimodal Prompts", - "authors": "Fei Ni, Jianye Hao, Shiguang Wu, Longxin Kou, Jiashun Liu, Yan Zheng, Bin Wang, Yuzheng Zhuang", + "authors": [ + { + "first_name": "Fei", + "last_name": "Ni" + }, + { + "first_name": "Jianye", + "last_name": "Hao" + }, + { + "first_name": "Shiguang", + "last_name": "Wu" + }, + { + "first_name": "Longxin", + "last_name": "Kou" + }, + { + "first_name": "Jiashun", + "last_name": "Liu" + }, + { + "first_name": "Yan", + "last_name": "Zheng" + }, + { + "first_name": "Bin", + "last_name": "Wang" + }, + { + "first_name": "Yuzheng", + "last_name": "Zhuang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Asymmetric Masked Distillation for Pre-Training Small Foundation Models", - "authors": "Zhiyu Zhao, Bingkun Huang, Sen Xing, Gangshan Wu, Yu Qiao, Limin Wang", + "authors": [ + { + "first_name": "Zhiyu", + "last_name": "Zhao" + }, + { + "first_name": "Bingkun", + "last_name": "Huang" + }, + { + "first_name": "Sen", + "last_name": "Xing" + }, + { + "first_name": "Gangshan", + "last_name": "Wu" + }, + { + "first_name": "Yu", + "last_name": "Qiao" + }, + { + "first_name": "Limin", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Inversion-Free Image Editing with Language-Guided Diffusion Models", - "authors": "Sihan Xu, Yidong Huang, Jiayi Pan, Ziqiao Ma, Joyce Chai", + "authors": [ + { + "first_name": "Sihan", + "last_name": "Xu" + }, + { + "first_name": "Yidong", + "last_name": "Huang" + }, + { + "first_name": "Jiayi", + "last_name": "Pan" + }, + { + "first_name": "Ziqiao", + "last_name": "Ma" + }, + { + "first_name": "Joyce", + "last_name": "Chai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HumMUSS: Human Motion Understanding using State Space Models", - "authors": "Arnab Mondal, Stefano Alletto, Denis Tome", + "authors": [ + { + "first_name": "Arnab", + "last_name": "Mondal" + }, + { + "first_name": "Stefano", + "last_name": "Alletto" + }, + { + "first_name": "Denis", + "last_name": "Tome" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MP5: A Multi-modal Open-ended Embodied System in Minecraft via Active Perception", - "authors": "Yiran Qin, Enshen Zhou, Qichang Liu, Zhenfei Yin, Lu Sheng, Ruimao Zhang, Yu Qiao, Jing Shao", + "authors": [ + { + "first_name": "Yiran", + "last_name": "Qin" + }, + { + "first_name": "Enshen", + "last_name": "Zhou" + }, + { + "first_name": "Qichang", + "last_name": "Liu" + }, + { + "first_name": "Zhenfei", + "last_name": "Yin" + }, + { + "first_name": "Lu", + "last_name": "Sheng" + }, + { + "first_name": "Ruimao", + "last_name": "Zhang" + }, + { + "first_name": "Yu", + "last_name": "Qiao" + }, + { + "first_name": "Jing", + "last_name": "Shao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Uncovering What Why and How: A Comprehensive Benchmark for Causation Understanding of Video Anomaly", - "authors": "Hang Du, Sicheng Zhang, Binzhu Xie, Guoshun Nan, Jiayang Zhang, Junrui Xu, Hangyu Liu, Sicong Leng, Jiangming Liu, Hehe Fan, Dajiu Huang, Jing Feng, Linli Chen, Can Zhang, Xuhuan Li, Hao Zhang, Jianhang Chen, Qimei Cui, Xiaofeng Tao", + "authors": [ + { + "first_name": "Hang", + "last_name": "Du" + }, + { + "first_name": "Sicheng", + "last_name": "Zhang" + }, + { + "first_name": "Binzhu", + "last_name": "Xie" + }, + { + "first_name": "Guoshun", + "last_name": "Nan" + }, + { + "first_name": "Jiayang", + "last_name": "Zhang" + }, + { + "first_name": "Junrui", + "last_name": "Xu" + }, + { + "first_name": "Hangyu", + "last_name": "Liu" + }, + { + "first_name": "Sicong", + "last_name": "Leng" + }, + { + "first_name": "Jiangming", + "last_name": "Liu" + }, + { + "first_name": "Hehe", + "last_name": "Fan" + }, + { + "first_name": "Dajiu", + "last_name": "Huang" + }, + { + "first_name": "Jing", + "last_name": "Feng" + }, + { + "first_name": "Linli", + "last_name": "Chen" + }, + { + "first_name": "Can", + "last_name": "Zhang" + }, + { + "first_name": "Xuhuan", + "last_name": "Li" + }, + { + "first_name": "Hao", + "last_name": "Zhang" + }, + { + "first_name": "Jianhang", + "last_name": "Chen" + }, + { + "first_name": "Qimei", + "last_name": "Cui" + }, + { + "first_name": "Xiaofeng", + "last_name": "Tao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MiKASA: Multi-Key-Anchor & Scene-Aware Transformer for 3D Visual Grounding", - "authors": "Chun-Peng Chang, Shaoxiang Wang, Alain Pagani, Didier Stricker", + "authors": [ + { + "first_name": "Chun-Peng", + "last_name": "Chang" + }, + { + "first_name": "Shaoxiang", + "last_name": "Wang" + }, + { + "first_name": "Alain", + "last_name": "Pagani" + }, + { + "first_name": "Didier", + "last_name": "Stricker" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ZePT: Zero-Shot Pan-Tumor Segmentation via Query-Disentangling and Self-Prompting", - "authors": "Yankai Jiang, Zhongzhen Huang, Rongzhao Zhang, Xiaofan Zhang, Shaoting Zhang", + "authors": [ + { + "first_name": "Yankai", + "last_name": "Jiang" + }, + { + "first_name": "Zhongzhen", + "last_name": "Huang" + }, + { + "first_name": "Rongzhao", + "last_name": "Zhang" + }, + { + "first_name": "Xiaofan", + "last_name": "Zhang" + }, + { + "first_name": "Shaoting", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Task-Driven Exploration: Decoupling and Inter-Task Feedback for Joint Moment Retrieval and Highlight Detection", - "authors": "Jin Yang, Ping Wei, Huan Li, Ziyang Ren", + "authors": [ + { + "first_name": "Jin", + "last_name": "Yang" + }, + { + "first_name": "Ping", + "last_name": "Wei" + }, + { + "first_name": "Huan", + "last_name": "Li" + }, + { + "first_name": "Ziyang", + "last_name": "Ren" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training", - "authors": "Pavan Kumar Anasosalu Vasu, Hadi Pouransari, Fartash Faghri, Raviteja Vemulapalli, Oncel Tuzel", + "authors": [ + { + "first_name": "Pavan", + "last_name": "Kumar Anasosalu Vasu" + }, + { + "first_name": "Hadi", + "last_name": "Pouransari" + }, + { + "first_name": "Fartash", + "last_name": "Faghri" + }, + { + "first_name": "Raviteja", + "last_name": "Vemulapalli" + }, + { + "first_name": "Oncel", + "last_name": "Tuzel" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Drag Your Noise: Interactive Point-based Editing via Diffusion Semantic Propagation", - "authors": "Haofeng Liu, Chenshu Xu, Yifei Yang, Lihua Zeng, Shengfeng He", + "authors": [ + { + "first_name": "Haofeng", + "last_name": "Liu" + }, + { + "first_name": "Chenshu", + "last_name": "Xu" + }, + { + "first_name": "Yifei", + "last_name": "Yang" + }, + { + "first_name": "Lihua", + "last_name": "Zeng" + }, + { + "first_name": "Shengfeng", + "last_name": "He" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CDMAD: Class-Distribution-Mismatch-Aware Debiasing for Class-Imbalanced Semi-Supervised Learning", - "authors": "Hyuck Lee, Heeyoung Kim", + "authors": [ + { + "first_name": "Hyuck", + "last_name": "Lee" + }, + { + "first_name": "Heeyoung", + "last_name": "Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "VideoCon: Robust Video-Language Alignment via Contrast Captions", - "authors": "Hritik Bansal, Yonatan Bitton, Idan Szpektor, Kai-Wei Chang, Aditya Grover", + "authors": [ + { + "first_name": "Hritik", + "last_name": "Bansal" + }, + { + "first_name": "Yonatan", + "last_name": "Bitton" + }, + { + "first_name": "Idan", + "last_name": "Szpektor" + }, + { + "first_name": "Kai-Wei", + "last_name": "Chang" + }, + { + "first_name": "Aditya", + "last_name": "Grover" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PanoPose: Self-supervised Relative Pose Estimation for Panoramic Images", - "authors": "Diantao Tu, Hainan Cui, Xianwei Zheng, Shuhan Shen", + "authors": [ + { + "first_name": "Diantao", + "last_name": "Tu" + }, + { + "first_name": "Hainan", + "last_name": "Cui" + }, + { + "first_name": "Xianwei", + "last_name": "Zheng" + }, + { + "first_name": "Shuhan", + "last_name": "Shen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ContextSeg: Sketch Semantic Segmentation by Querying the Context with Attention", - "authors": "Jiawei Wang, Changjian Li", + "authors": [ + { + "first_name": "Jiawei", + "last_name": "Wang" + }, + { + "first_name": "Changjian", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Describing Differences in Image Sets with Natural Language", - "authors": "Lisa Dunlap, Yuhui Zhang, Xiaohan Wang, Ruiqi Zhong, Trevor Darrell, Jacob Steinhardt, Joseph E. Gonzalez, Serena Yeung-Levy", + "authors": [ + { + "first_name": "Lisa", + "last_name": "Dunlap" + }, + { + "first_name": "Yuhui", + "last_name": "Zhang" + }, + { + "first_name": "Xiaohan", + "last_name": "Wang" + }, + { + "first_name": "Ruiqi", + "last_name": "Zhong" + }, + { + "first_name": "Trevor", + "last_name": "Darrell" + }, + { + "first_name": "Jacob", + "last_name": "Steinhardt" + }, + { + "first_name": "Joseph", + "last_name": "E. Gonzalez" + }, + { + "first_name": "Serena", + "last_name": "Yeung-Levy" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Discovering and Mitigating Visual Biases through Keyword Explanation", - "authors": "Younghyun Kim, Sangwoo Mo, Minkyu Kim, Kyungmin Lee, Jaeho Lee, Jinwoo Shin", + "authors": [ + { + "first_name": "Younghyun", + "last_name": "Kim" + }, + { + "first_name": "Sangwoo", + "last_name": "Mo" + }, + { + "first_name": "Minkyu", + "last_name": "Kim" + }, + { + "first_name": "Kyungmin", + "last_name": "Lee" + }, + { + "first_name": "Jaeho", + "last_name": "Lee" + }, + { + "first_name": "Jinwoo", + "last_name": "Shin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Robust Emotion Recognition in Context Debiasing", - "authors": "Dingkang Yang, Kun Yang, Mingcheng Li, Shunli Wang, Shuaibing Wang, Lihua Zhang", + "authors": [ + { + "first_name": "Dingkang", + "last_name": "Yang" + }, + { + "first_name": "Kun", + "last_name": "Yang" + }, + { + "first_name": "Mingcheng", + "last_name": "Li" + }, + { + "first_name": "Shunli", + "last_name": "Wang" + }, + { + "first_name": "Shuaibing", + "last_name": "Wang" + }, + { + "first_name": "Lihua", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Fully Geometric Panoramic Localization", - "authors": "Junho Kim, Jiwon Jeong, Young Min Kim", + "authors": [ + { + "first_name": "Junho", + "last_name": "Kim" + }, + { + "first_name": "Jiwon", + "last_name": "Jeong" + }, + { + "first_name": "Young", + "last_name": "Min Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CAPE: CAM as a Probabilistic Ensemble for Enhanced DNN Interpretation", - "authors": "Townim Faisal Chowdhury, Kewen Liao, Vu Minh Hieu Phan, Minh-Son To, Yutong Xie, Kevin Hung, David Ross, Anton van den Hengel, Johan W. Verjans, Zhibin Liao", + "authors": [ + { + "first_name": "Townim", + "last_name": "Faisal Chowdhury" + }, + { + "first_name": "Kewen", + "last_name": "Liao" + }, + { + "first_name": "Vu", + "last_name": "Minh Hieu Phan" + }, + { + "first_name": "Minh-Son", + "last_name": "To" + }, + { + "first_name": "Yutong", + "last_name": "Xie" + }, + { + "first_name": "Kevin", + "last_name": "Hung" + }, + { + "first_name": "David", + "last_name": "Ross" + }, + { + "first_name": "Anton", + "last_name": "van den Hengel" + }, + { + "first_name": "Johan", + "last_name": "W. Verjans" + }, + { + "first_name": "Zhibin", + "last_name": "Liao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "NeRF Director: Revisiting View Selection in Neural Volume Rendering", - "authors": "Wenhui Xiao, Rodrigo Santa Cruz, David Ahmedt-Aristizabal, Olivier Salvado, Clinton Fookes, Leo Lebrat", + "authors": [ + { + "first_name": "Wenhui", + "last_name": "Xiao" + }, + { + "first_name": "Rodrigo", + "last_name": "Santa Cruz" + }, + { + "first_name": "David", + "last_name": "Ahmedt-Aristizabal" + }, + { + "first_name": "Olivier", + "last_name": "Salvado" + }, + { + "first_name": "Clinton", + "last_name": "Fookes" + }, + { + "first_name": "Leo", + "last_name": "Lebrat" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Taming the Tail in Class-Conditional GANs: Knowledge Sharing via Unconditional Training at Lower Resolutions", - "authors": "Saeed Khorram, Mingqi Jiang, Mohamad Shahbazi, Mohamad H. Danesh, Li Fuxin", + "authors": [ + { + "first_name": "Saeed", + "last_name": "Khorram" + }, + { + "first_name": "Mingqi", + "last_name": "Jiang" + }, + { + "first_name": "Mohamad", + "last_name": "Shahbazi" + }, + { + "first_name": "Mohamad", + "last_name": "H. Danesh" + }, + { + "first_name": "Li", + "last_name": "Fuxin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "VideoSwap: Customized Video Subject Swapping with Interactive Semantic Point Correspondence", - "authors": "Yuchao Gu, Yipin Zhou, Bichen Wu, Licheng Yu, Jia-Wei Liu, Rui Zhao, Jay Zhangjie Wu, David Junhao Zhang, Mike Zheng Shou, Kevin Tang", + "authors": [ + { + "first_name": "Yuchao", + "last_name": "Gu" + }, + { + "first_name": "Yipin", + "last_name": "Zhou" + }, + { + "first_name": "Bichen", + "last_name": "Wu" + }, + { + "first_name": "Licheng", + "last_name": "Yu" + }, + { + "first_name": "Jia-Wei", + "last_name": "Liu" + }, + { + "first_name": "Rui", + "last_name": "Zhao" + }, + { + "first_name": "Jay", + "last_name": "Zhangjie Wu" + }, + { + "first_name": "David", + "last_name": "Junhao Zhang" + }, + { + "first_name": "Mike", + "last_name": "Zheng Shou" + }, + { + "first_name": "Kevin", + "last_name": "Tang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SonicVisionLM: Playing Sound with Vision Language Models", - "authors": "Zhifeng Xie, Shengye Yu, Qile He, Mengtian Li", + "authors": [ + { + "first_name": "Zhifeng", + "last_name": "Xie" + }, + { + "first_name": "Shengye", + "last_name": "Yu" + }, + { + "first_name": "Qile", + "last_name": "He" + }, + { + "first_name": "Mengtian", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Multi-Space Alignments Towards Universal LiDAR Segmentation", - "authors": "Youquan Liu, Lingdong Kong, Xiaoyang Wu, Runnan Chen, Xin Li, Liang Pan, Ziwei Liu, Yuexin Ma", + "authors": [ + { + "first_name": "Youquan", + "last_name": "Liu" + }, + { + "first_name": "Lingdong", + "last_name": "Kong" + }, + { + "first_name": "Xiaoyang", + "last_name": "Wu" + }, + { + "first_name": "Runnan", + "last_name": "Chen" + }, + { + "first_name": "Xin", + "last_name": "Li" + }, + { + "first_name": "Liang", + "last_name": "Pan" + }, + { + "first_name": "Ziwei", + "last_name": "Liu" + }, + { + "first_name": "Yuexin", + "last_name": "Ma" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis", - "authors": "Jiapeng Tang, Yinyu Nie, Lev Markhasin, Angela Dai, Justus Thies, Matthias Nießner", + "authors": [ + { + "first_name": "Jiapeng", + "last_name": "Tang" + }, + { + "first_name": "Yinyu", + "last_name": "Nie" + }, + { + "first_name": "Lev", + "last_name": "Markhasin" + }, + { + "first_name": "Angela", + "last_name": "Dai" + }, + { + "first_name": "Justus", + "last_name": "Thies" + }, + { + "first_name": "Matthias", + "last_name": "Nießner" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Hierarchical Histogram Threshold Segmentation - Auto-terminating High-detail Oversegmentation", - "authors": "Thomas V. Chang, Simon Seibt, Bartosz von Rymon Lipinski", + "authors": [ + { + "first_name": "Thomas", + "last_name": "V. Chang" + }, + { + "first_name": "Simon", + "last_name": "Seibt" + }, + { + "first_name": "Bartosz", + "last_name": "von Rymon Lipinski" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Once for Both: Single Stage of Importance and Sparsity Search for Vision Transformer Compression", - "authors": "Hancheng Ye, Chong Yu, Peng Ye, Renqiu Xia, Yansong Tang, Jiwen Lu, Tao Chen, Bo Zhang", + "authors": [ + { + "first_name": "Hancheng", + "last_name": "Ye" + }, + { + "first_name": "Chong", + "last_name": "Yu" + }, + { + "first_name": "Peng", + "last_name": "Ye" + }, + { + "first_name": "Renqiu", + "last_name": "Xia" + }, + { + "first_name": "Yansong", + "last_name": "Tang" + }, + { + "first_name": "Jiwen", + "last_name": "Lu" + }, + { + "first_name": "Tao", + "last_name": "Chen" + }, + { + "first_name": "Bo", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "As-Plausible-As-Possible: Plausibility-Aware Mesh Deformation Using 2D Diffusion Priors", - "authors": "Seungwoo Yoo, Kunho Kim, Vladimir G. Kim, Minhyuk Sung", + "authors": [ + { + "first_name": "Seungwoo", + "last_name": "Yoo" + }, + { + "first_name": "Kunho", + "last_name": "Kim" + }, + { + "first_name": "Vladimir", + "last_name": "G. Kim" + }, + { + "first_name": "Minhyuk", + "last_name": "Sung" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MCNet: Rethinking the Core Ingredients for Accurate and Efficient Homography Estimation", - "authors": "Haokai Zhu, Si-Yuan Cao, Jianxin Hu, Sitong Zuo, Beinan Yu, Jiacheng Ying, Junwei Li, Hui-Liang Shen", + "authors": [ + { + "first_name": "Haokai", + "last_name": "Zhu" + }, + { + "first_name": "Si-Yuan", + "last_name": "Cao" + }, + { + "first_name": "Jianxin", + "last_name": "Hu" + }, + { + "first_name": "Sitong", + "last_name": "Zuo" + }, + { + "first_name": "Beinan", + "last_name": "Yu" + }, + { + "first_name": "Jiacheng", + "last_name": "Ying" + }, + { + "first_name": "Junwei", + "last_name": "Li" + }, + { + "first_name": "Hui-Liang", + "last_name": "Shen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ECLIPSE: Efficient Continual Learning in Panoptic Segmentation with Visual Prompt Tuning", - "authors": "Beomyoung Kim, Joonsang Yu, Sung Ju Hwang", + "authors": [ + { + "first_name": "Beomyoung", + "last_name": "Kim" + }, + { + "first_name": "Joonsang", + "last_name": "Yu" + }, + { + "first_name": "Sung", + "last_name": "Ju Hwang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters", - "authors": "Jiazuo Yu, Yunzhi Zhuge, Lu Zhang, Ping Hu, Dong Wang, Huchuan Lu, You He", + "authors": [ + { + "first_name": "Jiazuo", + "last_name": "Yu" + }, + { + "first_name": "Yunzhi", + "last_name": "Zhuge" + }, + { + "first_name": "Lu", + "last_name": "Zhang" + }, + { + "first_name": "Ping", + "last_name": "Hu" + }, + { + "first_name": "Dong", + "last_name": "Wang" + }, + { + "first_name": "Huchuan", + "last_name": "Lu" + }, + { + "first_name": "You", + "last_name": "He" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MaGGIe: Masked Guided Gradual Human Instance Matting", - "authors": "Chuong Huynh, Seoung Wug Oh, Abhinav Shrivastava, Joon-Young Lee", + "authors": [ + { + "first_name": "Chuong", + "last_name": "Huynh" + }, + { + "first_name": "Seoung", + "last_name": "Wug Oh" + }, + { + "first_name": "Abhinav", + "last_name": "Shrivastava" + }, + { + "first_name": "Joon-Young", + "last_name": "Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FlowDiffuser: Advancing Optical Flow Estimation with Diffusion Models", - "authors": "Ao Luo, Xin Li, Fan Yang, Jiangyu Liu, Haoqiang Fan, Shuaicheng Liu", + "authors": [ + { + "first_name": "Ao", + "last_name": "Luo" + }, + { + "first_name": "Xin", + "last_name": "Li" + }, + { + "first_name": "Fan", + "last_name": "Yang" + }, + { + "first_name": "Jiangyu", + "last_name": "Liu" + }, + { + "first_name": "Haoqiang", + "last_name": "Fan" + }, + { + "first_name": "Shuaicheng", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Benchmarking Implicit Neural Representation and Geometric Rendering in Real-Time RGB-D SLAM", - "authors": "Tongyan Hua, Lin Wang", + "authors": [ + { + "first_name": "Tongyan", + "last_name": "Hua" + }, + { + "first_name": "Lin", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Free3D: Consistent Novel View Synthesis without 3D Representation", - "authors": "Chuanxia Zheng, Andrea Vedaldi", + "authors": [ + { + "first_name": "Chuanxia", + "last_name": "Zheng" + }, + { + "first_name": "Andrea", + "last_name": "Vedaldi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SuperSVG: Superpixel-based Scalable Vector Graphics Synthesis", - "authors": "Teng Hu, Ran Yi, Baihong Qian, Jiangning Zhang, Paul L. Rosin, Yu-Kun Lai", + "authors": [ + { + "first_name": "Teng", + "last_name": "Hu" + }, + { + "first_name": "Ran", + "last_name": "Yi" + }, + { + "first_name": "Baihong", + "last_name": "Qian" + }, + { + "first_name": "Jiangning", + "last_name": "Zhang" + }, + { + "first_name": "Paul", + "last_name": "L. Rosin" + }, + { + "first_name": "Yu-Kun", + "last_name": "Lai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech Representation", - "authors": "Jeongsoo Choi, Se Jin Park, Minsu Kim, Yong Man Ro", + "authors": [ + { + "first_name": "Jeongsoo", + "last_name": "Choi" + }, + { + "first_name": "Se", + "last_name": "Jin Park" + }, + { + "first_name": "Minsu", + "last_name": "Kim" + }, + { + "first_name": "Yong", + "last_name": "Man Ro" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards the Uncharted: Density-Descending Feature Perturbation for Semi-supervised Semantic Segmentation", - "authors": "Xiaoyang Wang, Huihui Bai, Limin Yu, Yao Zhao, Jimin Xiao", + "authors": [ + { + "first_name": "Xiaoyang", + "last_name": "Wang" + }, + { + "first_name": "Huihui", + "last_name": "Bai" + }, + { + "first_name": "Limin", + "last_name": "Yu" + }, + { + "first_name": "Yao", + "last_name": "Zhao" + }, + { + "first_name": "Jimin", + "last_name": "Xiao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "WALT3D: Generating Realistic Training Data from Time-Lapse Imagery for Reconstructing Dynamic Objects Under Occlusion", - "authors": "Khiem Vuong, N Dinesh Reddy, Robert Tamburo, Srinivasa G. Narasimhan", + "authors": [ + { + "first_name": "Khiem", + "last_name": "Vuong" + }, + { + "first_name": "N", + "last_name": "Dinesh Reddy" + }, + { + "first_name": "Robert", + "last_name": "Tamburo" + }, + { + "first_name": "Srinivasa", + "last_name": "G. Narasimhan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimation", - "authors": "Peng Lu, Tao Jiang, Yining Li, Xiangtai Li, Kai Chen, Wenming Yang", + "authors": [ + { + "first_name": "Peng", + "last_name": "Lu" + }, + { + "first_name": "Tao", + "last_name": "Jiang" + }, + { + "first_name": "Yining", + "last_name": "Li" + }, + { + "first_name": "Xiangtai", + "last_name": "Li" + }, + { + "first_name": "Kai", + "last_name": "Chen" + }, + { + "first_name": "Wenming", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Contrastive Mean-Shift Learning for Generalized Category Discovery", - "authors": "Sua Choi, Dahyun Kang, Minsu Cho", + "authors": [ + { + "first_name": "Sua", + "last_name": "Choi" + }, + { + "first_name": "Dahyun", + "last_name": "Kang" + }, + { + "first_name": "Minsu", + "last_name": "Cho" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards Language-Driven Video Inpainting via Multimodal Large Language Models", - "authors": "Jianzong Wu, Xiangtai Li, Chenyang Si, Shangchen Zhou, Jingkang Yang, Jiangning Zhang, Yining Li, Kai Chen, Yunhai Tong, Ziwei Liu, Chen Change Loy", + "authors": [ + { + "first_name": "Jianzong", + "last_name": "Wu" + }, + { + "first_name": "Xiangtai", + "last_name": "Li" + }, + { + "first_name": "Chenyang", + "last_name": "Si" + }, + { + "first_name": "Shangchen", + "last_name": "Zhou" + }, + { + "first_name": "Jingkang", + "last_name": "Yang" + }, + { + "first_name": "Jiangning", + "last_name": "Zhang" + }, + { + "first_name": "Yining", + "last_name": "Li" + }, + { + "first_name": "Kai", + "last_name": "Chen" + }, + { + "first_name": "Yunhai", + "last_name": "Tong" + }, + { + "first_name": "Ziwei", + "last_name": "Liu" + }, + { + "first_name": "Chen", + "last_name": "Change Loy" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "WaveFace: Authentic Face Restoration with Efficient Frequency Recovery", - "authors": "Yunqi Miao, Jiankang Deng, Jungong Han", + "authors": [ + { + "first_name": "Yunqi", + "last_name": "Miao" + }, + { + "first_name": "Jiankang", + "last_name": "Deng" + }, + { + "first_name": "Jungong", + "last_name": "Han" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CLIP-KD: An Empirical Study of CLIP Model Distillation", - "authors": "Chuanguang Yang, Zhulin An, Libo Huang, Junyu Bi, Xinqiang Yu, Han Yang, Boyu Diao, Yongjun Xu", + "authors": [ + { + "first_name": "Chuanguang", + "last_name": "Yang" + }, + { + "first_name": "Zhulin", + "last_name": "An" + }, + { + "first_name": "Libo", + "last_name": "Huang" + }, + { + "first_name": "Junyu", + "last_name": "Bi" + }, + { + "first_name": "Xinqiang", + "last_name": "Yu" + }, + { + "first_name": "Han", + "last_name": "Yang" + }, + { + "first_name": "Boyu", + "last_name": "Diao" + }, + { + "first_name": "Yongjun", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "UltrAvatar: A Realistic Animatable 3D Avatar Diffusion Model with Authenticity Guided Textures", - "authors": "Mingyuan Zhou, Rakib Hyder, Ziwei Xuan, Guojun Qi", + "authors": [ + { + "first_name": "Mingyuan", + "last_name": "Zhou" + }, + { + "first_name": "Rakib", + "last_name": "Hyder" + }, + { + "first_name": "Ziwei", + "last_name": "Xuan" + }, + { + "first_name": "Guojun", + "last_name": "Qi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning", - "authors": "Lingyi Hong, Shilin Yan, Renrui Zhang, Wanyun Li, Xinyu Zhou, Pinxue Guo, Kaixun Jiang, Yiting Chen, Jinglun Li, Zhaoyu Chen, Wenqiang Zhang", + "authors": [ + { + "first_name": "Lingyi", + "last_name": "Hong" + }, + { + "first_name": "Shilin", + "last_name": "Yan" + }, + { + "first_name": "Renrui", + "last_name": "Zhang" + }, + { + "first_name": "Wanyun", + "last_name": "Li" + }, + { + "first_name": "Xinyu", + "last_name": "Zhou" + }, + { + "first_name": "Pinxue", + "last_name": "Guo" + }, + { + "first_name": "Kaixun", + "last_name": "Jiang" + }, + { + "first_name": "Yiting", + "last_name": "Chen" + }, + { + "first_name": "Jinglun", + "last_name": "Li" + }, + { + "first_name": "Zhaoyu", + "last_name": "Chen" + }, + { + "first_name": "Wenqiang", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SC-Tune: Unleashing Self-Consistent Referential Comprehension in Large Vision Language Models", - "authors": "Tongtian Yue, Jie Cheng, Longteng Guo, Xingyuan Dai, Zijia Zhao, Xingjian He, Gang Xiong, Yisheng Lv, Jing Liu", + "authors": [ + { + "first_name": "Tongtian", + "last_name": "Yue" + }, + { + "first_name": "Jie", + "last_name": "Cheng" + }, + { + "first_name": "Longteng", + "last_name": "Guo" + }, + { + "first_name": "Xingyuan", + "last_name": "Dai" + }, + { + "first_name": "Zijia", + "last_name": "Zhao" + }, + { + "first_name": "Xingjian", + "last_name": "He" + }, + { + "first_name": "Gang", + "last_name": "Xiong" + }, + { + "first_name": "Yisheng", + "last_name": "Lv" + }, + { + "first_name": "Jing", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Improving Depth Completion via Depth Feature Upsampling", - "authors": "Yufei Wang, Ge Zhang, Shaoqian Wang, Bo Li, Qi Liu, Le Hui, Yuchao Dai", + "authors": [ + { + "first_name": "Yufei", + "last_name": "Wang" + }, + { + "first_name": "Ge", + "last_name": "Zhang" + }, + { + "first_name": "Shaoqian", + "last_name": "Wang" + }, + { + "first_name": "Bo", + "last_name": "Li" + }, + { + "first_name": "Qi", + "last_name": "Liu" + }, + { + "first_name": "Le", + "last_name": "Hui" + }, + { + "first_name": "Yuchao", + "last_name": "Dai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "NeRSP: Neural 3D Reconstruction for Reflective Objects with Sparse Polarized Images", - "authors": "Yufei Han, Heng Guo, Koki Fukai, Hiroaki Santo, Boxin Shi, Fumio Okura, Zhanyu Ma, Yunpeng Jia", + "authors": [ + { + "first_name": "Yufei", + "last_name": "Han" + }, + { + "first_name": "Heng", + "last_name": "Guo" + }, + { + "first_name": "Koki", + "last_name": "Fukai" + }, + { + "first_name": "Hiroaki", + "last_name": "Santo" + }, + { + "first_name": "Boxin", + "last_name": "Shi" + }, + { + "first_name": "Fumio", + "last_name": "Okura" + }, + { + "first_name": "Zhanyu", + "last_name": "Ma" + }, + { + "first_name": "Yunpeng", + "last_name": "Jia" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Retrieval-Augmented Embodied Agents", - "authors": "Yichen Zhu, Zhicai Ou, Xiaofeng Mou, Jian Tang", + "authors": [ + { + "first_name": "Yichen", + "last_name": "Zhu" + }, + { + "first_name": "Zhicai", + "last_name": "Ou" + }, + { + "first_name": "Xiaofeng", + "last_name": "Mou" + }, + { + "first_name": "Jian", + "last_name": "Tang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SAFDNet: A Simple and Effective Network for Fully Sparse 3D Object Detection", - "authors": "Gang Zhang, Junnan Chen, Guohuan Gao, Jianmin Li, Si Liu, Xiaolin Hu", + "authors": [ + { + "first_name": "Gang", + "last_name": "Zhang" + }, + { + "first_name": "Junnan", + "last_name": "Chen" + }, + { + "first_name": "Guohuan", + "last_name": "Gao" + }, + { + "first_name": "Jianmin", + "last_name": "Li" + }, + { + "first_name": "Si", + "last_name": "Liu" + }, + { + "first_name": "Xiaolin", + "last_name": "Hu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Attention-Propagation Network for Egocentric Heatmap to 3D Pose Lifting", - "authors": "Taeho Kang, Youngki Lee", + "authors": [ + { + "first_name": "Taeho", + "last_name": "Kang" + }, + { + "first_name": "Youngki", + "last_name": "Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "OmniMotionGPT: Animal Motion Generation with Limited Data", - "authors": "Zhangsihao Yang, Mingyuan Zhou, Mengyi Shan, Bingbing Wen, Ziwei Xuan, Mitch Hill, Junjie Bai, Guo-Jun Qi, Yalin Wang", + "authors": [ + { + "first_name": "Zhangsihao", + "last_name": "Yang" + }, + { + "first_name": "Mingyuan", + "last_name": "Zhou" + }, + { + "first_name": "Mengyi", + "last_name": "Shan" + }, + { + "first_name": "Bingbing", + "last_name": "Wen" + }, + { + "first_name": "Ziwei", + "last_name": "Xuan" + }, + { + "first_name": "Mitch", + "last_name": "Hill" + }, + { + "first_name": "Junjie", + "last_name": "Bai" + }, + { + "first_name": "Guo-Jun", + "last_name": "Qi" + }, + { + "first_name": "Yalin", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SNI-SLAM: Semantic Neural Implicit SLAM", - "authors": "Siting Zhu, Guangming Wang, Hermann Blum, Jiuming Liu, Liang Song, Marc Pollefeys, Hesheng Wang", + "authors": [ + { + "first_name": "Siting", + "last_name": "Zhu" + }, + { + "first_name": "Guangming", + "last_name": "Wang" + }, + { + "first_name": "Hermann", + "last_name": "Blum" + }, + { + "first_name": "Jiuming", + "last_name": "Liu" + }, + { + "first_name": "Liang", + "last_name": "Song" + }, + { + "first_name": "Marc", + "last_name": "Pollefeys" + }, + { + "first_name": "Hesheng", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "InstanceDiffusion: Instance-level Control for Image Generation", - "authors": "Xudong Wang, Trevor Darrell, Sai Saketh Rambhatla, Rohit Girdhar, Ishan Misra", + "authors": [ + { + "first_name": "Xudong", + "last_name": "Wang" + }, + { + "first_name": "Trevor", + "last_name": "Darrell" + }, + { + "first_name": "Sai", + "last_name": "Saketh Rambhatla" + }, + { + "first_name": "Rohit", + "last_name": "Girdhar" + }, + { + "first_name": "Ishan", + "last_name": "Misra" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Unifying Top-down and Bottom-up Scanpath Prediction Using Transformers", - "authors": "Zhibo Yang, Sounak Mondal, Seoyoung Ahn, Ruoyu Xue, Gregory Zelinsky, Minh Hoai, Dimitris Samaras", + "authors": [ + { + "first_name": "Zhibo", + "last_name": "Yang" + }, + { + "first_name": "Sounak", + "last_name": "Mondal" + }, + { + "first_name": "Seoyoung", + "last_name": "Ahn" + }, + { + "first_name": "Ruoyu", + "last_name": "Xue" + }, + { + "first_name": "Gregory", + "last_name": "Zelinsky" + }, + { + "first_name": "Minh", + "last_name": "Hoai" + }, + { + "first_name": "Dimitris", + "last_name": "Samaras" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HINTED: Hard Instance Enhanced Detector with Mixed-Density Feature Fusion for Sparsely-Supervised 3D Object Detection", - "authors": "Qiming Xia, Wei Ye, Hai Wu, Shijia Zhao, Leyuan Xing, Xun Huang, Jinhao Deng, Xin Li, Chenglu Wen, Cheng Wang", + "authors": [ + { + "first_name": "Qiming", + "last_name": "Xia" + }, + { + "first_name": "Wei", + "last_name": "Ye" + }, + { + "first_name": "Hai", + "last_name": "Wu" + }, + { + "first_name": "Shijia", + "last_name": "Zhao" + }, + { + "first_name": "Leyuan", + "last_name": "Xing" + }, + { + "first_name": "Xun", + "last_name": "Huang" + }, + { + "first_name": "Jinhao", + "last_name": "Deng" + }, + { + "first_name": "Xin", + "last_name": "Li" + }, + { + "first_name": "Chenglu", + "last_name": "Wen" + }, + { + "first_name": "Cheng", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Structured Gradient-based Interpretations via Norm-Regularized Adversarial Training", - "authors": "Shizhan Gong, Qi Dou, Farzan Farnia", + "authors": [ + { + "first_name": "Shizhan", + "last_name": "Gong" + }, + { + "first_name": "Qi", + "last_name": "Dou" + }, + { + "first_name": "Farzan", + "last_name": "Farnia" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Building a Strong Pre-Training Baseline for Universal 3D Large-Scale Perception", - "authors": "Haoming Chen, Zhizhong Zhang, Yanyun Qu, Ruixin Zhang, Xin Tan, Yuan Xie", + "authors": [ + { + "first_name": "Haoming", + "last_name": "Chen" + }, + { + "first_name": "Zhizhong", + "last_name": "Zhang" + }, + { + "first_name": "Yanyun", + "last_name": "Qu" + }, + { + "first_name": "Ruixin", + "last_name": "Zhang" + }, + { + "first_name": "Xin", + "last_name": "Tan" + }, + { + "first_name": "Yuan", + "last_name": "Xie" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DS-NeRV: Implicit Neural Video Representation with Decomposed Static and Dynamic Codes", - "authors": "Hao Yan, Zhihui Ke, Xiaobo Zhou, Tie Qiu, Xidong Shi, Dadong Jiang", + "authors": [ + { + "first_name": "Hao", + "last_name": "Yan" + }, + { + "first_name": "Zhihui", + "last_name": "Ke" + }, + { + "first_name": "Xiaobo", + "last_name": "Zhou" + }, + { + "first_name": "Tie", + "last_name": "Qiu" + }, + { + "first_name": "Xidong", + "last_name": "Shi" + }, + { + "first_name": "Dadong", + "last_name": "Jiang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "3D-Aware Face Editing via Warping-Guided Latent Direction Learning", - "authors": "Yuhao Cheng, Zhuo Chen, Xingyu Ren, Wenhan Zhu, Zhengqin Xu, Di Xu, Changpeng Yang, Yichao Yan", + "authors": [ + { + "first_name": "Yuhao", + "last_name": "Cheng" + }, + { + "first_name": "Zhuo", + "last_name": "Chen" + }, + { + "first_name": "Xingyu", + "last_name": "Ren" + }, + { + "first_name": "Wenhan", + "last_name": "Zhu" + }, + { + "first_name": "Zhengqin", + "last_name": "Xu" + }, + { + "first_name": "Di", + "last_name": "Xu" + }, + { + "first_name": "Changpeng", + "last_name": "Yang" + }, + { + "first_name": "Yichao", + "last_name": "Yan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "3DFIRES: Few Image 3D REconstruction for Scenes with Hidden Surfaces", - "authors": "Linyi Jin, Nilesh Kulkarni, David F. Fouhey", + "authors": [ + { + "first_name": "Linyi", + "last_name": "Jin" + }, + { + "first_name": "Nilesh", + "last_name": "Kulkarni" + }, + { + "first_name": "David", + "last_name": "F. Fouhey" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation", - "authors": "Seokju Cho, Heeseong Shin, Sunghwan Hong, Anurag Arnab, Paul Hongsuck Seo, Seungryong Kim", + "authors": [ + { + "first_name": "Seokju", + "last_name": "Cho" + }, + { + "first_name": "Heeseong", + "last_name": "Shin" + }, + { + "first_name": "Sunghwan", + "last_name": "Hong" + }, + { + "first_name": "Anurag", + "last_name": "Arnab" + }, + { + "first_name": "Paul", + "last_name": "Hongsuck Seo" + }, + { + "first_name": "Seungryong", + "last_name": "Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Focus on Your Instruction: Fine-grained and Multi-instruction Image Editing by Attention Modulation", - "authors": "Qin Guo, Tianwei Lin", + "authors": [ + { + "first_name": "Qin", + "last_name": "Guo" + }, + { + "first_name": "Tianwei", + "last_name": "Lin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Tracking", - "authors": "Xiaojun Hou, Jiazheng Xing, Yijie Qian, Yaowei Guo, Shuo Xin, Junhao Chen, Kai Tang, Mengmeng Wang, Zhengkai Jiang, Liang Liu, Yong Liu", + "authors": [ + { + "first_name": "Xiaojun", + "last_name": "Hou" + }, + { + "first_name": "Jiazheng", + "last_name": "Xing" + }, + { + "first_name": "Yijie", + "last_name": "Qian" + }, + { + "first_name": "Yaowei", + "last_name": "Guo" + }, + { + "first_name": "Shuo", + "last_name": "Xin" + }, + { + "first_name": "Junhao", + "last_name": "Chen" + }, + { + "first_name": "Kai", + "last_name": "Tang" + }, + { + "first_name": "Mengmeng", + "last_name": "Wang" + }, + { + "first_name": "Zhengkai", + "last_name": "Jiang" + }, + { + "first_name": "Liang", + "last_name": "Liu" + }, + { + "first_name": "Yong", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MCPNet: An Interpretable Classifier via Multi-Level Concept Prototypes", - "authors": "Bor-Shiun Wang, Chien-Yi Wang, Wei-Chen Chiu", + "authors": [ + { + "first_name": "Bor-Shiun", + "last_name": "Wang" + }, + { + "first_name": "Chien-Yi", + "last_name": "Wang" + }, + { + "first_name": "Wei-Chen", + "last_name": "Chiu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment", - "authors": "Alvi Md Ishmam, Christopher Thomas", + "authors": [ + { + "first_name": "Alvi", + "last_name": "Md Ishmam" + }, + { + "first_name": "Christopher", + "last_name": "Thomas" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "AvatarGPT: All-in-One Framework for Motion Understanding Planning Generation and Beyond", - "authors": "Zixiang Zhou, Yu Wan, Baoyuan Wang", + "authors": [ + { + "first_name": "Zixiang", + "last_name": "Zhou" + }, + { + "first_name": "Yu", + "last_name": "Wan" + }, + { + "first_name": "Baoyuan", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Rethinking the Up-Sampling Operations in CNN-based Generative Network for Generalizable Deepfake Detection", - "authors": "Chuangchuang Tan, Yao Zhao, Shikui Wei, Guanghua Gu, Ping Liu, Yunchao Wei", + "authors": [ + { + "first_name": "Chuangchuang", + "last_name": "Tan" + }, + { + "first_name": "Yao", + "last_name": "Zhao" + }, + { + "first_name": "Shikui", + "last_name": "Wei" + }, + { + "first_name": "Guanghua", + "last_name": "Gu" + }, + { + "first_name": "Ping", + "last_name": "Liu" + }, + { + "first_name": "Yunchao", + "last_name": "Wei" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion Model", - "authors": "Xu He, Qiaochu Huang, Zhensong Zhang, Zhiwei Lin, Zhiyong Wu, Sicheng Yang, Minglei Li, Zhiyi Chen, Songcen Xu, Xiaofei Wu", + "authors": [ + { + "first_name": "Xu", + "last_name": "He" + }, + { + "first_name": "Qiaochu", + "last_name": "Huang" + }, + { + "first_name": "Zhensong", + "last_name": "Zhang" + }, + { + "first_name": "Zhiwei", + "last_name": "Lin" + }, + { + "first_name": "Zhiyong", + "last_name": "Wu" + }, + { + "first_name": "Sicheng", + "last_name": "Yang" + }, + { + "first_name": "Minglei", + "last_name": "Li" + }, + { + "first_name": "Zhiyi", + "last_name": "Chen" + }, + { + "first_name": "Songcen", + "last_name": "Xu" + }, + { + "first_name": "Xiaofei", + "last_name": "Wu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CDFormer: When Degradation Prediction Embraces Diffusion Model for Blind Image Super-Resolution", - "authors": "Qingguo Liu, Chenyi Zhuang, Pan Gao, Jie Qin", + "authors": [ + { + "first_name": "Qingguo", + "last_name": "Liu" + }, + { + "first_name": "Chenyi", + "last_name": "Zhuang" + }, + { + "first_name": "Pan", + "last_name": "Gao" + }, + { + "first_name": "Jie", + "last_name": "Qin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HumanRef: Single Image to 3D Human Generation via Reference-Guided Diffusion", - "authors": "Jingbo Zhang, Xiaoyu Li, Qi Zhang, Yanpei Cao, Ying Shan, Jing Liao", + "authors": [ + { + "first_name": "Jingbo", + "last_name": "Zhang" + }, + { + "first_name": "Xiaoyu", + "last_name": "Li" + }, + { + "first_name": "Qi", + "last_name": "Zhang" + }, + { + "first_name": "Yanpei", + "last_name": "Cao" + }, + { + "first_name": "Ying", + "last_name": "Shan" + }, + { + "first_name": "Jing", + "last_name": "Liao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GlitchBench: Can Large Multimodal Models Detect Video Game Glitches?", - "authors": "Mohammad Reza Taesiri, Tianjun Feng, Cor-Paul Bezemer, Anh Nguyen", + "authors": [ + { + "first_name": "Mohammad", + "last_name": "Reza Taesiri" + }, + { + "first_name": "Tianjun", + "last_name": "Feng" + }, + { + "first_name": "Cor-Paul", + "last_name": "Bezemer" + }, + { + "first_name": "Anh", + "last_name": "Nguyen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Rethinking Interactive Image Segmentation with Low Latency High Quality and Diverse Prompts", - "authors": "Qin Liu, Jaemin Cho, Mohit Bansal, Marc Niethammer", + "authors": [ + { + "first_name": "Qin", + "last_name": "Liu" + }, + { + "first_name": "Jaemin", + "last_name": "Cho" + }, + { + "first_name": "Mohit", + "last_name": "Bansal" + }, + { + "first_name": "Marc", + "last_name": "Niethammer" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ALGM: Adaptive Local-then-Global Token Merging for Efficient Semantic Segmentation with Plain Vision Transformers", - "authors": "Narges Norouzi, Svetlana Orlova, Daan de Geus, Gijs Dubbelman", + "authors": [ + { + "first_name": "Narges", + "last_name": "Norouzi" + }, + { + "first_name": "Svetlana", + "last_name": "Orlova" + }, + { + "first_name": "Daan", + "last_name": "de Geus" + }, + { + "first_name": "Gijs", + "last_name": "Dubbelman" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DITTO: Dual and Integrated Latent Topologies for Implicit 3D Reconstruction", - "authors": "Jaehyeok Shim, Kyungdon Joo", + "authors": [ + { + "first_name": "Jaehyeok", + "last_name": "Shim" + }, + { + "first_name": "Kyungdon", + "last_name": "Joo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Single-Model and Any-Modality for Video Object Tracking", - "authors": "Zongwei Wu, Jilai Zheng, Xiangxuan Ren, Florin-Alexandru Vasluianu, Chao Ma, Danda Pani Paudel, Luc Van Gool, Radu Timofte", + "authors": [ + { + "first_name": "Zongwei", + "last_name": "Wu" + }, + { + "first_name": "Jilai", + "last_name": "Zheng" + }, + { + "first_name": "Xiangxuan", + "last_name": "Ren" + }, + { + "first_name": "Florin-Alexandru", + "last_name": "Vasluianu" + }, + { + "first_name": "Chao", + "last_name": "Ma" + }, + { + "first_name": "Danda", + "last_name": "Pani Paudel" + }, + { + "first_name": "Luc", + "last_name": "Van Gool" + }, + { + "first_name": "Radu", + "last_name": "Timofte" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FlowTrack: Revisiting Optical Flow for Long-Range Dense Tracking", - "authors": "Seokju Cho, Jiahui Huang, Seungryong Kim, Joon-Young Lee", + "authors": [ + { + "first_name": "Seokju", + "last_name": "Cho" + }, + { + "first_name": "Jiahui", + "last_name": "Huang" + }, + { + "first_name": "Seungryong", + "last_name": "Kim" + }, + { + "first_name": "Joon-Young", + "last_name": "Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HIT: Estimating Internal Human Implicit Tissues from the Body Surface", - "authors": "Marilyn Keller, Vaibhav Arora, Abdelmouttaleb Dakri, Shivam Chandhok, Jürgen Machann, Andreas Fritsche, Michael J. Black, Sergi Pujades", + "authors": [ + { + "first_name": "Marilyn", + "last_name": "Keller" + }, + { + "first_name": "Vaibhav", + "last_name": "Arora" + }, + { + "first_name": "Abdelmouttaleb", + "last_name": "Dakri" + }, + { + "first_name": "Shivam", + "last_name": "Chandhok" + }, + { + "first_name": "Jürgen", + "last_name": "Machann" + }, + { + "first_name": "Andreas", + "last_name": "Fritsche" + }, + { + "first_name": "Michael", + "last_name": "J. Black" + }, + { + "first_name": "Sergi", + "last_name": "Pujades" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DanceCamera3D: 3D Camera Movement Synthesis with Music and Dance", - "authors": "Zixuan Wang, Jia Jia, Shikun Sun, Haozhe Wu, Rong Han, Zhenyu Li, Di Tang, Jiaqing Zhou, Jiebo Luo", + "authors": [ + { + "first_name": "Zixuan", + "last_name": "Wang" + }, + { + "first_name": "Jia", + "last_name": "Jia" + }, + { + "first_name": "Shikun", + "last_name": "Sun" + }, + { + "first_name": "Haozhe", + "last_name": "Wu" + }, + { + "first_name": "Rong", + "last_name": "Han" + }, + { + "first_name": "Zhenyu", + "last_name": "Li" + }, + { + "first_name": "Di", + "last_name": "Tang" + }, + { + "first_name": "Jiaqing", + "last_name": "Zhou" + }, + { + "first_name": "Jiebo", + "last_name": "Luo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Synthesize Diagnose and Optimize: Towards Fine-Grained Vision-Language Understanding", - "authors": "Wujian Peng, Sicheng Xie, Zuyao You, Shiyi Lan, Zuxuan Wu", + "authors": [ + { + "first_name": "Wujian", + "last_name": "Peng" + }, + { + "first_name": "Sicheng", + "last_name": "Xie" + }, + { + "first_name": "Zuyao", + "last_name": "You" + }, + { + "first_name": "Shiyi", + "last_name": "Lan" + }, + { + "first_name": "Zuxuan", + "last_name": "Wu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Density-guided Translator Boosts Synthetic-to-Real Unsupervised Domain Adaptive Segmentation of 3D Point Clouds", - "authors": "Zhimin Yuan, Wankang Zeng, Yanfei Su, Weiquan Liu, Ming Cheng, Yulan Guo, Cheng Wang", + "authors": [ + { + "first_name": "Zhimin", + "last_name": "Yuan" + }, + { + "first_name": "Wankang", + "last_name": "Zeng" + }, + { + "first_name": "Yanfei", + "last_name": "Su" + }, + { + "first_name": "Weiquan", + "last_name": "Liu" + }, + { + "first_name": "Ming", + "last_name": "Cheng" + }, + { + "first_name": "Yulan", + "last_name": "Guo" + }, + { + "first_name": "Cheng", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Cross Initialization for Face Personalization of Text-to-Image Models", - "authors": "Lianyu Pang, Jian Yin, Haoran Xie, Qiping Wang, Qing Li, Xudong Mao", + "authors": [ + { + "first_name": "Lianyu", + "last_name": "Pang" + }, + { + "first_name": "Jian", + "last_name": "Yin" + }, + { + "first_name": "Haoran", + "last_name": "Xie" + }, + { + "first_name": "Qiping", + "last_name": "Wang" + }, + { + "first_name": "Qing", + "last_name": "Li" + }, + { + "first_name": "Xudong", + "last_name": "Mao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LEDITS++: Limitless Image Editing using Text-to-Image Models", - "authors": "Manuel Brack, Felix Friedrich, Katharia Kornmeier, Linoy Tsaban, Patrick Schramowski, Kristian Kersting, Apolinario Passos", + "authors": [ + { + "first_name": "Manuel", + "last_name": "Brack" + }, + { + "first_name": "Felix", + "last_name": "Friedrich" + }, + { + "first_name": "Katharia", + "last_name": "Kornmeier" + }, + { + "first_name": "Linoy", + "last_name": "Tsaban" + }, + { + "first_name": "Patrick", + "last_name": "Schramowski" + }, + { + "first_name": "Kristian", + "last_name": "Kersting" + }, + { + "first_name": "Apolinario", + "last_name": "Passos" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Video Interpolation with Diffusion Models", - "authors": "Siddhant Jain, Daniel Watson, Eric Tabellion, Aleksander Ho?ynski, Ben Poole, Janne Kontkanen", + "authors": [ + { + "first_name": "Siddhant", + "last_name": "Jain" + }, + { + "first_name": "Daniel", + "last_name": "Watson" + }, + { + "first_name": "Eric", + "last_name": "Tabellion" + }, + { + "first_name": "Aleksander", + "last_name": "Ho?ynski" + }, + { + "first_name": "Ben", + "last_name": "Poole" + }, + { + "first_name": "Janne", + "last_name": "Kontkanen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "WildlifeMapper: Aerial Image Analysis for Multi-Species Detection and Identification", - "authors": "Satish Kumar, Bowen Zhang, Chandrakanth Gudavalli, Connor Levenson, Lacey Hughey, Jared A. Stabach, Irene Amoke, Gordon Ojwang, Joseph Mukeka, Stephen Mwiu, Joseph Ogutu, Howard Frederick, B.S. Manjunath", + "authors": [ + { + "first_name": "Satish", + "last_name": "Kumar" + }, + { + "first_name": "Bowen", + "last_name": "Zhang" + }, + { + "first_name": "Chandrakanth", + "last_name": "Gudavalli" + }, + { + "first_name": "Connor", + "last_name": "Levenson" + }, + { + "first_name": "Lacey", + "last_name": "Hughey" + }, + { + "first_name": "Jared", + "last_name": "A. Stabach" + }, + { + "first_name": "Irene", + "last_name": "Amoke" + }, + { + "first_name": "Gordon", + "last_name": "Ojwang" + }, + { + "first_name": "Joseph", + "last_name": "Mukeka" + }, + { + "first_name": "Stephen", + "last_name": "Mwiu" + }, + { + "first_name": "Joseph", + "last_name": "Ogutu" + }, + { + "first_name": "Howard", + "last_name": "Frederick" + }, + { + "first_name": "B.S.", + "last_name": "Manjunath" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning Adaptive Spatial Coherent Correlations for Speech-Preserving Facial Expression Manipulation", - "authors": "Tianshui Chen, Jianman Lin, Zhijing Yang, Chunmei Qing, Liang Lin", + "authors": [ + { + "first_name": "Tianshui", + "last_name": "Chen" + }, + { + "first_name": "Jianman", + "last_name": "Lin" + }, + { + "first_name": "Zhijing", + "last_name": "Yang" + }, + { + "first_name": "Chunmei", + "last_name": "Qing" + }, + { + "first_name": "Liang", + "last_name": "Lin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Tune-An-Ellipse: CLIP Has Potential to Find What You Want", - "authors": "Jinheng Xie, Songhe Deng, Bing Li, Haozhe Liu, Yawen Huang, Yefeng Zheng, Jurgen Schmidhuber, Bernard Ghanem, Linlin Shen, Mike Zheng Shou", + "authors": [ + { + "first_name": "Jinheng", + "last_name": "Xie" + }, + { + "first_name": "Songhe", + "last_name": "Deng" + }, + { + "first_name": "Bing", + "last_name": "Li" + }, + { + "first_name": "Haozhe", + "last_name": "Liu" + }, + { + "first_name": "Yawen", + "last_name": "Huang" + }, + { + "first_name": "Yefeng", + "last_name": "Zheng" + }, + { + "first_name": "Jurgen", + "last_name": "Schmidhuber" + }, + { + "first_name": "Bernard", + "last_name": "Ghanem" + }, + { + "first_name": "Linlin", + "last_name": "Shen" + }, + { + "first_name": "Mike", + "last_name": "Zheng Shou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Neural Spline Fields for Burst Image Fusion and Layer Separation", - "authors": "Ilya Chugunov, David Shustin, Ruyu Yan, Chenyang Lei, Felix Heide", + "authors": [ + { + "first_name": "Ilya", + "last_name": "Chugunov" + }, + { + "first_name": "David", + "last_name": "Shustin" + }, + { + "first_name": "Ruyu", + "last_name": "Yan" + }, + { + "first_name": "Chenyang", + "last_name": "Lei" + }, + { + "first_name": "Felix", + "last_name": "Heide" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion", - "authors": "Soyong Shin, Juyong Kim, Eni Halilaj, Michael J. Black", + "authors": [ + { + "first_name": "Soyong", + "last_name": "Shin" + }, + { + "first_name": "Juyong", + "last_name": "Kim" + }, + { + "first_name": "Eni", + "last_name": "Halilaj" + }, + { + "first_name": "Michael", + "last_name": "J. Black" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "NAPGuard: Towards Detecting Naturalistic Adversarial Patches", - "authors": "Siyang Wu, Jiakai Wang, Jiejie Zhao, Yazhe Wang, Xianglong Liu", + "authors": [ + { + "first_name": "Siyang", + "last_name": "Wu" + }, + { + "first_name": "Jiakai", + "last_name": "Wang" + }, + { + "first_name": "Jiejie", + "last_name": "Zhao" + }, + { + "first_name": "Yazhe", + "last_name": "Wang" + }, + { + "first_name": "Xianglong", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DiffPerformer: Iterative Learning of Consistent Latent Guidance for Diffusion-based Human Video Generation", - "authors": "Chenyang Wang, Zerong Zheng, Tao Yu, Xiaoqian Lv, Bineng Zhong, Shengping Zhang, Liqiang Nie", + "authors": [ + { + "first_name": "Chenyang", + "last_name": "Wang" + }, + { + "first_name": "Zerong", + "last_name": "Zheng" + }, + { + "first_name": "Tao", + "last_name": "Yu" + }, + { + "first_name": "Xiaoqian", + "last_name": "Lv" + }, + { + "first_name": "Bineng", + "last_name": "Zhong" + }, + { + "first_name": "Shengping", + "last_name": "Zhang" + }, + { + "first_name": "Liqiang", + "last_name": "Nie" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Unified Language-driven Zero-shot Domain Adaptation", - "authors": "Senqiao Yang, Zhuotao Tian, Li Jiang, Jiaya Jia", + "authors": [ + { + "first_name": "Senqiao", + "last_name": "Yang" + }, + { + "first_name": "Zhuotao", + "last_name": "Tian" + }, + { + "first_name": "Li", + "last_name": "Jiang" + }, + { + "first_name": "Jiaya", + "last_name": "Jia" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Category-Level Multi-Part Multi-Joint 3D Shape Assembly", - "authors": "Yichen Li, Kaichun Mo, Yueqi Duan, He Wang, Jiequan Zhang, Lin Shao", + "authors": [ + { + "first_name": "Yichen", + "last_name": "Li" + }, + { + "first_name": "Kaichun", + "last_name": "Mo" + }, + { + "first_name": "Yueqi", + "last_name": "Duan" + }, + { + "first_name": "He", + "last_name": "Wang" + }, + { + "first_name": "Jiequan", + "last_name": "Zhang" + }, + { + "first_name": "Lin", + "last_name": "Shao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Equivariant Multi-Modality Image Fusion", - "authors": "Zixiang Zhao, Haowen Bai, Jiangshe Zhang, Yulun Zhang, Kai Zhang, Shuang Xu, Dongdong Chen, Radu Timofte, Luc Van Gool", + "authors": [ + { + "first_name": "Zixiang", + "last_name": "Zhao" + }, + { + "first_name": "Haowen", + "last_name": "Bai" + }, + { + "first_name": "Jiangshe", + "last_name": "Zhang" + }, + { + "first_name": "Yulun", + "last_name": "Zhang" + }, + { + "first_name": "Kai", + "last_name": "Zhang" + }, + { + "first_name": "Shuang", + "last_name": "Xu" + }, + { + "first_name": "Dongdong", + "last_name": "Chen" + }, + { + "first_name": "Radu", + "last_name": "Timofte" + }, + { + "first_name": "Luc", + "last_name": "Van Gool" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "NeLF-Pro: Neural Light Field Probes for Multi-Scale Novel View Synthesis", - "authors": "Zinuo You, Andreas Geiger, Anpei Chen", + "authors": [ + { + "first_name": "Zinuo", + "last_name": "You" + }, + { + "first_name": "Andreas", + "last_name": "Geiger" + }, + { + "first_name": "Anpei", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "One-Shot Open Affordance Learning with Foundation Models", - "authors": "Gen Li, Deqing Sun, Laura Sevilla-Lara, Varun Jampani", + "authors": [ + { + "first_name": "Gen", + "last_name": "Li" + }, + { + "first_name": "Deqing", + "last_name": "Sun" + }, + { + "first_name": "Laura", + "last_name": "Sevilla-Lara" + }, + { + "first_name": "Varun", + "last_name": "Jampani" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Don't Look into the Dark: Latent Codes for Pluralistic Image Inpainting", - "authors": "Haiwei Chen, Yajie Zhao", + "authors": [ + { + "first_name": "Haiwei", + "last_name": "Chen" + }, + { + "first_name": "Yajie", + "last_name": "Zhao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Incremental Nuclei Segmentation from Histopathological Images via Future-class Awareness and Compatibility-inspired Distillation", - "authors": "Huyong Wang, Huisi Wu, Jing Qin", + "authors": [ + { + "first_name": "Huyong", + "last_name": "Wang" + }, + { + "first_name": "Huisi", + "last_name": "Wu" + }, + { + "first_name": "Jing", + "last_name": "Qin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DiffEditor: Boosting Accuracy and Flexibility on Diffusion-based Image Editing", - "authors": "Chong Mou, Xintao Wang, Jiechong Song, Ying Shan, Jian Zhang", + "authors": [ + { + "first_name": "Chong", + "last_name": "Mou" + }, + { + "first_name": "Xintao", + "last_name": "Wang" + }, + { + "first_name": "Jiechong", + "last_name": "Song" + }, + { + "first_name": "Ying", + "last_name": "Shan" + }, + { + "first_name": "Jian", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Solving Masked Jigsaw Puzzles with Diffusion Vision Transformers", - "authors": "Jinyang Liu, Wondmgezahu Teshome, Sandesh Ghimire, Mario Sznaier, Octavia Camps", + "authors": [ + { + "first_name": "Jinyang", + "last_name": "Liu" + }, + { + "first_name": "Wondmgezahu", + "last_name": "Teshome" + }, + { + "first_name": "Sandesh", + "last_name": "Ghimire" + }, + { + "first_name": "Mario", + "last_name": "Sznaier" + }, + { + "first_name": "Octavia", + "last_name": "Camps" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "InstructVideo: Instructing Video Diffusion Models with Human Feedback", - "authors": "Hangjie Yuan, Shiwei Zhang, Xiang Wang, Yujie Wei, Tao Feng, Yining Pan, Yingya Zhang, Ziwei Liu, Samuel Albanie, Dong Ni", + "authors": [ + { + "first_name": "Hangjie", + "last_name": "Yuan" + }, + { + "first_name": "Shiwei", + "last_name": "Zhang" + }, + { + "first_name": "Xiang", + "last_name": "Wang" + }, + { + "first_name": "Yujie", + "last_name": "Wei" + }, + { + "first_name": "Tao", + "last_name": "Feng" + }, + { + "first_name": "Yining", + "last_name": "Pan" + }, + { + "first_name": "Yingya", + "last_name": "Zhang" + }, + { + "first_name": "Ziwei", + "last_name": "Liu" + }, + { + "first_name": "Samuel", + "last_name": "Albanie" + }, + { + "first_name": "Dong", + "last_name": "Ni" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Fully Exploiting Every Real Sample: SuperPixel Sample Gradient Model Stealing", - "authors": "Yunlong Zhao, Xiaoheng Deng, Yijing Liu, Xinjun Pei, Jiazhi Xia, Wei Chen", + "authors": [ + { + "first_name": "Yunlong", + "last_name": "Zhao" + }, + { + "first_name": "Xiaoheng", + "last_name": "Deng" + }, + { + "first_name": "Yijing", + "last_name": "Liu" + }, + { + "first_name": "Xinjun", + "last_name": "Pei" + }, + { + "first_name": "Jiazhi", + "last_name": "Xia" + }, + { + "first_name": "Wei", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Progressive Divide-and-Conquer via Subsampling Decomposition for Accelerated MRI", - "authors": "Chong Wang, Lanqing Guo, Yufei Wang, Hao Cheng, Yi Yu, Bihan Wen", + "authors": [ + { + "first_name": "Chong", + "last_name": "Wang" + }, + { + "first_name": "Lanqing", + "last_name": "Guo" + }, + { + "first_name": "Yufei", + "last_name": "Wang" + }, + { + "first_name": "Hao", + "last_name": "Cheng" + }, + { + "first_name": "Yi", + "last_name": "Yu" + }, + { + "first_name": "Bihan", + "last_name": "Wen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DiffMOT: A Real-time Diffusion-based Multiple Object Tracker with Non-linear Prediction", - "authors": "Weiyi Lv, Yuhang Huang, Ning Zhang, Ruei-Sung Lin, Mei Han, Dan Zeng", + "authors": [ + { + "first_name": "Weiyi", + "last_name": "Lv" + }, + { + "first_name": "Yuhang", + "last_name": "Huang" + }, + { + "first_name": "Ning", + "last_name": "Zhang" + }, + { + "first_name": "Ruei-Sung", + "last_name": "Lin" + }, + { + "first_name": "Mei", + "last_name": "Han" + }, + { + "first_name": "Dan", + "last_name": "Zeng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MV-Adapter: Multimodal Video Transfer Learning for Video Text Retrieval", - "authors": "Xiaojie Jin, Bowen Zhang, Weibo Gong, Kai Xu, Xueqing Deng, Peng Wang, Zhao Zhang, Xiaohui Shen, Jiashi Feng", + "authors": [ + { + "first_name": "Xiaojie", + "last_name": "Jin" + }, + { + "first_name": "Bowen", + "last_name": "Zhang" + }, + { + "first_name": "Weibo", + "last_name": "Gong" + }, + { + "first_name": "Kai", + "last_name": "Xu" + }, + { + "first_name": "Xueqing", + "last_name": "Deng" + }, + { + "first_name": "Peng", + "last_name": "Wang" + }, + { + "first_name": "Zhao", + "last_name": "Zhang" + }, + { + "first_name": "Xiaohui", + "last_name": "Shen" + }, + { + "first_name": "Jiashi", + "last_name": "Feng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Rethinking Multi-view Representation Learning via Distilled Disentangling", - "authors": "Guanzhou Ke, Bo Wang, Xiaoli Wang, Shengfeng He", + "authors": [ + { + "first_name": "Guanzhou", + "last_name": "Ke" + }, + { + "first_name": "Bo", + "last_name": "Wang" + }, + { + "first_name": "Xiaoli", + "last_name": "Wang" + }, + { + "first_name": "Shengfeng", + "last_name": "He" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Just Add π! Pose Induced Video Transformers for Understanding Activities of Daily Living", - "authors": "Dominick Reilly, Srijan Das", + "authors": [ + { + "first_name": "Dominick", + "last_name": "Reilly" + }, + { + "first_name": "Srijan", + "last_name": "Das" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ViLa-MIL: Dual-scale Vision-Language Multiple Instance Learning for Whole Slide Image Classification", - "authors": "Jiangbo Shi, Chen Li, Tieliang Gong, Yefeng Zheng, Huazhu Fu", + "authors": [ + { + "first_name": "Jiangbo", + "last_name": "Shi" + }, + { + "first_name": "Chen", + "last_name": "Li" + }, + { + "first_name": "Tieliang", + "last_name": "Gong" + }, + { + "first_name": "Yefeng", + "last_name": "Zheng" + }, + { + "first_name": "Huazhu", + "last_name": "Fu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Targeted Representation Alignment for Open-World Semi-Supervised Learning", - "authors": "Ruixuan Xiao, Lei Feng, Kai Tang, Junbo Zhao, Yixuan Li, Gang Chen, Haobo Wang", + "authors": [ + { + "first_name": "Ruixuan", + "last_name": "Xiao" + }, + { + "first_name": "Lei", + "last_name": "Feng" + }, + { + "first_name": "Kai", + "last_name": "Tang" + }, + { + "first_name": "Junbo", + "last_name": "Zhao" + }, + { + "first_name": "Yixuan", + "last_name": "Li" + }, + { + "first_name": "Gang", + "last_name": "Chen" + }, + { + "first_name": "Haobo", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Efficient Solution of Point-Line Absolute Pose", - "authors": "Petr Hruby, Timothy Duff, Marc Pollefeys", + "authors": [ + { + "first_name": "Petr", + "last_name": "Hruby" + }, + { + "first_name": "Timothy", + "last_name": "Duff" + }, + { + "first_name": "Marc", + "last_name": "Pollefeys" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Text-to-3D using Gaussian Splatting", - "authors": "Zilong Chen, Feng Wang, Yikai Wang, Huaping Liu", + "authors": [ + { + "first_name": "Zilong", + "last_name": "Chen" + }, + { + "first_name": "Feng", + "last_name": "Wang" + }, + { + "first_name": "Yikai", + "last_name": "Wang" + }, + { + "first_name": "Huaping", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CapsFusion: Rethinking Image-Text Data at Scale", - "authors": "Qiying Yu, Quan Sun, Xiaosong Zhang, Yufeng Cui, Fan Zhang, Yue Cao, Xinlong Wang, Jingjing Liu", + "authors": [ + { + "first_name": "Qiying", + "last_name": "Yu" + }, + { + "first_name": "Quan", + "last_name": "Sun" + }, + { + "first_name": "Xiaosong", + "last_name": "Zhang" + }, + { + "first_name": "Yufeng", + "last_name": "Cui" + }, + { + "first_name": "Fan", + "last_name": "Zhang" + }, + { + "first_name": "Yue", + "last_name": "Cao" + }, + { + "first_name": "Xinlong", + "last_name": "Wang" + }, + { + "first_name": "Jingjing", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "On the Content Bias in Frechet Video Distance", - "authors": "Songwei Ge, Aniruddha Mahapatra, Gaurav Parmar, Jun-Yan Zhu, Jia-Bin Huang", + "authors": [ + { + "first_name": "Songwei", + "last_name": "Ge" + }, + { + "first_name": "Aniruddha", + "last_name": "Mahapatra" + }, + { + "first_name": "Gaurav", + "last_name": "Parmar" + }, + { + "first_name": "Jun-Yan", + "last_name": "Zhu" + }, + { + "first_name": "Jia-Bin", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Tumor Micro-environment Interactions Guided Graph Learning for Survival Analysis of Human Cancers from Whole-slide Pathological Images", - "authors": "Wei Shao, YangYang Shi, Daoqiang Zhang, JunJie Zhou, Peng Wan", + "authors": [ + { + "first_name": "Wei", + "last_name": "Shao" + }, + { + "first_name": "YangYang", + "last_name": "Shi" + }, + { + "first_name": "Daoqiang", + "last_name": "Zhang" + }, + { + "first_name": "JunJie", + "last_name": "Zhou" + }, + { + "first_name": "Peng", + "last_name": "Wan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards Generalizable Multi-Object Tracking", - "authors": "Zheng Qin, Le Wang, Sanping Zhou, Panpan Fu, Gang Hua, Wei Tang", + "authors": [ + { + "first_name": "Zheng", + "last_name": "Qin" + }, + { + "first_name": "Le", + "last_name": "Wang" + }, + { + "first_name": "Sanping", + "last_name": "Zhou" + }, + { + "first_name": "Panpan", + "last_name": "Fu" + }, + { + "first_name": "Gang", + "last_name": "Hua" + }, + { + "first_name": "Wei", + "last_name": "Tang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "POPDG: Popular 3D Dance Generation with PopDanceSet", - "authors": "Zhenye Luo, Min Ren, Xuecai Hu, Yongzhen Huang, Li Yao", + "authors": [ + { + "first_name": "Zhenye", + "last_name": "Luo" + }, + { + "first_name": "Min", + "last_name": "Ren" + }, + { + "first_name": "Xuecai", + "last_name": "Hu" + }, + { + "first_name": "Yongzhen", + "last_name": "Huang" + }, + { + "first_name": "Li", + "last_name": "Yao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Image Neural Field Diffusion Models", - "authors": "Yinbo Chen, Oliver Wang, Richard Zhang, Eli Shechtman, Xiaolong Wang, Michael Gharbi", + "authors": [ + { + "first_name": "Yinbo", + "last_name": "Chen" + }, + { + "first_name": "Oliver", + "last_name": "Wang" + }, + { + "first_name": "Richard", + "last_name": "Zhang" + }, + { + "first_name": "Eli", + "last_name": "Shechtman" + }, + { + "first_name": "Xiaolong", + "last_name": "Wang" + }, + { + "first_name": "Michael", + "last_name": "Gharbi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Discriminative Probing and Tuning for Text-to-Image Generation", - "authors": "Leigang Qu, Wenjie Wang, Yongqi Li, Hanwang Zhang, Liqiang Nie, Tat-Seng Chua", + "authors": [ + { + "first_name": "Leigang", + "last_name": "Qu" + }, + { + "first_name": "Wenjie", + "last_name": "Wang" + }, + { + "first_name": "Yongqi", + "last_name": "Li" + }, + { + "first_name": "Hanwang", + "last_name": "Zhang" + }, + { + "first_name": "Liqiang", + "last_name": "Nie" + }, + { + "first_name": "Tat-Seng", + "last_name": "Chua" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Slice3D: Multi-Slice Occlusion-Revealing Single View 3D Reconstruction", - "authors": "Yizhi Wang, Wallace Lira, Wenqi Wang, Ali Mahdavi-Amiri, Hao Zhang", + "authors": [ + { + "first_name": "Yizhi", + "last_name": "Wang" + }, + { + "first_name": "Wallace", + "last_name": "Lira" + }, + { + "first_name": "Wenqi", + "last_name": "Wang" + }, + { + "first_name": "Ali", + "last_name": "Mahdavi-Amiri" + }, + { + "first_name": "Hao", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards More Accurate Diffusion Model Acceleration with A Timestep Tuner", - "authors": "Mengfei Xia, Yujun Shen, Changsong Lei, Yu Zhou, Deli Zhao, Ran Yi, Wenping Wang, Yong-Jin Liu", + "authors": [ + { + "first_name": "Mengfei", + "last_name": "Xia" + }, + { + "first_name": "Yujun", + "last_name": "Shen" + }, + { + "first_name": "Changsong", + "last_name": "Lei" + }, + { + "first_name": "Yu", + "last_name": "Zhou" + }, + { + "first_name": "Deli", + "last_name": "Zhao" + }, + { + "first_name": "Ran", + "last_name": "Yi" + }, + { + "first_name": "Wenping", + "last_name": "Wang" + }, + { + "first_name": "Yong-Jin", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Rethinking Generalizable Face Anti-spoofing via Hierarchical Prototype-guided Distribution Refinement in Hyperbolic Space", - "authors": "Chengyang Hu, Ke-Yue Zhang, Taiping Yao, Shouhong Ding, Lizhuang Ma", + "authors": [ + { + "first_name": "Chengyang", + "last_name": "Hu" + }, + { + "first_name": "Ke-Yue", + "last_name": "Zhang" + }, + { + "first_name": "Taiping", + "last_name": "Yao" + }, + { + "first_name": "Shouhong", + "last_name": "Ding" + }, + { + "first_name": "Lizhuang", + "last_name": "Ma" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "IIRP-Net: Iterative Inference Residual Pyramid Network for Enhanced Image Registration", - "authors": "Tai Ma, Suwei Zhang, Jiafeng Li, Ying Wen", + "authors": [ + { + "first_name": "Tai", + "last_name": "Ma" + }, + { + "first_name": "Suwei", + "last_name": "Zhang" + }, + { + "first_name": "Jiafeng", + "last_name": "Li" + }, + { + "first_name": "Ying", + "last_name": "Wen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning without Exact Guidance: Updating Large-scale High-resolution Land Cover Maps from Low-resolution Historical Labels", - "authors": "Zhuohong Li, Wei He, Jiepan Li, Fangxiao Lu, Hongyan Zhang", + "authors": [ + { + "first_name": "Zhuohong", + "last_name": "Li" + }, + { + "first_name": "Wei", + "last_name": "He" + }, + { + "first_name": "Jiepan", + "last_name": "Li" + }, + { + "first_name": "Fangxiao", + "last_name": "Lu" + }, + { + "first_name": "Hongyan", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GenesisTex: Adapting Image Denoising Diffusion to Texture Space", - "authors": "Chenjian Gao, Boyan Jiang, Xinghui Li, Yingpeng Zhang, Qian Yu", + "authors": [ + { + "first_name": "Chenjian", + "last_name": "Gao" + }, + { + "first_name": "Boyan", + "last_name": "Jiang" + }, + { + "first_name": "Xinghui", + "last_name": "Li" + }, + { + "first_name": "Yingpeng", + "last_name": "Zhang" + }, + { + "first_name": "Qian", + "last_name": "Yu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "TTA-EVF: Test-Time Adaptation for Event-based Video Frame Interpolation via Reliable Pixel and Sample Estimation", - "authors": "Hoonhee Cho, Taewoo Kim, Yuhwan Jeong, Kuk-Jin Yoon", + "authors": [ + { + "first_name": "Hoonhee", + "last_name": "Cho" + }, + { + "first_name": "Taewoo", + "last_name": "Kim" + }, + { + "first_name": "Yuhwan", + "last_name": "Jeong" + }, + { + "first_name": "Kuk-Jin", + "last_name": "Yoon" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Image-to-Image Matching via Foundation Models: A New Perspective for Open-Vocabulary Semantic Segmentation", - "authors": "Yuan Wang, Rui Sun, Naisong Luo, Yuwen Pan, Tianzhu Zhang", + "authors": [ + { + "first_name": "Yuan", + "last_name": "Wang" + }, + { + "first_name": "Rui", + "last_name": "Sun" + }, + { + "first_name": "Naisong", + "last_name": "Luo" + }, + { + "first_name": "Yuwen", + "last_name": "Pan" + }, + { + "first_name": "Tianzhu", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "BigGait: Learning Gait Representation You Want by Large Vision Models", - "authors": "Dingqiang Ye, Chao Fan, Jingzhe Ma, Xiaoming Liu, Shiqi Yu", + "authors": [ + { + "first_name": "Dingqiang", + "last_name": "Ye" + }, + { + "first_name": "Chao", + "last_name": "Fan" + }, + { + "first_name": "Jingzhe", + "last_name": "Ma" + }, + { + "first_name": "Xiaoming", + "last_name": "Liu" + }, + { + "first_name": "Shiqi", + "last_name": "Yu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "BEVNeXt: Reviving Dense BEV Frameworks for 3D Object Detection", - "authors": "Zhenxin Li, Shiyi Lan, Jose M. Alvarez, Zuxuan Wu", + "authors": [ + { + "first_name": "Zhenxin", + "last_name": "Li" + }, + { + "first_name": "Shiyi", + "last_name": "Lan" + }, + { + "first_name": "Jose", + "last_name": "M. Alvarez" + }, + { + "first_name": "Zuxuan", + "last_name": "Wu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SNIFFER: Multimodal Large Language Model for Explainable Out-of-Context Misinformation Detection", - "authors": "Peng Qi, Zehong Yan, Wynne Hsu, Mong Li Lee", + "authors": [ + { + "first_name": "Peng", + "last_name": "Qi" + }, + { + "first_name": "Zehong", + "last_name": "Yan" + }, + { + "first_name": "Wynne", + "last_name": "Hsu" + }, + { + "first_name": "Mong", + "last_name": "Li Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Beyond Seen Primitive Concepts and Attribute-Object Compositional Learning", - "authors": "Nirat Saini, Khoi Pham, Abhinav Shrivastava", + "authors": [ + { + "first_name": "Nirat", + "last_name": "Saini" + }, + { + "first_name": "Khoi", + "last_name": "Pham" + }, + { + "first_name": "Abhinav", + "last_name": "Shrivastava" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Unleashing Network Potentials for Semantic Scene Completion", - "authors": "Fengyun Wang, Qianru Sun, Dong Zhang, Jinhui Tang", + "authors": [ + { + "first_name": "Fengyun", + "last_name": "Wang" + }, + { + "first_name": "Qianru", + "last_name": "Sun" + }, + { + "first_name": "Dong", + "last_name": "Zhang" + }, + { + "first_name": "Jinhui", + "last_name": "Tang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HOIST-Former: Hand-held Objects Identification Segmentation and Tracking in the Wild", - "authors": "Supreeth Narasimhaswamy, Huy Anh Nguyen, Lihan Huang, Minh Hoai", + "authors": [ + { + "first_name": "Supreeth", + "last_name": "Narasimhaswamy" + }, + { + "first_name": "Huy", + "last_name": "Anh Nguyen" + }, + { + "first_name": "Lihan", + "last_name": "Huang" + }, + { + "first_name": "Minh", + "last_name": "Hoai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Contextrast: Contextual Contrastive Learning for Semantic Segmentation", - "authors": "Changki Sung, Wanhee Kim, Jungho An, Wooju Lee, Hyungtae Lim, Hyun Myung", + "authors": [ + { + "first_name": "Changki", + "last_name": "Sung" + }, + { + "first_name": "Wanhee", + "last_name": "Kim" + }, + { + "first_name": "Jungho", + "last_name": "An" + }, + { + "first_name": "Wooju", + "last_name": "Lee" + }, + { + "first_name": "Hyungtae", + "last_name": "Lim" + }, + { + "first_name": "Hyun", + "last_name": "Myung" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning Occupancy for Monocular 3D Object Detection", - "authors": "Liang Peng, Junkai Xu, Haoran Cheng, Zheng Yang, Xiaopei Wu, Wei Qian, Wenxiao Wang, Boxi Wu, Deng Cai", + "authors": [ + { + "first_name": "Liang", + "last_name": "Peng" + }, + { + "first_name": "Junkai", + "last_name": "Xu" + }, + { + "first_name": "Haoran", + "last_name": "Cheng" + }, + { + "first_name": "Zheng", + "last_name": "Yang" + }, + { + "first_name": "Xiaopei", + "last_name": "Wu" + }, + { + "first_name": "Wei", + "last_name": "Qian" + }, + { + "first_name": "Wenxiao", + "last_name": "Wang" + }, + { + "first_name": "Boxi", + "last_name": "Wu" + }, + { + "first_name": "Deng", + "last_name": "Cai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LAA-Net: Localized Artifact Attention Network for Quality-Agnostic and Generalizable Deepfake Detection", - "authors": "Dat Nguyen, Nesryne Mejri, Inder Pal Singh, Polina Kuleshova, Marcella Astrid, Anis Kacem, Enjie Ghorbel, Djamila Aouada", + "authors": [ + { + "first_name": "Dat", + "last_name": "Nguyen" + }, + { + "first_name": "Nesryne", + "last_name": "Mejri" + }, + { + "first_name": "Inder", + "last_name": "Pal Singh" + }, + { + "first_name": "Polina", + "last_name": "Kuleshova" + }, + { + "first_name": "Marcella", + "last_name": "Astrid" + }, + { + "first_name": "Anis", + "last_name": "Kacem" + }, + { + "first_name": "Enjie", + "last_name": "Ghorbel" + }, + { + "first_name": "Djamila", + "last_name": "Aouada" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LEAD: Learning Decomposition for Source-free Universal Domain Adaptation", - "authors": "Sanqing Qu, Tianpei Zou, Lianghua He, Florian Röhrbein, Alois Knoll, Guang Chen, Changjun Jiang", + "authors": [ + { + "first_name": "Sanqing", + "last_name": "Qu" + }, + { + "first_name": "Tianpei", + "last_name": "Zou" + }, + { + "first_name": "Lianghua", + "last_name": "He" + }, + { + "first_name": "Florian", + "last_name": "Röhrbein" + }, + { + "first_name": "Alois", + "last_name": "Knoll" + }, + { + "first_name": "Guang", + "last_name": "Chen" + }, + { + "first_name": "Changjun", + "last_name": "Jiang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "AUEditNet: Dual-Branch Facial Action Unit Intensity Manipulation with Implicit Disentanglement", - "authors": "Shiwei Jin, Zhen Wang, Lei Wang, Peng Liu, Ning Bi, Truong Nguyen", + "authors": [ + { + "first_name": "Shiwei", + "last_name": "Jin" + }, + { + "first_name": "Zhen", + "last_name": "Wang" + }, + { + "first_name": "Lei", + "last_name": "Wang" + }, + { + "first_name": "Peng", + "last_name": "Liu" + }, + { + "first_name": "Ning", + "last_name": "Bi" + }, + { + "first_name": "Truong", + "last_name": "Nguyen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "BodyMAP - Jointly Predicting Body Mesh and 3D Applied Pressure Map for People in Bed", - "authors": "Abhishek Tandon, Anujraaj Goyal, Henry M. Clever, Zackory Erickson", + "authors": [ + { + "first_name": "Abhishek", + "last_name": "Tandon" + }, + { + "first_name": "Anujraaj", + "last_name": "Goyal" + }, + { + "first_name": "Henry", + "last_name": "M. Clever" + }, + { + "first_name": "Zackory", + "last_name": "Erickson" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "OneLLM: One Framework to Align All Modalities with Language", - "authors": "Jiaming Han, Kaixiong Gong, Yiyuan Zhang, Jiaqi Wang, Kaipeng Zhang, Dahua Lin, Yu Qiao, Peng Gao, Xiangyu Yue", + "authors": [ + { + "first_name": "Jiaming", + "last_name": "Han" + }, + { + "first_name": "Kaixiong", + "last_name": "Gong" + }, + { + "first_name": "Yiyuan", + "last_name": "Zhang" + }, + { + "first_name": "Jiaqi", + "last_name": "Wang" + }, + { + "first_name": "Kaipeng", + "last_name": "Zhang" + }, + { + "first_name": "Dahua", + "last_name": "Lin" + }, + { + "first_name": "Yu", + "last_name": "Qiao" + }, + { + "first_name": "Peng", + "last_name": "Gao" + }, + { + "first_name": "Xiangyu", + "last_name": "Yue" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PAD: Patch-Agnostic Defense against Adversarial Patch Attacks", - "authors": "Lihua Jing, Rui Wang, Wenqi Ren, Xin Dong, Cong Zou", + "authors": [ + { + "first_name": "Lihua", + "last_name": "Jing" + }, + { + "first_name": "Rui", + "last_name": "Wang" + }, + { + "first_name": "Wenqi", + "last_name": "Ren" + }, + { + "first_name": "Xin", + "last_name": "Dong" + }, + { + "first_name": "Cong", + "last_name": "Zou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MULAN: A Multi Layer Annotated Dataset for Controllable Text-to-Image Generation", - "authors": "Petru-Daniel Tudosiu, Yongxin Yang, Shifeng Zhang, Fei Chen, Steven McDonagh, Gerasimos Lampouras, Ignacio Iacobacci, Sarah Parisot", + "authors": [ + { + "first_name": "Petru-Daniel", + "last_name": "Tudosiu" + }, + { + "first_name": "Yongxin", + "last_name": "Yang" + }, + { + "first_name": "Shifeng", + "last_name": "Zhang" + }, + { + "first_name": "Fei", + "last_name": "Chen" + }, + { + "first_name": "Steven", + "last_name": "McDonagh" + }, + { + "first_name": "Gerasimos", + "last_name": "Lampouras" + }, + { + "first_name": "Ignacio", + "last_name": "Iacobacci" + }, + { + "first_name": "Sarah", + "last_name": "Parisot" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Rotation-Agnostic Image Representation Learning for Digital Pathology", - "authors": "Saghir Alfasly, Abubakr Shafique, Peyman Nejat, Jibran Khan, Areej Alsaafin, Ghazal Alabtah, H.R. Tizhoosh", + "authors": [ + { + "first_name": "Saghir", + "last_name": "Alfasly" + }, + { + "first_name": "Abubakr", + "last_name": "Shafique" + }, + { + "first_name": "Peyman", + "last_name": "Nejat" + }, + { + "first_name": "Jibran", + "last_name": "Khan" + }, + { + "first_name": "Areej", + "last_name": "Alsaafin" + }, + { + "first_name": "Ghazal", + "last_name": "Alabtah" + }, + { + "first_name": "H.R.", + "last_name": "Tizhoosh" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Unbiased Faster R-CNN for Single-source Domain Generalized Object Detection", - "authors": "Yajing Liu, Shijun Zhou, Xiyao Liu, Chunhui Hao, Baojie Fan, Jiandong Tian", + "authors": [ + { + "first_name": "Yajing", + "last_name": "Liu" + }, + { + "first_name": "Shijun", + "last_name": "Zhou" + }, + { + "first_name": "Xiyao", + "last_name": "Liu" + }, + { + "first_name": "Chunhui", + "last_name": "Hao" + }, + { + "first_name": "Baojie", + "last_name": "Fan" + }, + { + "first_name": "Jiandong", + "last_name": "Tian" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Super-Resolution Reconstruction from Bayer-Pattern Spike Streams", - "authors": "Yanchen Dong, Ruiqin Xiong, Jian Zhang, Zhaofei Yu, Xiaopeng Fan, Shuyuan Zhu, Tiejun Huang", + "authors": [ + { + "first_name": "Yanchen", + "last_name": "Dong" + }, + { + "first_name": "Ruiqin", + "last_name": "Xiong" + }, + { + "first_name": "Jian", + "last_name": "Zhang" + }, + { + "first_name": "Zhaofei", + "last_name": "Yu" + }, + { + "first_name": "Xiaopeng", + "last_name": "Fan" + }, + { + "first_name": "Shuyuan", + "last_name": "Zhu" + }, + { + "first_name": "Tiejun", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "EASE-DETR: Easing the Competition among Object Queries", - "authors": "Yulu Gao, Yifan Sun, Xudong Ding, Chuyang Zhao, Si Liu", + "authors": [ + { + "first_name": "Yulu", + "last_name": "Gao" + }, + { + "first_name": "Yifan", + "last_name": "Sun" + }, + { + "first_name": "Xudong", + "last_name": "Ding" + }, + { + "first_name": "Chuyang", + "last_name": "Zhao" + }, + { + "first_name": "Si", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "KPConvX: Modernizing Kernel Point Convolution with Kernel Attention", - "authors": "Hugues Thomas, Yao-Hung Hubert Tsai, Timothy D. Barfoot, Jian Zhang", + "authors": [ + { + "first_name": "Hugues", + "last_name": "Thomas" + }, + { + "first_name": "Yao-Hung", + "last_name": "Hubert Tsai" + }, + { + "first_name": "Timothy", + "last_name": "D. Barfoot" + }, + { + "first_name": "Jian", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Clockwork Diffusion: Efficient Generation With Model-Step Distillation", - "authors": "Amirhossein Habibian, Amir Ghodrati, Noor Fathima, Guillaume Sautiere, Risheek Garrepalli, Fatih Porikli, Jens Petersen", + "authors": [ + { + "first_name": "Amirhossein", + "last_name": "Habibian" + }, + { + "first_name": "Amir", + "last_name": "Ghodrati" + }, + { + "first_name": "Noor", + "last_name": "Fathima" + }, + { + "first_name": "Guillaume", + "last_name": "Sautiere" + }, + { + "first_name": "Risheek", + "last_name": "Garrepalli" + }, + { + "first_name": "Fatih", + "last_name": "Porikli" + }, + { + "first_name": "Jens", + "last_name": "Petersen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Pick-or-Mix: Dynamic Channel Sampling for ConvNets", - "authors": "Ashish Kumar, Daneul Kim, Jaesik Park, Laxmidhar Behera", + "authors": [ + { + "first_name": "Ashish", + "last_name": "Kumar" + }, + { + "first_name": "Daneul", + "last_name": "Kim" + }, + { + "first_name": "Jaesik", + "last_name": "Park" + }, + { + "first_name": "Laxmidhar", + "last_name": "Behera" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generation", - "authors": "Hang Li, Chengzhi Shen, Philip Torr, Volker Tresp, Jindong Gu", + "authors": [ + { + "first_name": "Hang", + "last_name": "Li" + }, + { + "first_name": "Chengzhi", + "last_name": "Shen" + }, + { + "first_name": "Philip", + "last_name": "Torr" + }, + { + "first_name": "Volker", + "last_name": "Tresp" + }, + { + "first_name": "Jindong", + "last_name": "Gu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HiLo: Detailed and Robust 3D Clothed Human Reconstruction with High-and Low-Frequency Information of Parametric Models", - "authors": "Yifan Yang, Dong Liu, Shuhai Zhang, Zeshuai Deng, Zixiong Huang, Mingkui Tan", + "authors": [ + { + "first_name": "Yifan", + "last_name": "Yang" + }, + { + "first_name": "Dong", + "last_name": "Liu" + }, + { + "first_name": "Shuhai", + "last_name": "Zhang" + }, + { + "first_name": "Zeshuai", + "last_name": "Deng" + }, + { + "first_name": "Zixiong", + "last_name": "Huang" + }, + { + "first_name": "Mingkui", + "last_name": "Tan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Promptable Behaviors: Personalizing Multi-Objective Rewards from Human Preferences", - "authors": "Minyoung Hwang, Luca Weihs, Chanwoo Park, Kimin Lee, Aniruddha Kembhavi, Kiana Ehsani", + "authors": [ + { + "first_name": "Minyoung", + "last_name": "Hwang" + }, + { + "first_name": "Luca", + "last_name": "Weihs" + }, + { + "first_name": "Chanwoo", + "last_name": "Park" + }, + { + "first_name": "Kimin", + "last_name": "Lee" + }, + { + "first_name": "Aniruddha", + "last_name": "Kembhavi" + }, + { + "first_name": "Kiana", + "last_name": "Ehsani" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Stationary Representations: Optimally Approximating Compatibility and Implications for Improved Model Replacements", - "authors": "Niccolò Biondi, Federico Pernici, Simone Ricci, Alberto Del Bimbo", + "authors": [ + { + "first_name": "Niccolò", + "last_name": "Biondi" + }, + { + "first_name": "Federico", + "last_name": "Pernici" + }, + { + "first_name": "Simone", + "last_name": "Ricci" + }, + { + "first_name": "Alberto", + "last_name": "Del Bimbo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards Calibrated Multi-label Deep Neural Networks", - "authors": "Jiacheng Cheng, Nuno Vasconcelos", + "authors": [ + { + "first_name": "Jiacheng", + "last_name": "Cheng" + }, + { + "first_name": "Nuno", + "last_name": "Vasconcelos" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SceneTex: High-Quality Texture Synthesis for Indoor Scenes via Diffusion Priors", - "authors": "Dave Zhenyu Chen, Haoxuan Li, Hsin-Ying Lee, Sergey Tulyakov, Matthias Nießner", + "authors": [ + { + "first_name": "Dave", + "last_name": "Zhenyu Chen" + }, + { + "first_name": "Haoxuan", + "last_name": "Li" + }, + { + "first_name": "Hsin-Ying", + "last_name": "Lee" + }, + { + "first_name": "Sergey", + "last_name": "Tulyakov" + }, + { + "first_name": "Matthias", + "last_name": "Nießner" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Neural Underwater Scene Representation", - "authors": "Yunkai Tang, Chengxuan Zhu, Renjie Wan, Chao Xu, Boxin Shi", + "authors": [ + { + "first_name": "Yunkai", + "last_name": "Tang" + }, + { + "first_name": "Chengxuan", + "last_name": "Zhu" + }, + { + "first_name": "Renjie", + "last_name": "Wan" + }, + { + "first_name": "Chao", + "last_name": "Xu" + }, + { + "first_name": "Boxin", + "last_name": "Shi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Progress-Aware Online Action Segmentation for Egocentric Procedural Task Videos", - "authors": "Yuhan Shen, Ehsan Elhamifar", + "authors": [ + { + "first_name": "Yuhan", + "last_name": "Shen" + }, + { + "first_name": "Ehsan", + "last_name": "Elhamifar" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "TUMTraf V2X Cooperative Perception Dataset", - "authors": "Walter Zimmer, Gerhard Arya Wardana, Suren Sritharan, Xingcheng Zhou, Rui Song, Alois C. Knoll", + "authors": [ + { + "first_name": "Walter", + "last_name": "Zimmer" + }, + { + "first_name": "Gerhard", + "last_name": "Arya Wardana" + }, + { + "first_name": "Suren", + "last_name": "Sritharan" + }, + { + "first_name": "Xingcheng", + "last_name": "Zhou" + }, + { + "first_name": "Rui", + "last_name": "Song" + }, + { + "first_name": "Alois", + "last_name": "C. Knoll" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Constrained Layout Generation with Factor Graphs", - "authors": "Mohammed Haroon Dupty, Yanfei Dong, Sicong Leng, Guoji Fu, Yong Liang Goh, Wei Lu, Wee Sun Lee", + "authors": [ + { + "first_name": "Mohammed", + "last_name": "Haroon Dupty" + }, + { + "first_name": "Yanfei", + "last_name": "Dong" + }, + { + "first_name": "Sicong", + "last_name": "Leng" + }, + { + "first_name": "Guoji", + "last_name": "Fu" + }, + { + "first_name": "Yong", + "last_name": "Liang Goh" + }, + { + "first_name": "Wei", + "last_name": "Lu" + }, + { + "first_name": "Wee", + "last_name": "Sun Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SLICE: Stabilized LIME for Consistent Explanations for Image Classification", - "authors": "Revoti Prasad Bora, Philipp Terhörst, Raymond Veldhuis, Raghavendra Ramachandra, Kiran Raja", + "authors": [ + { + "first_name": "Revoti", + "last_name": "Prasad Bora" + }, + { + "first_name": "Philipp", + "last_name": "Terhörst" + }, + { + "first_name": "Raymond", + "last_name": "Veldhuis" + }, + { + "first_name": "Raghavendra", + "last_name": "Ramachandra" + }, + { + "first_name": "Kiran", + "last_name": "Raja" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Anomaly Heterogeneity Learning for Open-set Supervised Anomaly Detection", - "authors": "Jiawen Zhu, Choubo Ding, Yu Tian, Guansong Pang", + "authors": [ + { + "first_name": "Jiawen", + "last_name": "Zhu" + }, + { + "first_name": "Choubo", + "last_name": "Ding" + }, + { + "first_name": "Yu", + "last_name": "Tian" + }, + { + "first_name": "Guansong", + "last_name": "Pang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SPECAT: SPatial-spEctral Cumulative-Attention Transformer for High-Resolution Hyperspectral Image Reconstruction", - "authors": "Zhiyang Yao, Shuyang Liu, Xiaoyun Yuan, Lu Fang", + "authors": [ + { + "first_name": "Zhiyang", + "last_name": "Yao" + }, + { + "first_name": "Shuyang", + "last_name": "Liu" + }, + { + "first_name": "Xiaoyun", + "last_name": "Yuan" + }, + { + "first_name": "Lu", + "last_name": "Fang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Attentive Illumination Decomposition Model for Multi-Illuminant White Balancing", - "authors": "Dongyoung Kim, Jinwoo Kim, Junsang Yu, Seon Joo Kim", + "authors": [ + { + "first_name": "Dongyoung", + "last_name": "Kim" + }, + { + "first_name": "Jinwoo", + "last_name": "Kim" + }, + { + "first_name": "Junsang", + "last_name": "Yu" + }, + { + "first_name": "Seon", + "last_name": "Joo Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Efficient Stitchable Task Adaptation", - "authors": "Haoyu He, Zizheng Pan, Jing Liu, Jianfei Cai, Bohan Zhuang", + "authors": [ + { + "first_name": "Haoyu", + "last_name": "He" + }, + { + "first_name": "Zizheng", + "last_name": "Pan" + }, + { + "first_name": "Jing", + "last_name": "Liu" + }, + { + "first_name": "Jianfei", + "last_name": "Cai" + }, + { + "first_name": "Bohan", + "last_name": "Zhuang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Image Processing GNN: Breaking Rigidity in Super-Resolution", - "authors": "Yuchuan Tian, Hanting Chen, Chao Xu, Yunhe Wang", + "authors": [ + { + "first_name": "Yuchuan", + "last_name": "Tian" + }, + { + "first_name": "Hanting", + "last_name": "Chen" + }, + { + "first_name": "Chao", + "last_name": "Xu" + }, + { + "first_name": "Yunhe", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Revisiting Counterfactual Problems in Referring Expression Comprehension", - "authors": "Zhihan Yu, Ruifan Li", + "authors": [ + { + "first_name": "Zhihan", + "last_name": "Yu" + }, + { + "first_name": "Ruifan", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DyBluRF: Dynamic Neural Radiance Fields from Blurry Monocular Video", - "authors": "Huiqiang Sun, Xingyi Li, Liao Shen, Xinyi Ye, Ke Xian, Zhiguo Cao", + "authors": [ + { + "first_name": "Huiqiang", + "last_name": "Sun" + }, + { + "first_name": "Xingyi", + "last_name": "Li" + }, + { + "first_name": "Liao", + "last_name": "Shen" + }, + { + "first_name": "Xinyi", + "last_name": "Ye" + }, + { + "first_name": "Ke", + "last_name": "Xian" + }, + { + "first_name": "Zhiguo", + "last_name": "Cao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Compressed 3D Gaussian Splatting for Accelerated Novel View Synthesis", - "authors": "Simon Niedermayr, Josef Stumpfegger, Rüdiger Westermann", + "authors": [ + { + "first_name": "Simon", + "last_name": "Niedermayr" + }, + { + "first_name": "Josef", + "last_name": "Stumpfegger" + }, + { + "first_name": "Rüdiger", + "last_name": "Westermann" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Separating the "Chirp" from the "Chat": Self-supervised Visual Grounding of Sound and Language", - "authors": "Mark Hamilton, Andrew Zisserman, John R. Hershey, William T. Freeman", + "authors": [ + { + "first_name": "Mark", + "last_name": "Hamilton" + }, + { + "first_name": "Andrew", + "last_name": "Zisserman" + }, + { + "first_name": "John", + "last_name": "R. Hershey" + }, + { + "first_name": "William", + "last_name": "T. Freeman" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards Generalizing to Unseen Domains with Few Labels", - "authors": "Chamuditha Jayanga Galappaththige, Sanoojan Baliah, Malitha Gunawardhana, Muhammad Haris Khan", + "authors": [ + { + "first_name": "Chamuditha", + "last_name": "Jayanga Galappaththige" + }, + { + "first_name": "Sanoojan", + "last_name": "Baliah" + }, + { + "first_name": "Malitha", + "last_name": "Gunawardhana" + }, + { + "first_name": "Muhammad", + "last_name": "Haris Khan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding", - "authors": "Bo He, Hengduo Li, Young Kyun Jang, Menglin Jia, Xuefei Cao, Ashish Shah, Abhinav Shrivastava, Ser-Nam Lim", + "authors": [ + { + "first_name": "Bo", + "last_name": "He" + }, + { + "first_name": "Hengduo", + "last_name": "Li" + }, + { + "first_name": "Young", + "last_name": "Kyun Jang" + }, + { + "first_name": "Menglin", + "last_name": "Jia" + }, + { + "first_name": "Xuefei", + "last_name": "Cao" + }, + { + "first_name": "Ashish", + "last_name": "Shah" + }, + { + "first_name": "Abhinav", + "last_name": "Shrivastava" + }, + { + "first_name": "Ser-Nam", + "last_name": "Lim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "AAMDM: Accelerated Auto-regressive Motion Diffusion Model", - "authors": "Tianyu Li, Calvin Qiao, Guanqiao Ren, KangKang Yin, Sehoon Ha", + "authors": [ + { + "first_name": "Tianyu", + "last_name": "Li" + }, + { + "first_name": "Calvin", + "last_name": "Qiao" + }, + { + "first_name": "Guanqiao", + "last_name": "Ren" + }, + { + "first_name": "KangKang", + "last_name": "Yin" + }, + { + "first_name": "Sehoon", + "last_name": "Ha" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards Understanding Cross and Self-Attention in Stable Diffusion for Text-Guided Image Editing", - "authors": "Bingyan Liu, Chengyu Wang, Tingfeng Cao, Kui Jia, Jun Huang", + "authors": [ + { + "first_name": "Bingyan", + "last_name": "Liu" + }, + { + "first_name": "Chengyu", + "last_name": "Wang" + }, + { + "first_name": "Tingfeng", + "last_name": "Cao" + }, + { + "first_name": "Kui", + "last_name": "Jia" + }, + { + "first_name": "Jun", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Dr2Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient Finetuning", - "authors": "Chen Zhao, Shuming Liu, Karttikeya Mangalam, Guocheng Qian, Fatimah Zohra, Abdulmohsen Alghannam, Jitendra Malik, Bernard Ghanem", + "authors": [ + { + "first_name": "Chen", + "last_name": "Zhao" + }, + { + "first_name": "Shuming", + "last_name": "Liu" + }, + { + "first_name": "Karttikeya", + "last_name": "Mangalam" + }, + { + "first_name": "Guocheng", + "last_name": "Qian" + }, + { + "first_name": "Fatimah", + "last_name": "Zohra" + }, + { + "first_name": "Abdulmohsen", + "last_name": "Alghannam" + }, + { + "first_name": "Jitendra", + "last_name": "Malik" + }, + { + "first_name": "Bernard", + "last_name": "Ghanem" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PNeRV: Enhancing Spatial Consistency via Pyramidal Neural Representation for Videos", - "authors": "Qi Zhao, M. Salman Asif, Zhan Ma", + "authors": [ + { + "first_name": "Qi", + "last_name": "Zhao" + }, + { + "first_name": "M.", + "last_name": "Salman Asif" + }, + { + "first_name": "Zhan", + "last_name": "Ma" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LTGC: Long-tail Recognition via Leveraging LLMs-driven Generated Content", - "authors": "Qihao Zhao, Yalun Dai, Hao Li, Wei Hu, Fan Zhang, Jun Liu", + "authors": [ + { + "first_name": "Qihao", + "last_name": "Zhao" + }, + { + "first_name": "Yalun", + "last_name": "Dai" + }, + { + "first_name": "Hao", + "last_name": "Li" + }, + { + "first_name": "Wei", + "last_name": "Hu" + }, + { + "first_name": "Fan", + "last_name": "Zhang" + }, + { + "first_name": "Jun", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DiverGen: Improving Instance Segmentation by Learning Wider Data Distribution with More Diverse Generative Data", - "authors": "Chengxiang Fan, Muzhi Zhu, Hao Chen, Yang Liu, Weijia Wu, Huaqi Zhang, Chunhua Shen", + "authors": [ + { + "first_name": "Chengxiang", + "last_name": "Fan" + }, + { + "first_name": "Muzhi", + "last_name": "Zhu" + }, + { + "first_name": "Hao", + "last_name": "Chen" + }, + { + "first_name": "Yang", + "last_name": "Liu" + }, + { + "first_name": "Weijia", + "last_name": "Wu" + }, + { + "first_name": "Huaqi", + "last_name": "Zhang" + }, + { + "first_name": "Chunhua", + "last_name": "Shen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Neural Refinement for Absolute Pose Regression with Feature Synthesis", - "authors": "Shuai Chen, Yash Bhalgat, Xinghui Li, Jia-Wang Bian, Kejie Li, Zirui Wang, Victor Adrian Prisacariu", + "authors": [ + { + "first_name": "Shuai", + "last_name": "Chen" + }, + { + "first_name": "Yash", + "last_name": "Bhalgat" + }, + { + "first_name": "Xinghui", + "last_name": "Li" + }, + { + "first_name": "Jia-Wang", + "last_name": "Bian" + }, + { + "first_name": "Kejie", + "last_name": "Li" + }, + { + "first_name": "Zirui", + "last_name": "Wang" + }, + { + "first_name": "Victor", + "last_name": "Adrian Prisacariu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning Disentangled Identifiers for Action-Customized Text-to-Image Generation", - "authors": "Siteng Huang, Biao Gong, Yutong Feng, Xi Chen, Yuqian Fu, Yu Liu, Donglin Wang", + "authors": [ + { + "first_name": "Siteng", + "last_name": "Huang" + }, + { + "first_name": "Biao", + "last_name": "Gong" + }, + { + "first_name": "Yutong", + "last_name": "Feng" + }, + { + "first_name": "Xi", + "last_name": "Chen" + }, + { + "first_name": "Yuqian", + "last_name": "Fu" + }, + { + "first_name": "Yu", + "last_name": "Liu" + }, + { + "first_name": "Donglin", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Automatic Controllable Colorization via Imagination", - "authors": "Xiaoyan Cong, Yue Wu, Qifeng Chen, Chenyang Lei", + "authors": [ + { + "first_name": "Xiaoyan", + "last_name": "Cong" + }, + { + "first_name": "Yue", + "last_name": "Wu" + }, + { + "first_name": "Qifeng", + "last_name": "Chen" + }, + { + "first_name": "Chenyang", + "last_name": "Lei" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Point Transformer V3: Simpler Faster Stronger", - "authors": "Xiaoyang Wu, Li Jiang, Peng-Shuai Wang, Zhijian Liu, Xihui Liu, Yu Qiao, Wanli Ouyang, Tong He, Hengshuang Zhao", + "authors": [ + { + "first_name": "Xiaoyang", + "last_name": "Wu" + }, + { + "first_name": "Li", + "last_name": "Jiang" + }, + { + "first_name": "Peng-Shuai", + "last_name": "Wang" + }, + { + "first_name": "Zhijian", + "last_name": "Liu" + }, + { + "first_name": "Xihui", + "last_name": "Liu" + }, + { + "first_name": "Yu", + "last_name": "Qiao" + }, + { + "first_name": "Wanli", + "last_name": "Ouyang" + }, + { + "first_name": "Tong", + "last_name": "He" + }, + { + "first_name": "Hengshuang", + "last_name": "Zhao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DiffCast: A Unified Framework via Residual Diffusion for Precipitation Nowcasting", - "authors": "Demin Yu, Xutao Li, Yunming Ye, Baoquan Zhang, Chuyao Luo, Kuai Dai, Rui Wang, Xunlai Chen", + "authors": [ + { + "first_name": "Demin", + "last_name": "Yu" + }, + { + "first_name": "Xutao", + "last_name": "Li" + }, + { + "first_name": "Yunming", + "last_name": "Ye" + }, + { + "first_name": "Baoquan", + "last_name": "Zhang" + }, + { + "first_name": "Chuyao", + "last_name": "Luo" + }, + { + "first_name": "Kuai", + "last_name": "Dai" + }, + { + "first_name": "Rui", + "last_name": "Wang" + }, + { + "first_name": "Xunlai", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives", - "authors": "Kristen Grauman, Andrew Westbury, Lorenzo Torresani, Kris Kitani, Jitendra Malik, Triantafyllos Afouras, Kumar Ashutosh, Vijay Baiyya, Siddhant Bansal, Bikram Boote, Eugene Byrne, Zach Chavis, Joya Chen, Feng Cheng, Fu-Jen Chu, Sean Crane, Avijit Dasgupta, Jing Dong, Maria Escobar, Cristhian Forigua, Abrham Gebreselasie, Sanjay Haresh, Jing Huang, Md Mohaiminul Islam, Suyog Jain, Rawal Khirodkar, Devansh Kukreja, Kevin J Liang, Jia-Wei Liu, Sagnik Majumder, Yongsen Mao, Miguel Martin, Effrosyni Mavroudi, Tushar Nagarajan, Francesco Ragusa, Santhosh Kumar Ramakrishnan, Luigi Seminara, Arjun Somayazulu, Yale Song, Shan Su, Zihui Xue, Edward Zhang, Jinxu Zhang, Angela Castillo, Changan Chen, Xinzhu Fu, Ryosuke Furuta, Cristina Gonzalez, Prince Gupta, Jiabo Hu, Yifei Huang, Yiming Huang, Weslie Khoo, Anush Kumar, Robert Kuo, Sach Lakhavani, Miao Liu, Mi Luo, Zhengyi Luo, Brighid Meredith, Austin Miller, Oluwatumininu Oguntola, Xiaqing Pan, Penny Peng, Shraman Pramanick, Merey Ramazanova, Fiona Ryan, Wei Shan, Kiran Somasundaram, Chenan Song, Audrey Southerland, Masatoshi Tateno, Huiyu Wang, Yuchen Wang, Takuma Yagi, Mingfei Yan, Xitong Yang, Zecheng Yu, Shengxin Cindy Zha, Chen Zhao, Ziwei Zhao, Zhifan Zhu, Jeff Zhuo, Pablo Arbelaez, Gedas Bertasius, Dima Damen, Jakob Engel, Giovanni Maria Farinella, Antonino Furnari, Bernard Ghanem, Judy Hoffman, C.V. Jawahar, Richard Newcombe, Hyun Soo Park, James M. Rehg, Yoichi Sato, Manolis Savva, Jianbo Shi, Mike Zheng Shou, Michael Wray", + "authors": [ + { + "first_name": "Kristen", + "last_name": "Grauman" + }, + { + "first_name": "Andrew", + "last_name": "Westbury" + }, + { + "first_name": "Lorenzo", + "last_name": "Torresani" + }, + { + "first_name": "Kris", + "last_name": "Kitani" + }, + { + "first_name": "Jitendra", + "last_name": "Malik" + }, + { + "first_name": "Triantafyllos", + "last_name": "Afouras" + }, + { + "first_name": "Kumar", + "last_name": "Ashutosh" + }, + { + "first_name": "Vijay", + "last_name": "Baiyya" + }, + { + "first_name": "Siddhant", + "last_name": "Bansal" + }, + { + "first_name": "Bikram", + "last_name": "Boote" + }, + { + "first_name": "Eugene", + "last_name": "Byrne" + }, + { + "first_name": "Zach", + "last_name": "Chavis" + }, + { + "first_name": "Joya", + "last_name": "Chen" + }, + { + "first_name": "Feng", + "last_name": "Cheng" + }, + { + "first_name": "Fu-Jen", + "last_name": "Chu" + }, + { + "first_name": "Sean", + "last_name": "Crane" + }, + { + "first_name": "Avijit", + "last_name": "Dasgupta" + }, + { + "first_name": "Jing", + "last_name": "Dong" + }, + { + "first_name": "Maria", + "last_name": "Escobar" + }, + { + "first_name": "Cristhian", + "last_name": "Forigua" + }, + { + "first_name": "Abrham", + "last_name": "Gebreselasie" + }, + { + "first_name": "Sanjay", + "last_name": "Haresh" + }, + { + "first_name": "Jing", + "last_name": "Huang" + }, + { + "first_name": "Md", + "last_name": "Mohaiminul Islam" + }, + { + "first_name": "Suyog", + "last_name": "Jain" + }, + { + "first_name": "Rawal", + "last_name": "Khirodkar" + }, + { + "first_name": "Devansh", + "last_name": "Kukreja" + }, + { + "first_name": "Kevin", + "last_name": "J Liang" + }, + { + "first_name": "Jia-Wei", + "last_name": "Liu" + }, + { + "first_name": "Sagnik", + "last_name": "Majumder" + }, + { + "first_name": "Yongsen", + "last_name": "Mao" + }, + { + "first_name": "Miguel", + "last_name": "Martin" + }, + { + "first_name": "Effrosyni", + "last_name": "Mavroudi" + }, + { + "first_name": "Tushar", + "last_name": "Nagarajan" + }, + { + "first_name": "Francesco", + "last_name": "Ragusa" + }, + { + "first_name": "Santhosh", + "last_name": "Kumar Ramakrishnan" + }, + { + "first_name": "Luigi", + "last_name": "Seminara" + }, + { + "first_name": "Arjun", + "last_name": "Somayazulu" + }, + { + "first_name": "Yale", + "last_name": "Song" + }, + { + "first_name": "Shan", + "last_name": "Su" + }, + { + "first_name": "Zihui", + "last_name": "Xue" + }, + { + "first_name": "Edward", + "last_name": "Zhang" + }, + { + "first_name": "Jinxu", + "last_name": "Zhang" + }, + { + "first_name": "Angela", + "last_name": "Castillo" + }, + { + "first_name": "Changan", + "last_name": "Chen" + }, + { + "first_name": "Xinzhu", + "last_name": "Fu" + }, + { + "first_name": "Ryosuke", + "last_name": "Furuta" + }, + { + "first_name": "Cristina", + "last_name": "Gonzalez" + }, + { + "first_name": "Prince", + "last_name": "Gupta" + }, + { + "first_name": "Jiabo", + "last_name": "Hu" + }, + { + "first_name": "Yifei", + "last_name": "Huang" + }, + { + "first_name": "Yiming", + "last_name": "Huang" + }, + { + "first_name": "Weslie", + "last_name": "Khoo" + }, + { + "first_name": "Anush", + "last_name": "Kumar" + }, + { + "first_name": "Robert", + "last_name": "Kuo" + }, + { + "first_name": "Sach", + "last_name": "Lakhavani" + }, + { + "first_name": "Miao", + "last_name": "Liu" + }, + { + "first_name": "Mi", + "last_name": "Luo" + }, + { + "first_name": "Zhengyi", + "last_name": "Luo" + }, + { + "first_name": "Brighid", + "last_name": "Meredith" + }, + { + "first_name": "Austin", + "last_name": "Miller" + }, + { + "first_name": "Oluwatumininu", + "last_name": "Oguntola" + }, + { + "first_name": "Xiaqing", + "last_name": "Pan" + }, + { + "first_name": "Penny", + "last_name": "Peng" + }, + { + "first_name": "Shraman", + "last_name": "Pramanick" + }, + { + "first_name": "Merey", + "last_name": "Ramazanova" + }, + { + "first_name": "Fiona", + "last_name": "Ryan" + }, + { + "first_name": "Wei", + "last_name": "Shan" + }, + { + "first_name": "Kiran", + "last_name": "Somasundaram" + }, + { + "first_name": "Chenan", + "last_name": "Song" + }, + { + "first_name": "Audrey", + "last_name": "Southerland" + }, + { + "first_name": "Masatoshi", + "last_name": "Tateno" + }, + { + "first_name": "Huiyu", + "last_name": "Wang" + }, + { + "first_name": "Yuchen", + "last_name": "Wang" + }, + { + "first_name": "Takuma", + "last_name": "Yagi" + }, + { + "first_name": "Mingfei", + "last_name": "Yan" + }, + { + "first_name": "Xitong", + "last_name": "Yang" + }, + { + "first_name": "Zecheng", + "last_name": "Yu" + }, + { + "first_name": "Shengxin", + "last_name": "Cindy Zha" + }, + { + "first_name": "Chen", + "last_name": "Zhao" + }, + { + "first_name": "Ziwei", + "last_name": "Zhao" + }, + { + "first_name": "Zhifan", + "last_name": "Zhu" + }, + { + "first_name": "Jeff", + "last_name": "Zhuo" + }, + { + "first_name": "Pablo", + "last_name": "Arbelaez" + }, + { + "first_name": "Gedas", + "last_name": "Bertasius" + }, + { + "first_name": "Dima", + "last_name": "Damen" + }, + { + "first_name": "Jakob", + "last_name": "Engel" + }, + { + "first_name": "Giovanni", + "last_name": "Maria Farinella" + }, + { + "first_name": "Antonino", + "last_name": "Furnari" + }, + { + "first_name": "Bernard", + "last_name": "Ghanem" + }, + { + "first_name": "Judy", + "last_name": "Hoffman" + }, + { + "first_name": "C.V.", + "last_name": "Jawahar" + }, + { + "first_name": "Richard", + "last_name": "Newcombe" + }, + { + "first_name": "Hyun", + "last_name": "Soo Park" + }, + { + "first_name": "James", + "last_name": "M. Rehg" + }, + { + "first_name": "Yoichi", + "last_name": "Sato" + }, + { + "first_name": "Manolis", + "last_name": "Savva" + }, + { + "first_name": "Jianbo", + "last_name": "Shi" + }, + { + "first_name": "Mike", + "last_name": "Zheng Shou" + }, + { + "first_name": "Michael", + "last_name": "Wray" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Point Cloud Pre-training with Diffusion Models", - "authors": "Xiao Zheng, Xiaoshui Huang, Guofeng Mei, Yuenan Hou, Zhaoyang Lyu, Bo Dai, Wanli Ouyang, Yongshun Gong", + "authors": [ + { + "first_name": "Xiao", + "last_name": "Zheng" + }, + { + "first_name": "Xiaoshui", + "last_name": "Huang" + }, + { + "first_name": "Guofeng", + "last_name": "Mei" + }, + { + "first_name": "Yuenan", + "last_name": "Hou" + }, + { + "first_name": "Zhaoyang", + "last_name": "Lyu" + }, + { + "first_name": "Bo", + "last_name": "Dai" + }, + { + "first_name": "Wanli", + "last_name": "Ouyang" + }, + { + "first_name": "Yongshun", + "last_name": "Gong" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Mask4Align: Aligned Entity Prompting with Color Masks for Multi-Entity Localization Problems", - "authors": "Haoquan Zhang, Ronggang Huang, Yi Xie, Huaidong Zhang", + "authors": [ + { + "first_name": "Haoquan", + "last_name": "Zhang" + }, + { + "first_name": "Ronggang", + "last_name": "Huang" + }, + { + "first_name": "Yi", + "last_name": "Xie" + }, + { + "first_name": "Huaidong", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "RCL: Reliable Continual Learning for Unified Failure Detection", - "authors": "Fei Zhu, Zhen Cheng, Xu-Yao Zhang, Cheng-Lin Liu, Zhaoxiang Zhang", + "authors": [ + { + "first_name": "Fei", + "last_name": "Zhu" + }, + { + "first_name": "Zhen", + "last_name": "Cheng" + }, + { + "first_name": "Xu-Yao", + "last_name": "Zhang" + }, + { + "first_name": "Cheng-Lin", + "last_name": "Liu" + }, + { + "first_name": "Zhaoxiang", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Referring Image Editing: Object-level Image Editing via Referring Expressions", - "authors": "Chang Liu, Xiangtai Li, Henghui Ding", + "authors": [ + { + "first_name": "Chang", + "last_name": "Liu" + }, + { + "first_name": "Xiangtai", + "last_name": "Li" + }, + { + "first_name": "Henghui", + "last_name": "Ding" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CAMixerSR: Only Details Need More "Attention"", - "authors": "Yan Wang, Yi Liu, Shijie Zhao, Junlin Li, Li Zhang", + "authors": [ + { + "first_name": "Yan", + "last_name": "Wang" + }, + { + "first_name": "Yi", + "last_name": "Liu" + }, + { + "first_name": "Shijie", + "last_name": "Zhao" + }, + { + "first_name": "Junlin", + "last_name": "Li" + }, + { + "first_name": "Li", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards Backward-Compatible Continual Learning of Image Compression", - "authors": "Zhihao Duan, Ming Lu, Justin Yang, Jiangpeng He, Zhan Ma, Fengqing Zhu", + "authors": [ + { + "first_name": "Zhihao", + "last_name": "Duan" + }, + { + "first_name": "Ming", + "last_name": "Lu" + }, + { + "first_name": "Justin", + "last_name": "Yang" + }, + { + "first_name": "Jiangpeng", + "last_name": "He" + }, + { + "first_name": "Zhan", + "last_name": "Ma" + }, + { + "first_name": "Fengqing", + "last_name": "Zhu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Latent Modulated Function for Computational Optimal Continuous Image Representation", - "authors": "Zongyao He, Zhi Jin", + "authors": [ + { + "first_name": "Zongyao", + "last_name": "He" + }, + { + "first_name": "Zhi", + "last_name": "Jin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Unsupervised Video Domain Adaptation with Masked Pre-Training and Collaborative Self-Training", - "authors": "Arun Reddy, William Paul, Corban Rivera, Ketul Shah, Celso M. de Melo, Rama Chellappa", + "authors": [ + { + "first_name": "Arun", + "last_name": "Reddy" + }, + { + "first_name": "William", + "last_name": "Paul" + }, + { + "first_name": "Corban", + "last_name": "Rivera" + }, + { + "first_name": "Ketul", + "last_name": "Shah" + }, + { + "first_name": "Celso", + "last_name": "M. de Melo" + }, + { + "first_name": "Rama", + "last_name": "Chellappa" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "UniDepth: Universal Monocular Metric Depth Estimation", - "authors": "Luigi Piccinelli, Yung-Hsu Yang, Christos Sakaridis, Mattia Segu, Siyuan Li, Luc Van Gool, Fisher Yu", + "authors": [ + { + "first_name": "Luigi", + "last_name": "Piccinelli" + }, + { + "first_name": "Yung-Hsu", + "last_name": "Yang" + }, + { + "first_name": "Christos", + "last_name": "Sakaridis" + }, + { + "first_name": "Mattia", + "last_name": "Segu" + }, + { + "first_name": "Siyuan", + "last_name": "Li" + }, + { + "first_name": "Luc", + "last_name": "Van Gool" + }, + { + "first_name": "Fisher", + "last_name": "Yu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "EMOPortraits: Emotion-enhanced Multimodal One-shot Head Avatars", - "authors": "Nikita Drobyshev, Antoni Bigata Casademunt, Konstantinos Vougioukas, Zoe Landgraf, Stavros Petridis, Maja Pantic", + "authors": [ + { + "first_name": "Nikita", + "last_name": "Drobyshev" + }, + { + "first_name": "Antoni", + "last_name": "Bigata Casademunt" + }, + { + "first_name": "Konstantinos", + "last_name": "Vougioukas" + }, + { + "first_name": "Zoe", + "last_name": "Landgraf" + }, + { + "first_name": "Stavros", + "last_name": "Petridis" + }, + { + "first_name": "Maja", + "last_name": "Pantic" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "NeuRAD: Neural Rendering for Autonomous Driving", - "authors": "Adam Tonderski, Carl Lindström, Georg Hess, William Ljungbergh, Lennart Svensson, Christoffer Petersson", + "authors": [ + { + "first_name": "Adam", + "last_name": "Tonderski" + }, + { + "first_name": "Carl", + "last_name": "Lindström" + }, + { + "first_name": "Georg", + "last_name": "Hess" + }, + { + "first_name": "William", + "last_name": "Ljungbergh" + }, + { + "first_name": "Lennart", + "last_name": "Svensson" + }, + { + "first_name": "Christoffer", + "last_name": "Petersson" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation", - "authors": "Xudong Wang, Ishan Misra, Ziyun Zeng, Rohit Girdhar, Trevor Darrell", + "authors": [ + { + "first_name": "Xudong", + "last_name": "Wang" + }, + { + "first_name": "Ishan", + "last_name": "Misra" + }, + { + "first_name": "Ziyun", + "last_name": "Zeng" + }, + { + "first_name": "Rohit", + "last_name": "Girdhar" + }, + { + "first_name": "Trevor", + "last_name": "Darrell" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Bootstrapping Chest CT Image Understanding by Distilling Knowledge from X-ray Expert Models", - "authors": "Weiwei Cao, Jianpeng Zhang, Yingda Xia, Tony C. W. Mok, Zi Li, Xianghua Ye, Le Lu, Jian Zheng, Yuxing Tang, Ling Zhang", + "authors": [ + { + "first_name": "Weiwei", + "last_name": "Cao" + }, + { + "first_name": "Jianpeng", + "last_name": "Zhang" + }, + { + "first_name": "Yingda", + "last_name": "Xia" + }, + { + "first_name": "Tony", + "last_name": "C. W. Mok" + }, + { + "first_name": "Zi", + "last_name": "Li" + }, + { + "first_name": "Xianghua", + "last_name": "Ye" + }, + { + "first_name": "Le", + "last_name": "Lu" + }, + { + "first_name": "Jian", + "last_name": "Zheng" + }, + { + "first_name": "Yuxing", + "last_name": "Tang" + }, + { + "first_name": "Ling", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Magic Tokens: Select Diverse Tokens for Multi-modal Object Re-Identification", - "authors": "Pingping Zhang, Yuhao Wang, Yang Liu, Zhengzheng Tu, Huchuan Lu", + "authors": [ + { + "first_name": "Pingping", + "last_name": "Zhang" + }, + { + "first_name": "Yuhao", + "last_name": "Wang" + }, + { + "first_name": "Yang", + "last_name": "Liu" + }, + { + "first_name": "Zhengzheng", + "last_name": "Tu" + }, + { + "first_name": "Huchuan", + "last_name": "Lu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance", - "authors": "Phuc Nguyen, Tuan Duc Ngo, Evangelos Kalogerakis, Chuang Gan, Anh Tran, Cuong Pham, Khoi Nguyen", + "authors": [ + { + "first_name": "Phuc", + "last_name": "Nguyen" + }, + { + "first_name": "Tuan", + "last_name": "Duc Ngo" + }, + { + "first_name": "Evangelos", + "last_name": "Kalogerakis" + }, + { + "first_name": "Chuang", + "last_name": "Gan" + }, + { + "first_name": "Anh", + "last_name": "Tran" + }, + { + "first_name": "Cuong", + "last_name": "Pham" + }, + { + "first_name": "Khoi", + "last_name": "Nguyen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SignGraph: A Sign Sequence is Worth Graphs of Nodes", - "authors": "Shiwei Gan, Yafeng Yin, Zhiwei Jiang, Hongkai Wen, Lei Xie, Sanglu Lu", + "authors": [ + { + "first_name": "Shiwei", + "last_name": "Gan" + }, + { + "first_name": "Yafeng", + "last_name": "Yin" + }, + { + "first_name": "Zhiwei", + "last_name": "Jiang" + }, + { + "first_name": "Hongkai", + "last_name": "Wen" + }, + { + "first_name": "Lei", + "last_name": "Xie" + }, + { + "first_name": "Sanglu", + "last_name": "Lu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ControlRoom3D: Room Generation using Semantic Proxy Rooms", - "authors": "Jonas Schult, Sam Tsai, Lukas Höllein, Bichen Wu, Jialiang Wang, Chih-Yao Ma, Kunpeng Li, Xiaofang Wang, Felix Wimbauer, Zijian He, Peizhao Zhang, Bastian Leibe, Peter Vajda, Ji Hou", + "authors": [ + { + "first_name": "Jonas", + "last_name": "Schult" + }, + { + "first_name": "Sam", + "last_name": "Tsai" + }, + { + "first_name": "Lukas", + "last_name": "Höllein" + }, + { + "first_name": "Bichen", + "last_name": "Wu" + }, + { + "first_name": "Jialiang", + "last_name": "Wang" + }, + { + "first_name": "Chih-Yao", + "last_name": "Ma" + }, + { + "first_name": "Kunpeng", + "last_name": "Li" + }, + { + "first_name": "Xiaofang", + "last_name": "Wang" + }, + { + "first_name": "Felix", + "last_name": "Wimbauer" + }, + { + "first_name": "Zijian", + "last_name": "He" + }, + { + "first_name": "Peizhao", + "last_name": "Zhang" + }, + { + "first_name": "Bastian", + "last_name": "Leibe" + }, + { + "first_name": "Peter", + "last_name": "Vajda" + }, + { + "first_name": "Ji", + "last_name": "Hou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DeconfuseTrack: Dealing with Confusion for Multi-Object Tracking", - "authors": "Cheng Huang, Shoudong Han, Mengyu He, Wenbo Zheng, Yuhao Wei", + "authors": [ + { + "first_name": "Cheng", + "last_name": "Huang" + }, + { + "first_name": "Shoudong", + "last_name": "Han" + }, + { + "first_name": "Mengyu", + "last_name": "He" + }, + { + "first_name": "Wenbo", + "last_name": "Zheng" + }, + { + "first_name": "Yuhao", + "last_name": "Wei" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PAPR in Motion: Seamless Point-level 3D Scene Interpolation", - "authors": "Shichong Peng, Yanshu Zhang, Ke Li", + "authors": [ + { + "first_name": "Shichong", + "last_name": "Peng" + }, + { + "first_name": "Yanshu", + "last_name": "Zhang" + }, + { + "first_name": "Ke", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Causal Mode Multiplexer: A Novel Framework for Unbiased Multispectral Pedestrian Detection", - "authors": "Taeheon Kim, Sebin Shin, Youngjoon Yu, Hak Gu Kim, Yong Man Ro", + "authors": [ + { + "first_name": "Taeheon", + "last_name": "Kim" + }, + { + "first_name": "Sebin", + "last_name": "Shin" + }, + { + "first_name": "Youngjoon", + "last_name": "Yu" + }, + { + "first_name": "Hak", + "last_name": "Gu Kim" + }, + { + "first_name": "Yong", + "last_name": "Man Ro" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HIMap: HybrId Representation Learning for End-to-end Vectorized HD Map Construction", - "authors": "Yi Zhou, Hui Zhang, Jiaqian Yu, Yifan Yang, Sangil Jung, Seung-In Park, ByungIn Yoo", + "authors": [ + { + "first_name": "Yi", + "last_name": "Zhou" + }, + { + "first_name": "Hui", + "last_name": "Zhang" + }, + { + "first_name": "Jiaqian", + "last_name": "Yu" + }, + { + "first_name": "Yifan", + "last_name": "Yang" + }, + { + "first_name": "Sangil", + "last_name": "Jung" + }, + { + "first_name": "Seung-In", + "last_name": "Park" + }, + { + "first_name": "ByungIn", + "last_name": "Yoo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LTA-PCS: Learnable Task-Agnostic Point Cloud Sampling", - "authors": "Jiaheng Liu, Jianhao Li, Kaisiyuan Wang, Hongcheng Guo, Jian Yang, Junran Peng, Ke Xu, Xianglong Liu, Jinyang Guo", + "authors": [ + { + "first_name": "Jiaheng", + "last_name": "Liu" + }, + { + "first_name": "Jianhao", + "last_name": "Li" + }, + { + "first_name": "Kaisiyuan", + "last_name": "Wang" + }, + { + "first_name": "Hongcheng", + "last_name": "Guo" + }, + { + "first_name": "Jian", + "last_name": "Yang" + }, + { + "first_name": "Junran", + "last_name": "Peng" + }, + { + "first_name": "Ke", + "last_name": "Xu" + }, + { + "first_name": "Xianglong", + "last_name": "Liu" + }, + { + "first_name": "Jinyang", + "last_name": "Guo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Non-Rigid Structure-from-Motion: Temporally-Smooth Procrustean Alignment and Spatially-Variant Deformation Modeling", - "authors": "Jiawei Shi, Hui Deng, Yuchao Dai", + "authors": [ + { + "first_name": "Jiawei", + "last_name": "Shi" + }, + { + "first_name": "Hui", + "last_name": "Deng" + }, + { + "first_name": "Yuchao", + "last_name": "Dai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ShapeMatcher: Self-Supervised Joint Shape Canonicalization Segmentation Retrieval and Deformation", - "authors": "Yan Di, Chenyangguang Zhang, Chaowei Wang, Ruida Zhang, Guangyao Zhai, Yanyan Li, Bowen Fu, Xiangyang Ji, Shan Gao", + "authors": [ + { + "first_name": "Yan", + "last_name": "Di" + }, + { + "first_name": "Chenyangguang", + "last_name": "Zhang" + }, + { + "first_name": "Chaowei", + "last_name": "Wang" + }, + { + "first_name": "Ruida", + "last_name": "Zhang" + }, + { + "first_name": "Guangyao", + "last_name": "Zhai" + }, + { + "first_name": "Yanyan", + "last_name": "Li" + }, + { + "first_name": "Bowen", + "last_name": "Fu" + }, + { + "first_name": "Xiangyang", + "last_name": "Ji" + }, + { + "first_name": "Shan", + "last_name": "Gao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "UniPTS: A Unified Framework for Proficient Post-Training Sparsity", - "authors": "Jingjing Xie, Yuxin Zhang, Mingbao Lin, Liujuan Cao, Rongrong Ji", + "authors": [ + { + "first_name": "Jingjing", + "last_name": "Xie" + }, + { + "first_name": "Yuxin", + "last_name": "Zhang" + }, + { + "first_name": "Mingbao", + "last_name": "Lin" + }, + { + "first_name": "Liujuan", + "last_name": "Cao" + }, + { + "first_name": "Rongrong", + "last_name": "Ji" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HumanNorm: Learning Normal Diffusion Model for High-quality and Realistic 3D Human Generation", - "authors": "Xin Huang, Ruizhi Shao, Qi Zhang, Hongwen Zhang, Ying Feng, Yebin Liu, Qing Wang", + "authors": [ + { + "first_name": "Xin", + "last_name": "Huang" + }, + { + "first_name": "Ruizhi", + "last_name": "Shao" + }, + { + "first_name": "Qi", + "last_name": "Zhang" + }, + { + "first_name": "Hongwen", + "last_name": "Zhang" + }, + { + "first_name": "Ying", + "last_name": "Feng" + }, + { + "first_name": "Yebin", + "last_name": "Liu" + }, + { + "first_name": "Qing", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Unleashing Unlabeled Data: A Paradigm for Cross-View Geo-Localization", - "authors": "Guopeng Li, Ming Qian, Gui-Song Xia", + "authors": [ + { + "first_name": "Guopeng", + "last_name": "Li" + }, + { + "first_name": "Ming", + "last_name": "Qian" + }, + { + "first_name": "Gui-Song", + "last_name": "Xia" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Global Latent Neural Rendering", - "authors": "Thomas Tanay, Matteo Maggioni", + "authors": [ + { + "first_name": "Thomas", + "last_name": "Tanay" + }, + { + "first_name": "Matteo", + "last_name": "Maggioni" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentation", - "authors": "Yuqi Wang, Yuntao Chen, Xingyu Liao, Lue Fan, Zhaoxiang Zhang", + "authors": [ + { + "first_name": "Yuqi", + "last_name": "Wang" + }, + { + "first_name": "Yuntao", + "last_name": "Chen" + }, + { + "first_name": "Xingyu", + "last_name": "Liao" + }, + { + "first_name": "Lue", + "last_name": "Fan" + }, + { + "first_name": "Zhaoxiang", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Sparse Views Near Light: A Practical Paradigm for Uncalibrated Point-light Photometric Stereo", - "authors": "Mohammed Brahimi, Bjoern Haefner, Zhenzhang Ye, Bastian Goldluecke, Daniel Cremers", + "authors": [ + { + "first_name": "Mohammed", + "last_name": "Brahimi" + }, + { + "first_name": "Bjoern", + "last_name": "Haefner" + }, + { + "first_name": "Zhenzhang", + "last_name": "Ye" + }, + { + "first_name": "Bastian", + "last_name": "Goldluecke" + }, + { + "first_name": "Daniel", + "last_name": "Cremers" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Meta-Point Learning and Refining for Category-Agnostic Pose Estimation", - "authors": "Junjie Chen, Jiebin Yan, Yuming Fang, Li Niu", + "authors": [ + { + "first_name": "Junjie", + "last_name": "Chen" + }, + { + "first_name": "Jiebin", + "last_name": "Yan" + }, + { + "first_name": "Yuming", + "last_name": "Fang" + }, + { + "first_name": "Li", + "last_name": "Niu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Cross-view and Cross-pose Completion for 3D Human Understanding", - "authors": "Matthieu Armando, Salma Galaaoui, Fabien Baradel, Thomas Lucas, Vincent Leroy, Romain Brégier, Philippe Weinzaepfel, Grégory Rogez", + "authors": [ + { + "first_name": "Matthieu", + "last_name": "Armando" + }, + { + "first_name": "Salma", + "last_name": "Galaaoui" + }, + { + "first_name": "Fabien", + "last_name": "Baradel" + }, + { + "first_name": "Thomas", + "last_name": "Lucas" + }, + { + "first_name": "Vincent", + "last_name": "Leroy" + }, + { + "first_name": "Romain", + "last_name": "Brégier" + }, + { + "first_name": "Philippe", + "last_name": "Weinzaepfel" + }, + { + "first_name": "Grégory", + "last_name": "Rogez" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Batch Normalization Alleviates the Spectral Bias in Coordinate Networks", - "authors": "Zhicheng Cai, Hao Zhu, Qiu Shen, Xinran Wang, Xun Cao", + "authors": [ + { + "first_name": "Zhicheng", + "last_name": "Cai" + }, + { + "first_name": "Hao", + "last_name": "Zhu" + }, + { + "first_name": "Qiu", + "last_name": "Shen" + }, + { + "first_name": "Xinran", + "last_name": "Wang" + }, + { + "first_name": "Xun", + "last_name": "Cao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Efficient Scene Recovery Using Luminous Flux Prior", - "authors": "Zhongyu Li, Lei Zhang", + "authors": [ + { + "first_name": "Zhongyu", + "last_name": "Li" + }, + { + "first_name": "Lei", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LQMFormer: Language-aware Query Mask Transformer for Referring Image Segmentation", - "authors": "Nisarg A. Shah, Vibashan VS, Vishal M. Patel", + "authors": [ + { + "first_name": "Nisarg", + "last_name": "A. Shah" + }, + { + "first_name": "Vibashan", + "last_name": "VS" + }, + { + "first_name": "Vishal", + "last_name": "M. Patel" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Customize your NeRF: Adaptive Source Driven 3D Scene Editing via Local-Global Iterative Training", - "authors": "Runze He, Shaofei Huang, Xuecheng Nie, Tianrui Hui, Luoqi Liu, Jiao Dai, Jizhong Han, Guanbin Li, Si Liu", + "authors": [ + { + "first_name": "Runze", + "last_name": "He" + }, + { + "first_name": "Shaofei", + "last_name": "Huang" + }, + { + "first_name": "Xuecheng", + "last_name": "Nie" + }, + { + "first_name": "Tianrui", + "last_name": "Hui" + }, + { + "first_name": "Luoqi", + "last_name": "Liu" + }, + { + "first_name": "Jiao", + "last_name": "Dai" + }, + { + "first_name": "Jizhong", + "last_name": "Han" + }, + { + "first_name": "Guanbin", + "last_name": "Li" + }, + { + "first_name": "Si", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SplaTAM: Splat Track & Map 3D Gaussians for Dense RGB-D SLAM", - "authors": "Nikhil Keetha, Jay Karhade, Krishna Murthy Jatavallabhula, Gengshan Yang, Sebastian Scherer, Deva Ramanan, Jonathon Luiten", + "authors": [ + { + "first_name": "Nikhil", + "last_name": "Keetha" + }, + { + "first_name": "Jay", + "last_name": "Karhade" + }, + { + "first_name": "Krishna", + "last_name": "Murthy Jatavallabhula" + }, + { + "first_name": "Gengshan", + "last_name": "Yang" + }, + { + "first_name": "Sebastian", + "last_name": "Scherer" + }, + { + "first_name": "Deva", + "last_name": "Ramanan" + }, + { + "first_name": "Jonathon", + "last_name": "Luiten" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Instance-based Max-margin for Practical Few-shot Recognition", - "authors": "Minghao Fu, Ke Zhu", + "authors": [ + { + "first_name": "Minghao", + "last_name": "Fu" + }, + { + "first_name": "Ke", + "last_name": "Zhu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Spherical Mask: Coarse-to-Fine 3D Point Cloud Instance Segmentation with Spherical Representation", - "authors": "Sangyun Shin, Kaichen Zhou, Madhu Vankadari, Andrew Markham, Niki Trigoni", + "authors": [ + { + "first_name": "Sangyun", + "last_name": "Shin" + }, + { + "first_name": "Kaichen", + "last_name": "Zhou" + }, + { + "first_name": "Madhu", + "last_name": "Vankadari" + }, + { + "first_name": "Andrew", + "last_name": "Markham" + }, + { + "first_name": "Niki", + "last_name": "Trigoni" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Omni-Q: Omni-Directional Scene Understanding for Unsupervised Visual Grounding", - "authors": "Sai Wang, Yutian Lin, Yu Wu", + "authors": [ + { + "first_name": "Sai", + "last_name": "Wang" + }, + { + "first_name": "Yutian", + "last_name": "Lin" + }, + { + "first_name": "Yu", + "last_name": "Wu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "VISTA-LLAMA: Reducing Hallucination in Video Language Models via Equal Distance to Visual Tokens", - "authors": "Fan Ma, Xiaojie Jin, Heng Wang, Yuchen Xian, Jiashi Feng, Yi Yang", + "authors": [ + { + "first_name": "Fan", + "last_name": "Ma" + }, + { + "first_name": "Xiaojie", + "last_name": "Jin" + }, + { + "first_name": "Heng", + "last_name": "Wang" + }, + { + "first_name": "Yuchen", + "last_name": "Xian" + }, + { + "first_name": "Jiashi", + "last_name": "Feng" + }, + { + "first_name": "Yi", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FSRT: Facial Scene Representation Transformer for Face Reenactment from Factorized Appearance Head-pose and Facial Expression Features", - "authors": "Andre Rochow, Max Schwarz, Sven Behnke", + "authors": [ + { + "first_name": "Andre", + "last_name": "Rochow" + }, + { + "first_name": "Max", + "last_name": "Schwarz" + }, + { + "first_name": "Sven", + "last_name": "Behnke" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Efficient Multitask Dense Predictor via Binarization", - "authors": "Yuzhang Shang, Dan Xu, Gaowen Liu, Ramana Rao Kompella, Yan Yan", + "authors": [ + { + "first_name": "Yuzhang", + "last_name": "Shang" + }, + { + "first_name": "Dan", + "last_name": "Xu" + }, + { + "first_name": "Gaowen", + "last_name": "Liu" + }, + { + "first_name": "Ramana", + "last_name": "Rao Kompella" + }, + { + "first_name": "Yan", + "last_name": "Yan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "TetraSphere: A Neural Descriptor for O(3)-Invariant Point Cloud Analysis", - "authors": "Pavlo Melnyk, Andreas Robinson, Michael Felsberg, Mårten Wadenbäck", + "authors": [ + { + "first_name": "Pavlo", + "last_name": "Melnyk" + }, + { + "first_name": "Andreas", + "last_name": "Robinson" + }, + { + "first_name": "Michael", + "last_name": "Felsberg" + }, + { + "first_name": "Mårten", + "last_name": "Wadenbäck" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ZeroRF: Fast Sparse View 360deg Reconstruction with Zero Pretraining", - "authors": "Ruoxi Shi, Xinyue Wei, Cheng Wang, Hao Su", + "authors": [ + { + "first_name": "Ruoxi", + "last_name": "Shi" + }, + { + "first_name": "Xinyue", + "last_name": "Wei" + }, + { + "first_name": "Cheng", + "last_name": "Wang" + }, + { + "first_name": "Hao", + "last_name": "Su" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "RCooper: A Real-world Large-scale Dataset for Roadside Cooperative Perception", - "authors": "Ruiyang Hao, Siqi Fan, Yingru Dai, Zhenlin Zhang, Chenxi Li, Yuntian Wang, Haibao Yu, Wenxian Yang, Jirui Yuan, Zaiqing Nie", + "authors": [ + { + "first_name": "Ruiyang", + "last_name": "Hao" + }, + { + "first_name": "Siqi", + "last_name": "Fan" + }, + { + "first_name": "Yingru", + "last_name": "Dai" + }, + { + "first_name": "Zhenlin", + "last_name": "Zhang" + }, + { + "first_name": "Chenxi", + "last_name": "Li" + }, + { + "first_name": "Yuntian", + "last_name": "Wang" + }, + { + "first_name": "Haibao", + "last_name": "Yu" + }, + { + "first_name": "Wenxian", + "last_name": "Yang" + }, + { + "first_name": "Jirui", + "last_name": "Yuan" + }, + { + "first_name": "Zaiqing", + "last_name": "Nie" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "TutteNet: Injective 3D Deformations by Composition of 2D Mesh Deformations", - "authors": "Bo Sun, Thibault Groueix, Chen Song, Qixing Huang, Noam Aigerman", + "authors": [ + { + "first_name": "Bo", + "last_name": "Sun" + }, + { + "first_name": "Thibault", + "last_name": "Groueix" + }, + { + "first_name": "Chen", + "last_name": "Song" + }, + { + "first_name": "Qixing", + "last_name": "Huang" + }, + { + "first_name": "Noam", + "last_name": "Aigerman" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "WANDR: Intention-guided Human Motion Generation", - "authors": "Markos Diomataris, Nikos Athanasiou, Omid Taheri, Xi Wang, Otmar Hilliges, Michael J. Black", + "authors": [ + { + "first_name": "Markos", + "last_name": "Diomataris" + }, + { + "first_name": "Nikos", + "last_name": "Athanasiou" + }, + { + "first_name": "Omid", + "last_name": "Taheri" + }, + { + "first_name": "Xi", + "last_name": "Wang" + }, + { + "first_name": "Otmar", + "last_name": "Hilliges" + }, + { + "first_name": "Michael", + "last_name": "J. Black" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Jointly Training and Pruning CNNs via Learnable Agent Guidance and Alignment", - "authors": "Alireza Ganjdanesh, Shangqian Gao, Heng Huang", + "authors": [ + { + "first_name": "Alireza", + "last_name": "Ganjdanesh" + }, + { + "first_name": "Shangqian", + "last_name": "Gao" + }, + { + "first_name": "Heng", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Estimating Noisy Class Posterior with Part-level Labels for Noisy Label Learning", - "authors": "Rui Zhao, Bin Shi, Jianfei Ruan, Tianze Pan, Bo Dong", + "authors": [ + { + "first_name": "Rui", + "last_name": "Zhao" + }, + { + "first_name": "Bin", + "last_name": "Shi" + }, + { + "first_name": "Jianfei", + "last_name": "Ruan" + }, + { + "first_name": "Tianze", + "last_name": "Pan" + }, + { + "first_name": "Bo", + "last_name": "Dong" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Leveraging Vision-Language Models for Improving Domain Generalization in Image Classification", - "authors": "Sravanti Addepalli, Ashish Ramayee Asokan, Lakshay Sharma, R. Venkatesh Babu", + "authors": [ + { + "first_name": "Sravanti", + "last_name": "Addepalli" + }, + { + "first_name": "Ashish", + "last_name": "Ramayee Asokan" + }, + { + "first_name": "Lakshay", + "last_name": "Sharma" + }, + { + "first_name": "R.", + "last_name": "Venkatesh Babu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Diffusion-EDFs: Bi-equivariant Denoising Generative Modeling on SE(3) for Visual Robotic Manipulation", - "authors": "Hyunwoo Ryu, Jiwoo Kim, Hyunseok An, Junwoo Chang, Joohwan Seo, Taehan Kim, Yubin Kim, Chaewon Hwang, Jongeun Choi, Roberto Horowitz", + "authors": [ + { + "first_name": "Hyunwoo", + "last_name": "Ryu" + }, + { + "first_name": "Jiwoo", + "last_name": "Kim" + }, + { + "first_name": "Hyunseok", + "last_name": "An" + }, + { + "first_name": "Junwoo", + "last_name": "Chang" + }, + { + "first_name": "Joohwan", + "last_name": "Seo" + }, + { + "first_name": "Taehan", + "last_name": "Kim" + }, + { + "first_name": "Yubin", + "last_name": "Kim" + }, + { + "first_name": "Chaewon", + "last_name": "Hwang" + }, + { + "first_name": "Jongeun", + "last_name": "Choi" + }, + { + "first_name": "Roberto", + "last_name": "Horowitz" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Prompt Learning via Meta-Regularization", - "authors": "Jinyoung Park, Juyeon Ko, Hyunwoo J. Kim", + "authors": [ + { + "first_name": "Jinyoung", + "last_name": "Park" + }, + { + "first_name": "Juyeon", + "last_name": "Ko" + }, + { + "first_name": "Hyunwoo", + "last_name": "J. Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional Understanding", - "authors": "Le Zhang, Rabiul Awal, Aishwarya Agrawal", + "authors": [ + { + "first_name": "Le", + "last_name": "Zhang" + }, + { + "first_name": "Rabiul", + "last_name": "Awal" + }, + { + "first_name": "Aishwarya", + "last_name": "Agrawal" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CMA: A Chromaticity Map Adapter for Robust Detection of Screen-Recapture Document Images", - "authors": "Changsheng Chen, Liangwei Lin, Yongqi Chen, Bin Li, Jishen Zeng, Jiwu Huang", + "authors": [ + { + "first_name": "Changsheng", + "last_name": "Chen" + }, + { + "first_name": "Liangwei", + "last_name": "Lin" + }, + { + "first_name": "Yongqi", + "last_name": "Chen" + }, + { + "first_name": "Bin", + "last_name": "Li" + }, + { + "first_name": "Jishen", + "last_name": "Zeng" + }, + { + "first_name": "Jiwu", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld", - "authors": "Yijun Yang, Tianyi Zhou, Kanxue Li, Dapeng Tao, Lusong Li, Li Shen, Xiaodong He, Jing Jiang, Yuhui Shi", + "authors": [ + { + "first_name": "Yijun", + "last_name": "Yang" + }, + { + "first_name": "Tianyi", + "last_name": "Zhou" + }, + { + "first_name": "Kanxue", + "last_name": "Li" + }, + { + "first_name": "Dapeng", + "last_name": "Tao" + }, + { + "first_name": "Lusong", + "last_name": "Li" + }, + { + "first_name": "Li", + "last_name": "Shen" + }, + { + "first_name": "Xiaodong", + "last_name": "He" + }, + { + "first_name": "Jing", + "last_name": "Jiang" + }, + { + "first_name": "Yuhui", + "last_name": "Shi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "VA3: Virtually Assured Amplification Attack on Probabilistic Copyright Protection for Text-to-Image Generative Models", - "authors": "Xiang Li, Qianli Shen, Kenji Kawaguchi", + "authors": [ + { + "first_name": "Xiang", + "last_name": "Li" + }, + { + "first_name": "Qianli", + "last_name": "Shen" + }, + { + "first_name": "Kenji", + "last_name": "Kawaguchi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Point-VOS: Pointing Up Video Object Segmentation", - "authors": "Sabarinath Mahadevan, Idil Esen Zulfikar, Paul Voigtlaender, Bastian Leibe", + "authors": [ + { + "first_name": "Sabarinath", + "last_name": "Mahadevan" + }, + { + "first_name": "Idil", + "last_name": "Esen Zulfikar" + }, + { + "first_name": "Paul", + "last_name": "Voigtlaender" + }, + { + "first_name": "Bastian", + "last_name": "Leibe" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Intriguing Properties of Diffusion Models: An Empirical Study of the Natural Attack Capability in Text-to-Image Generative Models", - "authors": "Takami Sato, Justin Yue, Nanze Chen, Ningfei Wang, Qi Alfred Chen", + "authors": [ + { + "first_name": "Takami", + "last_name": "Sato" + }, + { + "first_name": "Justin", + "last_name": "Yue" + }, + { + "first_name": "Nanze", + "last_name": "Chen" + }, + { + "first_name": "Ningfei", + "last_name": "Wang" + }, + { + "first_name": "Qi", + "last_name": "Alfred Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GroupContrast: Semantic-aware Self-supervised Representation Learning for 3D Understanding", - "authors": "Chengyao Wang, Li Jiang, Xiaoyang Wu, Zhuotao Tian, Bohao Peng, Hengshuang Zhao, Jiaya Jia", + "authors": [ + { + "first_name": "Chengyao", + "last_name": "Wang" + }, + { + "first_name": "Li", + "last_name": "Jiang" + }, + { + "first_name": "Xiaoyang", + "last_name": "Wu" + }, + { + "first_name": "Zhuotao", + "last_name": "Tian" + }, + { + "first_name": "Bohao", + "last_name": "Peng" + }, + { + "first_name": "Hengshuang", + "last_name": "Zhao" + }, + { + "first_name": "Jiaya", + "last_name": "Jia" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HouseCat6D - A Large-Scale Multi-Modal Category Level 6D Object Perception Dataset with Household Objects in Realistic Scenarios", - "authors": "HyunJun Jung, Shun-Cheng Wu, Patrick Ruhkamp, Guangyao Zhai, Hannah Schieber, Giulia Rizzoli, Pengyuan Wang, Hongcheng Zhao, Lorenzo Garattoni, Sven Meier, Daniel Roth, Nassir Navab, Benjamin Busam", + "authors": [ + { + "first_name": "HyunJun", + "last_name": "Jung" + }, + { + "first_name": "Shun-Cheng", + "last_name": "Wu" + }, + { + "first_name": "Patrick", + "last_name": "Ruhkamp" + }, + { + "first_name": "Guangyao", + "last_name": "Zhai" + }, + { + "first_name": "Hannah", + "last_name": "Schieber" + }, + { + "first_name": "Giulia", + "last_name": "Rizzoli" + }, + { + "first_name": "Pengyuan", + "last_name": "Wang" + }, + { + "first_name": "Hongcheng", + "last_name": "Zhao" + }, + { + "first_name": "Lorenzo", + "last_name": "Garattoni" + }, + { + "first_name": "Sven", + "last_name": "Meier" + }, + { + "first_name": "Daniel", + "last_name": "Roth" + }, + { + "first_name": "Nassir", + "last_name": "Navab" + }, + { + "first_name": "Benjamin", + "last_name": "Busam" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Privacy-Preserving Face Recognition Using Trainable Feature Subtraction", - "authors": "Yuxi Mi, Zhizhou Zhong, Yuge Huang, Jiazhen Ji, Jianqing Xu, Jun Wang, Shaoming Wang, Shouhong Ding, Shuigeng Zhou", + "authors": [ + { + "first_name": "Yuxi", + "last_name": "Mi" + }, + { + "first_name": "Zhizhou", + "last_name": "Zhong" + }, + { + "first_name": "Yuge", + "last_name": "Huang" + }, + { + "first_name": "Jiazhen", + "last_name": "Ji" + }, + { + "first_name": "Jianqing", + "last_name": "Xu" + }, + { + "first_name": "Jun", + "last_name": "Wang" + }, + { + "first_name": "Shaoming", + "last_name": "Wang" + }, + { + "first_name": "Shouhong", + "last_name": "Ding" + }, + { + "first_name": "Shuigeng", + "last_name": "Zhou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards Co-Evaluation of Cameras HDR and Algorithms for Industrial-Grade 6DoF Pose Estimation", - "authors": "Agastya Kalra, Guy Stoppi, Dmitrii Marin, Vage Taamazyan, Aarrushi Shandilya, Rishav Agarwal, Anton Boykov, Tze Hao Chong, Michael Stark", + "authors": [ + { + "first_name": "Agastya", + "last_name": "Kalra" + }, + { + "first_name": "Guy", + "last_name": "Stoppi" + }, + { + "first_name": "Dmitrii", + "last_name": "Marin" + }, + { + "first_name": "Vage", + "last_name": "Taamazyan" + }, + { + "first_name": "Aarrushi", + "last_name": "Shandilya" + }, + { + "first_name": "Rishav", + "last_name": "Agarwal" + }, + { + "first_name": "Anton", + "last_name": "Boykov" + }, + { + "first_name": "Tze", + "last_name": "Hao Chong" + }, + { + "first_name": "Michael", + "last_name": "Stark" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning Visual Prompt for Gait Recognition", - "authors": "Kang Ma, Ying Fu, Chunshui Cao, Saihui Hou, Yongzhen Huang, Dezhi Zheng", + "authors": [ + { + "first_name": "Kang", + "last_name": "Ma" + }, + { + "first_name": "Ying", + "last_name": "Fu" + }, + { + "first_name": "Chunshui", + "last_name": "Cao" + }, + { + "first_name": "Saihui", + "last_name": "Hou" + }, + { + "first_name": "Yongzhen", + "last_name": "Huang" + }, + { + "first_name": "Dezhi", + "last_name": "Zheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MLP Can Be A Good Transformer Learner", - "authors": "Sihao Lin, Pumeng Lyu, Dongrui Liu, Tao Tang, Xiaodan Liang, Andy Song, Xiaojun Chang", + "authors": [ + { + "first_name": "Sihao", + "last_name": "Lin" + }, + { + "first_name": "Pumeng", + "last_name": "Lyu" + }, + { + "first_name": "Dongrui", + "last_name": "Liu" + }, + { + "first_name": "Tao", + "last_name": "Tang" + }, + { + "first_name": "Xiaodan", + "last_name": "Liang" + }, + { + "first_name": "Andy", + "last_name": "Song" + }, + { + "first_name": "Xiaojun", + "last_name": "Chang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GraphDreamer: Compositional 3D Scene Synthesis from Scene Graphs", - "authors": "Gege Gao, Weiyang Liu, Anpei Chen, Andreas Geiger, Bernhard Schölkopf", + "authors": [ + { + "first_name": "Gege", + "last_name": "Gao" + }, + { + "first_name": "Weiyang", + "last_name": "Liu" + }, + { + "first_name": "Anpei", + "last_name": "Chen" + }, + { + "first_name": "Andreas", + "last_name": "Geiger" + }, + { + "first_name": "Bernhard", + "last_name": "Schölkopf" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Visual-Augmented Dynamic Semantic Prototype for Generative Zero-Shot Learning", - "authors": "Wenjin Hou, Shiming Chen, Shuhuang Chen, Ziming Hong, Yan Wang, Xuetao Feng, Salman Khan, Fahad Shahbaz Khan, Xinge You", + "authors": [ + { + "first_name": "Wenjin", + "last_name": "Hou" + }, + { + "first_name": "Shiming", + "last_name": "Chen" + }, + { + "first_name": "Shuhuang", + "last_name": "Chen" + }, + { + "first_name": "Ziming", + "last_name": "Hong" + }, + { + "first_name": "Yan", + "last_name": "Wang" + }, + { + "first_name": "Xuetao", + "last_name": "Feng" + }, + { + "first_name": "Salman", + "last_name": "Khan" + }, + { + "first_name": "Fahad", + "last_name": "Shahbaz Khan" + }, + { + "first_name": "Xinge", + "last_name": "You" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Dynamic Prompt Optimizing for Text-to-Image Generation", - "authors": "Wenyi Mo, Tianyu Zhang, Yalong Bai, Bing Su, Ji-Rong Wen, Qing Yang", + "authors": [ + { + "first_name": "Wenyi", + "last_name": "Mo" + }, + { + "first_name": "Tianyu", + "last_name": "Zhang" + }, + { + "first_name": "Yalong", + "last_name": "Bai" + }, + { + "first_name": "Bing", + "last_name": "Su" + }, + { + "first_name": "Ji-Rong", + "last_name": "Wen" + }, + { + "first_name": "Qing", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes", - "authors": "Yi-Hua Huang, Yang-Tian Sun, Ziyi Yang, Xiaoyang Lyu, Yan-Pei Cao, Xiaojuan Qi", + "authors": [ + { + "first_name": "Yi-Hua", + "last_name": "Huang" + }, + { + "first_name": "Yang-Tian", + "last_name": "Sun" + }, + { + "first_name": "Ziyi", + "last_name": "Yang" + }, + { + "first_name": "Xiaoyang", + "last_name": "Lyu" + }, + { + "first_name": "Yan-Pei", + "last_name": "Cao" + }, + { + "first_name": "Xiaojuan", + "last_name": "Qi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "360Loc: A Dataset and Benchmark for Omnidirectional Visual Localization with Cross-device Queries", - "authors": "Huajian Huang, Changkun Liu, Yipeng Zhu, Hui Cheng, Tristan Braud, Sai-Kit Yeung", + "authors": [ + { + "first_name": "Huajian", + "last_name": "Huang" + }, + { + "first_name": "Changkun", + "last_name": "Liu" + }, + { + "first_name": "Yipeng", + "last_name": "Zhu" + }, + { + "first_name": "Hui", + "last_name": "Cheng" + }, + { + "first_name": "Tristan", + "last_name": "Braud" + }, + { + "first_name": "Sai-Kit", + "last_name": "Yeung" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Domain Gap Embeddings for Generative Dataset Augmentation", - "authors": "Yinong Oliver Wang, Younjoon Chung, Chen Henry Wu, Fernando De la Torre", + "authors": [ + { + "first_name": "Yinong", + "last_name": "Oliver Wang" + }, + { + "first_name": "Younjoon", + "last_name": "Chung" + }, + { + "first_name": "Chen", + "last_name": "Henry Wu" + }, + { + "first_name": "Fernando", + "last_name": "De la Torre" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Geometrically-driven Aggregation for Zero-shot 3D Point Cloud Understanding", - "authors": "Guofeng Mei, Luigi Riz, Yiming Wang, Fabio Poiesi", + "authors": [ + { + "first_name": "Guofeng", + "last_name": "Mei" + }, + { + "first_name": "Luigi", + "last_name": "Riz" + }, + { + "first_name": "Yiming", + "last_name": "Wang" + }, + { + "first_name": "Fabio", + "last_name": "Poiesi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning to Rank Patches for Unbiased Image Redundancy Reduction", - "authors": "Yang Luo, Zhineng Chen, Peng Zhou, Zuxuan Wu, Xieping Gao, Yu-Gang Jiang", + "authors": [ + { + "first_name": "Yang", + "last_name": "Luo" + }, + { + "first_name": "Zhineng", + "last_name": "Chen" + }, + { + "first_name": "Peng", + "last_name": "Zhou" + }, + { + "first_name": "Zuxuan", + "last_name": "Wu" + }, + { + "first_name": "Xieping", + "last_name": "Gao" + }, + { + "first_name": "Yu-Gang", + "last_name": "Jiang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Going Beyond Multi-Task Dense Prediction with Synergy Embedding Models", - "authors": "Huimin Huang, Yawen Huang, Lanfen Lin, Ruofeng Tong, Yen-Wei Chen, Hao Zheng, Yuexiang Li, Yefeng Zheng", + "authors": [ + { + "first_name": "Huimin", + "last_name": "Huang" + }, + { + "first_name": "Yawen", + "last_name": "Huang" + }, + { + "first_name": "Lanfen", + "last_name": "Lin" + }, + { + "first_name": "Ruofeng", + "last_name": "Tong" + }, + { + "first_name": "Yen-Wei", + "last_name": "Chen" + }, + { + "first_name": "Hao", + "last_name": "Zheng" + }, + { + "first_name": "Yuexiang", + "last_name": "Li" + }, + { + "first_name": "Yefeng", + "last_name": "Zheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Disentangled Pre-training for Human-Object Interaction Detection", - "authors": "Zhuolong Li, Xingao Li, Changxing Ding, Xiangmin Xu", + "authors": [ + { + "first_name": "Zhuolong", + "last_name": "Li" + }, + { + "first_name": "Xingao", + "last_name": "Li" + }, + { + "first_name": "Changxing", + "last_name": "Ding" + }, + { + "first_name": "Xiangmin", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Light the Night: A Multi-Condition Diffusion Framework for Unpaired Low-Light Enhancement in Autonomous Driving", - "authors": "Jinlong Li, Baolu Li, Zhengzhong Tu, Xinyu Liu, Qing Guo, Felix Juefei-Xu, Runsheng Xu, Hongkai Yu", + "authors": [ + { + "first_name": "Jinlong", + "last_name": "Li" + }, + { + "first_name": "Baolu", + "last_name": "Li" + }, + { + "first_name": "Zhengzhong", + "last_name": "Tu" + }, + { + "first_name": "Xinyu", + "last_name": "Liu" + }, + { + "first_name": "Qing", + "last_name": "Guo" + }, + { + "first_name": "Felix", + "last_name": "Juefei-Xu" + }, + { + "first_name": "Runsheng", + "last_name": "Xu" + }, + { + "first_name": "Hongkai", + "last_name": "Yu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MetaCloak: Preventing Unauthorized Subject-driven Text-to-image Diffusion-based Synthesis via Meta-learning", - "authors": "Yixin Liu, Chenrui Fan, Yutong Dai, Xun Chen, Pan Zhou, Lichao Sun", + "authors": [ + { + "first_name": "Yixin", + "last_name": "Liu" + }, + { + "first_name": "Chenrui", + "last_name": "Fan" + }, + { + "first_name": "Yutong", + "last_name": "Dai" + }, + { + "first_name": "Xun", + "last_name": "Chen" + }, + { + "first_name": "Pan", + "last_name": "Zhou" + }, + { + "first_name": "Lichao", + "last_name": "Sun" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Neural Modes: Self-supervised Learning of Nonlinear Modal Subspaces", - "authors": "Jiahong Wang, Yinwei Du, Stelian Coros, Bernhard Thomaszewski", + "authors": [ + { + "first_name": "Jiahong", + "last_name": "Wang" + }, + { + "first_name": "Yinwei", + "last_name": "Du" + }, + { + "first_name": "Stelian", + "last_name": "Coros" + }, + { + "first_name": "Bernhard", + "last_name": "Thomaszewski" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "How to Train Neural Field Representations: A Comprehensive Study and Benchmark", - "authors": "Samuele Papa, Riccardo Valperga, David Knigge, Miltiadis Kofinas, Phillip Lippe, Jan-Jakob Sonke, Efstratios Gavves", + "authors": [ + { + "first_name": "Samuele", + "last_name": "Papa" + }, + { + "first_name": "Riccardo", + "last_name": "Valperga" + }, + { + "first_name": "David", + "last_name": "Knigge" + }, + { + "first_name": "Miltiadis", + "last_name": "Kofinas" + }, + { + "first_name": "Phillip", + "last_name": "Lippe" + }, + { + "first_name": "Jan-Jakob", + "last_name": "Sonke" + }, + { + "first_name": "Efstratios", + "last_name": "Gavves" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Delving into the Trajectory Long-tail Distribution for Muti-object Tracking", - "authors": "Sijia Chen, En Yu, Jinyang Li, Wenbing Tao", + "authors": [ + { + "first_name": "Sijia", + "last_name": "Chen" + }, + { + "first_name": "En", + "last_name": "Yu" + }, + { + "first_name": "Jinyang", + "last_name": "Li" + }, + { + "first_name": "Wenbing", + "last_name": "Tao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Tri-Modal Motion Retrieval by Learning a Joint Embedding Space", - "authors": "Kangning Yin, Shihao Zou, Yuxuan Ge, Zheng Tian", + "authors": [ + { + "first_name": "Kangning", + "last_name": "Yin" + }, + { + "first_name": "Shihao", + "last_name": "Zou" + }, + { + "first_name": "Yuxuan", + "last_name": "Ge" + }, + { + "first_name": "Zheng", + "last_name": "Tian" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Seg2Reg: Differentiable 2D Segmentation to 1D Regression Rendering for 360 Room Layout Reconstruction", - "authors": "Cheng Sun, Wei-En Tai, Yu-Lin Shih, Kuan-Wei Chen, Yong-Jing Syu, Kent Selwyn The, Yu-Chiang Frank Wang, Hwann-Tzong Chen", + "authors": [ + { + "first_name": "Cheng", + "last_name": "Sun" + }, + { + "first_name": "Wei-En", + "last_name": "Tai" + }, + { + "first_name": "Yu-Lin", + "last_name": "Shih" + }, + { + "first_name": "Kuan-Wei", + "last_name": "Chen" + }, + { + "first_name": "Yong-Jing", + "last_name": "Syu" + }, + { + "first_name": "Kent", + "last_name": "Selwyn The" + }, + { + "first_name": "Yu-Chiang", + "last_name": "Frank Wang" + }, + { + "first_name": "Hwann-Tzong", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Strong Transferable Adversarial Attacks via Ensembled Asymptotically Normal Distribution Learning", - "authors": "Zhengwei Fang, Rui Wang, Tao Huang, Liping Jing", + "authors": [ + { + "first_name": "Zhengwei", + "last_name": "Fang" + }, + { + "first_name": "Rui", + "last_name": "Wang" + }, + { + "first_name": "Tao", + "last_name": "Huang" + }, + { + "first_name": "Liping", + "last_name": "Jing" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Spanning Training Progress: Temporal Dual-Depth Scoring (TDDS) for Enhanced Dataset Pruning", - "authors": "Xin Zhang, Jiawei Du, Yunsong Li, Weiying Xie, Joey Tianyi Zhou", + "authors": [ + { + "first_name": "Xin", + "last_name": "Zhang" + }, + { + "first_name": "Jiawei", + "last_name": "Du" + }, + { + "first_name": "Yunsong", + "last_name": "Li" + }, + { + "first_name": "Weiying", + "last_name": "Xie" + }, + { + "first_name": "Joey", + "last_name": "Tianyi Zhou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "UniMix: Towards Domain Adaptive and Generalizable LiDAR Semantic Segmentation in Adverse Weather", - "authors": "Haimei Zhao, Jing Zhang, Zhuo Chen, Shanshan Zhao, Dacheng Tao", + "authors": [ + { + "first_name": "Haimei", + "last_name": "Zhao" + }, + { + "first_name": "Jing", + "last_name": "Zhang" + }, + { + "first_name": "Zhuo", + "last_name": "Chen" + }, + { + "first_name": "Shanshan", + "last_name": "Zhao" + }, + { + "first_name": "Dacheng", + "last_name": "Tao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Visual Delta Generator with Large Multi-modal Models for Semi-supervised Composed Image Retrieval", - "authors": "Young Kyun Jang, Donghyun Kim, Zihang Meng, Dat Huynh, Ser-Nam Lim", + "authors": [ + { + "first_name": "Young", + "last_name": "Kyun Jang" + }, + { + "first_name": "Donghyun", + "last_name": "Kim" + }, + { + "first_name": "Zihang", + "last_name": "Meng" + }, + { + "first_name": "Dat", + "last_name": "Huynh" + }, + { + "first_name": "Ser-Nam", + "last_name": "Lim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Selective Interpretable and Motion Consistent Privacy Attribute Obfuscation for Action Recognition", - "authors": "Filip Ilic, He Zhao, Thomas Pock, Richard P. Wildes", + "authors": [ + { + "first_name": "Filip", + "last_name": "Ilic" + }, + { + "first_name": "He", + "last_name": "Zhao" + }, + { + "first_name": "Thomas", + "last_name": "Pock" + }, + { + "first_name": "Richard", + "last_name": "P. Wildes" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HiPose: Hierarchical Binary Surface Encoding and Correspondence Pruning for RGB-D 6DoF Object Pose Estimation", - "authors": "Yongliang Lin, Yongzhi Su, Praveen Nathan, Sandeep Inuganti, Yan Di, Martin Sundermeyer, Fabian Manhardt, Didier Stricker, Jason Rambach, Yu Zhang", + "authors": [ + { + "first_name": "Yongliang", + "last_name": "Lin" + }, + { + "first_name": "Yongzhi", + "last_name": "Su" + }, + { + "first_name": "Praveen", + "last_name": "Nathan" + }, + { + "first_name": "Sandeep", + "last_name": "Inuganti" + }, + { + "first_name": "Yan", + "last_name": "Di" + }, + { + "first_name": "Martin", + "last_name": "Sundermeyer" + }, + { + "first_name": "Fabian", + "last_name": "Manhardt" + }, + { + "first_name": "Didier", + "last_name": "Stricker" + }, + { + "first_name": "Jason", + "last_name": "Rambach" + }, + { + "first_name": "Yu", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DiffForensics: Leveraging Diffusion Prior to Image Forgery Detection and Localization", - "authors": "Zeqin Yu, Jiangqun Ni, Yuzhen Lin, Haoyi Deng, Bin Li", + "authors": [ + { + "first_name": "Zeqin", + "last_name": "Yu" + }, + { + "first_name": "Jiangqun", + "last_name": "Ni" + }, + { + "first_name": "Yuzhen", + "last_name": "Lin" + }, + { + "first_name": "Haoyi", + "last_name": "Deng" + }, + { + "first_name": "Bin", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CoSeR: Bridging Image and Language for Cognitive Super-Resolution", - "authors": "Haoze Sun, Wenbo Li, Jianzhuang Liu, Haoyu Chen, Renjing Pei, Xueyi Zou, Youliang Yan, Yujiu Yang", + "authors": [ + { + "first_name": "Haoze", + "last_name": "Sun" + }, + { + "first_name": "Wenbo", + "last_name": "Li" + }, + { + "first_name": "Jianzhuang", + "last_name": "Liu" + }, + { + "first_name": "Haoyu", + "last_name": "Chen" + }, + { + "first_name": "Renjing", + "last_name": "Pei" + }, + { + "first_name": "Xueyi", + "last_name": "Zou" + }, + { + "first_name": "Youliang", + "last_name": "Yan" + }, + { + "first_name": "Yujiu", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Geometry-aware Reconstruction and Fusion-refined Rendering for Generalizable Neural Radiance Fields", - "authors": "Tianqi Liu, Xinyi Ye, Min Shi, Zihao Huang, Zhiyu Pan, Zhan Peng, Zhiguo Cao", + "authors": [ + { + "first_name": "Tianqi", + "last_name": "Liu" + }, + { + "first_name": "Xinyi", + "last_name": "Ye" + }, + { + "first_name": "Min", + "last_name": "Shi" + }, + { + "first_name": "Zihao", + "last_name": "Huang" + }, + { + "first_name": "Zhiyu", + "last_name": "Pan" + }, + { + "first_name": "Zhan", + "last_name": "Peng" + }, + { + "first_name": "Zhiguo", + "last_name": "Cao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Boosting Self-Supervision for Single-View Scene Completion via Knowledge Distillation", - "authors": "Keonhee Han, Dominik Muhle, Felix Wimbauer, Daniel Cremers", + "authors": [ + { + "first_name": "Keonhee", + "last_name": "Han" + }, + { + "first_name": "Dominik", + "last_name": "Muhle" + }, + { + "first_name": "Felix", + "last_name": "Wimbauer" + }, + { + "first_name": "Daniel", + "last_name": "Cremers" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PromptKD: Unsupervised Prompt Distillation for Vision-Language Models", - "authors": "Zheng Li, Xiang Li, Xinyi Fu, Xin Zhang, Weiqiang Wang, Shuo Chen, Jian Yang", + "authors": [ + { + "first_name": "Zheng", + "last_name": "Li" + }, + { + "first_name": "Xiang", + "last_name": "Li" + }, + { + "first_name": "Xinyi", + "last_name": "Fu" + }, + { + "first_name": "Xin", + "last_name": "Zhang" + }, + { + "first_name": "Weiqiang", + "last_name": "Wang" + }, + { + "first_name": "Shuo", + "last_name": "Chen" + }, + { + "first_name": "Jian", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "VideoBooth: Diffusion-based Video Generation with Image Prompts", - "authors": "Yuming Jiang, Tianxing Wu, Shuai Yang, Chenyang Si, Dahua Lin, Yu Qiao, Chen Change Loy, Ziwei Liu", + "authors": [ + { + "first_name": "Yuming", + "last_name": "Jiang" + }, + { + "first_name": "Tianxing", + "last_name": "Wu" + }, + { + "first_name": "Shuai", + "last_name": "Yang" + }, + { + "first_name": "Chenyang", + "last_name": "Si" + }, + { + "first_name": "Dahua", + "last_name": "Lin" + }, + { + "first_name": "Yu", + "last_name": "Qiao" + }, + { + "first_name": "Chen", + "last_name": "Change Loy" + }, + { + "first_name": "Ziwei", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Robust Overfitting Does Matter: Test-Time Adversarial Purification With FGSM", - "authors": "Linyu Tang, Lei Zhang", + "authors": [ + { + "first_name": "Linyu", + "last_name": "Tang" + }, + { + "first_name": "Lei", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Sparse Global Matching for Video Frame Interpolation with Large Motion", - "authors": "Chunxu Liu, Guozhen Zhang, Rui Zhao, Limin Wang", + "authors": [ + { + "first_name": "Chunxu", + "last_name": "Liu" + }, + { + "first_name": "Guozhen", + "last_name": "Zhang" + }, + { + "first_name": "Rui", + "last_name": "Zhao" + }, + { + "first_name": "Limin", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ExtDM: Distribution Extrapolation Diffusion Model for Video Prediction", - "authors": "Zhicheng Zhang, Junyao Hu, Wentao Cheng, Danda Paudel, Jufeng Yang", + "authors": [ + { + "first_name": "Zhicheng", + "last_name": "Zhang" + }, + { + "first_name": "Junyao", + "last_name": "Hu" + }, + { + "first_name": "Wentao", + "last_name": "Cheng" + }, + { + "first_name": "Danda", + "last_name": "Paudel" + }, + { + "first_name": "Jufeng", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Modality-Collaborative Test-Time Adaptation for Action Recognition", - "authors": "Baochen Xiong, Xiaoshan Yang, Yaguang Song, Yaowei Wang, Changsheng Xu", + "authors": [ + { + "first_name": "Baochen", + "last_name": "Xiong" + }, + { + "first_name": "Xiaoshan", + "last_name": "Yang" + }, + { + "first_name": "Yaguang", + "last_name": "Song" + }, + { + "first_name": "Yaowei", + "last_name": "Wang" + }, + { + "first_name": "Changsheng", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SCULPT: Shape-Conditioned Unpaired Learning of Pose-dependent Clothed and Textured Human Meshes", - "authors": "Soubhik Sanyal, Partha Ghosh, Jinlong Yang, Michael J. Black, Justus Thies, Timo Bolkart", + "authors": [ + { + "first_name": "Soubhik", + "last_name": "Sanyal" + }, + { + "first_name": "Partha", + "last_name": "Ghosh" + }, + { + "first_name": "Jinlong", + "last_name": "Yang" + }, + { + "first_name": "Michael", + "last_name": "J. Black" + }, + { + "first_name": "Justus", + "last_name": "Thies" + }, + { + "first_name": "Timo", + "last_name": "Bolkart" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Point Segment and Count: A Generalized Framework for Object Counting", - "authors": "Zhizhong Huang, Mingliang Dai, Yi Zhang, Junping Zhang, Hongming Shan", + "authors": [ + { + "first_name": "Zhizhong", + "last_name": "Huang" + }, + { + "first_name": "Mingliang", + "last_name": "Dai" + }, + { + "first_name": "Yi", + "last_name": "Zhang" + }, + { + "first_name": "Junping", + "last_name": "Zhang" + }, + { + "first_name": "Hongming", + "last_name": "Shan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Small Steps and Level Sets: Fitting Neural Surface Models with Point Guidance", - "authors": "Chamin Hewa Koneputugodage, Yizhak Ben-Shabat, Dylan Campbell, Stephen Gould", + "authors": [ + { + "first_name": "Chamin", + "last_name": "Hewa Koneputugodage" + }, + { + "first_name": "Yizhak", + "last_name": "Ben-Shabat" + }, + { + "first_name": "Dylan", + "last_name": "Campbell" + }, + { + "first_name": "Stephen", + "last_name": "Gould" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Domain-Agnostic Mutual Prompting for Unsupervised Domain Adaptation", - "authors": "Zhekai Du, Xinyao Li, Fengling Li, Ke Lu, Lei Zhu, Jingjing Li", + "authors": [ + { + "first_name": "Zhekai", + "last_name": "Du" + }, + { + "first_name": "Xinyao", + "last_name": "Li" + }, + { + "first_name": "Fengling", + "last_name": "Li" + }, + { + "first_name": "Ke", + "last_name": "Lu" + }, + { + "first_name": "Lei", + "last_name": "Zhu" + }, + { + "first_name": "Jingjing", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PTT: Point-Trajectory Transformer for Efficient Temporal 3D Object Detection", - "authors": "Kuan-Chih Huang, Weijie Lyu, Ming-Hsuan Yang, Yi-Hsuan Tsai", + "authors": [ + { + "first_name": "Kuan-Chih", + "last_name": "Huang" + }, + { + "first_name": "Weijie", + "last_name": "Lyu" + }, + { + "first_name": "Ming-Hsuan", + "last_name": "Yang" + }, + { + "first_name": "Yi-Hsuan", + "last_name": "Tsai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Generative Proxemics: A Prior for 3D Social Interaction from Images", - "authors": "Lea Müller, Vickie Ye, Georgios Pavlakos, Michael Black, Angjoo Kanazawa", + "authors": [ + { + "first_name": "Lea", + "last_name": "Müller" + }, + { + "first_name": "Vickie", + "last_name": "Ye" + }, + { + "first_name": "Georgios", + "last_name": "Pavlakos" + }, + { + "first_name": "Michael", + "last_name": "Black" + }, + { + "first_name": "Angjoo", + "last_name": "Kanazawa" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "A Simple and Effective Point-based Network for Event Camera 6-DOFs Pose Relocalization", - "authors": "Hongwei Ren, Jiadong Zhu, Yue Zhou, Haotian Fu, Yulong Huang, Bojun Cheng", + "authors": [ + { + "first_name": "Hongwei", + "last_name": "Ren" + }, + { + "first_name": "Jiadong", + "last_name": "Zhu" + }, + { + "first_name": "Yue", + "last_name": "Zhou" + }, + { + "first_name": "Haotian", + "last_name": "Fu" + }, + { + "first_name": "Yulong", + "last_name": "Huang" + }, + { + "first_name": "Bojun", + "last_name": "Cheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Semantic-Aware Multi-Label Adversarial Attacks", - "authors": "Hassan Mahmood, Ehsan Elhamifar", + "authors": [ + { + "first_name": "Hassan", + "last_name": "Mahmood" + }, + { + "first_name": "Ehsan", + "last_name": "Elhamifar" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "EasyDrag: Efficient Point-based Manipulation on Diffusion Models", - "authors": "Xingzhong Hou, Boxiao Liu, Yi Zhang, Jihao Liu, Yu Liu, Haihang You", + "authors": [ + { + "first_name": "Xingzhong", + "last_name": "Hou" + }, + { + "first_name": "Boxiao", + "last_name": "Liu" + }, + { + "first_name": "Yi", + "last_name": "Zhang" + }, + { + "first_name": "Jihao", + "last_name": "Liu" + }, + { + "first_name": "Yu", + "last_name": "Liu" + }, + { + "first_name": "Haihang", + "last_name": "You" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Region-Based Representations Revisited", - "authors": "Michal Shlapentokh-Rothman, Ansel Blume, Yao Xiao, Yuqun Wu, Sethuraman TV, Heyi Tao, Jae Yong Lee, Wilfredo Torres, Yu-Xiong Wang, Derek Hoiem", + "authors": [ + { + "first_name": "Michal", + "last_name": "Shlapentokh-Rothman" + }, + { + "first_name": "Ansel", + "last_name": "Blume" + }, + { + "first_name": "Yao", + "last_name": "Xiao" + }, + { + "first_name": "Yuqun", + "last_name": "Wu" + }, + { + "first_name": "Sethuraman", + "last_name": "TV" + }, + { + "first_name": "Heyi", + "last_name": "Tao" + }, + { + "first_name": "Jae", + "last_name": "Yong Lee" + }, + { + "first_name": "Wilfredo", + "last_name": "Torres" + }, + { + "first_name": "Yu-Xiong", + "last_name": "Wang" + }, + { + "first_name": "Derek", + "last_name": "Hoiem" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GenH2R: Learning Generalizable Human-to-Robot Handover via Scalable Simulation Demonstration and Imitation", - "authors": "Zifan Wang, Junyu Chen, Ziqing Chen, Pengwei Xie, Rui Chen, Li Yi", + "authors": [ + { + "first_name": "Zifan", + "last_name": "Wang" + }, + { + "first_name": "Junyu", + "last_name": "Chen" + }, + { + "first_name": "Ziqing", + "last_name": "Chen" + }, + { + "first_name": "Pengwei", + "last_name": "Xie" + }, + { + "first_name": "Rui", + "last_name": "Chen" + }, + { + "first_name": "Li", + "last_name": "Yi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Modality-Agnostic Structural Image Representation Learning for Deformable Multi-Modality Medical Image Registration", - "authors": "Tony C. W. Mok, Zi Li, Yunhao Bai, Jianpeng Zhang, Wei Liu, Yan-Jie Zhou, Ke Yan, Dakai Jin, Yu Shi, Xiaoli Yin, Le Lu, Ling Zhang", + "authors": [ + { + "first_name": "Tony", + "last_name": "C. W. Mok" + }, + { + "first_name": "Zi", + "last_name": "Li" + }, + { + "first_name": "Yunhao", + "last_name": "Bai" + }, + { + "first_name": "Jianpeng", + "last_name": "Zhang" + }, + { + "first_name": "Wei", + "last_name": "Liu" + }, + { + "first_name": "Yan-Jie", + "last_name": "Zhou" + }, + { + "first_name": "Ke", + "last_name": "Yan" + }, + { + "first_name": "Dakai", + "last_name": "Jin" + }, + { + "first_name": "Yu", + "last_name": "Shi" + }, + { + "first_name": "Xiaoli", + "last_name": "Yin" + }, + { + "first_name": "Le", + "last_name": "Lu" + }, + { + "first_name": "Ling", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Any-Shift Prompting for Generalization over Distributions", - "authors": "Zehao Xiao, Jiayi Shen, Mohammad Mahdi Derakhshani, Shengcai Liao, Cees G. M. Snoek", + "authors": [ + { + "first_name": "Zehao", + "last_name": "Xiao" + }, + { + "first_name": "Jiayi", + "last_name": "Shen" + }, + { + "first_name": "Mohammad", + "last_name": "Mahdi Derakhshani" + }, + { + "first_name": "Shengcai", + "last_name": "Liao" + }, + { + "first_name": "Cees", + "last_name": "G. M. Snoek" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "InterHandGen: Two-Hand Interaction Generation via Cascaded Reverse Diffusion", - "authors": "Jihyun Lee, Shunsuke Saito, Giljoo Nam, Minhyuk Sung, Tae-Kyun Kim", + "authors": [ + { + "first_name": "Jihyun", + "last_name": "Lee" + }, + { + "first_name": "Shunsuke", + "last_name": "Saito" + }, + { + "first_name": "Giljoo", + "last_name": "Nam" + }, + { + "first_name": "Minhyuk", + "last_name": "Sung" + }, + { + "first_name": "Tae-Kyun", + "last_name": "Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CPR-Coach: Recognizing Composite Error Actions based on Single-class Training", - "authors": "Shunli Wang, Shuaibing Wang, Dingkang Yang, Mingcheng Li, Haopeng Kuang, Xiao Zhao, Liuzhen Su, Peng Zhai, Lihua Zhang", + "authors": [ + { + "first_name": "Shunli", + "last_name": "Wang" + }, + { + "first_name": "Shuaibing", + "last_name": "Wang" + }, + { + "first_name": "Dingkang", + "last_name": "Yang" + }, + { + "first_name": "Mingcheng", + "last_name": "Li" + }, + { + "first_name": "Haopeng", + "last_name": "Kuang" + }, + { + "first_name": "Xiao", + "last_name": "Zhao" + }, + { + "first_name": "Liuzhen", + "last_name": "Su" + }, + { + "first_name": "Peng", + "last_name": "Zhai" + }, + { + "first_name": "Lihua", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Video2Game: Real-time Interactive Realistic and Browser-Compatible Environment from a Single Video", - "authors": "Hongchi Xia, Zhi-Hao Lin, Wei-Chiu Ma, Shenlong Wang", + "authors": [ + { + "first_name": "Hongchi", + "last_name": "Xia" + }, + { + "first_name": "Zhi-Hao", + "last_name": "Lin" + }, + { + "first_name": "Wei-Chiu", + "last_name": "Ma" + }, + { + "first_name": "Shenlong", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Tackling the Singularities at the Endpoints of Time Intervals in Diffusion Models", - "authors": "Pengze Zhang, Hubery Yin, Chen Li, Xiaohua Xie", + "authors": [ + { + "first_name": "Pengze", + "last_name": "Zhang" + }, + { + "first_name": "Hubery", + "last_name": "Yin" + }, + { + "first_name": "Chen", + "last_name": "Li" + }, + { + "first_name": "Xiaohua", + "last_name": "Xie" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MatSynth: A Modern PBR Materials Dataset", - "authors": "Giuseppe Vecchio, Valentin Deschaintre", + "authors": [ + { + "first_name": "Giuseppe", + "last_name": "Vecchio" + }, + { + "first_name": "Valentin", + "last_name": "Deschaintre" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CHAIN: Enhancing Generalization in Data-Efficient GANs via lipsCHitz continuity constrAIned Normalization", - "authors": "Yao Ni, Piotr Koniusz", + "authors": [ + { + "first_name": "Yao", + "last_name": "Ni" + }, + { + "first_name": "Piotr", + "last_name": "Koniusz" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "RTracker: Recoverable Tracking via PN Tree Structured Memory", - "authors": "Yuqing Huang, Xin Li, Zikun Zhou, Yaowei Wang, Zhenyu He, Ming-Hsuan Yang", + "authors": [ + { + "first_name": "Yuqing", + "last_name": "Huang" + }, + { + "first_name": "Xin", + "last_name": "Li" + }, + { + "first_name": "Zikun", + "last_name": "Zhou" + }, + { + "first_name": "Yaowei", + "last_name": "Wang" + }, + { + "first_name": "Zhenyu", + "last_name": "He" + }, + { + "first_name": "Ming-Hsuan", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "High-Quality Facial Geometry and Appearance Capture at Home", - "authors": "Yuxuan Han, Junfeng Lyu, Feng Xu", + "authors": [ + { + "first_name": "Yuxuan", + "last_name": "Han" + }, + { + "first_name": "Junfeng", + "last_name": "Lyu" + }, + { + "first_name": "Feng", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DualAD: Disentangling the Dynamic and Static World for End-to-End Driving", - "authors": "Simon Doll, Niklas Hanselmann, Lukas Schneider, Richard Schulz, Marius Cordts, Markus Enzweiler, Hendrik P. A. Lensch", + "authors": [ + { + "first_name": "Simon", + "last_name": "Doll" + }, + { + "first_name": "Niklas", + "last_name": "Hanselmann" + }, + { + "first_name": "Lukas", + "last_name": "Schneider" + }, + { + "first_name": "Richard", + "last_name": "Schulz" + }, + { + "first_name": "Marius", + "last_name": "Cordts" + }, + { + "first_name": "Markus", + "last_name": "Enzweiler" + }, + { + "first_name": "Hendrik", + "last_name": "P. A. Lensch" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "OTE: Exploring Accurate Scene Text Recognition Using One Token", - "authors": "Jianjun Xu, Yuxin Wang, Hongtao Xie, Yongdong Zhang", + "authors": [ + { + "first_name": "Jianjun", + "last_name": "Xu" + }, + { + "first_name": "Yuxin", + "last_name": "Wang" + }, + { + "first_name": "Hongtao", + "last_name": "Xie" + }, + { + "first_name": "Yongdong", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detection", - "authors": "Jakub Micorek, Horst Possegger, Dominik Narnhofer, Horst Bischof, Mateusz Kozinski", + "authors": [ + { + "first_name": "Jakub", + "last_name": "Micorek" + }, + { + "first_name": "Horst", + "last_name": "Possegger" + }, + { + "first_name": "Dominik", + "last_name": "Narnhofer" + }, + { + "first_name": "Horst", + "last_name": "Bischof" + }, + { + "first_name": "Mateusz", + "last_name": "Kozinski" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Your Image is My Video: Reshaping the Receptive Field via Image-To-Video Differentiable AutoAugmentation and Fusion", - "authors": "Sofia Casarin, Cynthia I. Ugwu, Sergio Escalera, Oswald Lanz", + "authors": [ + { + "first_name": "Sofia", + "last_name": "Casarin" + }, + { + "first_name": "Cynthia", + "last_name": "I. Ugwu" + }, + { + "first_name": "Sergio", + "last_name": "Escalera" + }, + { + "first_name": "Oswald", + "last_name": "Lanz" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PTQ4SAM: Post-Training Quantization for Segment Anything", - "authors": "Chengtao Lv, Hong Chen, Jinyang Guo, Yifu Ding, Xianglong Liu", + "authors": [ + { + "first_name": "Chengtao", + "last_name": "Lv" + }, + { + "first_name": "Hong", + "last_name": "Chen" + }, + { + "first_name": "Jinyang", + "last_name": "Guo" + }, + { + "first_name": "Yifu", + "last_name": "Ding" + }, + { + "first_name": "Xianglong", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Improving Bird's Eye View Semantic Segmentation by Task Decomposition", - "authors": "Tianhao Zhao, Yongcan Chen, Yu Wu, Tianyang Liu, Bo Du, Peilun Xiao, Shi Qiu, Hongda Yang, Guozhen Li, Yi Yang, Yutian Lin", + "authors": [ + { + "first_name": "Tianhao", + "last_name": "Zhao" + }, + { + "first_name": "Yongcan", + "last_name": "Chen" + }, + { + "first_name": "Yu", + "last_name": "Wu" + }, + { + "first_name": "Tianyang", + "last_name": "Liu" + }, + { + "first_name": "Bo", + "last_name": "Du" + }, + { + "first_name": "Peilun", + "last_name": "Xiao" + }, + { + "first_name": "Shi", + "last_name": "Qiu" + }, + { + "first_name": "Hongda", + "last_name": "Yang" + }, + { + "first_name": "Guozhen", + "last_name": "Li" + }, + { + "first_name": "Yi", + "last_name": "Yang" + }, + { + "first_name": "Yutian", + "last_name": "Lin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SpikingResformer: Bridging ResNet and Vision Transformer in Spiking Neural Networks", - "authors": "Xinyu Shi, Zecheng Hao, Zhaofei Yu", + "authors": [ + { + "first_name": "Xinyu", + "last_name": "Shi" + }, + { + "first_name": "Zecheng", + "last_name": "Hao" + }, + { + "first_name": "Zhaofei", + "last_name": "Yu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Scene Adaptive Sparse Transformer for Event-based Object Detection", - "authors": "Yansong Peng, Hebei Li, Yueyi Zhang, Xiaoyan Sun, Feng Wu", + "authors": [ + { + "first_name": "Yansong", + "last_name": "Peng" + }, + { + "first_name": "Hebei", + "last_name": "Li" + }, + { + "first_name": "Yueyi", + "last_name": "Zhang" + }, + { + "first_name": "Xiaoyan", + "last_name": "Sun" + }, + { + "first_name": "Feng", + "last_name": "Wu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Gaussian Shadow Casting for Neural Characters", - "authors": "Luis Bolanos, Shih-Yang Su, Helge Rhodin", + "authors": [ + { + "first_name": "Luis", + "last_name": "Bolanos" + }, + { + "first_name": "Shih-Yang", + "last_name": "Su" + }, + { + "first_name": "Helge", + "last_name": "Rhodin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CURSOR: Scalable Mixed-Order Hypergraph Matching with CUR Decomposition", - "authors": "Qixuan Zheng, Ming Zhang, Hong Yan", + "authors": [ + { + "first_name": "Qixuan", + "last_name": "Zheng" + }, + { + "first_name": "Ming", + "last_name": "Zhang" + }, + { + "first_name": "Hong", + "last_name": "Yan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Federated Online Adaptation for Deep Stereo", - "authors": "Matteo Poggi, Fabio Tosi", + "authors": [ + { + "first_name": "Matteo", + "last_name": "Poggi" + }, + { + "first_name": "Fabio", + "last_name": "Tosi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Sequential Modeling Enables Scalable Learning for Large Vision Models", - "authors": "Yutong Bai, Xinyang Geng, Karttikeya Mangalam, Amir Bar, Alan L. Yuille, Trevor Darrell, Jitendra Malik, Alexei A. Efros", + "authors": [ + { + "first_name": "Yutong", + "last_name": "Bai" + }, + { + "first_name": "Xinyang", + "last_name": "Geng" + }, + { + "first_name": "Karttikeya", + "last_name": "Mangalam" + }, + { + "first_name": "Amir", + "last_name": "Bar" + }, + { + "first_name": "Alan", + "last_name": "L. Yuille" + }, + { + "first_name": "Trevor", + "last_name": "Darrell" + }, + { + "first_name": "Jitendra", + "last_name": "Malik" + }, + { + "first_name": "Alexei", + "last_name": "A. Efros" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Self-Supervised Dual Contouring", - "authors": "Ramana Sundararaman, Roman Klokov, Maks Ovsjanikov", + "authors": [ + { + "first_name": "Ramana", + "last_name": "Sundararaman" + }, + { + "first_name": "Roman", + "last_name": "Klokov" + }, + { + "first_name": "Maks", + "last_name": "Ovsjanikov" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Regularized Parameter Uncertainty for Improving Generalization in Reinforcement Learning", - "authors": "Pehuen Moure, Longbiao Cheng, Joachim Ott, Zuowen Wang, Shih-Chii Liu", + "authors": [ + { + "first_name": "Pehuen", + "last_name": "Moure" + }, + { + "first_name": "Longbiao", + "last_name": "Cheng" + }, + { + "first_name": "Joachim", + "last_name": "Ott" + }, + { + "first_name": "Zuowen", + "last_name": "Wang" + }, + { + "first_name": "Shih-Chii", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GigaTraj: Predicting Long-term Trajectories of Hundreds of Pedestrians in Gigapixel Complex Scenes", - "authors": "Haozhe Lin, Chunyu Wei, Li He, Yuchen Guo, Yunqi Zhao, Shanglong Li, Lu Fang", + "authors": [ + { + "first_name": "Haozhe", + "last_name": "Lin" + }, + { + "first_name": "Chunyu", + "last_name": "Wei" + }, + { + "first_name": "Li", + "last_name": "He" + }, + { + "first_name": "Yuchen", + "last_name": "Guo" + }, + { + "first_name": "Yunqi", + "last_name": "Zhao" + }, + { + "first_name": "Shanglong", + "last_name": "Li" + }, + { + "first_name": "Lu", + "last_name": "Fang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GSVA: Generalized Segmentation via Multimodal Large Language Models", - "authors": "Zhuofan Xia, Dongchen Han, Yizeng Han, Xuran Pan, Shiji Song, Gao Huang", + "authors": [ + { + "first_name": "Zhuofan", + "last_name": "Xia" + }, + { + "first_name": "Dongchen", + "last_name": "Han" + }, + { + "first_name": "Yizeng", + "last_name": "Han" + }, + { + "first_name": "Xuran", + "last_name": "Pan" + }, + { + "first_name": "Shiji", + "last_name": "Song" + }, + { + "first_name": "Gao", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "AdaBM: On-the-Fly Adaptive Bit Mapping for Image Super-Resolution", - "authors": "Cheeun Hong, Kyoung Mu Lee", + "authors": [ + { + "first_name": "Cheeun", + "last_name": "Hong" + }, + { + "first_name": "Kyoung", + "last_name": "Mu Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CoralSCOP: Segment any COral Image on this Planet", - "authors": "Ziqiang Zheng, Haixin Liang, Binh-Son Hua, Yue Him Wong, Put Ang Jr, Apple Pui Yi Chui, Sai-Kit Yeung", + "authors": [ + { + "first_name": "Ziqiang", + "last_name": "Zheng" + }, + { + "first_name": "Haixin", + "last_name": "Liang" + }, + { + "first_name": "Binh-Son", + "last_name": "Hua" + }, + { + "first_name": "Yue", + "last_name": "Him Wong" + }, + { + "first_name": "Put", + "last_name": "Ang Jr" + }, + { + "first_name": "Apple", + "last_name": "Pui Yi Chui" + }, + { + "first_name": "Sai-Kit", + "last_name": "Yeung" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SVGDreamer: Text Guided SVG Generation with Diffusion Model", - "authors": "Ximing Xing, Haitao Zhou, Chuang Wang, Jing Zhang, Dong Xu, Qian Yu", + "authors": [ + { + "first_name": "Ximing", + "last_name": "Xing" + }, + { + "first_name": "Haitao", + "last_name": "Zhou" + }, + { + "first_name": "Chuang", + "last_name": "Wang" + }, + { + "first_name": "Jing", + "last_name": "Zhang" + }, + { + "first_name": "Dong", + "last_name": "Xu" + }, + { + "first_name": "Qian", + "last_name": "Yu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "BlockGCN: Redefine Topology Awareness for Skeleton-Based Action Recognition", - "authors": "Yuxuan Zhou, Xudong Yan, Zhi-Qi Cheng, Yan Yan, Qi Dai, Xian-Sheng Hua", + "authors": [ + { + "first_name": "Yuxuan", + "last_name": "Zhou" + }, + { + "first_name": "Xudong", + "last_name": "Yan" + }, + { + "first_name": "Zhi-Qi", + "last_name": "Cheng" + }, + { + "first_name": "Yan", + "last_name": "Yan" + }, + { + "first_name": "Qi", + "last_name": "Dai" + }, + { + "first_name": "Xian-Sheng", + "last_name": "Hua" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Improved Baselines with Visual Instruction Tuning", - "authors": "Haotian Liu, Chunyuan Li, Yuheng Li, Yong Jae Lee", + "authors": [ + { + "first_name": "Haotian", + "last_name": "Liu" + }, + { + "first_name": "Chunyuan", + "last_name": "Li" + }, + { + "first_name": "Yuheng", + "last_name": "Li" + }, + { + "first_name": "Yong", + "last_name": "Jae Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Structure-Guided Adversarial Training of Diffusion Models", - "authors": "Ling Yang, Haotian Qian, Zhilong Zhang, Jingwei Liu, Bin Cui", + "authors": [ + { + "first_name": "Ling", + "last_name": "Yang" + }, + { + "first_name": "Haotian", + "last_name": "Qian" + }, + { + "first_name": "Zhilong", + "last_name": "Zhang" + }, + { + "first_name": "Jingwei", + "last_name": "Liu" + }, + { + "first_name": "Bin", + "last_name": "Cui" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "NIFTY: Neural Object Interaction Fields for Guided Human Motion Synthesis", - "authors": "Nilesh Kulkarni, Davis Rempe, Kyle Genova, Abhijit Kundu, Justin Johnson, David Fouhey, Leonidas Guibas", + "authors": [ + { + "first_name": "Nilesh", + "last_name": "Kulkarni" + }, + { + "first_name": "Davis", + "last_name": "Rempe" + }, + { + "first_name": "Kyle", + "last_name": "Genova" + }, + { + "first_name": "Abhijit", + "last_name": "Kundu" + }, + { + "first_name": "Justin", + "last_name": "Johnson" + }, + { + "first_name": "David", + "last_name": "Fouhey" + }, + { + "first_name": "Leonidas", + "last_name": "Guibas" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "C2KD: Bridging the Modality Gap for Cross-Modal Knowledge Distillation", - "authors": "Fushuo Huo, Wenchao Xu, Jingcai Guo, Haozhao Wang, Song Guo", + "authors": [ + { + "first_name": "Fushuo", + "last_name": "Huo" + }, + { + "first_name": "Wenchao", + "last_name": "Xu" + }, + { + "first_name": "Jingcai", + "last_name": "Guo" + }, + { + "first_name": "Haozhao", + "last_name": "Wang" + }, + { + "first_name": "Song", + "last_name": "Guo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Traceable Federated Continual Learning", - "authors": "Qiang Wang, Bingyan Liu, Yawen Li", + "authors": [ + { + "first_name": "Qiang", + "last_name": "Wang" + }, + { + "first_name": "Bingyan", + "last_name": "Liu" + }, + { + "first_name": "Yawen", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Can Language Beat Numerical Regression? Language-Based Multimodal Trajectory Prediction", - "authors": "Inhwan Bae, Junoh Lee, Hae-Gon Jeon", + "authors": [ + { + "first_name": "Inhwan", + "last_name": "Bae" + }, + { + "first_name": "Junoh", + "last_name": "Lee" + }, + { + "first_name": "Hae-Gon", + "last_name": "Jeon" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Building Optimal Neural Architectures using Interpretable Knowledge", - "authors": "Keith G. Mills, Fred X. Han, Mohammad Salameh, Shengyao Lu, Chunhua Zhou, Jiao He, Fengyu Sun, Di Niu", + "authors": [ + { + "first_name": "Keith", + "last_name": "G. Mills" + }, + { + "first_name": "Fred", + "last_name": "X. Han" + }, + { + "first_name": "Mohammad", + "last_name": "Salameh" + }, + { + "first_name": "Shengyao", + "last_name": "Lu" + }, + { + "first_name": "Chunhua", + "last_name": "Zhou" + }, + { + "first_name": "Jiao", + "last_name": "He" + }, + { + "first_name": "Fengyu", + "last_name": "Sun" + }, + { + "first_name": "Di", + "last_name": "Niu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "V?: Guided Visual Search as a Core Mechanism in Multimodal LLMs", - "authors": "Penghao Wu, Saining Xie", + "authors": [ + { + "first_name": "Penghao", + "last_name": "Wu" + }, + { + "first_name": "Saining", + "last_name": "Xie" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Unexplored Faces of Robustness and Out-of-Distribution: Covariate Shifts in Environment and Sensor Domains", - "authors": "Eunsu Baek, Keondo Park, Jiyoon Kim, Hyung-Sin Kim", + "authors": [ + { + "first_name": "Eunsu", + "last_name": "Baek" + }, + { + "first_name": "Keondo", + "last_name": "Park" + }, + { + "first_name": "Jiyoon", + "last_name": "Kim" + }, + { + "first_name": "Hyung-Sin", + "last_name": "Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Uncertainty Visualization via Low-Dimensional Posterior Projections", - "authors": "Omer Yair, Elias Nehme, Tomer Michaeli", + "authors": [ + { + "first_name": "Omer", + "last_name": "Yair" + }, + { + "first_name": "Elias", + "last_name": "Nehme" + }, + { + "first_name": "Tomer", + "last_name": "Michaeli" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "VSCode: General Visual Salient and Camouflaged Object Detection with 2D Prompt Learning", - "authors": "Ziyang Luo, Nian Liu, Wangbo Zhao, Xuguang Yang, Dingwen Zhang, Deng-Ping Fan, Fahad Khan, Junwei Han", + "authors": [ + { + "first_name": "Ziyang", + "last_name": "Luo" + }, + { + "first_name": "Nian", + "last_name": "Liu" + }, + { + "first_name": "Wangbo", + "last_name": "Zhao" + }, + { + "first_name": "Xuguang", + "last_name": "Yang" + }, + { + "first_name": "Dingwen", + "last_name": "Zhang" + }, + { + "first_name": "Deng-Ping", + "last_name": "Fan" + }, + { + "first_name": "Fahad", + "last_name": "Khan" + }, + { + "first_name": "Junwei", + "last_name": "Han" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting", - "authors": "Yiwen Chen, Zilong Chen, Chi Zhang, Feng Wang, Xiaofeng Yang, Yikai Wang, Zhongang Cai, Lei Yang, Huaping Liu, Guosheng Lin", + "authors": [ + { + "first_name": "Yiwen", + "last_name": "Chen" + }, + { + "first_name": "Zilong", + "last_name": "Chen" + }, + { + "first_name": "Chi", + "last_name": "Zhang" + }, + { + "first_name": "Feng", + "last_name": "Wang" + }, + { + "first_name": "Xiaofeng", + "last_name": "Yang" + }, + { + "first_name": "Yikai", + "last_name": "Wang" + }, + { + "first_name": "Zhongang", + "last_name": "Cai" + }, + { + "first_name": "Lei", + "last_name": "Yang" + }, + { + "first_name": "Huaping", + "last_name": "Liu" + }, + { + "first_name": "Guosheng", + "last_name": "Lin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Holo-Relighting: Controllable Volumetric Portrait Relighting from a Single Image", - "authors": "Yiqun Mei, Yu Zeng, He Zhang, Zhixin Shu, Xuaner Zhang, Sai Bi, Jianming Zhang, HyunJoon Jung, Vishal M. Patel", + "authors": [ + { + "first_name": "Yiqun", + "last_name": "Mei" + }, + { + "first_name": "Yu", + "last_name": "Zeng" + }, + { + "first_name": "He", + "last_name": "Zhang" + }, + { + "first_name": "Zhixin", + "last_name": "Shu" + }, + { + "first_name": "Xuaner", + "last_name": "Zhang" + }, + { + "first_name": "Sai", + "last_name": "Bi" + }, + { + "first_name": "Jianming", + "last_name": "Zhang" + }, + { + "first_name": "HyunJoon", + "last_name": "Jung" + }, + { + "first_name": "Vishal", + "last_name": "M. Patel" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Noisy One-point Homographies are Surprisingly Good", - "authors": "Yaqing Ding, Jonathan Astermark, Magnus Oskarsson, Viktor Larsson", + "authors": [ + { + "first_name": "Yaqing", + "last_name": "Ding" + }, + { + "first_name": "Jonathan", + "last_name": "Astermark" + }, + { + "first_name": "Magnus", + "last_name": "Oskarsson" + }, + { + "first_name": "Viktor", + "last_name": "Larsson" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PointInfinity: Resolution-Invariant Point Diffusion Models", - "authors": "Zixuan Huang, Justin Johnson, Shoubhik Debnath, James M. Rehg, Chao-Yuan Wu", + "authors": [ + { + "first_name": "Zixuan", + "last_name": "Huang" + }, + { + "first_name": "Justin", + "last_name": "Johnson" + }, + { + "first_name": "Shoubhik", + "last_name": "Debnath" + }, + { + "first_name": "James", + "last_name": "M. Rehg" + }, + { + "first_name": "Chao-Yuan", + "last_name": "Wu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Panacea: Panoramic and Controllable Video Generation for Autonomous Driving", - "authors": "Yuqing Wen, Yucheng Zhao, Yingfei Liu, Fan Jia, Yanhui Wang, Chong Luo, Chi Zhang, Tiancai Wang, Xiaoyan Sun, Xiangyu Zhang", + "authors": [ + { + "first_name": "Yuqing", + "last_name": "Wen" + }, + { + "first_name": "Yucheng", + "last_name": "Zhao" + }, + { + "first_name": "Yingfei", + "last_name": "Liu" + }, + { + "first_name": "Fan", + "last_name": "Jia" + }, + { + "first_name": "Yanhui", + "last_name": "Wang" + }, + { + "first_name": "Chong", + "last_name": "Luo" + }, + { + "first_name": "Chi", + "last_name": "Zhang" + }, + { + "first_name": "Tiancai", + "last_name": "Wang" + }, + { + "first_name": "Xiaoyan", + "last_name": "Sun" + }, + { + "first_name": "Xiangyu", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Open-Vocabulary Semantic Segmentation with Image Embedding Balancing", - "authors": "Xiangheng Shan, Dongyue Wu, Guilin Zhu, Yuanjie Shao, Nong Sang, Changxin Gao", + "authors": [ + { + "first_name": "Xiangheng", + "last_name": "Shan" + }, + { + "first_name": "Dongyue", + "last_name": "Wu" + }, + { + "first_name": "Guilin", + "last_name": "Zhu" + }, + { + "first_name": "Yuanjie", + "last_name": "Shao" + }, + { + "first_name": "Nong", + "last_name": "Sang" + }, + { + "first_name": "Changxin", + "last_name": "Gao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Structured Model Probing: Empowering Efficient Transfer Learning by Structured Regularization", - "authors": "Zhi-Fan Wu, Chaojie Mao, Wue Wang, Jianwen Jiang, Yiliang Lv, Rong Jin", + "authors": [ + { + "first_name": "Zhi-Fan", + "last_name": "Wu" + }, + { + "first_name": "Chaojie", + "last_name": "Mao" + }, + { + "first_name": "Wue", + "last_name": "Wang" + }, + { + "first_name": "Jianwen", + "last_name": "Jiang" + }, + { + "first_name": "Yiliang", + "last_name": "Lv" + }, + { + "first_name": "Rong", + "last_name": "Jin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Multi-Modal Proxy Learning Towards Personalized Visual Multiple Clustering", - "authors": "Jiawei Yao, Qi Qian, Juhua Hu", + "authors": [ + { + "first_name": "Jiawei", + "last_name": "Yao" + }, + { + "first_name": "Qi", + "last_name": "Qian" + }, + { + "first_name": "Juhua", + "last_name": "Hu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DreamMatcher: Appearance Matching Self-Attention for Semantically-Consistent Text-to-Image Personalization", - "authors": "Jisu Nam, Heesu Kim, DongJae Lee, Siyoon Jin, Seungryong Kim, Seunggyu Chang", + "authors": [ + { + "first_name": "Jisu", + "last_name": "Nam" + }, + { + "first_name": "Heesu", + "last_name": "Kim" + }, + { + "first_name": "DongJae", + "last_name": "Lee" + }, + { + "first_name": "Siyoon", + "last_name": "Jin" + }, + { + "first_name": "Seungryong", + "last_name": "Kim" + }, + { + "first_name": "Seunggyu", + "last_name": "Chang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Stronger Fewer & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation", - "authors": "Zhixiang Wei, Lin Chen, Yi Jin, Xiaoxiao Ma, Tianle Liu, Pengyang Ling, Ben Wang, Huaian Chen, Jinjin Zheng", + "authors": [ + { + "first_name": "Zhixiang", + "last_name": "Wei" + }, + { + "first_name": "Lin", + "last_name": "Chen" + }, + { + "first_name": "Yi", + "last_name": "Jin" + }, + { + "first_name": "Xiaoxiao", + "last_name": "Ma" + }, + { + "first_name": "Tianle", + "last_name": "Liu" + }, + { + "first_name": "Pengyang", + "last_name": "Ling" + }, + { + "first_name": "Ben", + "last_name": "Wang" + }, + { + "first_name": "Huaian", + "last_name": "Chen" + }, + { + "first_name": "Jinjin", + "last_name": "Zheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PolarMatte: Fully Computational Ground-Truth-Quality Alpha Matte Extraction for Images and Video using Polarized Screen Matting", - "authors": "Kenji Enomoto, TJ Rhodes, Brian Price, Gavin Miller", + "authors": [ + { + "first_name": "Kenji", + "last_name": "Enomoto" + }, + { + "first_name": "TJ", + "last_name": "Rhodes" + }, + { + "first_name": "Brian", + "last_name": "Price" + }, + { + "first_name": "Gavin", + "last_name": "Miller" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ChAda-ViT : Channel Adaptive Attention for Joint Representation Learning of Heterogeneous Microscopy Images", - "authors": "Nicolas Bourriez, Ihab Bendidi, Ethan Cohen, Gabriel Watkinson, Maxime Sanchez, Guillaume Bollot, Auguste Genovesio", + "authors": [ + { + "first_name": "Nicolas", + "last_name": "Bourriez" + }, + { + "first_name": "Ihab", + "last_name": "Bendidi" + }, + { + "first_name": "Ethan", + "last_name": "Cohen" + }, + { + "first_name": "Gabriel", + "last_name": "Watkinson" + }, + { + "first_name": "Maxime", + "last_name": "Sanchez" + }, + { + "first_name": "Guillaume", + "last_name": "Bollot" + }, + { + "first_name": "Auguste", + "last_name": "Genovesio" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CARZero: Cross-Attention Alignment for Radiology Zero-Shot Classification", - "authors": "Haoran Lai, Qingsong Yao, Zihang Jiang, Rongsheng Wang, Zhiyang He, Xiaodong Tao, S. Kevin Zhou", + "authors": [ + { + "first_name": "Haoran", + "last_name": "Lai" + }, + { + "first_name": "Qingsong", + "last_name": "Yao" + }, + { + "first_name": "Zihang", + "last_name": "Jiang" + }, + { + "first_name": "Rongsheng", + "last_name": "Wang" + }, + { + "first_name": "Zhiyang", + "last_name": "He" + }, + { + "first_name": "Xiaodong", + "last_name": "Tao" + }, + { + "first_name": "S.", + "last_name": "Kevin Zhou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HOIDiffusion: Generating Realistic 3D Hand-Object Interaction Data", - "authors": "Mengqi Zhang, Yang Fu, Zheng Ding, Sifei Liu, Zhuowen Tu, Xiaolong Wang", + "authors": [ + { + "first_name": "Mengqi", + "last_name": "Zhang" + }, + { + "first_name": "Yang", + "last_name": "Fu" + }, + { + "first_name": "Zheng", + "last_name": "Ding" + }, + { + "first_name": "Sifei", + "last_name": "Liu" + }, + { + "first_name": "Zhuowen", + "last_name": "Tu" + }, + { + "first_name": "Xiaolong", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "VecFusion: Vector Font Generation with Diffusion", - "authors": "Vikas Thamizharasan, Difan Liu, Shantanu Agarwal, Matthew Fisher, Michael Gharbi, Oliver Wang, Alec Jacobson, Evangelos Kalogerakis", + "authors": [ + { + "first_name": "Vikas", + "last_name": "Thamizharasan" + }, + { + "first_name": "Difan", + "last_name": "Liu" + }, + { + "first_name": "Shantanu", + "last_name": "Agarwal" + }, + { + "first_name": "Matthew", + "last_name": "Fisher" + }, + { + "first_name": "Michael", + "last_name": "Gharbi" + }, + { + "first_name": "Oliver", + "last_name": "Wang" + }, + { + "first_name": "Alec", + "last_name": "Jacobson" + }, + { + "first_name": "Evangelos", + "last_name": "Kalogerakis" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Multi-Modal Hallucination Control by Visual Information Grounding", - "authors": "Alessandro Favero, Luca Zancato, Matthew Trager, Siddharth Choudhary, Pramuditha Perera, Alessandro Achille, Ashwin Swaminathan, Stefano Soatto", + "authors": [ + { + "first_name": "Alessandro", + "last_name": "Favero" + }, + { + "first_name": "Luca", + "last_name": "Zancato" + }, + { + "first_name": "Matthew", + "last_name": "Trager" + }, + { + "first_name": "Siddharth", + "last_name": "Choudhary" + }, + { + "first_name": "Pramuditha", + "last_name": "Perera" + }, + { + "first_name": "Alessandro", + "last_name": "Achille" + }, + { + "first_name": "Ashwin", + "last_name": "Swaminathan" + }, + { + "first_name": "Stefano", + "last_name": "Soatto" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards Text-guided 3D Scene Composition", - "authors": "Qihang Zhang, Chaoyang Wang, Aliaksandr Siarohin, Peiye Zhuang, Yinghao Xu, Ceyuan Yang, Dahua Lin, Bolei Zhou, Sergey Tulyakov, Hsin-Ying Lee", + "authors": [ + { + "first_name": "Qihang", + "last_name": "Zhang" + }, + { + "first_name": "Chaoyang", + "last_name": "Wang" + }, + { + "first_name": "Aliaksandr", + "last_name": "Siarohin" + }, + { + "first_name": "Peiye", + "last_name": "Zhuang" + }, + { + "first_name": "Yinghao", + "last_name": "Xu" + }, + { + "first_name": "Ceyuan", + "last_name": "Yang" + }, + { + "first_name": "Dahua", + "last_name": "Lin" + }, + { + "first_name": "Bolei", + "last_name": "Zhou" + }, + { + "first_name": "Sergey", + "last_name": "Tulyakov" + }, + { + "first_name": "Hsin-Ying", + "last_name": "Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling", - "authors": "Haiyang Liu, Zihao Zhu, Giorgio Becherini, Yichen Peng, Mingyang Su, You Zhou, Xuefei Zhe, Naoya Iwamoto, Bo Zheng, Michael J. Black", + "authors": [ + { + "first_name": "Haiyang", + "last_name": "Liu" + }, + { + "first_name": "Zihao", + "last_name": "Zhu" + }, + { + "first_name": "Giorgio", + "last_name": "Becherini" + }, + { + "first_name": "Yichen", + "last_name": "Peng" + }, + { + "first_name": "Mingyang", + "last_name": "Su" + }, + { + "first_name": "You", + "last_name": "Zhou" + }, + { + "first_name": "Xuefei", + "last_name": "Zhe" + }, + { + "first_name": "Naoya", + "last_name": "Iwamoto" + }, + { + "first_name": "Bo", + "last_name": "Zheng" + }, + { + "first_name": "Michael", + "last_name": "J. Black" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Adversarial Text to Continuous Image Generation", - "authors": "Kilichbek Haydarov, Aashiq Muhamed, Xiaoqian Shen, Jovana Lazarevic, Ivan Skorokhodov, Chamuditha Jayanga Galappaththige, Mohamed Elhoseiny", + "authors": [ + { + "first_name": "Kilichbek", + "last_name": "Haydarov" + }, + { + "first_name": "Aashiq", + "last_name": "Muhamed" + }, + { + "first_name": "Xiaoqian", + "last_name": "Shen" + }, + { + "first_name": "Jovana", + "last_name": "Lazarevic" + }, + { + "first_name": "Ivan", + "last_name": "Skorokhodov" + }, + { + "first_name": "Chamuditha", + "last_name": "Jayanga Galappaththige" + }, + { + "first_name": "Mohamed", + "last_name": "Elhoseiny" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "The Neglected Tails in Vision-Language Models", - "authors": "Shubham Parashar, Zhiqiu Lin, Tian Liu, Xiangjue Dong, Yanan Li, Deva Ramanan, James Caverlee, Shu Kong", + "authors": [ + { + "first_name": "Shubham", + "last_name": "Parashar" + }, + { + "first_name": "Zhiqiu", + "last_name": "Lin" + }, + { + "first_name": "Tian", + "last_name": "Liu" + }, + { + "first_name": "Xiangjue", + "last_name": "Dong" + }, + { + "first_name": "Yanan", + "last_name": "Li" + }, + { + "first_name": "Deva", + "last_name": "Ramanan" + }, + { + "first_name": "James", + "last_name": "Caverlee" + }, + { + "first_name": "Shu", + "last_name": "Kong" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning Background Prompts to Discover Implicit Knowledge for Open Vocabulary Object Detection", - "authors": "Jiaming Li, Jiacheng Zhang, Jichang Li, Ge Li, Si Liu, Liang Lin, Guanbin Li", + "authors": [ + { + "first_name": "Jiaming", + "last_name": "Li" + }, + { + "first_name": "Jiacheng", + "last_name": "Zhang" + }, + { + "first_name": "Jichang", + "last_name": "Li" + }, + { + "first_name": "Ge", + "last_name": "Li" + }, + { + "first_name": "Si", + "last_name": "Liu" + }, + { + "first_name": "Liang", + "last_name": "Lin" + }, + { + "first_name": "Guanbin", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HumanNeRF-SE: A Simple yet Effective Approach to Animate HumanNeRF with Diverse Poses", - "authors": "Caoyuan Ma, Yu-Lun Liu, Zhixiang Wang, Wu Liu, Xinchen Liu, Zheng Wang", + "authors": [ + { + "first_name": "Caoyuan", + "last_name": "Ma" + }, + { + "first_name": "Yu-Lun", + "last_name": "Liu" + }, + { + "first_name": "Zhixiang", + "last_name": "Wang" + }, + { + "first_name": "Wu", + "last_name": "Liu" + }, + { + "first_name": "Xinchen", + "last_name": "Liu" + }, + { + "first_name": "Zheng", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video", - "authors": "Zicong Fan, Maria Parelli, Maria Eleni Kadoglou, Xu Chen, Muhammed Kocabas, Michael J. Black, Otmar Hilliges", + "authors": [ + { + "first_name": "Zicong", + "last_name": "Fan" + }, + { + "first_name": "Maria", + "last_name": "Parelli" + }, + { + "first_name": "Maria", + "last_name": "Eleni Kadoglou" + }, + { + "first_name": "Xu", + "last_name": "Chen" + }, + { + "first_name": "Muhammed", + "last_name": "Kocabas" + }, + { + "first_name": "Michael", + "last_name": "J. Black" + }, + { + "first_name": "Otmar", + "last_name": "Hilliges" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Continual Segmentation with Disentangled Objectness Learning and Class Recognition", - "authors": "Yizheng Gong, Siyue Yu, Xiaoyang Wang, Jimin Xiao", + "authors": [ + { + "first_name": "Yizheng", + "last_name": "Gong" + }, + { + "first_name": "Siyue", + "last_name": "Yu" + }, + { + "first_name": "Xiaoyang", + "last_name": "Wang" + }, + { + "first_name": "Jimin", + "last_name": "Xiao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards Accurate Post-training Quantization for Diffusion Models", - "authors": "Changyuan Wang, Ziwei Wang, Xiuwei Xu, Yansong Tang, Jie Zhou, Jiwen Lu", + "authors": [ + { + "first_name": "Changyuan", + "last_name": "Wang" + }, + { + "first_name": "Ziwei", + "last_name": "Wang" + }, + { + "first_name": "Xiuwei", + "last_name": "Xu" + }, + { + "first_name": "Yansong", + "last_name": "Tang" + }, + { + "first_name": "Jie", + "last_name": "Zhou" + }, + { + "first_name": "Jiwen", + "last_name": "Lu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ASAM: Boosting Segment Anything Model with Adversarial Tuning", - "authors": "Bo Li, Haoke Xiao, Lv Tang", + "authors": [ + { + "first_name": "Bo", + "last_name": "Li" + }, + { + "first_name": "Haoke", + "last_name": "Xiao" + }, + { + "first_name": "Lv", + "last_name": "Tang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "UniBind: LLM-Augmented Unified and Balanced Representation Space to Bind Them All", - "authors": "Yuanhuiyi Lyu, Xu Zheng, Jiazhou Zhou, Lin Wang", + "authors": [ + { + "first_name": "Yuanhuiyi", + "last_name": "Lyu" + }, + { + "first_name": "Xu", + "last_name": "Zheng" + }, + { + "first_name": "Jiazhou", + "last_name": "Zhou" + }, + { + "first_name": "Lin", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Dynamic Support Information Mining for Category-Agnostic Pose Estimation", - "authors": "Pengfei Ren, Yuanyuan Gao, Haifeng Sun, Qi Qi, Jingyu Wang, Jianxin Liao", + "authors": [ + { + "first_name": "Pengfei", + "last_name": "Ren" + }, + { + "first_name": "Yuanyuan", + "last_name": "Gao" + }, + { + "first_name": "Haifeng", + "last_name": "Sun" + }, + { + "first_name": "Qi", + "last_name": "Qi" + }, + { + "first_name": "Jingyu", + "last_name": "Wang" + }, + { + "first_name": "Jianxin", + "last_name": "Liao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Test-Time Adaptation for Depth Completion", - "authors": "Hyoungseob Park, Anjali Gupta, Alex Wong", + "authors": [ + { + "first_name": "Hyoungseob", + "last_name": "Park" + }, + { + "first_name": "Anjali", + "last_name": "Gupta" + }, + { + "first_name": "Alex", + "last_name": "Wong" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GOAT-Bench: A Benchmark for Multi-Modal Lifelong Navigation", - "authors": "Mukul Khanna, Ram Ramrakhya, Gunjan Chhablani, Sriram Yenamandra, Theophile Gervet, Matthew Chang, Zsolt Kira, Devendra Singh Chaplot, Dhruv Batra, Roozbeh Mottaghi", + "authors": [ + { + "first_name": "Mukul", + "last_name": "Khanna" + }, + { + "first_name": "Ram", + "last_name": "Ramrakhya" + }, + { + "first_name": "Gunjan", + "last_name": "Chhablani" + }, + { + "first_name": "Sriram", + "last_name": "Yenamandra" + }, + { + "first_name": "Theophile", + "last_name": "Gervet" + }, + { + "first_name": "Matthew", + "last_name": "Chang" + }, + { + "first_name": "Zsolt", + "last_name": "Kira" + }, + { + "first_name": "Devendra", + "last_name": "Singh Chaplot" + }, + { + "first_name": "Dhruv", + "last_name": "Batra" + }, + { + "first_name": "Roozbeh", + "last_name": "Mottaghi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Taming Mode Collapse in Score Distillation for Text-to-3D Generation", - "authors": "Peihao Wang, Dejia Xu, Zhiwen Fan, Dilin Wang, Sreyas Mohan, Forrest Iandola, Rakesh Ranjan, Yilei Li, Qiang Liu, Zhangyang Wang, Vikas Chandra", + "authors": [ + { + "first_name": "Peihao", + "last_name": "Wang" + }, + { + "first_name": "Dejia", + "last_name": "Xu" + }, + { + "first_name": "Zhiwen", + "last_name": "Fan" + }, + { + "first_name": "Dilin", + "last_name": "Wang" + }, + { + "first_name": "Sreyas", + "last_name": "Mohan" + }, + { + "first_name": "Forrest", + "last_name": "Iandola" + }, + { + "first_name": "Rakesh", + "last_name": "Ranjan" + }, + { + "first_name": "Yilei", + "last_name": "Li" + }, + { + "first_name": "Qiang", + "last_name": "Liu" + }, + { + "first_name": "Zhangyang", + "last_name": "Wang" + }, + { + "first_name": "Vikas", + "last_name": "Chandra" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Binarized Low-light Raw Video Enhancement", - "authors": "Gengchen Zhang, Yulun Zhang, Xin Yuan, Ying Fu", + "authors": [ + { + "first_name": "Gengchen", + "last_name": "Zhang" + }, + { + "first_name": "Yulun", + "last_name": "Zhang" + }, + { + "first_name": "Xin", + "last_name": "Yuan" + }, + { + "first_name": "Ying", + "last_name": "Fu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MorpheuS: Neural Dynamic 360deg Surface Reconstruction from Monocular RGB-D Video", - "authors": "Hengyi Wang, Jingwen Wang, Lourdes Agapito", + "authors": [ + { + "first_name": "Hengyi", + "last_name": "Wang" + }, + { + "first_name": "Jingwen", + "last_name": "Wang" + }, + { + "first_name": "Lourdes", + "last_name": "Agapito" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation", - "authors": "Shuting He, Henghui Ding", + "authors": [ + { + "first_name": "Shuting", + "last_name": "He" + }, + { + "first_name": "Henghui", + "last_name": "Ding" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model", - "authors": "Zhongcong Xu, Jianfeng Zhang, Jun Hao Liew, Hanshu Yan, Jia-Wei Liu, Chenxu Zhang, Jiashi Feng, Mike Zheng Shou", + "authors": [ + { + "first_name": "Zhongcong", + "last_name": "Xu" + }, + { + "first_name": "Jianfeng", + "last_name": "Zhang" + }, + { + "first_name": "Jun", + "last_name": "Hao Liew" + }, + { + "first_name": "Hanshu", + "last_name": "Yan" + }, + { + "first_name": "Jia-Wei", + "last_name": "Liu" + }, + { + "first_name": "Chenxu", + "last_name": "Zhang" + }, + { + "first_name": "Jiashi", + "last_name": "Feng" + }, + { + "first_name": "Mike", + "last_name": "Zheng Shou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Dense Vision Transformer Compression with Few Samples", - "authors": "Hanxiao Zhang, Yifan Zhou, Guo-Hua Wang", + "authors": [ + { + "first_name": "Hanxiao", + "last_name": "Zhang" + }, + { + "first_name": "Yifan", + "last_name": "Zhou" + }, + { + "first_name": "Guo-Hua", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Masked AutoDecoder is Effective Multi-Task Vision Generalist", - "authors": "Han Qiu, Jiaxing Huang, Peng Gao, Lewei Lu, Xiaoqin Zhang, Shijian Lu", + "authors": [ + { + "first_name": "Han", + "last_name": "Qiu" + }, + { + "first_name": "Jiaxing", + "last_name": "Huang" + }, + { + "first_name": "Peng", + "last_name": "Gao" + }, + { + "first_name": "Lewei", + "last_name": "Lu" + }, + { + "first_name": "Xiaoqin", + "last_name": "Zhang" + }, + { + "first_name": "Shijian", + "last_name": "Lu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Weakly Misalignment-free Adaptive Feature Alignment for UAVs-based Multimodal Object Detection", - "authors": "Chen Chen, Jiahao Qi, Xingyue Liu, Kangcheng Bin, Ruigang Fu, Xikun Hu, Ping Zhong", + "authors": [ + { + "first_name": "Chen", + "last_name": "Chen" + }, + { + "first_name": "Jiahao", + "last_name": "Qi" + }, + { + "first_name": "Xingyue", + "last_name": "Liu" + }, + { + "first_name": "Kangcheng", + "last_name": "Bin" + }, + { + "first_name": "Ruigang", + "last_name": "Fu" + }, + { + "first_name": "Xikun", + "last_name": "Hu" + }, + { + "first_name": "Ping", + "last_name": "Zhong" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "From Correspondences to Pose: Non-minimal Certifiably Optimal Relative Pose without Disambiguation", - "authors": "Javier Tirado-Garín, Javier Civera", + "authors": [ + { + "first_name": "Javier", + "last_name": "Tirado-Garín" + }, + { + "first_name": "Javier", + "last_name": "Civera" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Passive Snapshot Coded Aperture Dual-Pixel RGB-D Imaging", - "authors": "Bhargav Ghanekar, Salman Siddique Khan, Pranav Sharma, Shreyas Singh, Vivek Boominathan, Kaushik Mitra, Ashok Veeraraghavan", + "authors": [ + { + "first_name": "Bhargav", + "last_name": "Ghanekar" + }, + { + "first_name": "Salman", + "last_name": "Siddique Khan" + }, + { + "first_name": "Pranav", + "last_name": "Sharma" + }, + { + "first_name": "Shreyas", + "last_name": "Singh" + }, + { + "first_name": "Vivek", + "last_name": "Boominathan" + }, + { + "first_name": "Kaushik", + "last_name": "Mitra" + }, + { + "first_name": "Ashok", + "last_name": "Veeraraghavan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Loose Inertial Poser: Motion Capture with IMU-attached Loose-Wear Jacket", - "authors": "Chengxu Zuo, Yiming Wang, Lishuang Zhan, Shihui Guo, Xinyu Yi, Feng Xu, Yipeng Qin", + "authors": [ + { + "first_name": "Chengxu", + "last_name": "Zuo" + }, + { + "first_name": "Yiming", + "last_name": "Wang" + }, + { + "first_name": "Lishuang", + "last_name": "Zhan" + }, + { + "first_name": "Shihui", + "last_name": "Guo" + }, + { + "first_name": "Xinyu", + "last_name": "Yi" + }, + { + "first_name": "Feng", + "last_name": "Xu" + }, + { + "first_name": "Yipeng", + "last_name": "Qin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Instance Tracking in 3D Scenes from Egocentric Videos", - "authors": "Yunhan Zhao, Haoyu Ma, Shu Kong, Charless Fowlkes", + "authors": [ + { + "first_name": "Yunhan", + "last_name": "Zhao" + }, + { + "first_name": "Haoyu", + "last_name": "Ma" + }, + { + "first_name": "Shu", + "last_name": "Kong" + }, + { + "first_name": "Charless", + "last_name": "Fowlkes" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Correlation-aware Coarse-to-fine MLPs for Deformable Medical Image Registration", - "authors": "Mingyuan Meng, Dagan Feng, Lei Bi, Jinman Kim", + "authors": [ + { + "first_name": "Mingyuan", + "last_name": "Meng" + }, + { + "first_name": "Dagan", + "last_name": "Feng" + }, + { + "first_name": "Lei", + "last_name": "Bi" + }, + { + "first_name": "Jinman", + "last_name": "Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Prompts", - "authors": "Jiawen Zhu, Guansong Pang", + "authors": [ + { + "first_name": "Jiawen", + "last_name": "Zhu" + }, + { + "first_name": "Guansong", + "last_name": "Pang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Fourier-basis Functions to Bridge Augmentation Gap: Rethinking Frequency Augmentation in Image Classification", - "authors": "Puru Vaish, Shunxin Wang, Nicola Strisciuglio", + "authors": [ + { + "first_name": "Puru", + "last_name": "Vaish" + }, + { + "first_name": "Shunxin", + "last_name": "Wang" + }, + { + "first_name": "Nicola", + "last_name": "Strisciuglio" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning to Transform Dynamically for Better Adversarial Transferability", - "authors": "Rongyi Zhu, Zeliang Zhang, Susan Liang, Zhuo Liu, Chenliang Xu", + "authors": [ + { + "first_name": "Rongyi", + "last_name": "Zhu" + }, + { + "first_name": "Zeliang", + "last_name": "Zhang" + }, + { + "first_name": "Susan", + "last_name": "Liang" + }, + { + "first_name": "Zhuo", + "last_name": "Liu" + }, + { + "first_name": "Chenliang", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PlatoNeRF: 3D Reconstruction in Plato's Cave via Single-View Two-Bounce Lidar", - "authors": "Tzofi Klinghoffer, Xiaoyu Xiang, Siddharth Somasundaram, Yuchen Fan, Christian Richardt, Ramesh Raskar, Rakesh Ranjan", + "authors": [ + { + "first_name": "Tzofi", + "last_name": "Klinghoffer" + }, + { + "first_name": "Xiaoyu", + "last_name": "Xiang" + }, + { + "first_name": "Siddharth", + "last_name": "Somasundaram" + }, + { + "first_name": "Yuchen", + "last_name": "Fan" + }, + { + "first_name": "Christian", + "last_name": "Richardt" + }, + { + "first_name": "Ramesh", + "last_name": "Raskar" + }, + { + "first_name": "Rakesh", + "last_name": "Ranjan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PanoContext-Former: Panoramic Total Scene Understanding with a Transformer", - "authors": "Yuan Dong, Chuan Fang, Liefeng Bo, Zilong Dong, Ping Tan", + "authors": [ + { + "first_name": "Yuan", + "last_name": "Dong" + }, + { + "first_name": "Chuan", + "last_name": "Fang" + }, + { + "first_name": "Liefeng", + "last_name": "Bo" + }, + { + "first_name": "Zilong", + "last_name": "Dong" + }, + { + "first_name": "Ping", + "last_name": "Tan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Training-Free Pretrained Model Merging", - "authors": "Zhengqi Xu, Ke Yuan, Huiqiong Wang, Yong Wang, Mingli Song, Jie Song", + "authors": [ + { + "first_name": "Zhengqi", + "last_name": "Xu" + }, + { + "first_name": "Ke", + "last_name": "Yuan" + }, + { + "first_name": "Huiqiong", + "last_name": "Wang" + }, + { + "first_name": "Yong", + "last_name": "Wang" + }, + { + "first_name": "Mingli", + "last_name": "Song" + }, + { + "first_name": "Jie", + "last_name": "Song" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "NC-SDF: Enhancing Indoor Scene Reconstruction Using Neural SDFs with View-Dependent Normal Compensation", - "authors": "Ziyi Chen, Xiaolong Wu, Yu Zhang", + "authors": [ + { + "first_name": "Ziyi", + "last_name": "Chen" + }, + { + "first_name": "Xiaolong", + "last_name": "Wu" + }, + { + "first_name": "Yu", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "An Interactive Navigation Method with Effect-oriented Affordance", - "authors": "Xiaohan Wang, Yuehu Liu, Xinhang Song, Yuyi Liu, Sixian Zhang, Shuqiang Jiang", + "authors": [ + { + "first_name": "Xiaohan", + "last_name": "Wang" + }, + { + "first_name": "Yuehu", + "last_name": "Liu" + }, + { + "first_name": "Xinhang", + "last_name": "Song" + }, + { + "first_name": "Yuyi", + "last_name": "Liu" + }, + { + "first_name": "Sixian", + "last_name": "Zhang" + }, + { + "first_name": "Shuqiang", + "last_name": "Jiang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Person in Place: Generating Associative Skeleton-Guidance Maps for Human-Object Interaction Image Editing", - "authors": "ChangHee Yang, ChanHee Kang, Kyeongbo Kong, Hanni Oh, Suk-Ju Kang", + "authors": [ + { + "first_name": "ChangHee", + "last_name": "Yang" + }, + { + "first_name": "ChanHee", + "last_name": "Kang" + }, + { + "first_name": "Kyeongbo", + "last_name": "Kong" + }, + { + "first_name": "Hanni", + "last_name": "Oh" + }, + { + "first_name": "Suk-Ju", + "last_name": "Kang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PREGO: Online Mistake Detection in PRocedural EGOcentric Videos", - "authors": "Alessandro Flaborea, Guido Maria D'Amely di Melendugno, Leonardo Plini, Luca Scofano, Edoardo De Matteis, Antonino Furnari, Giovanni Maria Farinella, Fabio Galasso", + "authors": [ + { + "first_name": "Alessandro", + "last_name": "Flaborea" + }, + { + "first_name": "Guido", + "last_name": "Maria D'Amely di Melendugno" + }, + { + "first_name": "Leonardo", + "last_name": "Plini" + }, + { + "first_name": "Luca", + "last_name": "Scofano" + }, + { + "first_name": "Edoardo", + "last_name": "De Matteis" + }, + { + "first_name": "Antonino", + "last_name": "Furnari" + }, + { + "first_name": "Giovanni", + "last_name": "Maria Farinella" + }, + { + "first_name": "Fabio", + "last_name": "Galasso" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ChatPose: Chatting about 3D Human Pose", - "authors": "Yao Feng, Jing Lin, Sai Kumar Dwivedi, Yu Sun, Priyanka Patel, Michael J. Black", + "authors": [ + { + "first_name": "Yao", + "last_name": "Feng" + }, + { + "first_name": "Jing", + "last_name": "Lin" + }, + { + "first_name": "Sai", + "last_name": "Kumar Dwivedi" + }, + { + "first_name": "Yu", + "last_name": "Sun" + }, + { + "first_name": "Priyanka", + "last_name": "Patel" + }, + { + "first_name": "Michael", + "last_name": "J. Black" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Prompt3D: Random Prompt Assisted Weakly-Supervised 3D Object Detection", - "authors": "Xiaohong Zhang, Huisheng Ye, Jingwen Li, Qinyu Tang, Yuanqi Li, Yanwen Guo, Jie Guo", + "authors": [ + { + "first_name": "Xiaohong", + "last_name": "Zhang" + }, + { + "first_name": "Huisheng", + "last_name": "Ye" + }, + { + "first_name": "Jingwen", + "last_name": "Li" + }, + { + "first_name": "Qinyu", + "last_name": "Tang" + }, + { + "first_name": "Yuanqi", + "last_name": "Li" + }, + { + "first_name": "Yanwen", + "last_name": "Guo" + }, + { + "first_name": "Jie", + "last_name": "Guo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Logit Standardization in Knowledge Distillation", - "authors": "Shangquan Sun, Wenqi Ren, Jingzhi Li, Rui Wang, Xiaochun Cao", + "authors": [ + { + "first_name": "Shangquan", + "last_name": "Sun" + }, + { + "first_name": "Wenqi", + "last_name": "Ren" + }, + { + "first_name": "Jingzhi", + "last_name": "Li" + }, + { + "first_name": "Rui", + "last_name": "Wang" + }, + { + "first_name": "Xiaochun", + "last_name": "Cao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Fine-grained Prototypical Voting with Heterogeneous Mixup for Semi-supervised 2D-3D Cross-modal Retrieval", - "authors": "Fan Zhang, Xian-Sheng Hua, Chong Chen, Xiao Luo", + "authors": [ + { + "first_name": "Fan", + "last_name": "Zhang" + }, + { + "first_name": "Xian-Sheng", + "last_name": "Hua" + }, + { + "first_name": "Chong", + "last_name": "Chen" + }, + { + "first_name": "Xiao", + "last_name": "Luo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Leak and Learn: An Attacker's Cookbook to Train Using Leaked Data from Federated Learning", - "authors": "Joshua C. Zhao, Ahaan Dabholkar, Atul Sharma, Saurabh Bagchi", + "authors": [ + { + "first_name": "Joshua", + "last_name": "C. Zhao" + }, + { + "first_name": "Ahaan", + "last_name": "Dabholkar" + }, + { + "first_name": "Atul", + "last_name": "Sharma" + }, + { + "first_name": "Saurabh", + "last_name": "Bagchi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "OCAI: Improving Optical Flow Estimation by Occlusion and Consistency Aware Interpolation", - "authors": "Jisoo Jeong, Hong Cai, Risheek Garrepalli, Jamie Menjay Lin, Munawar Hayat, Fatih Porikli", + "authors": [ + { + "first_name": "Jisoo", + "last_name": "Jeong" + }, + { + "first_name": "Hong", + "last_name": "Cai" + }, + { + "first_name": "Risheek", + "last_name": "Garrepalli" + }, + { + "first_name": "Jamie", + "last_name": "Menjay Lin" + }, + { + "first_name": "Munawar", + "last_name": "Hayat" + }, + { + "first_name": "Fatih", + "last_name": "Porikli" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Distilling ODE Solvers of Diffusion Models into Smaller Steps", - "authors": "Sanghwan Kim, Hao Tang, Fisher Yu", + "authors": [ + { + "first_name": "Sanghwan", + "last_name": "Kim" + }, + { + "first_name": "Hao", + "last_name": "Tang" + }, + { + "first_name": "Fisher", + "last_name": "Yu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Navigating Beyond Dropout: An Intriguing Solution towards Generalizable Image Super Resolution", - "authors": "Hongjun Wang, Jiyuan Chen, Yinqiang Zheng, Tieyong Zeng", + "authors": [ + { + "first_name": "Hongjun", + "last_name": "Wang" + }, + { + "first_name": "Jiyuan", + "last_name": "Chen" + }, + { + "first_name": "Yinqiang", + "last_name": "Zheng" + }, + { + "first_name": "Tieyong", + "last_name": "Zeng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Doodle Your 3D: From Abstract Freehand Sketches to Precise 3D Shapes", - "authors": "Hmrishav Bandyopadhyay, Subhadeep Koley, Ayan Das, Ayan Kumar Bhunia, Aneeshan Sain, Pinaki Nath Chowdhury, Tao Xiang, Yi-Zhe Song", + "authors": [ + { + "first_name": "Hmrishav", + "last_name": "Bandyopadhyay" + }, + { + "first_name": "Subhadeep", + "last_name": "Koley" + }, + { + "first_name": "Ayan", + "last_name": "Das" + }, + { + "first_name": "Ayan", + "last_name": "Kumar Bhunia" + }, + { + "first_name": "Aneeshan", + "last_name": "Sain" + }, + { + "first_name": "Pinaki", + "last_name": "Nath Chowdhury" + }, + { + "first_name": "Tao", + "last_name": "Xiang" + }, + { + "first_name": "Yi-Zhe", + "last_name": "Song" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LightIt: Illumination Modeling and Control for Diffusion Models", - "authors": "Peter Kocsis, Julien Philip, Kalyan Sunkavalli, Matthias Nießner, Yannick Hold-Geoffroy", + "authors": [ + { + "first_name": "Peter", + "last_name": "Kocsis" + }, + { + "first_name": "Julien", + "last_name": "Philip" + }, + { + "first_name": "Kalyan", + "last_name": "Sunkavalli" + }, + { + "first_name": "Matthias", + "last_name": "Nießner" + }, + { + "first_name": "Yannick", + "last_name": "Hold-Geoffroy" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Single View Refractive Index Tomography with Neural Fields", - "authors": "Brandon Zhao, Aviad Levis, Liam Connor, Pratul P. Srinivasan, Katherine L. Bouman", + "authors": [ + { + "first_name": "Brandon", + "last_name": "Zhao" + }, + { + "first_name": "Aviad", + "last_name": "Levis" + }, + { + "first_name": "Liam", + "last_name": "Connor" + }, + { + "first_name": "Pratul", + "last_name": "P. Srinivasan" + }, + { + "first_name": "Katherine", + "last_name": "L. Bouman" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Neural Lineage", - "authors": "Runpeng Yu, Xinchao Wang", + "authors": [ + { + "first_name": "Runpeng", + "last_name": "Yu" + }, + { + "first_name": "Xinchao", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Visual Layout Composer: Image-Vector Dual Diffusion Model for Design Layout Generation", - "authors": "Mohammad Amin Shabani, Zhaowen Wang, Difan Liu, Nanxuan Zhao, Jimei Yang, Yasutaka Furukawa", + "authors": [ + { + "first_name": "Mohammad", + "last_name": "Amin Shabani" + }, + { + "first_name": "Zhaowen", + "last_name": "Wang" + }, + { + "first_name": "Difan", + "last_name": "Liu" + }, + { + "first_name": "Nanxuan", + "last_name": "Zhao" + }, + { + "first_name": "Jimei", + "last_name": "Yang" + }, + { + "first_name": "Yasutaka", + "last_name": "Furukawa" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FC-GNN: Recovering Reliable and Accurate Correspondences from Interferences", - "authors": "Haobo Xu, Jun Zhou, Hua Yang, Renjie Pan, Cunyan Li", + "authors": [ + { + "first_name": "Haobo", + "last_name": "Xu" + }, + { + "first_name": "Jun", + "last_name": "Zhou" + }, + { + "first_name": "Hua", + "last_name": "Yang" + }, + { + "first_name": "Renjie", + "last_name": "Pan" + }, + { + "first_name": "Cunyan", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Turb-Seg-Res: A Segment-then-Restore Pipeline for Dynamic Videos with Atmospheric Turbulence", - "authors": "Ripon Kumar Saha, Dehao Qin, Nianyi Li, Jinwei Ye, Suren Jayasuriya", + "authors": [ + { + "first_name": "Ripon", + "last_name": "Kumar Saha" + }, + { + "first_name": "Dehao", + "last_name": "Qin" + }, + { + "first_name": "Nianyi", + "last_name": "Li" + }, + { + "first_name": "Jinwei", + "last_name": "Ye" + }, + { + "first_name": "Suren", + "last_name": "Jayasuriya" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Real-time Acquisition and Reconstruction of Dynamic Volumes with Neural Structured Illumination", - "authors": "Yixin Zeng, Zoubin Bi, Mingrui Yin, Xiang Feng, Kun Zhou, Hongzhi Wu", + "authors": [ + { + "first_name": "Yixin", + "last_name": "Zeng" + }, + { + "first_name": "Zoubin", + "last_name": "Bi" + }, + { + "first_name": "Mingrui", + "last_name": "Yin" + }, + { + "first_name": "Xiang", + "last_name": "Feng" + }, + { + "first_name": "Kun", + "last_name": "Zhou" + }, + { + "first_name": "Hongzhi", + "last_name": "Wu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "3D Multi-frame Fusion for Video Stabilization", - "authors": "Zhan Peng, Xinyi Ye, Weiyue Zhao, Tianqi Liu, Huiqiang Sun, Baopu Li, Zhiguo Cao", + "authors": [ + { + "first_name": "Zhan", + "last_name": "Peng" + }, + { + "first_name": "Xinyi", + "last_name": "Ye" + }, + { + "first_name": "Weiyue", + "last_name": "Zhao" + }, + { + "first_name": "Tianqi", + "last_name": "Liu" + }, + { + "first_name": "Huiqiang", + "last_name": "Sun" + }, + { + "first_name": "Baopu", + "last_name": "Li" + }, + { + "first_name": "Zhiguo", + "last_name": "Cao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Local-consistent Transformation Learning for Rotation-invariant Point Cloud Analysis", - "authors": "Yiyang Chen, Lunhao Duan, Shanshan Zhao, Changxing Ding, Dacheng Tao", + "authors": [ + { + "first_name": "Yiyang", + "last_name": "Chen" + }, + { + "first_name": "Lunhao", + "last_name": "Duan" + }, + { + "first_name": "Shanshan", + "last_name": "Zhao" + }, + { + "first_name": "Changxing", + "last_name": "Ding" + }, + { + "first_name": "Dacheng", + "last_name": "Tao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Tailored Visions: Enhancing Text-to-Image Generation with Personalized Prompt Rewriting", - "authors": "Zijie Chen, Lichao Zhang, Fangsheng Weng, Lili Pan, Zhenzhong Lan", + "authors": [ + { + "first_name": "Zijie", + "last_name": "Chen" + }, + { + "first_name": "Lichao", + "last_name": "Zhang" + }, + { + "first_name": "Fangsheng", + "last_name": "Weng" + }, + { + "first_name": "Lili", + "last_name": "Pan" + }, + { + "first_name": "Zhenzhong", + "last_name": "Lan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for Vision Applications", - "authors": "Yuwen Xiong, Zhiqi Li, Yuntao Chen, Feng Wang, Xizhou Zhu, Jiapeng Luo, Wenhai Wang, Tong Lu, Hongsheng Li, Yu Qiao, Lewei Lu, Jie Zhou, Jifeng Dai", + "authors": [ + { + "first_name": "Yuwen", + "last_name": "Xiong" + }, + { + "first_name": "Zhiqi", + "last_name": "Li" + }, + { + "first_name": "Yuntao", + "last_name": "Chen" + }, + { + "first_name": "Feng", + "last_name": "Wang" + }, + { + "first_name": "Xizhou", + "last_name": "Zhu" + }, + { + "first_name": "Jiapeng", + "last_name": "Luo" + }, + { + "first_name": "Wenhai", + "last_name": "Wang" + }, + { + "first_name": "Tong", + "last_name": "Lu" + }, + { + "first_name": "Hongsheng", + "last_name": "Li" + }, + { + "first_name": "Yu", + "last_name": "Qiao" + }, + { + "first_name": "Lewei", + "last_name": "Lu" + }, + { + "first_name": "Jie", + "last_name": "Zhou" + }, + { + "first_name": "Jifeng", + "last_name": "Dai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CoDe: An Explicit Content Decoupling Framework for Image Restoration", - "authors": "Enxuan Gu, Hongwei Ge, Yong Guo", + "authors": [ + { + "first_name": "Enxuan", + "last_name": "Gu" + }, + { + "first_name": "Hongwei", + "last_name": "Ge" + }, + { + "first_name": "Yong", + "last_name": "Guo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "XFibrosis: Explicit Vessel-Fiber Modeling for Fibrosis Staging from Liver Pathology Images", - "authors": "Chong Yin, Siqi Liu, Fei Lyu, Jiahao Lu, Sune Darkner, Vincent Wai-Sun Wong, Pong C. Yuen", + "authors": [ + { + "first_name": "Chong", + "last_name": "Yin" + }, + { + "first_name": "Siqi", + "last_name": "Liu" + }, + { + "first_name": "Fei", + "last_name": "Lyu" + }, + { + "first_name": "Jiahao", + "last_name": "Lu" + }, + { + "first_name": "Sune", + "last_name": "Darkner" + }, + { + "first_name": "Vincent", + "last_name": "Wai-Sun Wong" + }, + { + "first_name": "Pong", + "last_name": "C. Yuen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "UnO: Unsupervised Occupancy Fields for Perception and Forecasting", - "authors": "Ben Agro, Quinlan Sykora, Sergio Casas, Thomas Gilles, Raquel Urtasun", + "authors": [ + { + "first_name": "Ben", + "last_name": "Agro" + }, + { + "first_name": "Quinlan", + "last_name": "Sykora" + }, + { + "first_name": "Sergio", + "last_name": "Casas" + }, + { + "first_name": "Thomas", + "last_name": "Gilles" + }, + { + "first_name": "Raquel", + "last_name": "Urtasun" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities", - "authors": "Boyuan Chen, Zhuo Xu, Sean Kirmani, Brain Ichter, Dorsa Sadigh, Leonidas Guibas, Fei Xia", + "authors": [ + { + "first_name": "Boyuan", + "last_name": "Chen" + }, + { + "first_name": "Zhuo", + "last_name": "Xu" + }, + { + "first_name": "Sean", + "last_name": "Kirmani" + }, + { + "first_name": "Brain", + "last_name": "Ichter" + }, + { + "first_name": "Dorsa", + "last_name": "Sadigh" + }, + { + "first_name": "Leonidas", + "last_name": "Guibas" + }, + { + "first_name": "Fei", + "last_name": "Xia" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "InstructDiffusion: A Generalist Modeling Interface for Vision Tasks", - "authors": "Zigang Geng, Binxin Yang, Tiankai Hang, Chen Li, Shuyang Gu, Ting Zhang, Jianmin Bao, Zheng Zhang, Houqiang Li, Han Hu, Dong Chen, Baining Guo", + "authors": [ + { + "first_name": "Zigang", + "last_name": "Geng" + }, + { + "first_name": "Binxin", + "last_name": "Yang" + }, + { + "first_name": "Tiankai", + "last_name": "Hang" + }, + { + "first_name": "Chen", + "last_name": "Li" + }, + { + "first_name": "Shuyang", + "last_name": "Gu" + }, + { + "first_name": "Ting", + "last_name": "Zhang" + }, + { + "first_name": "Jianmin", + "last_name": "Bao" + }, + { + "first_name": "Zheng", + "last_name": "Zhang" + }, + { + "first_name": "Houqiang", + "last_name": "Li" + }, + { + "first_name": "Han", + "last_name": "Hu" + }, + { + "first_name": "Dong", + "last_name": "Chen" + }, + { + "first_name": "Baining", + "last_name": "Guo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DreamVideo: Composing Your Dream Videos with Customized Subject and Motion", - "authors": "Yujie Wei, Shiwei Zhang, Zhiwu Qing, Hangjie Yuan, Zhiheng Liu, Yu Liu, Yingya Zhang, Jingren Zhou, Hongming Shan", + "authors": [ + { + "first_name": "Yujie", + "last_name": "Wei" + }, + { + "first_name": "Shiwei", + "last_name": "Zhang" + }, + { + "first_name": "Zhiwu", + "last_name": "Qing" + }, + { + "first_name": "Hangjie", + "last_name": "Yuan" + }, + { + "first_name": "Zhiheng", + "last_name": "Liu" + }, + { + "first_name": "Yu", + "last_name": "Liu" + }, + { + "first_name": "Yingya", + "last_name": "Zhang" + }, + { + "first_name": "Jingren", + "last_name": "Zhou" + }, + { + "first_name": "Hongming", + "last_name": "Shan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Gated Fields: Learning Scene Reconstruction from Gated Videos", - "authors": "Andrea Ramazzina, Stefanie Walz, Pragyan Dahal, Mario Bijelic, Felix Heide", + "authors": [ + { + "first_name": "Andrea", + "last_name": "Ramazzina" + }, + { + "first_name": "Stefanie", + "last_name": "Walz" + }, + { + "first_name": "Pragyan", + "last_name": "Dahal" + }, + { + "first_name": "Mario", + "last_name": "Bijelic" + }, + { + "first_name": "Felix", + "last_name": "Heide" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "RadarDistill: Boosting Radar-based Object Detection Performance via Knowledge Distillation from LiDAR Features", - "authors": "Geonho Bang, Kwangjin Choi, Jisong Kim, Dongsuk Kum, Jun Won Choi", + "authors": [ + { + "first_name": "Geonho", + "last_name": "Bang" + }, + { + "first_name": "Kwangjin", + "last_name": "Choi" + }, + { + "first_name": "Jisong", + "last_name": "Kim" + }, + { + "first_name": "Dongsuk", + "last_name": "Kum" + }, + { + "first_name": "Jun", + "last_name": "Won Choi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Probabilistic Sampling of Balanced K-Means using Adiabatic Quantum Computing", - "authors": "Jan-Nico Zaech, Martin Danelljan, Tolga Birdal, Luc Van Gool", + "authors": [ + { + "first_name": "Jan-Nico", + "last_name": "Zaech" + }, + { + "first_name": "Martin", + "last_name": "Danelljan" + }, + { + "first_name": "Tolga", + "last_name": "Birdal" + }, + { + "first_name": "Luc", + "last_name": "Van Gool" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "UniPT: Universal Parallel Tuning for Transfer Learning with Efficient Parameter and Memory", - "authors": "Haiwen Diao, Bo Wan, Ying Zhang, Xu Jia, Huchuan Lu, Long Chen", + "authors": [ + { + "first_name": "Haiwen", + "last_name": "Diao" + }, + { + "first_name": "Bo", + "last_name": "Wan" + }, + { + "first_name": "Ying", + "last_name": "Zhang" + }, + { + "first_name": "Xu", + "last_name": "Jia" + }, + { + "first_name": "Huchuan", + "last_name": "Lu" + }, + { + "first_name": "Long", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Composed Video Retrieval via Enriched Context and Discriminative Embeddings", - "authors": "Omkar Thawakar, Muzammal Naseer, Rao Muhammad Anwer, Salman Khan, Michael Felsberg, Mubarak Shah, Fahad Shahbaz Khan", + "authors": [ + { + "first_name": "Omkar", + "last_name": "Thawakar" + }, + { + "first_name": "Muzammal", + "last_name": "Naseer" + }, + { + "first_name": "Rao", + "last_name": "Muhammad Anwer" + }, + { + "first_name": "Salman", + "last_name": "Khan" + }, + { + "first_name": "Michael", + "last_name": "Felsberg" + }, + { + "first_name": "Mubarak", + "last_name": "Shah" + }, + { + "first_name": "Fahad", + "last_name": "Shahbaz Khan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model", - "authors": "Kai Yang, Jian Tao, Jiafei Lyu, Chunjiang Ge, Jiaxin Chen, Weihan Shen, Xiaolong Zhu, Xiu Li", + "authors": [ + { + "first_name": "Kai", + "last_name": "Yang" + }, + { + "first_name": "Jian", + "last_name": "Tao" + }, + { + "first_name": "Jiafei", + "last_name": "Lyu" + }, + { + "first_name": "Chunjiang", + "last_name": "Ge" + }, + { + "first_name": "Jiaxin", + "last_name": "Chen" + }, + { + "first_name": "Weihan", + "last_name": "Shen" + }, + { + "first_name": "Xiaolong", + "last_name": "Zhu" + }, + { + "first_name": "Xiu", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Perceptual Assessment and Optimization of HDR Image Rendering", - "authors": "Peibei Cao, Rafal K. Mantiuk, Kede Ma", + "authors": [ + { + "first_name": "Peibei", + "last_name": "Cao" + }, + { + "first_name": "Rafal", + "last_name": "K. Mantiuk" + }, + { + "first_name": "Kede", + "last_name": "Ma" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Multiview Aerial Visual RECognition (MAVREC): Can Multi-view Improve Aerial Visual Perception?", - "authors": "Aritra Dutta, Srijan Das, Jacob Nielsen, Rajatsubhra Chakraborty, Mubarak Shah", + "authors": [ + { + "first_name": "Aritra", + "last_name": "Dutta" + }, + { + "first_name": "Srijan", + "last_name": "Das" + }, + { + "first_name": "Jacob", + "last_name": "Nielsen" + }, + { + "first_name": "Rajatsubhra", + "last_name": "Chakraborty" + }, + { + "first_name": "Mubarak", + "last_name": "Shah" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Diffusion-driven GAN Inversion for Multi-Modal Face Image Generation", - "authors": "Jihyun Kim, Changjae Oh, Hoseok Do, Soohyun Kim, Kwanghoon Sohn", + "authors": [ + { + "first_name": "Jihyun", + "last_name": "Kim" + }, + { + "first_name": "Changjae", + "last_name": "Oh" + }, + { + "first_name": "Hoseok", + "last_name": "Do" + }, + { + "first_name": "Soohyun", + "last_name": "Kim" + }, + { + "first_name": "Kwanghoon", + "last_name": "Sohn" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Low-Rank Knowledge Decomposition for Medical Foundation Models", - "authors": "Yuhang Zhou, Haolin Li, Siyuan Du, Jiangchao Yao, Ya Zhang, Yanfeng Wang", + "authors": [ + { + "first_name": "Yuhang", + "last_name": "Zhou" + }, + { + "first_name": "Haolin", + "last_name": "Li" + }, + { + "first_name": "Siyuan", + "last_name": "Du" + }, + { + "first_name": "Jiangchao", + "last_name": "Yao" + }, + { + "first_name": "Ya", + "last_name": "Zhang" + }, + { + "first_name": "Yanfeng", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SaCo Loss: Sample-wise Affinity Consistency for Vision-Language Pre-training", - "authors": "Sitong Wu, Haoru Tan, Zhuotao Tian, Yukang Chen, Xiaojuan Qi, Jiaya Jia", + "authors": [ + { + "first_name": "Sitong", + "last_name": "Wu" + }, + { + "first_name": "Haoru", + "last_name": "Tan" + }, + { + "first_name": "Zhuotao", + "last_name": "Tian" + }, + { + "first_name": "Yukang", + "last_name": "Chen" + }, + { + "first_name": "Xiaojuan", + "last_name": "Qi" + }, + { + "first_name": "Jiaya", + "last_name": "Jia" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Steganographic Passport: An Owner and User Verifiable Credential for Deep Model IP Protection Without Retraining", - "authors": "Qi Cui, Ruohan Meng, Chaohui Xu, Chip-Hong Chang", + "authors": [ + { + "first_name": "Qi", + "last_name": "Cui" + }, + { + "first_name": "Ruohan", + "last_name": "Meng" + }, + { + "first_name": "Chaohui", + "last_name": "Xu" + }, + { + "first_name": "Chip-Hong", + "last_name": "Chang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Stable Neighbor Denoising for Source-free Domain Adaptive Segmentation", - "authors": "Dong Zhao, Shuang Wang, Qi Zang, Licheng Jiao, Nicu Sebe, Zhun Zhong", + "authors": [ + { + "first_name": "Dong", + "last_name": "Zhao" + }, + { + "first_name": "Shuang", + "last_name": "Wang" + }, + { + "first_name": "Qi", + "last_name": "Zang" + }, + { + "first_name": "Licheng", + "last_name": "Jiao" + }, + { + "first_name": "Nicu", + "last_name": "Sebe" + }, + { + "first_name": "Zhun", + "last_name": "Zhong" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SynSP: Synergy of Smoothness and Precision in Pose Sequences Refinement", - "authors": "Tao Wang, Lei Jin, Zheng Wang, Jianshu Li, Liang Li, Fang Zhao, Yu Cheng, Li Yuan, Li Zhou, Junliang Xing, Jian Zhao", + "authors": [ + { + "first_name": "Tao", + "last_name": "Wang" + }, + { + "first_name": "Lei", + "last_name": "Jin" + }, + { + "first_name": "Zheng", + "last_name": "Wang" + }, + { + "first_name": "Jianshu", + "last_name": "Li" + }, + { + "first_name": "Liang", + "last_name": "Li" + }, + { + "first_name": "Fang", + "last_name": "Zhao" + }, + { + "first_name": "Yu", + "last_name": "Cheng" + }, + { + "first_name": "Li", + "last_name": "Yuan" + }, + { + "first_name": "Li", + "last_name": "Zhou" + }, + { + "first_name": "Junliang", + "last_name": "Xing" + }, + { + "first_name": "Jian", + "last_name": "Zhao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "En3D: An Enhanced Generative Model for Sculpting 3D Humans from 2D Synthetic Data", - "authors": "Yifang Men, Biwen Lei, Yuan Yao, Miaomiao Cui, Zhouhui Lian, Xuansong Xie", + "authors": [ + { + "first_name": "Yifang", + "last_name": "Men" + }, + { + "first_name": "Biwen", + "last_name": "Lei" + }, + { + "first_name": "Yuan", + "last_name": "Yao" + }, + { + "first_name": "Miaomiao", + "last_name": "Cui" + }, + { + "first_name": "Zhouhui", + "last_name": "Lian" + }, + { + "first_name": "Xuansong", + "last_name": "Xie" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Neural Visibility Field for Uncertainty-Driven Active Mapping", - "authors": "Shangjie Xue, Jesse Dill, Pranay Mathur, Frank Dellaert, Panagiotis Tsiotra, Danfei Xu", + "authors": [ + { + "first_name": "Shangjie", + "last_name": "Xue" + }, + { + "first_name": "Jesse", + "last_name": "Dill" + }, + { + "first_name": "Pranay", + "last_name": "Mathur" + }, + { + "first_name": "Frank", + "last_name": "Dellaert" + }, + { + "first_name": "Panagiotis", + "last_name": "Tsiotra" + }, + { + "first_name": "Danfei", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Tri-Perspective View Decomposition for Geometry-Aware Depth Completion", - "authors": "Zhiqiang Yan, Yuankai Lin, Kun Wang, Yupeng Zheng, Yufei Wang, Zhenyu Zhang, Jun Li, Jian Yang", + "authors": [ + { + "first_name": "Zhiqiang", + "last_name": "Yan" + }, + { + "first_name": "Yuankai", + "last_name": "Lin" + }, + { + "first_name": "Kun", + "last_name": "Wang" + }, + { + "first_name": "Yupeng", + "last_name": "Zheng" + }, + { + "first_name": "Yufei", + "last_name": "Wang" + }, + { + "first_name": "Zhenyu", + "last_name": "Zhang" + }, + { + "first_name": "Jun", + "last_name": "Li" + }, + { + "first_name": "Jian", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Boosting Adversarial Training via Fisher-Rao Norm-based Regularization", - "authors": "Xiangyu Yin, Wenjie Ruan", + "authors": [ + { + "first_name": "Xiangyu", + "last_name": "Yin" + }, + { + "first_name": "Wenjie", + "last_name": "Ruan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learned Representation-Guided Diffusion Models for Large-Image Generation", - "authors": "Alexandros Graikos, Srikar Yellapragada, Minh-Quan Le, Saarthak Kapse, Prateek Prasanna, Joel Saltz, Dimitris Samaras", + "authors": [ + { + "first_name": "Alexandros", + "last_name": "Graikos" + }, + { + "first_name": "Srikar", + "last_name": "Yellapragada" + }, + { + "first_name": "Minh-Quan", + "last_name": "Le" + }, + { + "first_name": "Saarthak", + "last_name": "Kapse" + }, + { + "first_name": "Prateek", + "last_name": "Prasanna" + }, + { + "first_name": "Joel", + "last_name": "Saltz" + }, + { + "first_name": "Dimitris", + "last_name": "Samaras" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DAVE - A Detect-and-Verify Paradigm for Low-Shot Counting", - "authors": "Jer Pelhan, Alan Lukeži?, Vitjan Zavrtanik, Matej Kristan", + "authors": [ + { + "first_name": "Jer", + "last_name": "Pelhan" + }, + { + "first_name": "Alan", + "last_name": "Lukeži?" + }, + { + "first_name": "Vitjan", + "last_name": "Zavrtanik" + }, + { + "first_name": "Matej", + "last_name": "Kristan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Ranni: Taming Text-to-Image Diffusion for Accurate Instruction Following", - "authors": "Yutong Feng, Biao Gong, Di Chen, Yujun Shen, Yu Liu, Jingren Zhou", + "authors": [ + { + "first_name": "Yutong", + "last_name": "Feng" + }, + { + "first_name": "Biao", + "last_name": "Gong" + }, + { + "first_name": "Di", + "last_name": "Chen" + }, + { + "first_name": "Yujun", + "last_name": "Shen" + }, + { + "first_name": "Yu", + "last_name": "Liu" + }, + { + "first_name": "Jingren", + "last_name": "Zhou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Relaxed Contrastive Learning for Federated Learning", - "authors": "Seonguk Seo, Jinkyu Kim, Geeho Kim, Bohyung Han", + "authors": [ + { + "first_name": "Seonguk", + "last_name": "Seo" + }, + { + "first_name": "Jinkyu", + "last_name": "Kim" + }, + { + "first_name": "Geeho", + "last_name": "Kim" + }, + { + "first_name": "Bohyung", + "last_name": "Han" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Direct2.5: Diverse Text-to-3D Generation via Multi-view 2.5D Diffusion", - "authors": "Yuanxun Lu, Jingyang Zhang, Shiwei Li, Tian Fang, David McKinnon, Yanghai Tsin, Long Quan, Xun Cao, Yao Yao", + "authors": [ + { + "first_name": "Yuanxun", + "last_name": "Lu" + }, + { + "first_name": "Jingyang", + "last_name": "Zhang" + }, + { + "first_name": "Shiwei", + "last_name": "Li" + }, + { + "first_name": "Tian", + "last_name": "Fang" + }, + { + "first_name": "David", + "last_name": "McKinnon" + }, + { + "first_name": "Yanghai", + "last_name": "Tsin" + }, + { + "first_name": "Long", + "last_name": "Quan" + }, + { + "first_name": "Xun", + "last_name": "Cao" + }, + { + "first_name": "Yao", + "last_name": "Yao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed", - "authors": "Yifan Wang, Xingyi He, Sida Peng, Dongli Tan, Xiaowei Zhou", + "authors": [ + { + "first_name": "Yifan", + "last_name": "Wang" + }, + { + "first_name": "Xingyi", + "last_name": "He" + }, + { + "first_name": "Sida", + "last_name": "Peng" + }, + { + "first_name": "Dongli", + "last_name": "Tan" + }, + { + "first_name": "Xiaowei", + "last_name": "Zhou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Contextual Augmented Global Contrast for Multimodal Intent Recognition", - "authors": "Kaili Sun, Zhiwen Xie, Mang Ye, Huyin Zhang", + "authors": [ + { + "first_name": "Kaili", + "last_name": "Sun" + }, + { + "first_name": "Zhiwen", + "last_name": "Xie" + }, + { + "first_name": "Mang", + "last_name": "Ye" + }, + { + "first_name": "Huyin", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Pre-trained Model Guided Fine-Tuning for Zero-Shot Adversarial Robustness", - "authors": "Sibo Wang, Jie Zhang, Zheng Yuan, Shiguang Shan", + "authors": [ + { + "first_name": "Sibo", + "last_name": "Wang" + }, + { + "first_name": "Jie", + "last_name": "Zhang" + }, + { + "first_name": "Zheng", + "last_name": "Yuan" + }, + { + "first_name": "Shiguang", + "last_name": "Shan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MatFuse: Controllable Material Generation with Diffusion Models", - "authors": "Giuseppe Vecchio, Renato Sortino, Simone Palazzo, Concetto Spampinato", + "authors": [ + { + "first_name": "Giuseppe", + "last_name": "Vecchio" + }, + { + "first_name": "Renato", + "last_name": "Sortino" + }, + { + "first_name": "Simone", + "last_name": "Palazzo" + }, + { + "first_name": "Concetto", + "last_name": "Spampinato" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CoGS: Controllable Gaussian Splatting", - "authors": "Heng Yu, Joel Julin, Zoltán A. Milacski, Koichiro Niinuma, László A. Jeni", + "authors": [ + { + "first_name": "Heng", + "last_name": "Yu" + }, + { + "first_name": "Joel", + "last_name": "Julin" + }, + { + "first_name": "Zoltán", + "last_name": "A. Milacski" + }, + { + "first_name": "Koichiro", + "last_name": "Niinuma" + }, + { + "first_name": "László", + "last_name": "A. Jeni" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Partial-to-Partial Shape Matching with Geometric Consistency", - "authors": "Viktoria Ehm, Maolin Gao, Paul Roetzer, Marvin Eisenberger, Daniel Cremers, Florian Bernard", + "authors": [ + { + "first_name": "Viktoria", + "last_name": "Ehm" + }, + { + "first_name": "Maolin", + "last_name": "Gao" + }, + { + "first_name": "Paul", + "last_name": "Roetzer" + }, + { + "first_name": "Marvin", + "last_name": "Eisenberger" + }, + { + "first_name": "Daniel", + "last_name": "Cremers" + }, + { + "first_name": "Florian", + "last_name": "Bernard" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Descriptor and Word Soups: Overcoming the Parameter Efficiency Accuracy Tradeoff for Out-of-Distribution Few-shot Learning", - "authors": "Christopher Liao, Theodoros Tsiligkaridis, Brian Kulis", + "authors": [ + { + "first_name": "Christopher", + "last_name": "Liao" + }, + { + "first_name": "Theodoros", + "last_name": "Tsiligkaridis" + }, + { + "first_name": "Brian", + "last_name": "Kulis" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Harnessing the Power of MLLMs for Transferable Text-to-Image Person ReID", - "authors": "Wentan Tan, Changxing Ding, Jiayu Jiang, Fei Wang, Yibing Zhan, Dapeng Tao", + "authors": [ + { + "first_name": "Wentan", + "last_name": "Tan" + }, + { + "first_name": "Changxing", + "last_name": "Ding" + }, + { + "first_name": "Jiayu", + "last_name": "Jiang" + }, + { + "first_name": "Fei", + "last_name": "Wang" + }, + { + "first_name": "Yibing", + "last_name": "Zhan" + }, + { + "first_name": "Dapeng", + "last_name": "Tao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "360+x: A Panoptic Multi-modal Scene Understanding Dataset", - "authors": "Hao Chen, Yuqi Hou, Chenyuan Qu, Irene Testini, Xiaohan Hong, Jianbo Jiao", + "authors": [ + { + "first_name": "Hao", + "last_name": "Chen" + }, + { + "first_name": "Yuqi", + "last_name": "Hou" + }, + { + "first_name": "Chenyuan", + "last_name": "Qu" + }, + { + "first_name": "Irene", + "last_name": "Testini" + }, + { + "first_name": "Xiaohan", + "last_name": "Hong" + }, + { + "first_name": "Jianbo", + "last_name": "Jiao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Weakly Supervised Video Individual Counting", - "authors": "Xinyan Liu, Guorong Li, Yuankai Qi, Ziheng Yan, Zhenjun Han, Anton van den Hengel, Ming-Hsuan Yang, Qingming Huang", + "authors": [ + { + "first_name": "Xinyan", + "last_name": "Liu" + }, + { + "first_name": "Guorong", + "last_name": "Li" + }, + { + "first_name": "Yuankai", + "last_name": "Qi" + }, + { + "first_name": "Ziheng", + "last_name": "Yan" + }, + { + "first_name": "Zhenjun", + "last_name": "Han" + }, + { + "first_name": "Anton", + "last_name": "van den Hengel" + }, + { + "first_name": "Ming-Hsuan", + "last_name": "Yang" + }, + { + "first_name": "Qingming", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models", - "authors": "Zijin Yang, Kai Zeng, Kejiang Chen, Han Fang, Weiming Zhang, Nenghai Yu", + "authors": [ + { + "first_name": "Zijin", + "last_name": "Yang" + }, + { + "first_name": "Kai", + "last_name": "Zeng" + }, + { + "first_name": "Kejiang", + "last_name": "Chen" + }, + { + "first_name": "Han", + "last_name": "Fang" + }, + { + "first_name": "Weiming", + "last_name": "Zhang" + }, + { + "first_name": "Nenghai", + "last_name": "Yu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Generalized Event Cameras", - "authors": "Varun Sundar, Matthew Dutson, Andrei Ardelean, Claudio Bruschini, Edoardo Charbon, Mohit Gupta", + "authors": [ + { + "first_name": "Varun", + "last_name": "Sundar" + }, + { + "first_name": "Matthew", + "last_name": "Dutson" + }, + { + "first_name": "Andrei", + "last_name": "Ardelean" + }, + { + "first_name": "Claudio", + "last_name": "Bruschini" + }, + { + "first_name": "Edoardo", + "last_name": "Charbon" + }, + { + "first_name": "Mohit", + "last_name": "Gupta" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "3D Neural Edge Reconstruction", - "authors": "Lei Li, Songyou Peng, Zehao Yu, Shaohui Liu, Rémi Pautrat, Xiaochuan Yin, Marc Pollefeys", + "authors": [ + { + "first_name": "Lei", + "last_name": "Li" + }, + { + "first_name": "Songyou", + "last_name": "Peng" + }, + { + "first_name": "Zehao", + "last_name": "Yu" + }, + { + "first_name": "Shaohui", + "last_name": "Liu" + }, + { + "first_name": "Rémi", + "last_name": "Pautrat" + }, + { + "first_name": "Xiaochuan", + "last_name": "Yin" + }, + { + "first_name": "Marc", + "last_name": "Pollefeys" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DocRes: A Generalist Model Toward Unifying Document Image Restoration Tasks", - "authors": "Jiaxin Zhang, Dezhi Peng, Chongyu Liu, Peirong Zhang, Lianwen Jin", + "authors": [ + { + "first_name": "Jiaxin", + "last_name": "Zhang" + }, + { + "first_name": "Dezhi", + "last_name": "Peng" + }, + { + "first_name": "Chongyu", + "last_name": "Liu" + }, + { + "first_name": "Peirong", + "last_name": "Zhang" + }, + { + "first_name": "Lianwen", + "last_name": "Jin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Honeybee: Locality-enhanced Projector for Multimodal LLM", - "authors": "Junbum Cha, Wooyoung Kang, Jonghwan Mun, Byungseok Roh", + "authors": [ + { + "first_name": "Junbum", + "last_name": "Cha" + }, + { + "first_name": "Wooyoung", + "last_name": "Kang" + }, + { + "first_name": "Jonghwan", + "last_name": "Mun" + }, + { + "first_name": "Byungseok", + "last_name": "Roh" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learned Trajectory Embedding for Subspace Clustering", - "authors": "Yaroslava Lochman, Carl Olsson, Christopher Zach", + "authors": [ + { + "first_name": "Yaroslava", + "last_name": "Lochman" + }, + { + "first_name": "Carl", + "last_name": "Olsson" + }, + { + "first_name": "Christopher", + "last_name": "Zach" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Training Vision Transformers for Semi-Supervised Semantic Segmentation", - "authors": "Xinting Hu, Li Jiang, Bernt Schiele", + "authors": [ + { + "first_name": "Xinting", + "last_name": "Hu" + }, + { + "first_name": "Li", + "last_name": "Jiang" + }, + { + "first_name": "Bernt", + "last_name": "Schiele" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HarmonyView: Harmonizing Consistency and Diversity in One-Image-to-3D", - "authors": "Sangmin Woo, Byeongjun Park, Hyojun Go, Jin-Young Kim, Changick Kim", + "authors": [ + { + "first_name": "Sangmin", + "last_name": "Woo" + }, + { + "first_name": "Byeongjun", + "last_name": "Park" + }, + { + "first_name": "Hyojun", + "last_name": "Go" + }, + { + "first_name": "Jin-Young", + "last_name": "Kim" + }, + { + "first_name": "Changick", + "last_name": "Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DGC-GNN: Leveraging Geometry and Color Cues for Visual Descriptor-Free 2D-3D Matching", - "authors": "Shuzhe Wang, Juho Kannala, Daniel Barath", + "authors": [ + { + "first_name": "Shuzhe", + "last_name": "Wang" + }, + { + "first_name": "Juho", + "last_name": "Kannala" + }, + { + "first_name": "Daniel", + "last_name": "Barath" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CuVLER: Enhanced Unsupervised Object Discoveries through Exhaustive Self-Supervised Transformers", - "authors": "Shahaf Arica, Or Rubin, Sapir Gershov, Shlomi Laufer", + "authors": [ + { + "first_name": "Shahaf", + "last_name": "Arica" + }, + { + "first_name": "Or", + "last_name": "Rubin" + }, + { + "first_name": "Sapir", + "last_name": "Gershov" + }, + { + "first_name": "Shlomi", + "last_name": "Laufer" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Quantifying Task Priority for Multi-Task Optimization", - "authors": "Wooseong Jeong, Kuk-Jin Yoon", + "authors": [ + { + "first_name": "Wooseong", + "last_name": "Jeong" + }, + { + "first_name": "Kuk-Jin", + "last_name": "Yoon" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "UnSAMFlow: Unsupervised Optical Flow Guided by Segment Anything Model", - "authors": "Shuai Yuan, Lei Luo, Zhuo Hui, Can Pu, Xiaoyu Xiang, Rakesh Ranjan, Denis Demandolx", + "authors": [ + { + "first_name": "Shuai", + "last_name": "Yuan" + }, + { + "first_name": "Lei", + "last_name": "Luo" + }, + { + "first_name": "Zhuo", + "last_name": "Hui" + }, + { + "first_name": "Can", + "last_name": "Pu" + }, + { + "first_name": "Xiaoyu", + "last_name": "Xiang" + }, + { + "first_name": "Rakesh", + "last_name": "Ranjan" + }, + { + "first_name": "Denis", + "last_name": "Demandolx" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Exploiting Inter-sample and Inter-feature Relations in Dataset Distillation", - "authors": "Wenxiao Deng, Wenbin Li, Tianyu Ding, Lei Wang, Hongguang Zhang, Kuihua Huang, Jing Huo, Yang Gao", + "authors": [ + { + "first_name": "Wenxiao", + "last_name": "Deng" + }, + { + "first_name": "Wenbin", + "last_name": "Li" + }, + { + "first_name": "Tianyu", + "last_name": "Ding" + }, + { + "first_name": "Lei", + "last_name": "Wang" + }, + { + "first_name": "Hongguang", + "last_name": "Zhang" + }, + { + "first_name": "Kuihua", + "last_name": "Huang" + }, + { + "first_name": "Jing", + "last_name": "Huo" + }, + { + "first_name": "Yang", + "last_name": "Gao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "On the Scalability of Diffusion-based Text-to-Image Generation", - "authors": "Hao Li, Yang Zou, Ying Wang, Orchid Majumder, Yusheng Xie, R. Manmatha, Ashwin Swaminathan, Zhuowen Tu, Stefano Ermon, Stefano Soatto", + "authors": [ + { + "first_name": "Hao", + "last_name": "Li" + }, + { + "first_name": "Yang", + "last_name": "Zou" + }, + { + "first_name": "Ying", + "last_name": "Wang" + }, + { + "first_name": "Orchid", + "last_name": "Majumder" + }, + { + "first_name": "Yusheng", + "last_name": "Xie" + }, + { + "first_name": "R.", + "last_name": "Manmatha" + }, + { + "first_name": "Ashwin", + "last_name": "Swaminathan" + }, + { + "first_name": "Zhuowen", + "last_name": "Tu" + }, + { + "first_name": "Stefano", + "last_name": "Ermon" + }, + { + "first_name": "Stefano", + "last_name": "Soatto" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Entity-NeRF: Detecting and Removing Moving Entities in Urban Scenes", - "authors": "Takashi Otonari, Satoshi Ikehata, Kiyoharu Aizawa", + "authors": [ + { + "first_name": "Takashi", + "last_name": "Otonari" + }, + { + "first_name": "Satoshi", + "last_name": "Ikehata" + }, + { + "first_name": "Kiyoharu", + "last_name": "Aizawa" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "TAMM: TriAdapter Multi-Modal Learning for 3D Shape Understanding", - "authors": "Zhihao Zhang, Shengcao Cao, Yu-Xiong Wang", + "authors": [ + { + "first_name": "Zhihao", + "last_name": "Zhang" + }, + { + "first_name": "Shengcao", + "last_name": "Cao" + }, + { + "first_name": "Yu-Xiong", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GauHuman: Articulated Gaussian Splatting from Monocular Human Videos", - "authors": "Shoukang Hu, Tao Hu, Ziwei Liu", + "authors": [ + { + "first_name": "Shoukang", + "last_name": "Hu" + }, + { + "first_name": "Tao", + "last_name": "Hu" + }, + { + "first_name": "Ziwei", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "AnySkill: Learning Open-Vocabulary Physical Skill for Interactive Agents", - "authors": "Jieming Cui, Tengyu Liu, Nian Liu, Yaodong Yang, Yixin Zhu, Siyuan Huang", + "authors": [ + { + "first_name": "Jieming", + "last_name": "Cui" + }, + { + "first_name": "Tengyu", + "last_name": "Liu" + }, + { + "first_name": "Nian", + "last_name": "Liu" + }, + { + "first_name": "Yaodong", + "last_name": "Yang" + }, + { + "first_name": "Yixin", + "last_name": "Zhu" + }, + { + "first_name": "Siyuan", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "EGTR: Extracting Graph from Transformer for Scene Graph Generation", - "authors": "Jinbae Im, JeongYeon Nam, Nokyung Park, Hyungmin Lee, Seunghyun Park", + "authors": [ + { + "first_name": "Jinbae", + "last_name": "Im" + }, + { + "first_name": "JeongYeon", + "last_name": "Nam" + }, + { + "first_name": "Nokyung", + "last_name": "Park" + }, + { + "first_name": "Hyungmin", + "last_name": "Lee" + }, + { + "first_name": "Seunghyun", + "last_name": "Park" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Generative Unlearning for Any Identity", - "authors": "Juwon Seo, Sung-Hoon Lee, Tae-Young Lee, Seungjun Moon, Gyeong-Moon Park", + "authors": [ + { + "first_name": "Juwon", + "last_name": "Seo" + }, + { + "first_name": "Sung-Hoon", + "last_name": "Lee" + }, + { + "first_name": "Tae-Young", + "last_name": "Lee" + }, + { + "first_name": "Seungjun", + "last_name": "Moon" + }, + { + "first_name": "Gyeong-Moon", + "last_name": "Park" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Context-based and Diversity-driven Specificity in Compositional Zero-Shot Learning", - "authors": "Yun Li, Zhe Liu, Hang Chen, Lina Yao", + "authors": [ + { + "first_name": "Yun", + "last_name": "Li" + }, + { + "first_name": "Zhe", + "last_name": "Liu" + }, + { + "first_name": "Hang", + "last_name": "Chen" + }, + { + "first_name": "Lina", + "last_name": "Yao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis", - "authors": "Feng Liang, Bichen Wu, Jialiang Wang, Licheng Yu, Kunpeng Li, Yinan Zhao, Ishan Misra, Jia-Bin Huang, Peizhao Zhang, Peter Vajda, Diana Marculescu", + "authors": [ + { + "first_name": "Feng", + "last_name": "Liang" + }, + { + "first_name": "Bichen", + "last_name": "Wu" + }, + { + "first_name": "Jialiang", + "last_name": "Wang" + }, + { + "first_name": "Licheng", + "last_name": "Yu" + }, + { + "first_name": "Kunpeng", + "last_name": "Li" + }, + { + "first_name": "Yinan", + "last_name": "Zhao" + }, + { + "first_name": "Ishan", + "last_name": "Misra" + }, + { + "first_name": "Jia-Bin", + "last_name": "Huang" + }, + { + "first_name": "Peizhao", + "last_name": "Zhang" + }, + { + "first_name": "Peter", + "last_name": "Vajda" + }, + { + "first_name": "Diana", + "last_name": "Marculescu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "StyleCineGAN: Landscape Cinemagraph Generation using a Pre-trained StyleGAN", - "authors": "Jongwoo Choi, Kwanggyoon Seo, Amirsaman Ashtari, Junyong Noh", + "authors": [ + { + "first_name": "Jongwoo", + "last_name": "Choi" + }, + { + "first_name": "Kwanggyoon", + "last_name": "Seo" + }, + { + "first_name": "Amirsaman", + "last_name": "Ashtari" + }, + { + "first_name": "Junyong", + "last_name": "Noh" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Rethinking Multi-domain Generalization with A General Learning Objective", - "authors": "Zhaorui Tan, Xi Yang, Kaizhu Huang", + "authors": [ + { + "first_name": "Zhaorui", + "last_name": "Tan" + }, + { + "first_name": "Xi", + "last_name": "Yang" + }, + { + "first_name": "Kaizhu", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Laplacian-guided Entropy Model in Neural Codec with Blur-dissipated Synthesis", - "authors": "Atefeh Khoshkhahtinat, Ali Zafari, Piyush M. Mehta, Nasser M. Nasrabadi", + "authors": [ + { + "first_name": "Atefeh", + "last_name": "Khoshkhahtinat" + }, + { + "first_name": "Ali", + "last_name": "Zafari" + }, + { + "first_name": "Piyush", + "last_name": "M. Mehta" + }, + { + "first_name": "Nasser", + "last_name": "M. Nasrabadi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Universal Novelty Detection Through Adaptive Contrastive Learning", - "authors": "Hossein Mirzaei, Mojtaba Nafez, Mohammad Jafari, Mohammad Bagher Soltani, Mohammad Azizmalayeri, Jafar Habibi, Mohammad Sabokrou, Mohammad Hossein Rohban", + "authors": [ + { + "first_name": "Hossein", + "last_name": "Mirzaei" + }, + { + "first_name": "Mojtaba", + "last_name": "Nafez" + }, + { + "first_name": "Mohammad", + "last_name": "Jafari" + }, + { + "first_name": "Mohammad", + "last_name": "Bagher Soltani" + }, + { + "first_name": "Mohammad", + "last_name": "Azizmalayeri" + }, + { + "first_name": "Jafar", + "last_name": "Habibi" + }, + { + "first_name": "Mohammad", + "last_name": "Sabokrou" + }, + { + "first_name": "Mohammad", + "last_name": "Hossein Rohban" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Rethinking Diffusion Model for Multi-Contrast MRI Super-Resolution", - "authors": "Guangyuan Li, Chen Rao, Juncheng Mo, Zhanjie Zhang, Wei Xing, Lei Zhao", + "authors": [ + { + "first_name": "Guangyuan", + "last_name": "Li" + }, + { + "first_name": "Chen", + "last_name": "Rao" + }, + { + "first_name": "Juncheng", + "last_name": "Mo" + }, + { + "first_name": "Zhanjie", + "last_name": "Zhang" + }, + { + "first_name": "Wei", + "last_name": "Xing" + }, + { + "first_name": "Lei", + "last_name": "Zhao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Resurrecting Old Classes with New Data for Exemplar-Free Continual Learning", - "authors": "Dipam Goswami, Albin Soutif-Cormerais, Yuyang Liu, Sandesh Kamath, Bart?omiej Twardowski, Joost van de Weijer", + "authors": [ + { + "first_name": "Dipam", + "last_name": "Goswami" + }, + { + "first_name": "Albin", + "last_name": "Soutif-Cormerais" + }, + { + "first_name": "Yuyang", + "last_name": "Liu" + }, + { + "first_name": "Sandesh", + "last_name": "Kamath" + }, + { + "first_name": "Bart?omiej", + "last_name": "Twardowski" + }, + { + "first_name": "Joost", + "last_name": "van de Weijer" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Unknown Prompt the only Lacuna: Unveiling CLIP's Potential for Open Domain Generalization", - "authors": "Mainak Singha, Ankit Jha, Shirsha Bose, Ashwin Nair, Moloud Abdar, Biplab Banerjee", + "authors": [ + { + "first_name": "Mainak", + "last_name": "Singha" + }, + { + "first_name": "Ankit", + "last_name": "Jha" + }, + { + "first_name": "Shirsha", + "last_name": "Bose" + }, + { + "first_name": "Ashwin", + "last_name": "Nair" + }, + { + "first_name": "Moloud", + "last_name": "Abdar" + }, + { + "first_name": "Biplab", + "last_name": "Banerjee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Poly Kernel Inception Network for Remote Sensing Detection", - "authors": "Xinhao Cai, Qiuxia Lai, Yuwei Wang, Wenguan Wang, Zeren Sun, Yazhou Yao", + "authors": [ + { + "first_name": "Xinhao", + "last_name": "Cai" + }, + { + "first_name": "Qiuxia", + "last_name": "Lai" + }, + { + "first_name": "Yuwei", + "last_name": "Wang" + }, + { + "first_name": "Wenguan", + "last_name": "Wang" + }, + { + "first_name": "Zeren", + "last_name": "Sun" + }, + { + "first_name": "Yazhou", + "last_name": "Yao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "RMT: Retentive Networks Meet Vision Transformers", - "authors": "Qihang Fan, Huaibo Huang, Mingrui Chen, Hongmin Liu, Ran He", + "authors": [ + { + "first_name": "Qihang", + "last_name": "Fan" + }, + { + "first_name": "Huaibo", + "last_name": "Huang" + }, + { + "first_name": "Mingrui", + "last_name": "Chen" + }, + { + "first_name": "Hongmin", + "last_name": "Liu" + }, + { + "first_name": "Ran", + "last_name": "He" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "From Coarse to Fine-Grained Open-Set Recognition", - "authors": "Nico Lang, Vésteinn Snæbjarnarson, Elijah Cole, Oisin Mac Aodha, Christian Igel, Serge Belongie", + "authors": [ + { + "first_name": "Nico", + "last_name": "Lang" + }, + { + "first_name": "Vésteinn", + "last_name": "Snæbjarnarson" + }, + { + "first_name": "Elijah", + "last_name": "Cole" + }, + { + "first_name": "Oisin", + "last_name": "Mac Aodha" + }, + { + "first_name": "Christian", + "last_name": "Igel" + }, + { + "first_name": "Serge", + "last_name": "Belongie" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Multimodal Pathway: Improve Transformers with Irrelevant Data from Other Modalities", - "authors": "Yiyuan Zhang, Xiaohan Ding, Kaixiong Gong, Yixiao Ge, Ying Shan, Xiangyu Yue", + "authors": [ + { + "first_name": "Yiyuan", + "last_name": "Zhang" + }, + { + "first_name": "Xiaohan", + "last_name": "Ding" + }, + { + "first_name": "Kaixiong", + "last_name": "Gong" + }, + { + "first_name": "Yixiao", + "last_name": "Ge" + }, + { + "first_name": "Ying", + "last_name": "Shan" + }, + { + "first_name": "Xiangyu", + "last_name": "Yue" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FaceChain-ImagineID: Freely Crafting High-Fidelity Diverse Talking Faces from Disentangled Audio", - "authors": "Chao Xu, Yang Liu, Jiazheng Xing, Weida Wang, Mingze Sun, Jun Dan, Tianxin Huang, Siyuan Li, Zhi-Qi Cheng, Ying Tai, Baigui Sun", + "authors": [ + { + "first_name": "Chao", + "last_name": "Xu" + }, + { + "first_name": "Yang", + "last_name": "Liu" + }, + { + "first_name": "Jiazheng", + "last_name": "Xing" + }, + { + "first_name": "Weida", + "last_name": "Wang" + }, + { + "first_name": "Mingze", + "last_name": "Sun" + }, + { + "first_name": "Jun", + "last_name": "Dan" + }, + { + "first_name": "Tianxin", + "last_name": "Huang" + }, + { + "first_name": "Siyuan", + "last_name": "Li" + }, + { + "first_name": "Zhi-Qi", + "last_name": "Cheng" + }, + { + "first_name": "Ying", + "last_name": "Tai" + }, + { + "first_name": "Baigui", + "last_name": "Sun" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "OmniViD: A Generative Framework for Universal Video Understanding", - "authors": "Junke Wang, Dongdong Chen, Chong Luo, Bo He, Lu Yuan, Zuxuan Wu, Yu-Gang Jiang", + "authors": [ + { + "first_name": "Junke", + "last_name": "Wang" + }, + { + "first_name": "Dongdong", + "last_name": "Chen" + }, + { + "first_name": "Chong", + "last_name": "Luo" + }, + { + "first_name": "Bo", + "last_name": "He" + }, + { + "first_name": "Lu", + "last_name": "Yuan" + }, + { + "first_name": "Zuxuan", + "last_name": "Wu" + }, + { + "first_name": "Yu-Gang", + "last_name": "Jiang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Naturally Supervised 3D Visual Grounding with Language-Regularized Concept Learners", - "authors": "Chun Feng, Joy Hsu, Weiyu Liu, Jiajun Wu", + "authors": [ + { + "first_name": "Chun", + "last_name": "Feng" + }, + { + "first_name": "Joy", + "last_name": "Hsu" + }, + { + "first_name": "Weiyu", + "last_name": "Liu" + }, + { + "first_name": "Jiajun", + "last_name": "Wu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generation", - "authors": "Yuxuan Zhang, Yiren Song, Jiaming Liu, Rui Wang, Jinpeng Yu, Hao Tang, Huaxia Li, Xu Tang, Yao Hu, Han Pan, Zhongliang Jing", + "authors": [ + { + "first_name": "Yuxuan", + "last_name": "Zhang" + }, + { + "first_name": "Yiren", + "last_name": "Song" + }, + { + "first_name": "Jiaming", + "last_name": "Liu" + }, + { + "first_name": "Rui", + "last_name": "Wang" + }, + { + "first_name": "Jinpeng", + "last_name": "Yu" + }, + { + "first_name": "Hao", + "last_name": "Tang" + }, + { + "first_name": "Huaxia", + "last_name": "Li" + }, + { + "first_name": "Xu", + "last_name": "Tang" + }, + { + "first_name": "Yao", + "last_name": "Hu" + }, + { + "first_name": "Han", + "last_name": "Pan" + }, + { + "first_name": "Zhongliang", + "last_name": "Jing" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CA-Jaccard: Camera-aware Jaccard Distance for Person Re-identification", - "authors": "Yiyu Chen, Zheyi Fan, Zhaoru Chen, Yixuan Zhu", + "authors": [ + { + "first_name": "Yiyu", + "last_name": "Chen" + }, + { + "first_name": "Zheyi", + "last_name": "Fan" + }, + { + "first_name": "Zhaoru", + "last_name": "Chen" + }, + { + "first_name": "Yixuan", + "last_name": "Zhu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Dual Prior Unfolding for Snapshot Compressive Imaging", - "authors": "Jiancheng Zhang, Haijin Zeng, Jiezhang Cao, Yongyong Chen, Dengxiu Yu, Yin-Ping Zhao", + "authors": [ + { + "first_name": "Jiancheng", + "last_name": "Zhang" + }, + { + "first_name": "Haijin", + "last_name": "Zeng" + }, + { + "first_name": "Jiezhang", + "last_name": "Cao" + }, + { + "first_name": "Yongyong", + "last_name": "Chen" + }, + { + "first_name": "Dengxiu", + "last_name": "Yu" + }, + { + "first_name": "Yin-Ping", + "last_name": "Zhao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "COLMAP-Free 3D Gaussian Splatting", - "authors": "Yang Fu, Sifei Liu, Amey Kulkarni, Jan Kautz, Alexei A. Efros, Xiaolong Wang", + "authors": [ + { + "first_name": "Yang", + "last_name": "Fu" + }, + { + "first_name": "Sifei", + "last_name": "Liu" + }, + { + "first_name": "Amey", + "last_name": "Kulkarni" + }, + { + "first_name": "Jan", + "last_name": "Kautz" + }, + { + "first_name": "Alexei", + "last_name": "A. Efros" + }, + { + "first_name": "Xiaolong", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MVIP-NeRF: Multi-view 3D Inpainting on NeRF Scenes via Diffusion Prior", - "authors": "Honghua Chen, Chen Change Loy, Xingang Pan", + "authors": [ + { + "first_name": "Honghua", + "last_name": "Chen" + }, + { + "first_name": "Chen", + "last_name": "Change Loy" + }, + { + "first_name": "Xingang", + "last_name": "Pan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "StegoGAN: Leveraging Steganography for Non-Bijective Image-to-Image Translation", - "authors": "Sidi Wu, Yizi Chen, Samuel Mermet, Lorenz Hurni, Konrad Schindler, Nicolas Gonthier, Loic Landrieu", + "authors": [ + { + "first_name": "Sidi", + "last_name": "Wu" + }, + { + "first_name": "Yizi", + "last_name": "Chen" + }, + { + "first_name": "Samuel", + "last_name": "Mermet" + }, + { + "first_name": "Lorenz", + "last_name": "Hurni" + }, + { + "first_name": "Konrad", + "last_name": "Schindler" + }, + { + "first_name": "Nicolas", + "last_name": "Gonthier" + }, + { + "first_name": "Loic", + "last_name": "Landrieu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "M&M VTO: Multi-Garment Virtual Try-On and Editing", - "authors": "Luyang Zhu, Yingwei Li, Nan Liu, Hao Peng, Dawei Yang, Ira Kemelmacher-Shlizerman", + "authors": [ + { + "first_name": "Luyang", + "last_name": "Zhu" + }, + { + "first_name": "Yingwei", + "last_name": "Li" + }, + { + "first_name": "Nan", + "last_name": "Liu" + }, + { + "first_name": "Hao", + "last_name": "Peng" + }, + { + "first_name": "Dawei", + "last_name": "Yang" + }, + { + "first_name": "Ira", + "last_name": "Kemelmacher-Shlizerman" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "AutoAD III: The Prequel - Back to the Pixels", - "authors": "Tengda Han, Max Bain, Arsha Nagrani, Gül Varol, Weidi Xie, Andrew Zisserman", + "authors": [ + { + "first_name": "Tengda", + "last_name": "Han" + }, + { + "first_name": "Max", + "last_name": "Bain" + }, + { + "first_name": "Arsha", + "last_name": "Nagrani" + }, + { + "first_name": "Gül", + "last_name": "Varol" + }, + { + "first_name": "Weidi", + "last_name": "Xie" + }, + { + "first_name": "Andrew", + "last_name": "Zisserman" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Characteristics Matching Based Hash Codes Generation for Efficient Fine-grained Image Retrieval", - "authors": "Zhen-Duo Chen, Li-Jun Zhao, Zi-Chao Zhang, Xin Luo, Xin-Shun Xu", + "authors": [ + { + "first_name": "Zhen-Duo", + "last_name": "Chen" + }, + { + "first_name": "Li-Jun", + "last_name": "Zhao" + }, + { + "first_name": "Zi-Chao", + "last_name": "Zhang" + }, + { + "first_name": "Xin", + "last_name": "Luo" + }, + { + "first_name": "Xin-Shun", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning", - "authors": "Siyuan Liang, Mingli Zhu, Aishan Liu, Baoyuan Wu, Xiaochun Cao, Ee-Chien Chang", + "authors": [ + { + "first_name": "Siyuan", + "last_name": "Liang" + }, + { + "first_name": "Mingli", + "last_name": "Zhu" + }, + { + "first_name": "Aishan", + "last_name": "Liu" + }, + { + "first_name": "Baoyuan", + "last_name": "Wu" + }, + { + "first_name": "Xiaochun", + "last_name": "Cao" + }, + { + "first_name": "Ee-Chien", + "last_name": "Chang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Dynamic Inertial Poser (DynaIP): Part-Based Motion Dynamics Learning for Enhanced Human Pose Estimation with Sparse Inertial Sensors", - "authors": "Yu Zhang, Songpengcheng Xia, Lei Chu, Jiarui Yang, Qi Wu, Ling Pei", + "authors": [ + { + "first_name": "Yu", + "last_name": "Zhang" + }, + { + "first_name": "Songpengcheng", + "last_name": "Xia" + }, + { + "first_name": "Lei", + "last_name": "Chu" + }, + { + "first_name": "Jiarui", + "last_name": "Yang" + }, + { + "first_name": "Qi", + "last_name": "Wu" + }, + { + "first_name": "Ling", + "last_name": "Pei" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Matching 2D Images in 3D: Metric Relative Pose from Metric Correspondences", - "authors": "Axel Barroso-Laguna, Sowmya Munukutla, Victor Adrian Prisacariu, Eric Brachmann", + "authors": [ + { + "first_name": "Axel", + "last_name": "Barroso-Laguna" + }, + { + "first_name": "Sowmya", + "last_name": "Munukutla" + }, + { + "first_name": "Victor", + "last_name": "Adrian Prisacariu" + }, + { + "first_name": "Eric", + "last_name": "Brachmann" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Efficient Vision-Language Pre-training by Cluster Masking", - "authors": "Zihao Wei, Zixuan Pan, Andrew Owens", + "authors": [ + { + "first_name": "Zihao", + "last_name": "Wei" + }, + { + "first_name": "Zixuan", + "last_name": "Pan" + }, + { + "first_name": "Andrew", + "last_name": "Owens" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GraCo: Granularity-Controllable Interactive Segmentation", - "authors": "Yian Zhao, Kehan Li, Zesen Cheng, Pengchong Qiao, Xiawu Zheng, Rongrong Ji, Chang Liu, Li Yuan, Jie Chen", + "authors": [ + { + "first_name": "Yian", + "last_name": "Zhao" + }, + { + "first_name": "Kehan", + "last_name": "Li" + }, + { + "first_name": "Zesen", + "last_name": "Cheng" + }, + { + "first_name": "Pengchong", + "last_name": "Qiao" + }, + { + "first_name": "Xiawu", + "last_name": "Zheng" + }, + { + "first_name": "Rongrong", + "last_name": "Ji" + }, + { + "first_name": "Chang", + "last_name": "Liu" + }, + { + "first_name": "Li", + "last_name": "Yuan" + }, + { + "first_name": "Jie", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "M3-UDA: A New Benchmark for Unsupervised Domain Adaptive Fetal Cardiac Structure Detection", - "authors": "Bin Pu, Liwen Wang, Jiewen Yang, Guannan He, Xingbo Dong, Shengli Li, Ying Tan, Ming Chen, Zhe Jin, Kenli Li, Xiaomeng Li", + "authors": [ + { + "first_name": "Bin", + "last_name": "Pu" + }, + { + "first_name": "Liwen", + "last_name": "Wang" + }, + { + "first_name": "Jiewen", + "last_name": "Yang" + }, + { + "first_name": "Guannan", + "last_name": "He" + }, + { + "first_name": "Xingbo", + "last_name": "Dong" + }, + { + "first_name": "Shengli", + "last_name": "Li" + }, + { + "first_name": "Ying", + "last_name": "Tan" + }, + { + "first_name": "Ming", + "last_name": "Chen" + }, + { + "first_name": "Zhe", + "last_name": "Jin" + }, + { + "first_name": "Kenli", + "last_name": "Li" + }, + { + "first_name": "Xiaomeng", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis", - "authors": "Shunyuan Zheng, Boyao Zhou, Ruizhi Shao, Boning Liu, Shengping Zhang, Liqiang Nie, Yebin Liu", + "authors": [ + { + "first_name": "Shunyuan", + "last_name": "Zheng" + }, + { + "first_name": "Boyao", + "last_name": "Zhou" + }, + { + "first_name": "Ruizhi", + "last_name": "Shao" + }, + { + "first_name": "Boning", + "last_name": "Liu" + }, + { + "first_name": "Shengping", + "last_name": "Zhang" + }, + { + "first_name": "Liqiang", + "last_name": "Nie" + }, + { + "first_name": "Yebin", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding", - "authors": "Peng Jin, Ryuichi Takanobu, Wancai Zhang, Xiaochun Cao, Li Yuan", + "authors": [ + { + "first_name": "Peng", + "last_name": "Jin" + }, + { + "first_name": "Ryuichi", + "last_name": "Takanobu" + }, + { + "first_name": "Wancai", + "last_name": "Zhang" + }, + { + "first_name": "Xiaochun", + "last_name": "Cao" + }, + { + "first_name": "Li", + "last_name": "Yuan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MAGICK: A Large-scale Captioned Dataset from Matting Generated Images using Chroma Keying", - "authors": "Ryan D. Burgert, Brian L. Price, Jason Kuen, Yijun Li, Michael S. Ryoo", + "authors": [ + { + "first_name": "Ryan", + "last_name": "D. Burgert" + }, + { + "first_name": "Brian", + "last_name": "L. Price" + }, + { + "first_name": "Jason", + "last_name": "Kuen" + }, + { + "first_name": "Yijun", + "last_name": "Li" + }, + { + "first_name": "Michael", + "last_name": "S. Ryoo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Video Super-Resolution Transformer with Masked Inter&Intra-Frame Attention", - "authors": "Xingyu Zhou, Leheng Zhang, Xiaorui Zhao, Keze Wang, Leida Li, Shuhang Gu", + "authors": [ + { + "first_name": "Xingyu", + "last_name": "Zhou" + }, + { + "first_name": "Leheng", + "last_name": "Zhang" + }, + { + "first_name": "Xiaorui", + "last_name": "Zhao" + }, + { + "first_name": "Keze", + "last_name": "Wang" + }, + { + "first_name": "Leida", + "last_name": "Li" + }, + { + "first_name": "Shuhang", + "last_name": "Gu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Token Transformation Matters: Towards Faithful Post-hoc Explanation for Vision Transformer", - "authors": "Junyi Wu, Bin Duan, Weitai Kang, Hao Tang, Yan Yan", + "authors": [ + { + "first_name": "Junyi", + "last_name": "Wu" + }, + { + "first_name": "Bin", + "last_name": "Duan" + }, + { + "first_name": "Weitai", + "last_name": "Kang" + }, + { + "first_name": "Hao", + "last_name": "Tang" + }, + { + "first_name": "Yan", + "last_name": "Yan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Bayesian Differentiable Physics for Cloth Digitalization", - "authors": "Deshan Gong, Ningtao Mao, He Wang", + "authors": [ + { + "first_name": "Deshan", + "last_name": "Gong" + }, + { + "first_name": "Ningtao", + "last_name": "Mao" + }, + { + "first_name": "He", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "G-HOP: Generative Hand-Object Prior for Interaction Reconstruction and Grasp Synthesis", - "authors": "Yufei Ye, Abhinav Gupta, Kris Kitani, Shubham Tulsiani", + "authors": [ + { + "first_name": "Yufei", + "last_name": "Ye" + }, + { + "first_name": "Abhinav", + "last_name": "Gupta" + }, + { + "first_name": "Kris", + "last_name": "Kitani" + }, + { + "first_name": "Shubham", + "last_name": "Tulsiani" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Higher-order Relational Reasoning for Pedestrian Trajectory Prediction", - "authors": "Sungjune Kim, Hyung-gun Chi, Hyerin Lim, Karthik Ramani, Jinkyu Kim, Sangpil Kim", + "authors": [ + { + "first_name": "Sungjune", + "last_name": "Kim" + }, + { + "first_name": "Hyung-gun", + "last_name": "Chi" + }, + { + "first_name": "Hyerin", + "last_name": "Lim" + }, + { + "first_name": "Karthik", + "last_name": "Ramani" + }, + { + "first_name": "Jinkyu", + "last_name": "Kim" + }, + { + "first_name": "Sangpil", + "last_name": "Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SurroundSDF: Implicit 3D Scene Understanding Based on Signed Distance Field", - "authors": "Lizhe Liu, Bohua Wang, Hongwei Xie, Daqi Liu, Li Liu, Zhiqiang Tian, Kuiyuan Yang, Bing Wang", + "authors": [ + { + "first_name": "Lizhe", + "last_name": "Liu" + }, + { + "first_name": "Bohua", + "last_name": "Wang" + }, + { + "first_name": "Hongwei", + "last_name": "Xie" + }, + { + "first_name": "Daqi", + "last_name": "Liu" + }, + { + "first_name": "Li", + "last_name": "Liu" + }, + { + "first_name": "Zhiqiang", + "last_name": "Tian" + }, + { + "first_name": "Kuiyuan", + "last_name": "Yang" + }, + { + "first_name": "Bing", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Contrastive Denoising Score for Text-guided Latent Diffusion Image Editing", - "authors": "Hyelin Nam, Gihyun Kwon, Geon Yeong Park, Jong Chul Ye", + "authors": [ + { + "first_name": "Hyelin", + "last_name": "Nam" + }, + { + "first_name": "Gihyun", + "last_name": "Kwon" + }, + { + "first_name": "Geon", + "last_name": "Yeong Park" + }, + { + "first_name": "Jong", + "last_name": "Chul Ye" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Neural Point Cloud Diffusion for Disentangled 3D Shape and Appearance Generation", - "authors": "Philipp Schröppel, Christopher Wewer, Jan Eric Lenssen, Eddy Ilg, Thomas Brox", + "authors": [ + { + "first_name": "Philipp", + "last_name": "Schröppel" + }, + { + "first_name": "Christopher", + "last_name": "Wewer" + }, + { + "first_name": "Jan", + "last_name": "Eric Lenssen" + }, + { + "first_name": "Eddy", + "last_name": "Ilg" + }, + { + "first_name": "Thomas", + "last_name": "Brox" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection", - "authors": "Ximiao Zhang, Min Xu, Xiuzhuang Zhou", + "authors": [ + { + "first_name": "Ximiao", + "last_name": "Zhang" + }, + { + "first_name": "Min", + "last_name": "Xu" + }, + { + "first_name": "Xiuzhuang", + "last_name": "Zhou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Outdoor Scene Extrapolation with Hierarchical Generative Cellular Automata", - "authors": "Dongsu Zhang, Francis Williams, Zan Gojcic, Karsten Kreis, Sanja Fidler, Young Min Kim, Amlan Kar", + "authors": [ + { + "first_name": "Dongsu", + "last_name": "Zhang" + }, + { + "first_name": "Francis", + "last_name": "Williams" + }, + { + "first_name": "Zan", + "last_name": "Gojcic" + }, + { + "first_name": "Karsten", + "last_name": "Kreis" + }, + { + "first_name": "Sanja", + "last_name": "Fidler" + }, + { + "first_name": "Young", + "last_name": "Min Kim" + }, + { + "first_name": "Amlan", + "last_name": "Kar" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Instruct 4D-to-4D: Editing 4D Scenes as Pseudo-3D Scenes Using 2D Diffusion", - "authors": "Linzhan Mou, Jun-Kun Chen, Yu-Xiong Wang", + "authors": [ + { + "first_name": "Linzhan", + "last_name": "Mou" + }, + { + "first_name": "Jun-Kun", + "last_name": "Chen" + }, + { + "first_name": "Yu-Xiong", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "VAREN: Very Accurate and Realistic Equine Network", - "authors": "Silvia Zuffi, Ylva Mellbin, Ci Li, Markus Hoeschle, Hedvig Kjellström, Senya Polikovsky, Elin Hernlund, Michael J. Black", + "authors": [ + { + "first_name": "Silvia", + "last_name": "Zuffi" + }, + { + "first_name": "Ylva", + "last_name": "Mellbin" + }, + { + "first_name": "Ci", + "last_name": "Li" + }, + { + "first_name": "Markus", + "last_name": "Hoeschle" + }, + { + "first_name": "Hedvig", + "last_name": "Kjellström" + }, + { + "first_name": "Senya", + "last_name": "Polikovsky" + }, + { + "first_name": "Elin", + "last_name": "Hernlund" + }, + { + "first_name": "Michael", + "last_name": "J. Black" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular Stereo and RGB-D Cameras", - "authors": "Huajian Huang, Longwei Li, Hui Cheng, Sai-Kit Yeung", + "authors": [ + { + "first_name": "Huajian", + "last_name": "Huang" + }, + { + "first_name": "Longwei", + "last_name": "Li" + }, + { + "first_name": "Hui", + "last_name": "Cheng" + }, + { + "first_name": "Sai-Kit", + "last_name": "Yeung" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SD-DiT: Unleashing the Power of Self-supervised Discrimination in Diffusion Transformer", - "authors": "Rui Zhu, Yingwei Pan, Yehao Li, Ting Yao, Zhenglong Sun, Tao Mei, Chang Wen Chen", + "authors": [ + { + "first_name": "Rui", + "last_name": "Zhu" + }, + { + "first_name": "Yingwei", + "last_name": "Pan" + }, + { + "first_name": "Yehao", + "last_name": "Li" + }, + { + "first_name": "Ting", + "last_name": "Yao" + }, + { + "first_name": "Zhenglong", + "last_name": "Sun" + }, + { + "first_name": "Tao", + "last_name": "Mei" + }, + { + "first_name": "Chang", + "last_name": "Wen Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Multi-modal Instruction Tuned LLMs with Fine-grained Visual Perception", - "authors": "Junwen He, Yifan Wang, Lijun Wang, Huchuan Lu, Jun-Yan He, Jin-Peng Lan, Bin Luo, Xuansong Xie", + "authors": [ + { + "first_name": "Junwen", + "last_name": "He" + }, + { + "first_name": "Yifan", + "last_name": "Wang" + }, + { + "first_name": "Lijun", + "last_name": "Wang" + }, + { + "first_name": "Huchuan", + "last_name": "Lu" + }, + { + "first_name": "Jun-Yan", + "last_name": "He" + }, + { + "first_name": "Jin-Peng", + "last_name": "Lan" + }, + { + "first_name": "Bin", + "last_name": "Luo" + }, + { + "first_name": "Xuansong", + "last_name": "Xie" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ProMotion: Prototypes As Motion Learners", - "authors": "Yawen Lu, Dongfang Liu, Qifan Wang, Cheng Han, Yiming Cui, Zhiwen Cao, Xueling Zhang, Yingjie Victor Chen, Heng Fan", + "authors": [ + { + "first_name": "Yawen", + "last_name": "Lu" + }, + { + "first_name": "Dongfang", + "last_name": "Liu" + }, + { + "first_name": "Qifan", + "last_name": "Wang" + }, + { + "first_name": "Cheng", + "last_name": "Han" + }, + { + "first_name": "Yiming", + "last_name": "Cui" + }, + { + "first_name": "Zhiwen", + "last_name": "Cao" + }, + { + "first_name": "Xueling", + "last_name": "Zhang" + }, + { + "first_name": "Yingjie", + "last_name": "Victor Chen" + }, + { + "first_name": "Heng", + "last_name": "Fan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SpatialTracker: Tracking Any 2D Pixels in 3D Space", - "authors": "Yuxi Xiao, Qianqian Wang, Shangzhan Zhang, Nan Xue, Sida Peng, Yujun Shen, Xiaowei Zhou", + "authors": [ + { + "first_name": "Yuxi", + "last_name": "Xiao" + }, + { + "first_name": "Qianqian", + "last_name": "Wang" + }, + { + "first_name": "Shangzhan", + "last_name": "Zhang" + }, + { + "first_name": "Nan", + "last_name": "Xue" + }, + { + "first_name": "Sida", + "last_name": "Peng" + }, + { + "first_name": "Yujun", + "last_name": "Shen" + }, + { + "first_name": "Xiaowei", + "last_name": "Zhou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LaMPilot: An Open Benchmark Dataset for Autonomous Driving with Language Model Programs", - "authors": "Yunsheng Ma, Can Cui, Xu Cao, Wenqian Ye, Peiran Liu, Juanwu Lu, Amr Abdelraouf, Rohit Gupta, Kyungtae Han, Aniket Bera, James M. Rehg, Ziran Wang", + "authors": [ + { + "first_name": "Yunsheng", + "last_name": "Ma" + }, + { + "first_name": "Can", + "last_name": "Cui" + }, + { + "first_name": "Xu", + "last_name": "Cao" + }, + { + "first_name": "Wenqian", + "last_name": "Ye" + }, + { + "first_name": "Peiran", + "last_name": "Liu" + }, + { + "first_name": "Juanwu", + "last_name": "Lu" + }, + { + "first_name": "Amr", + "last_name": "Abdelraouf" + }, + { + "first_name": "Rohit", + "last_name": "Gupta" + }, + { + "first_name": "Kyungtae", + "last_name": "Han" + }, + { + "first_name": "Aniket", + "last_name": "Bera" + }, + { + "first_name": "James", + "last_name": "M. Rehg" + }, + { + "first_name": "Ziran", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MedBN: Robust Test-Time Adaptation against Malicious Test Samples", - "authors": "Hyejin Park, Jeongyeon Hwang, Sunung Mun, Sangdon Park, Jungseul Ok", + "authors": [ + { + "first_name": "Hyejin", + "last_name": "Park" + }, + { + "first_name": "Jeongyeon", + "last_name": "Hwang" + }, + { + "first_name": "Sunung", + "last_name": "Mun" + }, + { + "first_name": "Sangdon", + "last_name": "Park" + }, + { + "first_name": "Jungseul", + "last_name": "Ok" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Unsupervised Gaze Representation Learning from Multi-view Face Images", - "authors": "Yiwei Bao, Feng Lu", + "authors": [ + { + "first_name": "Yiwei", + "last_name": "Bao" + }, + { + "first_name": "Feng", + "last_name": "Lu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FairDeDup: Detecting and Mitigating Vision-Language Fairness Disparities in Semantic Dataset Deduplication", - "authors": "Eric Slyman, Stefan Lee, Scott Cohen, Kushal Kafle", + "authors": [ + { + "first_name": "Eric", + "last_name": "Slyman" + }, + { + "first_name": "Stefan", + "last_name": "Lee" + }, + { + "first_name": "Scott", + "last_name": "Cohen" + }, + { + "first_name": "Kushal", + "last_name": "Kafle" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CrossMAE: Cross-Modality Masked Autoencoders for Region-Aware Audio-Visual Pre-Training", - "authors": "Yuxin Guo, Siyang Sun, Shuailei Ma, Kecheng Zheng, Xiaoyi Bao, Shijie Ma, Wei Zou, Yun Zheng", + "authors": [ + { + "first_name": "Yuxin", + "last_name": "Guo" + }, + { + "first_name": "Siyang", + "last_name": "Sun" + }, + { + "first_name": "Shuailei", + "last_name": "Ma" + }, + { + "first_name": "Kecheng", + "last_name": "Zheng" + }, + { + "first_name": "Xiaoyi", + "last_name": "Bao" + }, + { + "first_name": "Shijie", + "last_name": "Ma" + }, + { + "first_name": "Wei", + "last_name": "Zou" + }, + { + "first_name": "Yun", + "last_name": "Zheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Osprey: Pixel Understanding with Visual Instruction Tuning", - "authors": "Yuqian Yuan, Wentong Li, Jian Liu, Dongqi Tang, Xinjie Luo, Chi Qin, Lei Zhang, Jianke Zhu", + "authors": [ + { + "first_name": "Yuqian", + "last_name": "Yuan" + }, + { + "first_name": "Wentong", + "last_name": "Li" + }, + { + "first_name": "Jian", + "last_name": "Liu" + }, + { + "first_name": "Dongqi", + "last_name": "Tang" + }, + { + "first_name": "Xinjie", + "last_name": "Luo" + }, + { + "first_name": "Chi", + "last_name": "Qin" + }, + { + "first_name": "Lei", + "last_name": "Zhang" + }, + { + "first_name": "Jianke", + "last_name": "Zhu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Modality-agnostic Domain Generalizable Medical Image Segmentation by Multi-Frequency in Multi-Scale Attention", - "authors": "Ju-Hyeon Nam, Nur Suriza Syazwany, Su Jung Kim, Sang-Chul Lee", + "authors": [ + { + "first_name": "Ju-Hyeon", + "last_name": "Nam" + }, + { + "first_name": "Nur", + "last_name": "Suriza Syazwany" + }, + { + "first_name": "Su", + "last_name": "Jung Kim" + }, + { + "first_name": "Sang-Chul", + "last_name": "Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Few-shot Learner Parameterization by Diffusion Time-steps", - "authors": "Zhongqi Yue, Pan Zhou, Richang Hong, Hanwang Zhang, Qianru Sun", + "authors": [ + { + "first_name": "Zhongqi", + "last_name": "Yue" + }, + { + "first_name": "Pan", + "last_name": "Zhou" + }, + { + "first_name": "Richang", + "last_name": "Hong" + }, + { + "first_name": "Hanwang", + "last_name": "Zhang" + }, + { + "first_name": "Qianru", + "last_name": "Sun" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraft", - "authors": "Hao Li, Xue Yang, Zhaokai Wang, Xizhou Zhu, Jie Zhou, Yu Qiao, Xiaogang Wang, Hongsheng Li, Lewei Lu, Jifeng Dai", + "authors": [ + { + "first_name": "Hao", + "last_name": "Li" + }, + { + "first_name": "Xue", + "last_name": "Yang" + }, + { + "first_name": "Zhaokai", + "last_name": "Wang" + }, + { + "first_name": "Xizhou", + "last_name": "Zhu" + }, + { + "first_name": "Jie", + "last_name": "Zhou" + }, + { + "first_name": "Yu", + "last_name": "Qiao" + }, + { + "first_name": "Xiaogang", + "last_name": "Wang" + }, + { + "first_name": "Hongsheng", + "last_name": "Li" + }, + { + "first_name": "Lewei", + "last_name": "Lu" + }, + { + "first_name": "Jifeng", + "last_name": "Dai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GenFlow: Generalizable Recurrent Flow for 6D Pose Refinement of Novel Objects", - "authors": "Sungphill Moon, Hyeontae Son, Dongcheol Hur, Sangwook Kim", + "authors": [ + { + "first_name": "Sungphill", + "last_name": "Moon" + }, + { + "first_name": "Hyeontae", + "last_name": "Son" + }, + { + "first_name": "Dongcheol", + "last_name": "Hur" + }, + { + "first_name": "Sangwook", + "last_name": "Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "OrCo: Towards Better Generalization via Orthogonality and Contrast for Few-Shot Class-Incremental Learning", - "authors": "Noor Ahmed, Anna Kukleva, Bernt Schiele", + "authors": [ + { + "first_name": "Noor", + "last_name": "Ahmed" + }, + { + "first_name": "Anna", + "last_name": "Kukleva" + }, + { + "first_name": "Bernt", + "last_name": "Schiele" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MuGE: Multiple Granularity Edge Detection", - "authors": "Caixia Zhou, Yaping Huang, Mengyang Pu, Qingji Guan, Ruoxi Deng, Haibin Ling", + "authors": [ + { + "first_name": "Caixia", + "last_name": "Zhou" + }, + { + "first_name": "Yaping", + "last_name": "Huang" + }, + { + "first_name": "Mengyang", + "last_name": "Pu" + }, + { + "first_name": "Qingji", + "last_name": "Guan" + }, + { + "first_name": "Ruoxi", + "last_name": "Deng" + }, + { + "first_name": "Haibin", + "last_name": "Ling" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Real-World Efficient Blind Motion Deblurring via Blur Pixel Discretization", - "authors": "Insoo Kim, Jae Seok Choi, Geonseok Seo, Kinam Kwon, Jinwoo Shin, Hyong-Euk Lee", + "authors": [ + { + "first_name": "Insoo", + "last_name": "Kim" + }, + { + "first_name": "Jae", + "last_name": "Seok Choi" + }, + { + "first_name": "Geonseok", + "last_name": "Seo" + }, + { + "first_name": "Kinam", + "last_name": "Kwon" + }, + { + "first_name": "Jinwoo", + "last_name": "Shin" + }, + { + "first_name": "Hyong-Euk", + "last_name": "Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "EmoVIT: Revolutionizing Emotion Insights with Visual Instruction Tuning", - "authors": "Hongxia Xie, Chu-Jun Peng, Yu-Wen Tseng, Hung-Jen Chen, Chan-Feng Hsu, Hong-Han Shuai, Wen-Huang Cheng", + "authors": [ + { + "first_name": "Hongxia", + "last_name": "Xie" + }, + { + "first_name": "Chu-Jun", + "last_name": "Peng" + }, + { + "first_name": "Yu-Wen", + "last_name": "Tseng" + }, + { + "first_name": "Hung-Jen", + "last_name": "Chen" + }, + { + "first_name": "Chan-Feng", + "last_name": "Hsu" + }, + { + "first_name": "Hong-Han", + "last_name": "Shuai" + }, + { + "first_name": "Wen-Huang", + "last_name": "Cheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning to Count without Annotations", - "authors": "Lukas Knobel, Tengda Han, Yuki M. Asano", + "authors": [ + { + "first_name": "Lukas", + "last_name": "Knobel" + }, + { + "first_name": "Tengda", + "last_name": "Han" + }, + { + "first_name": "Yuki", + "last_name": "M. Asano" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Logarithmic Lenses: Exploring Log RGB Data for Image Classification", - "authors": "Bruce A. Maxwell, Sumegha Singhania, Avnish Patel, Rahul Kumar, Heather Fryling, Sihan Li, Haonan Sun, Ping He, Zewen Li", + "authors": [ + { + "first_name": "Bruce", + "last_name": "A. Maxwell" + }, + { + "first_name": "Sumegha", + "last_name": "Singhania" + }, + { + "first_name": "Avnish", + "last_name": "Patel" + }, + { + "first_name": "Rahul", + "last_name": "Kumar" + }, + { + "first_name": "Heather", + "last_name": "Fryling" + }, + { + "first_name": "Sihan", + "last_name": "Li" + }, + { + "first_name": "Haonan", + "last_name": "Sun" + }, + { + "first_name": "Ping", + "last_name": "He" + }, + { + "first_name": "Zewen", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "AEROBLADE: Training-Free Detection of Latent Diffusion Images Using Autoencoder Reconstruction Error", - "authors": "Jonas Ricker, Denis Lukovnikov, Asja Fischer", + "authors": [ + { + "first_name": "Jonas", + "last_name": "Ricker" + }, + { + "first_name": "Denis", + "last_name": "Lukovnikov" + }, + { + "first_name": "Asja", + "last_name": "Fischer" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Scaled Decoupled Distillation", - "authors": "Shicai Wei, Chunbo Luo, Yang Luo", + "authors": [ + { + "first_name": "Shicai", + "last_name": "Wei" + }, + { + "first_name": "Chunbo", + "last_name": "Luo" + }, + { + "first_name": "Yang", + "last_name": "Luo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "NARUTO: Neural Active Reconstruction from Uncertain Target Observations", - "authors": "Ziyue Feng, Huangying Zhan, Zheng Chen, Qingan Yan, Xiangyu Xu, Changjiang Cai, Bing Li, Qilun Zhu, Yi Xu", + "authors": [ + { + "first_name": "Ziyue", + "last_name": "Feng" + }, + { + "first_name": "Huangying", + "last_name": "Zhan" + }, + { + "first_name": "Zheng", + "last_name": "Chen" + }, + { + "first_name": "Qingan", + "last_name": "Yan" + }, + { + "first_name": "Xiangyu", + "last_name": "Xu" + }, + { + "first_name": "Changjiang", + "last_name": "Cai" + }, + { + "first_name": "Bing", + "last_name": "Li" + }, + { + "first_name": "Qilun", + "last_name": "Zhu" + }, + { + "first_name": "Yi", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Point2CAD: Reverse Engineering CAD Models from 3D Point Clouds", - "authors": "Yujia Liu, Anton Obukhov, Jan Dirk Wegner, Konrad Schindler", + "authors": [ + { + "first_name": "Yujia", + "last_name": "Liu" + }, + { + "first_name": "Anton", + "last_name": "Obukhov" + }, + { + "first_name": "Jan", + "last_name": "Dirk Wegner" + }, + { + "first_name": "Konrad", + "last_name": "Schindler" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learnable Earth Parser: Discovering 3D Prototypes in Aerial Scans", - "authors": "Romain Loiseau, Elliot Vincent, Mathieu Aubry, Loic Landrieu", + "authors": [ + { + "first_name": "Romain", + "last_name": "Loiseau" + }, + { + "first_name": "Elliot", + "last_name": "Vincent" + }, + { + "first_name": "Mathieu", + "last_name": "Aubry" + }, + { + "first_name": "Loic", + "last_name": "Landrieu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "NeRFiller: Completing Scenes via Generative 3D Inpainting", - "authors": "Ethan Weber, Aleksander Holynski, Varun Jampani, Saurabh Saxena, Noah Snavely, Abhishek Kar, Angjoo Kanazawa", + "authors": [ + { + "first_name": "Ethan", + "last_name": "Weber" + }, + { + "first_name": "Aleksander", + "last_name": "Holynski" + }, + { + "first_name": "Varun", + "last_name": "Jampani" + }, + { + "first_name": "Saurabh", + "last_name": "Saxena" + }, + { + "first_name": "Noah", + "last_name": "Snavely" + }, + { + "first_name": "Abhishek", + "last_name": "Kar" + }, + { + "first_name": "Angjoo", + "last_name": "Kanazawa" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Cloud-Device Collaborative Learning for Multimodal Large Language Models", - "authors": "Guanqun Wang, Jiaming Liu, Chenxuan Li, Yuan Zhang, Junpeng Ma, Xinyu Wei, Kevin Zhang, Maurice Chong, Renrui Zhang, Yijiang Liu, Shanghang Zhang", + "authors": [ + { + "first_name": "Guanqun", + "last_name": "Wang" + }, + { + "first_name": "Jiaming", + "last_name": "Liu" + }, + { + "first_name": "Chenxuan", + "last_name": "Li" + }, + { + "first_name": "Yuan", + "last_name": "Zhang" + }, + { + "first_name": "Junpeng", + "last_name": "Ma" + }, + { + "first_name": "Xinyu", + "last_name": "Wei" + }, + { + "first_name": "Kevin", + "last_name": "Zhang" + }, + { + "first_name": "Maurice", + "last_name": "Chong" + }, + { + "first_name": "Renrui", + "last_name": "Zhang" + }, + { + "first_name": "Yijiang", + "last_name": "Liu" + }, + { + "first_name": "Shanghang", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "KD-DETR: Knowledge Distillation for Detection Transformer with Consistent Distillation Points Sampling", - "authors": "Yu Wang, Xin Li, Shengzhao Weng, Gang Zhang, Haixiao Yue, Haocheng Feng, Junyu Han, Errui Ding", + "authors": [ + { + "first_name": "Yu", + "last_name": "Wang" + }, + { + "first_name": "Xin", + "last_name": "Li" + }, + { + "first_name": "Shengzhao", + "last_name": "Weng" + }, + { + "first_name": "Gang", + "last_name": "Zhang" + }, + { + "first_name": "Haixiao", + "last_name": "Yue" + }, + { + "first_name": "Haocheng", + "last_name": "Feng" + }, + { + "first_name": "Junyu", + "last_name": "Han" + }, + { + "first_name": "Errui", + "last_name": "Ding" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Absolute Pose from One or Two Scaled and Oriented Features", - "authors": "Jonathan Ventura, Zuzana Kukelova, Torsten Sattler, Dániel Baráth", + "authors": [ + { + "first_name": "Jonathan", + "last_name": "Ventura" + }, + { + "first_name": "Zuzana", + "last_name": "Kukelova" + }, + { + "first_name": "Torsten", + "last_name": "Sattler" + }, + { + "first_name": "Dániel", + "last_name": "Baráth" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Source-Free Domain Adaptation with Frozen Multimodal Foundation Model", - "authors": "Song Tang, Wenxin Su, Mao Ye, Xiatian Zhu", + "authors": [ + { + "first_name": "Song", + "last_name": "Tang" + }, + { + "first_name": "Wenxin", + "last_name": "Su" + }, + { + "first_name": "Mao", + "last_name": "Ye" + }, + { + "first_name": "Xiatian", + "last_name": "Zhu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LocLLM: Exploiting Generalizable Human Keypoint Localization via Large Language Model", - "authors": "Dongkai Wang, Shiyu Xuan, Shiliang Zhang", + "authors": [ + { + "first_name": "Dongkai", + "last_name": "Wang" + }, + { + "first_name": "Shiyu", + "last_name": "Xuan" + }, + { + "first_name": "Shiliang", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MMA-Diffusion: MultiModal Attack on Diffusion Models", - "authors": "Yijun Yang, Ruiyuan Gao, Xiaosen Wang, Tsung-Yi Ho, Nan Xu, Qiang Xu", + "authors": [ + { + "first_name": "Yijun", + "last_name": "Yang" + }, + { + "first_name": "Ruiyuan", + "last_name": "Gao" + }, + { + "first_name": "Xiaosen", + "last_name": "Wang" + }, + { + "first_name": "Tsung-Yi", + "last_name": "Ho" + }, + { + "first_name": "Nan", + "last_name": "Xu" + }, + { + "first_name": "Qiang", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Benchmarking Audio Visual Segmentation for Long-Untrimmed Videos", - "authors": "Chen Liu, Peike Patrick Li, Qingtao Yu, Hongwei Sheng, Dadong Wang, Lincheng Li, Xin Yu", + "authors": [ + { + "first_name": "Chen", + "last_name": "Liu" + }, + { + "first_name": "Peike", + "last_name": "Patrick Li" + }, + { + "first_name": "Qingtao", + "last_name": "Yu" + }, + { + "first_name": "Hongwei", + "last_name": "Sheng" + }, + { + "first_name": "Dadong", + "last_name": "Wang" + }, + { + "first_name": "Lincheng", + "last_name": "Li" + }, + { + "first_name": "Xin", + "last_name": "Yu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentation", - "authors": "Md Mostafijur Rahman, Mustafa Munir, Radu Marculescu", + "authors": [ + { + "first_name": "Md", + "last_name": "Mostafijur Rahman" + }, + { + "first_name": "Mustafa", + "last_name": "Munir" + }, + { + "first_name": "Radu", + "last_name": "Marculescu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "VTQA: Visual Text Question Answering via Entity Alignment and Cross-Media Reasoning", - "authors": "Kang Chen, Xiangqian Wu", + "authors": [ + { + "first_name": "Kang", + "last_name": "Chen" + }, + { + "first_name": "Xiangqian", + "last_name": "Wu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "QN-Mixer: A Quasi-Newton MLP-Mixer Model for Sparse-View CT Reconstruction", - "authors": "Ishak Ayad, Nicolas Larue, Mai K. Nguyen", + "authors": [ + { + "first_name": "Ishak", + "last_name": "Ayad" + }, + { + "first_name": "Nicolas", + "last_name": "Larue" + }, + { + "first_name": "Mai", + "last_name": "K. Nguyen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning CNN on ViT: A Hybrid Model to Explicitly Class-specific Boundaries for Domain Adaptation", - "authors": "Ba Hung Ngo, Nhat-Tuong Do-Tran, Tuan-Ngoc Nguyen, Hae-Gon Jeon, Tae Jong Choi", + "authors": [ + { + "first_name": "Ba", + "last_name": "Hung Ngo" + }, + { + "first_name": "Nhat-Tuong", + "last_name": "Do-Tran" + }, + { + "first_name": "Tuan-Ngoc", + "last_name": "Nguyen" + }, + { + "first_name": "Hae-Gon", + "last_name": "Jeon" + }, + { + "first_name": "Tae", + "last_name": "Jong Choi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "A Picture is Worth More Than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions", - "authors": "Jack Urbanek, Florian Bordes, Pietro Astolfi, Mary Williamson, Vasu Sharma, Adriana Romero-Soriano", + "authors": [ + { + "first_name": "Jack", + "last_name": "Urbanek" + }, + { + "first_name": "Florian", + "last_name": "Bordes" + }, + { + "first_name": "Pietro", + "last_name": "Astolfi" + }, + { + "first_name": "Mary", + "last_name": "Williamson" + }, + { + "first_name": "Vasu", + "last_name": "Sharma" + }, + { + "first_name": "Adriana", + "last_name": "Romero-Soriano" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HanDiffuser: Text-to-Image Generation With Realistic Hand Appearances", - "authors": "Supreeth Narasimhaswamy, Uttaran Bhattacharya, Xiang Chen, Ishita Dasgupta, Saayan Mitra, Minh Hoai", + "authors": [ + { + "first_name": "Supreeth", + "last_name": "Narasimhaswamy" + }, + { + "first_name": "Uttaran", + "last_name": "Bhattacharya" + }, + { + "first_name": "Xiang", + "last_name": "Chen" + }, + { + "first_name": "Ishita", + "last_name": "Dasgupta" + }, + { + "first_name": "Saayan", + "last_name": "Mitra" + }, + { + "first_name": "Minh", + "last_name": "Hoai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generation", - "authors": "Alexander Raistrick, Lingjie Mei, Karhan Kayan, David Yan, Yiming Zuo, Beining Han, Hongyu Wen, Meenal Parakh, Stamatis Alexandropoulos, Lahav Lipson, Zeyu Ma, Jia Deng", + "authors": [ + { + "first_name": "Alexander", + "last_name": "Raistrick" + }, + { + "first_name": "Lingjie", + "last_name": "Mei" + }, + { + "first_name": "Karhan", + "last_name": "Kayan" + }, + { + "first_name": "David", + "last_name": "Yan" + }, + { + "first_name": "Yiming", + "last_name": "Zuo" + }, + { + "first_name": "Beining", + "last_name": "Han" + }, + { + "first_name": "Hongyu", + "last_name": "Wen" + }, + { + "first_name": "Meenal", + "last_name": "Parakh" + }, + { + "first_name": "Stamatis", + "last_name": "Alexandropoulos" + }, + { + "first_name": "Lahav", + "last_name": "Lipson" + }, + { + "first_name": "Zeyu", + "last_name": "Ma" + }, + { + "first_name": "Jia", + "last_name": "Deng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MART: Masked Affective RepresenTation Learning via Masked Temporal Distribution Distillation", - "authors": "Zhicheng Zhang, Pancheng Zhao, Eunil Park, Jufeng Yang", + "authors": [ + { + "first_name": "Zhicheng", + "last_name": "Zhang" + }, + { + "first_name": "Pancheng", + "last_name": "Zhao" + }, + { + "first_name": "Eunil", + "last_name": "Park" + }, + { + "first_name": "Jufeng", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MTLoRA: Low-Rank Adaptation Approach for Efficient Multi-Task Learning", - "authors": "Ahmed Agiza, Marina Neseem, Sherief Reda", + "authors": [ + { + "first_name": "Ahmed", + "last_name": "Agiza" + }, + { + "first_name": "Marina", + "last_name": "Neseem" + }, + { + "first_name": "Sherief", + "last_name": "Reda" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Hierarchical Patch Diffusion Models for High-Resolution Video Generation", - "authors": "Ivan Skorokhodov, Willi Menapace, Aliaksandr Siarohin, Sergey Tulyakov", + "authors": [ + { + "first_name": "Ivan", + "last_name": "Skorokhodov" + }, + { + "first_name": "Willi", + "last_name": "Menapace" + }, + { + "first_name": "Aliaksandr", + "last_name": "Siarohin" + }, + { + "first_name": "Sergey", + "last_name": "Tulyakov" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Motion Blur Decomposition with Cross-shutter Guidance", - "authors": "Xiang Ji, Haiyang Jiang, Yinqiang Zheng", + "authors": [ + { + "first_name": "Xiang", + "last_name": "Ji" + }, + { + "first_name": "Haiyang", + "last_name": "Jiang" + }, + { + "first_name": "Yinqiang", + "last_name": "Zheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Scene-adaptive and Region-aware Multi-modal Prompt for Open Vocabulary Object Detection", - "authors": "Xiaowei Zhao, Xianglong Liu, Duorui Wang, Yajun Gao, Zhide Liu", + "authors": [ + { + "first_name": "Xiaowei", + "last_name": "Zhao" + }, + { + "first_name": "Xianglong", + "last_name": "Liu" + }, + { + "first_name": "Duorui", + "last_name": "Wang" + }, + { + "first_name": "Yajun", + "last_name": "Gao" + }, + { + "first_name": "Zhide", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MimicDiffusion: Purifying Adversarial Perturbation via Mimicking Clean Diffusion Model", - "authors": "Kaiyu Song, Hanjiang Lai, Yan Pan, Jian Yin", + "authors": [ + { + "first_name": "Kaiyu", + "last_name": "Song" + }, + { + "first_name": "Hanjiang", + "last_name": "Lai" + }, + { + "first_name": "Yan", + "last_name": "Pan" + }, + { + "first_name": "Jian", + "last_name": "Yin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Neural Implicit Morphing of Face Images", - "authors": "Guilherme Schardong, Tiago Novello, Hallison Paz, Iurii Medvedev, Vinícius da Silva, Luiz Velho, Nuno Gonçalves", + "authors": [ + { + "first_name": "Guilherme", + "last_name": "Schardong" + }, + { + "first_name": "Tiago", + "last_name": "Novello" + }, + { + "first_name": "Hallison", + "last_name": "Paz" + }, + { + "first_name": "Iurii", + "last_name": "Medvedev" + }, + { + "first_name": "Vinícius", + "last_name": "da Silva" + }, + { + "first_name": "Luiz", + "last_name": "Velho" + }, + { + "first_name": "Nuno", + "last_name": "Gonçalves" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "UniGS: Unified Representation for Image Generation and Segmentation", - "authors": "Lu Qi, Lehan Yang, Weidong Guo, Yu Xu, Bo Du, Varun Jampani, Ming-Hsuan Yang", + "authors": [ + { + "first_name": "Lu", + "last_name": "Qi" + }, + { + "first_name": "Lehan", + "last_name": "Yang" + }, + { + "first_name": "Weidong", + "last_name": "Guo" + }, + { + "first_name": "Yu", + "last_name": "Xu" + }, + { + "first_name": "Bo", + "last_name": "Du" + }, + { + "first_name": "Varun", + "last_name": "Jampani" + }, + { + "first_name": "Ming-Hsuan", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Robust Synthetic-to-Real Transfer for Stereo Matching", - "authors": "Jiawei Zhang, Jiahe Li, Lei Huang, Xiaohan Yu, Lin Gu, Jin Zheng, Xiao Bai", + "authors": [ + { + "first_name": "Jiawei", + "last_name": "Zhang" + }, + { + "first_name": "Jiahe", + "last_name": "Li" + }, + { + "first_name": "Lei", + "last_name": "Huang" + }, + { + "first_name": "Xiaohan", + "last_name": "Yu" + }, + { + "first_name": "Lin", + "last_name": "Gu" + }, + { + "first_name": "Jin", + "last_name": "Zheng" + }, + { + "first_name": "Xiao", + "last_name": "Bai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Instance-Aware Group Quantization for Vision Transformers", - "authors": "Jaehyeon Moon, Dohyung Kim, Junyong Cheon, Bumsub Ham", + "authors": [ + { + "first_name": "Jaehyeon", + "last_name": "Moon" + }, + { + "first_name": "Dohyung", + "last_name": "Kim" + }, + { + "first_name": "Junyong", + "last_name": "Cheon" + }, + { + "first_name": "Bumsub", + "last_name": "Ham" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "A General and Efficient Training for Transformer via Token Expansion", - "authors": "Wenxuan Huang, Yunhang Shen, Jiao Xie, Baochang Zhang, Gaoqi He, Ke Li, Xing Sun, Shaohui Lin", + "authors": [ + { + "first_name": "Wenxuan", + "last_name": "Huang" + }, + { + "first_name": "Yunhang", + "last_name": "Shen" + }, + { + "first_name": "Jiao", + "last_name": "Xie" + }, + { + "first_name": "Baochang", + "last_name": "Zhang" + }, + { + "first_name": "Gaoqi", + "last_name": "He" + }, + { + "first_name": "Ke", + "last_name": "Li" + }, + { + "first_name": "Xing", + "last_name": "Sun" + }, + { + "first_name": "Shaohui", + "last_name": "Lin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GenZI: Zero-Shot 3D Human-Scene Interaction Generation", - "authors": "Lei Li, Angela Dai", + "authors": [ + { + "first_name": "Lei", + "last_name": "Li" + }, + { + "first_name": "Angela", + "last_name": "Dai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Tyche: Stochastic In-Context Learning for Medical Image Segmentation", - "authors": "Marianne Rakic, Hallee E. Wong, Jose Javier Gonzalez Ortiz, Beth A. Cimini, John V. Guttag, Adrian V. Dalca", + "authors": [ + { + "first_name": "Marianne", + "last_name": "Rakic" + }, + { + "first_name": "Hallee", + "last_name": "E. Wong" + }, + { + "first_name": "Jose", + "last_name": "Javier Gonzalez Ortiz" + }, + { + "first_name": "Beth", + "last_name": "A. Cimini" + }, + { + "first_name": "John", + "last_name": "V. Guttag" + }, + { + "first_name": "Adrian", + "last_name": "V. Dalca" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DiffAssemble: A Unified Graph-Diffusion Model for 2D and 3D Reassembly", - "authors": "Gianluca Scarpellini, Stefano Fiorini, Francesco Giuliari, Pietro Moreiro, Alessio Del Bue", + "authors": [ + { + "first_name": "Gianluca", + "last_name": "Scarpellini" + }, + { + "first_name": "Stefano", + "last_name": "Fiorini" + }, + { + "first_name": "Francesco", + "last_name": "Giuliari" + }, + { + "first_name": "Pietro", + "last_name": "Moreiro" + }, + { + "first_name": "Alessio", + "last_name": "Del Bue" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "NeISF: Neural Incident Stokes Field for Geometry and Material Estimation", - "authors": "Chenhao Li, Taishi Ono, Takeshi Uemori, Hajime Mihara, Alexander Gatto, Hajime Nagahara, Yusuke Moriuchi", + "authors": [ + { + "first_name": "Chenhao", + "last_name": "Li" + }, + { + "first_name": "Taishi", + "last_name": "Ono" + }, + { + "first_name": "Takeshi", + "last_name": "Uemori" + }, + { + "first_name": "Hajime", + "last_name": "Mihara" + }, + { + "first_name": "Alexander", + "last_name": "Gatto" + }, + { + "first_name": "Hajime", + "last_name": "Nagahara" + }, + { + "first_name": "Yusuke", + "last_name": "Moriuchi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Training-Free Open-Vocabulary Segmentation with Offline Diffusion-Augmented Prototype Generation", - "authors": "Luca Barsellotti, Roberto Amoroso, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara", + "authors": [ + { + "first_name": "Luca", + "last_name": "Barsellotti" + }, + { + "first_name": "Roberto", + "last_name": "Amoroso" + }, + { + "first_name": "Marcella", + "last_name": "Cornia" + }, + { + "first_name": "Lorenzo", + "last_name": "Baraldi" + }, + { + "first_name": "Rita", + "last_name": "Cucchiara" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "YOLO-World: Real-Time Open-Vocabulary Object Detection", - "authors": "Tianheng Cheng, Lin Song, Yixiao Ge, Wenyu Liu, Xinggang Wang, Ying Shan", + "authors": [ + { + "first_name": "Tianheng", + "last_name": "Cheng" + }, + { + "first_name": "Lin", + "last_name": "Song" + }, + { + "first_name": "Yixiao", + "last_name": "Ge" + }, + { + "first_name": "Wenyu", + "last_name": "Liu" + }, + { + "first_name": "Xinggang", + "last_name": "Wang" + }, + { + "first_name": "Ying", + "last_name": "Shan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ViT-Lens: Towards Omni-modal Representations", - "authors": "Weixian Lei, Yixiao Ge, Kun Yi, Jianfeng Zhang, Difei Gao, Dylan Sun, Yuying Ge, Ying Shan, Mike Zheng Shou", + "authors": [ + { + "first_name": "Weixian", + "last_name": "Lei" + }, + { + "first_name": "Yixiao", + "last_name": "Ge" + }, + { + "first_name": "Kun", + "last_name": "Yi" + }, + { + "first_name": "Jianfeng", + "last_name": "Zhang" + }, + { + "first_name": "Difei", + "last_name": "Gao" + }, + { + "first_name": "Dylan", + "last_name": "Sun" + }, + { + "first_name": "Yuying", + "last_name": "Ge" + }, + { + "first_name": "Ying", + "last_name": "Shan" + }, + { + "first_name": "Mike", + "last_name": "Zheng Shou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Cross-Dimension Affinity Distillation for 3D EM Neuron Segmentation", - "authors": "Xiaoyu Liu, Miaomiao Cai, Yinda Chen, Yueyi Zhang, Te Shi, Ruobing Zhang, Xuejin Chen, Zhiwei Xiong", + "authors": [ + { + "first_name": "Xiaoyu", + "last_name": "Liu" + }, + { + "first_name": "Miaomiao", + "last_name": "Cai" + }, + { + "first_name": "Yinda", + "last_name": "Chen" + }, + { + "first_name": "Yueyi", + "last_name": "Zhang" + }, + { + "first_name": "Te", + "last_name": "Shi" + }, + { + "first_name": "Ruobing", + "last_name": "Zhang" + }, + { + "first_name": "Xuejin", + "last_name": "Chen" + }, + { + "first_name": "Zhiwei", + "last_name": "Xiong" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HUGS: Human Gaussian Splats", - "authors": "Muhammed Kocabas, Jen-Hao Rick Chang, James Gabriel, Oncel Tuzel, Anurag Ranjan", + "authors": [ + { + "first_name": "Muhammed", + "last_name": "Kocabas" + }, + { + "first_name": "Jen-Hao", + "last_name": "Rick Chang" + }, + { + "first_name": "James", + "last_name": "Gabriel" + }, + { + "first_name": "Oncel", + "last_name": "Tuzel" + }, + { + "first_name": "Anurag", + "last_name": "Ranjan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GeoChat: Grounded Large Vision-Language Model for Remote Sensing", - "authors": "Kartik Kuckreja, Muhammad Sohail Danish, Muzammal Naseer, Abhijit Das, Salman Khan, Fahad Shahbaz Khan", + "authors": [ + { + "first_name": "Kartik", + "last_name": "Kuckreja" + }, + { + "first_name": "Muhammad", + "last_name": "Sohail Danish" + }, + { + "first_name": "Muzammal", + "last_name": "Naseer" + }, + { + "first_name": "Abhijit", + "last_name": "Das" + }, + { + "first_name": "Salman", + "last_name": "Khan" + }, + { + "first_name": "Fahad", + "last_name": "Shahbaz Khan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PhysPT: Physics-aware Pretrained Transformer for Estimating Human Dynamics from Monocular Videos", - "authors": "Yufei Zhang, Jeffrey O. Kephart, Zijun Cui, Qiang Ji", + "authors": [ + { + "first_name": "Yufei", + "last_name": "Zhang" + }, + { + "first_name": "Jeffrey", + "last_name": "O. Kephart" + }, + { + "first_name": "Zijun", + "last_name": "Cui" + }, + { + "first_name": "Qiang", + "last_name": "Ji" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Producing and Leveraging Online Map Uncertainty in Trajectory Prediction", - "authors": "Xunjiang Gu, Guanyu Song, Igor Gilitschenski, Marco Pavone, Boris Ivanovic", + "authors": [ + { + "first_name": "Xunjiang", + "last_name": "Gu" + }, + { + "first_name": "Guanyu", + "last_name": "Song" + }, + { + "first_name": "Igor", + "last_name": "Gilitschenski" + }, + { + "first_name": "Marco", + "last_name": "Pavone" + }, + { + "first_name": "Boris", + "last_name": "Ivanovic" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PerceptionGPT: Effectively Fusing Visual Perception into LLM", - "authors": "Renjie Pi, Lewei Yao, Jiahui Gao, Jipeng Zhang, Tong Zhang", + "authors": [ + { + "first_name": "Renjie", + "last_name": "Pi" + }, + { + "first_name": "Lewei", + "last_name": "Yao" + }, + { + "first_name": "Jiahui", + "last_name": "Gao" + }, + { + "first_name": "Jipeng", + "last_name": "Zhang" + }, + { + "first_name": "Tong", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Probabilistic Speech-Driven 3D Facial Motion Synthesis: New Benchmarks Methods and Applications", - "authors": "Karren D. Yang, Anurag Ranjan, Jen-Hao Rick Chang, Raviteja Vemulapalli, Oncel Tuzel", + "authors": [ + { + "first_name": "Karren", + "last_name": "D. Yang" + }, + { + "first_name": "Anurag", + "last_name": "Ranjan" + }, + { + "first_name": "Jen-Hao", + "last_name": "Rick Chang" + }, + { + "first_name": "Raviteja", + "last_name": "Vemulapalli" + }, + { + "first_name": "Oncel", + "last_name": "Tuzel" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LASO: Language-guided Affordance Segmentation on 3D Object", - "authors": "Yicong Li, Na Zhao, Junbin Xiao, Chun Feng, Xiang Wang, Tat-seng Chua", + "authors": [ + { + "first_name": "Yicong", + "last_name": "Li" + }, + { + "first_name": "Na", + "last_name": "Zhao" + }, + { + "first_name": "Junbin", + "last_name": "Xiao" + }, + { + "first_name": "Chun", + "last_name": "Feng" + }, + { + "first_name": "Xiang", + "last_name": "Wang" + }, + { + "first_name": "Tat-seng", + "last_name": "Chua" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Riemannian Multinomial Logistics Regression for SPD Neural Networks", - "authors": "Ziheng Chen, Yue Song, Gaowen Liu, Ramana Rao Kompella, Xiao-Jun Wu, Nicu Sebe", + "authors": [ + { + "first_name": "Ziheng", + "last_name": "Chen" + }, + { + "first_name": "Yue", + "last_name": "Song" + }, + { + "first_name": "Gaowen", + "last_name": "Liu" + }, + { + "first_name": "Ramana", + "last_name": "Rao Kompella" + }, + { + "first_name": "Xiao-Jun", + "last_name": "Wu" + }, + { + "first_name": "Nicu", + "last_name": "Sebe" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FreGS: 3D Gaussian Splatting with Progressive Frequency Regularization", - "authors": "Jiahui Zhang, Fangneng Zhan, Muyu Xu, Shijian Lu, Eric Xing", + "authors": [ + { + "first_name": "Jiahui", + "last_name": "Zhang" + }, + { + "first_name": "Fangneng", + "last_name": "Zhan" + }, + { + "first_name": "Muyu", + "last_name": "Xu" + }, + { + "first_name": "Shijian", + "last_name": "Lu" + }, + { + "first_name": "Eric", + "last_name": "Xing" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Discriminative Sample-Guided and Parameter-Efficient Feature Space Adaptation for Cross-Domain Few-Shot Learning", - "authors": "Rashindrie Perera, Saman Halgamuge", + "authors": [ + { + "first_name": "Rashindrie", + "last_name": "Perera" + }, + { + "first_name": "Saman", + "last_name": "Halgamuge" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "What Sketch Explainability Really Means for Downstream Tasks?", - "authors": "Hmrishav Bandyopadhyay, Pinaki Nath Chowdhury, Ayan Kumar Bhunia, Aneeshan Sain, Tao Xiang, Yi-Zhe Song", + "authors": [ + { + "first_name": "Hmrishav", + "last_name": "Bandyopadhyay" + }, + { + "first_name": "Pinaki", + "last_name": "Nath Chowdhury" + }, + { + "first_name": "Ayan", + "last_name": "Kumar Bhunia" + }, + { + "first_name": "Aneeshan", + "last_name": "Sain" + }, + { + "first_name": "Tao", + "last_name": "Xiang" + }, + { + "first_name": "Yi-Zhe", + "last_name": "Song" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Neural Exposure Fusion for High-Dynamic Range Object Detection", - "authors": "Emmanuel Onzon, Maximilian Bömer, Fahim Mannan, Felix Heide", + "authors": [ + { + "first_name": "Emmanuel", + "last_name": "Onzon" + }, + { + "first_name": "Maximilian", + "last_name": "Bömer" + }, + { + "first_name": "Fahim", + "last_name": "Mannan" + }, + { + "first_name": "Felix", + "last_name": "Heide" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "EfficientDreamer: High-Fidelity and Robust 3D Creation via Orthogonal-view Diffusion Priors", - "authors": "Zhipeng Hu, Minda Zhao, Chaoyi Zhao, Xinyue Liang, Lincheng Li, Zeng Zhao, Changjie Fan, Xiaowei Zhou, Xin Yu", + "authors": [ + { + "first_name": "Zhipeng", + "last_name": "Hu" + }, + { + "first_name": "Minda", + "last_name": "Zhao" + }, + { + "first_name": "Chaoyi", + "last_name": "Zhao" + }, + { + "first_name": "Xinyue", + "last_name": "Liang" + }, + { + "first_name": "Lincheng", + "last_name": "Li" + }, + { + "first_name": "Zeng", + "last_name": "Zhao" + }, + { + "first_name": "Changjie", + "last_name": "Fan" + }, + { + "first_name": "Xiaowei", + "last_name": "Zhou" + }, + { + "first_name": "Xin", + "last_name": "Yu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HOIAnimator: Generating Text-prompt Human-object Animations using Novel Perceptive Diffusion Models", - "authors": "Wenfeng Song, Xinyu Zhang, Shuai Li, Yang Gao, Aimin Hao, Xia Hou, Chenglizhao Chen, Ning Li, Hong Qin", + "authors": [ + { + "first_name": "Wenfeng", + "last_name": "Song" + }, + { + "first_name": "Xinyu", + "last_name": "Zhang" + }, + { + "first_name": "Shuai", + "last_name": "Li" + }, + { + "first_name": "Yang", + "last_name": "Gao" + }, + { + "first_name": "Aimin", + "last_name": "Hao" + }, + { + "first_name": "Xia", + "last_name": "Hou" + }, + { + "first_name": "Chenglizhao", + "last_name": "Chen" + }, + { + "first_name": "Ning", + "last_name": "Li" + }, + { + "first_name": "Hong", + "last_name": "Qin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis", - "authors": "Ziqiao Peng, Wentao Hu, Yue Shi, Xiangyu Zhu, Xiaomei Zhang, Hao Zhao, Jun He, Hongyan Liu, Zhaoxin Fan", + "authors": [ + { + "first_name": "Ziqiao", + "last_name": "Peng" + }, + { + "first_name": "Wentao", + "last_name": "Hu" + }, + { + "first_name": "Yue", + "last_name": "Shi" + }, + { + "first_name": "Xiangyu", + "last_name": "Zhu" + }, + { + "first_name": "Xiaomei", + "last_name": "Zhang" + }, + { + "first_name": "Hao", + "last_name": "Zhao" + }, + { + "first_name": "Jun", + "last_name": "He" + }, + { + "first_name": "Hongyan", + "last_name": "Liu" + }, + { + "first_name": "Zhaoxin", + "last_name": "Fan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SFOD: Spiking Fusion Object Detector", - "authors": "Yimeng Fan, Wei Zhang, Changsong Liu, Mingyang Li, Wenrui Lu", + "authors": [ + { + "first_name": "Yimeng", + "last_name": "Fan" + }, + { + "first_name": "Wei", + "last_name": "Zhang" + }, + { + "first_name": "Changsong", + "last_name": "Liu" + }, + { + "first_name": "Mingyang", + "last_name": "Li" + }, + { + "first_name": "Wenrui", + "last_name": "Lu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Detector-Free Structure from Motion", - "authors": "Xingyi He, Jiaming Sun, Yifan Wang, Sida Peng, Qixing Huang, Hujun Bao, Xiaowei Zhou", + "authors": [ + { + "first_name": "Xingyi", + "last_name": "He" + }, + { + "first_name": "Jiaming", + "last_name": "Sun" + }, + { + "first_name": "Yifan", + "last_name": "Wang" + }, + { + "first_name": "Sida", + "last_name": "Peng" + }, + { + "first_name": "Qixing", + "last_name": "Huang" + }, + { + "first_name": "Hujun", + "last_name": "Bao" + }, + { + "first_name": "Xiaowei", + "last_name": "Zhou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CG-HOI: Contact-Guided 3D Human-Object Interaction Generation", - "authors": "Christian Diller, Angela Dai", + "authors": [ + { + "first_name": "Christian", + "last_name": "Diller" + }, + { + "first_name": "Angela", + "last_name": "Dai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards Surveillance Video-and-Language Understanding: New Dataset Baselines and Challenges", - "authors": "Tongtong Yuan, Xuange Zhang, Kun Liu, Bo Liu, Chen Chen, Jian Jin, Zhenzhen Jiao", + "authors": [ + { + "first_name": "Tongtong", + "last_name": "Yuan" + }, + { + "first_name": "Xuange", + "last_name": "Zhang" + }, + { + "first_name": "Kun", + "last_name": "Liu" + }, + { + "first_name": "Bo", + "last_name": "Liu" + }, + { + "first_name": "Chen", + "last_name": "Chen" + }, + { + "first_name": "Jian", + "last_name": "Jin" + }, + { + "first_name": "Zhenzhen", + "last_name": "Jiao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "AdaRevD: Adaptive Patch Exiting Reversible Decoder Pushes the Limit of Image Deblurring", - "authors": "Xintian Mao, Qingli Li, Yan Wang", + "authors": [ + { + "first_name": "Xintian", + "last_name": "Mao" + }, + { + "first_name": "Qingli", + "last_name": "Li" + }, + { + "first_name": "Yan", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning to Remove Wrinkled Transparent Film with Polarized Prior", - "authors": "Jiaqi Tang, Ruizheng Wu, Xiaogang Xu, Sixing Hu, Ying-Cong Chen", + "authors": [ + { + "first_name": "Jiaqi", + "last_name": "Tang" + }, + { + "first_name": "Ruizheng", + "last_name": "Wu" + }, + { + "first_name": "Xiaogang", + "last_name": "Xu" + }, + { + "first_name": "Sixing", + "last_name": "Hu" + }, + { + "first_name": "Ying-Cong", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "OpenEQA: Embodied Question Answering in the Era of Foundation Models", - "authors": "Arjun Majumdar, Anurag Ajay, Xiaohan Zhang, Pranav Putta, Sriram Yenamandra, Mikael Henaff, Sneha Silwal, Paul Mcvay, Oleksandr Maksymets, Sergio Arnaud, Karmesh Yadav, Qiyang Li, Ben Newman, Mohit Sharma, Vincent Berges, Shiqi Zhang, Pulkit Agrawal, Yonatan Bisk, Dhruv Batra, Mrinal Kalakrishnan, Franziska Meier, Chris Paxton, Alexander Sax, Aravind Rajeswaran", + "authors": [ + { + "first_name": "Arjun", + "last_name": "Majumdar" + }, + { + "first_name": "Anurag", + "last_name": "Ajay" + }, + { + "first_name": "Xiaohan", + "last_name": "Zhang" + }, + { + "first_name": "Pranav", + "last_name": "Putta" + }, + { + "first_name": "Sriram", + "last_name": "Yenamandra" + }, + { + "first_name": "Mikael", + "last_name": "Henaff" + }, + { + "first_name": "Sneha", + "last_name": "Silwal" + }, + { + "first_name": "Paul", + "last_name": "Mcvay" + }, + { + "first_name": "Oleksandr", + "last_name": "Maksymets" + }, + { + "first_name": "Sergio", + "last_name": "Arnaud" + }, + { + "first_name": "Karmesh", + "last_name": "Yadav" + }, + { + "first_name": "Qiyang", + "last_name": "Li" + }, + { + "first_name": "Ben", + "last_name": "Newman" + }, + { + "first_name": "Mohit", + "last_name": "Sharma" + }, + { + "first_name": "Vincent", + "last_name": "Berges" + }, + { + "first_name": "Shiqi", + "last_name": "Zhang" + }, + { + "first_name": "Pulkit", + "last_name": "Agrawal" + }, + { + "first_name": "Yonatan", + "last_name": "Bisk" + }, + { + "first_name": "Dhruv", + "last_name": "Batra" + }, + { + "first_name": "Mrinal", + "last_name": "Kalakrishnan" + }, + { + "first_name": "Franziska", + "last_name": "Meier" + }, + { + "first_name": "Chris", + "last_name": "Paxton" + }, + { + "first_name": "Alexander", + "last_name": "Sax" + }, + { + "first_name": "Aravind", + "last_name": "Rajeswaran" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DreamSalon: A Staged Diffusion Framework for Preserving Identity-Context in Editable Face Generation", - "authors": "Haonan Lin", + "authors": [ + { + "first_name": "Haonan", + "last_name": "Lin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Dispel Darkness for Better Fusion: A Controllable Visual Enhancer based on Cross-modal Conditional Adversarial Learning", - "authors": "Hao Zhang, Linfeng Tang, Xinyu Xiang, Xuhui Zuo, Jiayi Ma", + "authors": [ + { + "first_name": "Hao", + "last_name": "Zhang" + }, + { + "first_name": "Linfeng", + "last_name": "Tang" + }, + { + "first_name": "Xinyu", + "last_name": "Xiang" + }, + { + "first_name": "Xuhui", + "last_name": "Zuo" + }, + { + "first_name": "Jiayi", + "last_name": "Ma" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Querying as Prompt: Parameter-Efficient Learning for Multimodal Language Model", - "authors": "Tian Liang, Jing Huang, Ming Kong, Luyuan Chen, Qiang Zhu", + "authors": [ + { + "first_name": "Tian", + "last_name": "Liang" + }, + { + "first_name": "Jing", + "last_name": "Huang" + }, + { + "first_name": "Ming", + "last_name": "Kong" + }, + { + "first_name": "Luyuan", + "last_name": "Chen" + }, + { + "first_name": "Qiang", + "last_name": "Zhu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DePT: Decoupled Prompt Tuning", - "authors": "Ji Zhang, Shihan Wu, Lianli Gao, Heng Tao Shen, Jingkuan Song", + "authors": [ + { + "first_name": "Ji", + "last_name": "Zhang" + }, + { + "first_name": "Shihan", + "last_name": "Wu" + }, + { + "first_name": "Lianli", + "last_name": "Gao" + }, + { + "first_name": "Heng", + "last_name": "Tao Shen" + }, + { + "first_name": "Jingkuan", + "last_name": "Song" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Neural Super-Resolution for Real-time Rendering with Radiance Demodulation", - "authors": "Jia Li, Ziling Chen, Xiaolong Wu, Lu Wang, Beibei Wang, Lei Zhang", + "authors": [ + { + "first_name": "Jia", + "last_name": "Li" + }, + { + "first_name": "Ziling", + "last_name": "Chen" + }, + { + "first_name": "Xiaolong", + "last_name": "Wu" + }, + { + "first_name": "Lu", + "last_name": "Wang" + }, + { + "first_name": "Beibei", + "last_name": "Wang" + }, + { + "first_name": "Lei", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction", - "authors": "Ziyi Yang, Xinyu Gao, Wen Zhou, Shaohui Jiao, Yuqing Zhang, Xiaogang Jin", + "authors": [ + { + "first_name": "Ziyi", + "last_name": "Yang" + }, + { + "first_name": "Xinyu", + "last_name": "Gao" + }, + { + "first_name": "Wen", + "last_name": "Zhou" + }, + { + "first_name": "Shaohui", + "last_name": "Jiao" + }, + { + "first_name": "Yuqing", + "last_name": "Zhang" + }, + { + "first_name": "Xiaogang", + "last_name": "Jin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Enhancing 3D Object Detection with 2D Detection-Guided Query Anchors", - "authors": "Haoxuanye Ji, Pengpeng Liang, Erkang Cheng", + "authors": [ + { + "first_name": "Haoxuanye", + "last_name": "Ji" + }, + { + "first_name": "Pengpeng", + "last_name": "Liang" + }, + { + "first_name": "Erkang", + "last_name": "Cheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Continual Forgetting for Pre-trained Vision Models", - "authors": "Hongbo Zhao, Bolin Ni, Junsong Fan, Yuxi Wang, Yuntao Chen, Gaofeng Meng, Zhaoxiang Zhang", + "authors": [ + { + "first_name": "Hongbo", + "last_name": "Zhao" + }, + { + "first_name": "Bolin", + "last_name": "Ni" + }, + { + "first_name": "Junsong", + "last_name": "Fan" + }, + { + "first_name": "Yuxi", + "last_name": "Wang" + }, + { + "first_name": "Yuntao", + "last_name": "Chen" + }, + { + "first_name": "Gaofeng", + "last_name": "Meng" + }, + { + "first_name": "Zhaoxiang", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Real Acoustic Fields: An Audio-Visual Room Acoustics Dataset and Benchmark", - "authors": "Ziyang Chen, Israel D. Gebru, Christian Richardt, Anurag Kumar, William Laney, Andrew Owens, Alexander Richard", + "authors": [ + { + "first_name": "Ziyang", + "last_name": "Chen" + }, + { + "first_name": "Israel", + "last_name": "D. Gebru" + }, + { + "first_name": "Christian", + "last_name": "Richardt" + }, + { + "first_name": "Anurag", + "last_name": "Kumar" + }, + { + "first_name": "William", + "last_name": "Laney" + }, + { + "first_name": "Andrew", + "last_name": "Owens" + }, + { + "first_name": "Alexander", + "last_name": "Richard" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "A Generative Approach for Wikipedia-Scale Visual Entity Recognition", - "authors": "Mathilde Caron, Ahmet Iscen, Alireza Fathi, Cordelia Schmid", + "authors": [ + { + "first_name": "Mathilde", + "last_name": "Caron" + }, + { + "first_name": "Ahmet", + "last_name": "Iscen" + }, + { + "first_name": "Alireza", + "last_name": "Fathi" + }, + { + "first_name": "Cordelia", + "last_name": "Schmid" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "A Physics-informed Low-rank Deep Neural Network for Blind and Universal Lens Aberration Correction", - "authors": "Jin Gong, Runzhao Yang, Weihang Zhang, Jinli Suo, Qionghai Dai", + "authors": [ + { + "first_name": "Jin", + "last_name": "Gong" + }, + { + "first_name": "Runzhao", + "last_name": "Yang" + }, + { + "first_name": "Weihang", + "last_name": "Zhang" + }, + { + "first_name": "Jinli", + "last_name": "Suo" + }, + { + "first_name": "Qionghai", + "last_name": "Dai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Open-Vocabulary Object 6D Pose Estimation", - "authors": "Jaime Corsetti, Davide Boscaini, Changjae Oh, Andrea Cavallaro, Fabio Poiesi", + "authors": [ + { + "first_name": "Jaime", + "last_name": "Corsetti" + }, + { + "first_name": "Davide", + "last_name": "Boscaini" + }, + { + "first_name": "Changjae", + "last_name": "Oh" + }, + { + "first_name": "Andrea", + "last_name": "Cavallaro" + }, + { + "first_name": "Fabio", + "last_name": "Poiesi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Plug and Play Active Learning for Object Detection", - "authors": "Chenhongyi Yang, Lichao Huang, Elliot J. Crowley", + "authors": [ + { + "first_name": "Chenhongyi", + "last_name": "Yang" + }, + { + "first_name": "Lichao", + "last_name": "Huang" + }, + { + "first_name": "Elliot", + "last_name": "J. Crowley" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Calibrating Multi-modal Representations: A Pursuit of Group Robustness without Annotations", - "authors": "Chenyu You, Yifei Min, Weicheng Dai, Jasjeet S. Sekhon, Lawrence Staib, James S. Duncan", + "authors": [ + { + "first_name": "Chenyu", + "last_name": "You" + }, + { + "first_name": "Yifei", + "last_name": "Min" + }, + { + "first_name": "Weicheng", + "last_name": "Dai" + }, + { + "first_name": "Jasjeet", + "last_name": "S. Sekhon" + }, + { + "first_name": "Lawrence", + "last_name": "Staib" + }, + { + "first_name": "James", + "last_name": "S. Duncan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LiSA: LiDAR Localization with Semantic Awareness", - "authors": "Bochun Yang, Zijun Li, Wen Li, Zhipeng Cai, Chenglu Wen, Yu Zang, Matthias Muller, Cheng Wang", + "authors": [ + { + "first_name": "Bochun", + "last_name": "Yang" + }, + { + "first_name": "Zijun", + "last_name": "Li" + }, + { + "first_name": "Wen", + "last_name": "Li" + }, + { + "first_name": "Zhipeng", + "last_name": "Cai" + }, + { + "first_name": "Chenglu", + "last_name": "Wen" + }, + { + "first_name": "Yu", + "last_name": "Zang" + }, + { + "first_name": "Matthias", + "last_name": "Muller" + }, + { + "first_name": "Cheng", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MMM: Generative Masked Motion Model", - "authors": "Ekkasit Pinyoanuntapong, Pu Wang, Minwoo Lee, Chen Chen", + "authors": [ + { + "first_name": "Ekkasit", + "last_name": "Pinyoanuntapong" + }, + { + "first_name": "Pu", + "last_name": "Wang" + }, + { + "first_name": "Minwoo", + "last_name": "Lee" + }, + { + "first_name": "Chen", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PEGASUS: Personalized Generative 3D Avatars with Composable Attributes", - "authors": "Hyunsoo Cha, Byungjun Kim, Hanbyul Joo", + "authors": [ + { + "first_name": "Hyunsoo", + "last_name": "Cha" + }, + { + "first_name": "Byungjun", + "last_name": "Kim" + }, + { + "first_name": "Hanbyul", + "last_name": "Joo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LMDrive: Closed-Loop End-to-End Driving with Large Language Models", - "authors": "Hao Shao, Yuxuan Hu, Letian Wang, Guanglu Song, Steven L. Waslander, Yu Liu, Hongsheng Li", + "authors": [ + { + "first_name": "Hao", + "last_name": "Shao" + }, + { + "first_name": "Yuxuan", + "last_name": "Hu" + }, + { + "first_name": "Letian", + "last_name": "Wang" + }, + { + "first_name": "Guanglu", + "last_name": "Song" + }, + { + "first_name": "Steven", + "last_name": "L. Waslander" + }, + { + "first_name": "Yu", + "last_name": "Liu" + }, + { + "first_name": "Hongsheng", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MCD: Diverse Large-Scale Multi-Campus Dataset for Robot Perception", - "authors": "Thien-Minh Nguyen, Shenghai Yuan, Thien Hoang Nguyen, Pengyu Yin, Haozhi Cao, Lihua Xie, Maciej Wozniak, Patric Jensfelt, Marko Thiel, Justin Ziegenbein, Noel Blunder", + "authors": [ + { + "first_name": "Thien-Minh", + "last_name": "Nguyen" + }, + { + "first_name": "Shenghai", + "last_name": "Yuan" + }, + { + "first_name": "Thien", + "last_name": "Hoang Nguyen" + }, + { + "first_name": "Pengyu", + "last_name": "Yin" + }, + { + "first_name": "Haozhi", + "last_name": "Cao" + }, + { + "first_name": "Lihua", + "last_name": "Xie" + }, + { + "first_name": "Maciej", + "last_name": "Wozniak" + }, + { + "first_name": "Patric", + "last_name": "Jensfelt" + }, + { + "first_name": "Marko", + "last_name": "Thiel" + }, + { + "first_name": "Justin", + "last_name": "Ziegenbein" + }, + { + "first_name": "Noel", + "last_name": "Blunder" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Diff-Plugin: Revitalizing Details for Diffusion-based Low-level Tasks", - "authors": "Yuhao Liu, Zhanghan Ke, Fang Liu, Nanxuan Zhao, Rynson W.H. Lau", + "authors": [ + { + "first_name": "Yuhao", + "last_name": "Liu" + }, + { + "first_name": "Zhanghan", + "last_name": "Ke" + }, + { + "first_name": "Fang", + "last_name": "Liu" + }, + { + "first_name": "Nanxuan", + "last_name": "Zhao" + }, + { + "first_name": "Rynson", + "last_name": "W.H. Lau" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "AHIVE: Anatomy-aware Hierarchical Vision Encoding for Interactive Radiology Report Retrieval", - "authors": "Sixing Yan, William K. Cheung, Ivor W. Tsang, Keith Chiu, Terence M. Tong, Ka Chun Cheung, Simon See", + "authors": [ + { + "first_name": "Sixing", + "last_name": "Yan" + }, + { + "first_name": "William", + "last_name": "K. Cheung" + }, + { + "first_name": "Ivor", + "last_name": "W. Tsang" + }, + { + "first_name": "Keith", + "last_name": "Chiu" + }, + { + "first_name": "Terence", + "last_name": "M. Tong" + }, + { + "first_name": "Ka", + "last_name": "Chun Cheung" + }, + { + "first_name": "Simon", + "last_name": "See" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CyberDemo: Augmenting Simulated Human Demonstration for Real-World Dexterous Manipulation", - "authors": "Jun Wang, Yuzhe Qin, Kaiming Kuang, Yigit Korkmaz, Akhilan Gurumoorthy, Hao Su, Xiaolong Wang", + "authors": [ + { + "first_name": "Jun", + "last_name": "Wang" + }, + { + "first_name": "Yuzhe", + "last_name": "Qin" + }, + { + "first_name": "Kaiming", + "last_name": "Kuang" + }, + { + "first_name": "Yigit", + "last_name": "Korkmaz" + }, + { + "first_name": "Akhilan", + "last_name": "Gurumoorthy" + }, + { + "first_name": "Hao", + "last_name": "Su" + }, + { + "first_name": "Xiaolong", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning", - "authors": "Mohamed Abdelfattah, Mariam Hassan, Alexandre Alahi", + "authors": [ + { + "first_name": "Mohamed", + "last_name": "Abdelfattah" + }, + { + "first_name": "Mariam", + "last_name": "Hassan" + }, + { + "first_name": "Alexandre", + "last_name": "Alahi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Narrative Action Evaluation with Prompt-Guided Multimodal Interaction", - "authors": "Shiyi Zhang, Sule Bai, Guangyi Chen, Lei Chen, Jiwen Lu, Junle Wang, Yansong Tang", + "authors": [ + { + "first_name": "Shiyi", + "last_name": "Zhang" + }, + { + "first_name": "Sule", + "last_name": "Bai" + }, + { + "first_name": "Guangyi", + "last_name": "Chen" + }, + { + "first_name": "Lei", + "last_name": "Chen" + }, + { + "first_name": "Jiwen", + "last_name": "Lu" + }, + { + "first_name": "Junle", + "last_name": "Wang" + }, + { + "first_name": "Yansong", + "last_name": "Tang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "R-Cyclic Diffuser: Reductive and Cyclic Latent Diffusion for 3D Clothed Human Digitalization", - "authors": "Kennard Yanting Chan, Fayao Liu, Guosheng Lin, Chuan Sheng Foo, Weisi Lin", + "authors": [ + { + "first_name": "Kennard", + "last_name": "Yanting Chan" + }, + { + "first_name": "Fayao", + "last_name": "Liu" + }, + { + "first_name": "Guosheng", + "last_name": "Lin" + }, + { + "first_name": "Chuan", + "last_name": "Sheng Foo" + }, + { + "first_name": "Weisi", + "last_name": "Lin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Intelligent Grimm - Open-ended Visual Storytelling via Latent Diffusion Models", - "authors": "Chang Liu, Haoning Wu, Yujie Zhong, Xiaoyun Zhang, Yanfeng Wang, Weidi Xie", + "authors": [ + { + "first_name": "Chang", + "last_name": "Liu" + }, + { + "first_name": "Haoning", + "last_name": "Wu" + }, + { + "first_name": "Yujie", + "last_name": "Zhong" + }, + { + "first_name": "Xiaoyun", + "last_name": "Zhang" + }, + { + "first_name": "Yanfeng", + "last_name": "Wang" + }, + { + "first_name": "Weidi", + "last_name": "Xie" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Validating Privacy-Preserving Face Recognition under a Minimum Assumption", - "authors": "Hui Zhang, Xingbo Dong, YenLung Lai, Ying Zhou, Xiaoyan Zhang, Xingguo Lv, Zhe Jin, Xuejun Li", + "authors": [ + { + "first_name": "Hui", + "last_name": "Zhang" + }, + { + "first_name": "Xingbo", + "last_name": "Dong" + }, + { + "first_name": "YenLung", + "last_name": "Lai" + }, + { + "first_name": "Ying", + "last_name": "Zhou" + }, + { + "first_name": "Xiaoyan", + "last_name": "Zhang" + }, + { + "first_name": "Xingguo", + "last_name": "Lv" + }, + { + "first_name": "Zhe", + "last_name": "Jin" + }, + { + "first_name": "Xuejun", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Long-Tailed Anomaly Detection with Learnable Class Names", - "authors": "Chih-Hui Ho, Kuan-Chuan Peng, Nuno Vasconcelos", + "authors": [ + { + "first_name": "Chih-Hui", + "last_name": "Ho" + }, + { + "first_name": "Kuan-Chuan", + "last_name": "Peng" + }, + { + "first_name": "Nuno", + "last_name": "Vasconcelos" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ArGue: Attribute-Guided Prompt Tuning for Vision-Language Models", - "authors": "Xinyu Tian, Shu Zou, Zhaoyuan Yang, Jing Zhang", + "authors": [ + { + "first_name": "Xinyu", + "last_name": "Tian" + }, + { + "first_name": "Shu", + "last_name": "Zou" + }, + { + "first_name": "Zhaoyuan", + "last_name": "Yang" + }, + { + "first_name": "Jing", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Rapid 3D Model Generation with Intuitive 3D Input", - "authors": "Tianrun Chen, Chaotao Ding, Shangzhan Zhang, Chunan Yu, Ying Zang, Zejian Li, Sida Peng, Lingyun Sun", + "authors": [ + { + "first_name": "Tianrun", + "last_name": "Chen" + }, + { + "first_name": "Chaotao", + "last_name": "Ding" + }, + { + "first_name": "Shangzhan", + "last_name": "Zhang" + }, + { + "first_name": "Chunan", + "last_name": "Yu" + }, + { + "first_name": "Ying", + "last_name": "Zang" + }, + { + "first_name": "Zejian", + "last_name": "Li" + }, + { + "first_name": "Sida", + "last_name": "Peng" + }, + { + "first_name": "Lingyun", + "last_name": "Sun" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GenTron: Diffusion Transformers for Image and Video Generation", - "authors": "Shoufa Chen, Mengmeng Xu, Jiawei Ren, Yuren Cong, Sen He, Yanping Xie, Animesh Sinha, Ping Luo, Tao Xiang, Juan-Manuel Perez-Rua", + "authors": [ + { + "first_name": "Shoufa", + "last_name": "Chen" + }, + { + "first_name": "Mengmeng", + "last_name": "Xu" + }, + { + "first_name": "Jiawei", + "last_name": "Ren" + }, + { + "first_name": "Yuren", + "last_name": "Cong" + }, + { + "first_name": "Sen", + "last_name": "He" + }, + { + "first_name": "Yanping", + "last_name": "Xie" + }, + { + "first_name": "Animesh", + "last_name": "Sinha" + }, + { + "first_name": "Ping", + "last_name": "Luo" + }, + { + "first_name": "Tao", + "last_name": "Xiang" + }, + { + "first_name": "Juan-Manuel", + "last_name": "Perez-Rua" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Close Imitation of Expert Retouching for Black-and-White Photography", - "authors": "Seunghyun Shin, Jisu Shin, Jihwan Bae, Inwook Shim, Hae-Gon Jeon", + "authors": [ + { + "first_name": "Seunghyun", + "last_name": "Shin" + }, + { + "first_name": "Jisu", + "last_name": "Shin" + }, + { + "first_name": "Jihwan", + "last_name": "Bae" + }, + { + "first_name": "Inwook", + "last_name": "Shim" + }, + { + "first_name": "Hae-Gon", + "last_name": "Jeon" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "TRIP: Temporal Residual Learning with Image Noise Prior for Image-to-Video Diffusion Models", - "authors": "Zhongwei Zhang, Fuchen Long, Yingwei Pan, Zhaofan Qiu, Ting Yao, Yang Cao, Tao Mei", + "authors": [ + { + "first_name": "Zhongwei", + "last_name": "Zhang" + }, + { + "first_name": "Fuchen", + "last_name": "Long" + }, + { + "first_name": "Yingwei", + "last_name": "Pan" + }, + { + "first_name": "Zhaofan", + "last_name": "Qiu" + }, + { + "first_name": "Ting", + "last_name": "Yao" + }, + { + "first_name": "Yang", + "last_name": "Cao" + }, + { + "first_name": "Tao", + "last_name": "Mei" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "TexVocab: Texture Vocabulary-conditioned Human Avatars", - "authors": "Yuxiao Liu, Zhe Li, Yebin Liu, Haoqian Wang", + "authors": [ + { + "first_name": "Yuxiao", + "last_name": "Liu" + }, + { + "first_name": "Zhe", + "last_name": "Li" + }, + { + "first_name": "Yebin", + "last_name": "Liu" + }, + { + "first_name": "Haoqian", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "KITRO: Refining Human Mesh by 2D Clues and Kinematic-tree Rotation", - "authors": "Fengyuan Yang, Kerui Gu, Angela Yao", + "authors": [ + { + "first_name": "Fengyuan", + "last_name": "Yang" + }, + { + "first_name": "Kerui", + "last_name": "Gu" + }, + { + "first_name": "Angela", + "last_name": "Yao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "BoQ: A Place is Worth a Bag of Learnable Queries", - "authors": "Amar Ali-bey, Brahim Chaib-draa, Philippe Giguère", + "authors": [ + { + "first_name": "Amar", + "last_name": "Ali-bey" + }, + { + "first_name": "Brahim", + "last_name": "Chaib-draa" + }, + { + "first_name": "Philippe", + "last_name": "Giguère" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering", - "authors": "Antoine Guédon, Vincent Lepetit", + "authors": [ + { + "first_name": "Antoine", + "last_name": "Guédon" + }, + { + "first_name": "Vincent", + "last_name": "Lepetit" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Understanding and Improving Source-free Domain Adaptation from a Theoretical Perspective", - "authors": "Yu Mitsuzumi, Akisato Kimura, Hisashi Kashima", + "authors": [ + { + "first_name": "Yu", + "last_name": "Mitsuzumi" + }, + { + "first_name": "Akisato", + "last_name": "Kimura" + }, + { + "first_name": "Hisashi", + "last_name": "Kashima" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning SO(3)-Invariant Semantic Correspondence via Local Shape Transform", - "authors": "Chunghyun Park, Seungwook Kim, Jaesik Park, Minsu Cho", + "authors": [ + { + "first_name": "Chunghyun", + "last_name": "Park" + }, + { + "first_name": "Seungwook", + "last_name": "Kim" + }, + { + "first_name": "Jaesik", + "last_name": "Park" + }, + { + "first_name": "Minsu", + "last_name": "Cho" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence", - "authors": "Van Nguyen Nguyen, Thibault Groueix, Mathieu Salzmann, Vincent Lepetit", + "authors": [ + { + "first_name": "Van", + "last_name": "Nguyen Nguyen" + }, + { + "first_name": "Thibault", + "last_name": "Groueix" + }, + { + "first_name": "Mathieu", + "last_name": "Salzmann" + }, + { + "first_name": "Vincent", + "last_name": "Lepetit" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Imagine Before Go: Self-Supervised Generative Map for Object Goal Navigation", - "authors": "Sixian Zhang, Xinyao Yu, Xinhang Song, Xiaohan Wang, Shuqiang Jiang", + "authors": [ + { + "first_name": "Sixian", + "last_name": "Zhang" + }, + { + "first_name": "Xinyao", + "last_name": "Yu" + }, + { + "first_name": "Xinhang", + "last_name": "Song" + }, + { + "first_name": "Xiaohan", + "last_name": "Wang" + }, + { + "first_name": "Shuqiang", + "last_name": "Jiang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards Effective Usage of Human-Centric Priors in Diffusion Models for Text-based Human Image Generation", - "authors": "Junyan Wang, Zhenhong Sun, Zhiyu Tan, Xuanbai Chen, Weihua Chen, Hao Li, Cheng Zhang, Yang Song", + "authors": [ + { + "first_name": "Junyan", + "last_name": "Wang" + }, + { + "first_name": "Zhenhong", + "last_name": "Sun" + }, + { + "first_name": "Zhiyu", + "last_name": "Tan" + }, + { + "first_name": "Xuanbai", + "last_name": "Chen" + }, + { + "first_name": "Weihua", + "last_name": "Chen" + }, + { + "first_name": "Hao", + "last_name": "Li" + }, + { + "first_name": "Cheng", + "last_name": "Zhang" + }, + { + "first_name": "Yang", + "last_name": "Song" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "A Video is Worth 256 Bases: Spatial-Temporal Expectation-Maximization Inversion for Zero-Shot Video Editing", - "authors": "Maomao Li, Yu Li, Tianyu Yang, Yunfei Liu, Dongxu Yue, Zhihui Lin, Dong Xu", + "authors": [ + { + "first_name": "Maomao", + "last_name": "Li" + }, + { + "first_name": "Yu", + "last_name": "Li" + }, + { + "first_name": "Tianyu", + "last_name": "Yang" + }, + { + "first_name": "Yunfei", + "last_name": "Liu" + }, + { + "first_name": "Dongxu", + "last_name": "Yue" + }, + { + "first_name": "Zhihui", + "last_name": "Lin" + }, + { + "first_name": "Dong", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HIPTrack: Visual Tracking with Historical Prompts", - "authors": "Wenrui Cai, Qingjie Liu, Yunhong Wang", + "authors": [ + { + "first_name": "Wenrui", + "last_name": "Cai" + }, + { + "first_name": "Qingjie", + "last_name": "Liu" + }, + { + "first_name": "Yunhong", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "URHand: Universal Relightable Hands", - "authors": "Zhaoxi Chen, Gyeongsik Moon, Kaiwen Guo, Chen Cao, Stanislav Pidhorskyi, Tomas Simon, Rohan Joshi, Yuan Dong, Yichen Xu, Bernardo Pires, He Wen, Lucas Evans, Bo Peng, Julia Buffalini, Autumn Trimble, Kevyn McPhail, Melissa Schoeller, Shoou-I Yu, Javier Romero, Michael Zollhofer, Yaser Sheikh, Ziwei Liu, Shunsuke Saito", + "authors": [ + { + "first_name": "Zhaoxi", + "last_name": "Chen" + }, + { + "first_name": "Gyeongsik", + "last_name": "Moon" + }, + { + "first_name": "Kaiwen", + "last_name": "Guo" + }, + { + "first_name": "Chen", + "last_name": "Cao" + }, + { + "first_name": "Stanislav", + "last_name": "Pidhorskyi" + }, + { + "first_name": "Tomas", + "last_name": "Simon" + }, + { + "first_name": "Rohan", + "last_name": "Joshi" + }, + { + "first_name": "Yuan", + "last_name": "Dong" + }, + { + "first_name": "Yichen", + "last_name": "Xu" + }, + { + "first_name": "Bernardo", + "last_name": "Pires" + }, + { + "first_name": "He", + "last_name": "Wen" + }, + { + "first_name": "Lucas", + "last_name": "Evans" + }, + { + "first_name": "Bo", + "last_name": "Peng" + }, + { + "first_name": "Julia", + "last_name": "Buffalini" + }, + { + "first_name": "Autumn", + "last_name": "Trimble" + }, + { + "first_name": "Kevyn", + "last_name": "McPhail" + }, + { + "first_name": "Melissa", + "last_name": "Schoeller" + }, + { + "first_name": "Shoou-I", + "last_name": "Yu" + }, + { + "first_name": "Javier", + "last_name": "Romero" + }, + { + "first_name": "Michael", + "last_name": "Zollhofer" + }, + { + "first_name": "Yaser", + "last_name": "Sheikh" + }, + { + "first_name": "Ziwei", + "last_name": "Liu" + }, + { + "first_name": "Shunsuke", + "last_name": "Saito" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "An N-Point Linear Solver for Line and Motion Estimation with Event Cameras", - "authors": "Ling Gao, Daniel Gehrig, Hang Su, Davide Scaramuzza, Laurent Kneip", + "authors": [ + { + "first_name": "Ling", + "last_name": "Gao" + }, + { + "first_name": "Daniel", + "last_name": "Gehrig" + }, + { + "first_name": "Hang", + "last_name": "Su" + }, + { + "first_name": "Davide", + "last_name": "Scaramuzza" + }, + { + "first_name": "Laurent", + "last_name": "Kneip" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GenNBV: Generalizable Next-Best-View Policy for Active 3D Reconstruction", - "authors": "Xiao Chen, Quanyi Li, Tai Wang, Tianfan Xue, Jiangmiao Pang", + "authors": [ + { + "first_name": "Xiao", + "last_name": "Chen" + }, + { + "first_name": "Quanyi", + "last_name": "Li" + }, + { + "first_name": "Tai", + "last_name": "Wang" + }, + { + "first_name": "Tianfan", + "last_name": "Xue" + }, + { + "first_name": "Jiangmiao", + "last_name": "Pang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Deep-TROJ: An Inference Stage Trojan Insertion Algorithm through Efficient Weight Replacement Attack", - "authors": "Sabbir Ahmed, Ranyang Zhou, Shaahin Angizi, Adnan Siraj Rakin", + "authors": [ + { + "first_name": "Sabbir", + "last_name": "Ahmed" + }, + { + "first_name": "Ranyang", + "last_name": "Zhou" + }, + { + "first_name": "Shaahin", + "last_name": "Angizi" + }, + { + "first_name": "Adnan", + "last_name": "Siraj Rakin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Investigating and Mitigating the Side Effects of Noisy Views for Self-Supervised Clustering Algorithms in Practical Multi-View Scenarios", - "authors": "Jie Xu, Yazhou Ren, Xiaolong Wang, Lei Feng, Zheng Zhang, Gang Niu, Xiaofeng Zhu", + "authors": [ + { + "first_name": "Jie", + "last_name": "Xu" + }, + { + "first_name": "Yazhou", + "last_name": "Ren" + }, + { + "first_name": "Xiaolong", + "last_name": "Wang" + }, + { + "first_name": "Lei", + "last_name": "Feng" + }, + { + "first_name": "Zheng", + "last_name": "Zhang" + }, + { + "first_name": "Gang", + "last_name": "Niu" + }, + { + "first_name": "Xiaofeng", + "last_name": "Zhu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "EvalCrafter: Benchmarking and Evaluating Large Video Generation Models", - "authors": "Yaofang Liu, Xiaodong Cun, Xuebo Liu, Xintao Wang, Yong Zhang, Haoxin Chen, Yang Liu, Tieyong Zeng, Raymond Chan, Ying Shan", + "authors": [ + { + "first_name": "Yaofang", + "last_name": "Liu" + }, + { + "first_name": "Xiaodong", + "last_name": "Cun" + }, + { + "first_name": "Xuebo", + "last_name": "Liu" + }, + { + "first_name": "Xintao", + "last_name": "Wang" + }, + { + "first_name": "Yong", + "last_name": "Zhang" + }, + { + "first_name": "Haoxin", + "last_name": "Chen" + }, + { + "first_name": "Yang", + "last_name": "Liu" + }, + { + "first_name": "Tieyong", + "last_name": "Zeng" + }, + { + "first_name": "Raymond", + "last_name": "Chan" + }, + { + "first_name": "Ying", + "last_name": "Shan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SelfOcc: Self-Supervised Vision-Based 3D Occupancy Prediction", - "authors": "Yuanhui Huang, Wenzhao Zheng, Borui Zhang, Jie Zhou, Jiwen Lu", + "authors": [ + { + "first_name": "Yuanhui", + "last_name": "Huang" + }, + { + "first_name": "Wenzhao", + "last_name": "Zheng" + }, + { + "first_name": "Borui", + "last_name": "Zhang" + }, + { + "first_name": "Jie", + "last_name": "Zhou" + }, + { + "first_name": "Jiwen", + "last_name": "Lu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SubT-MRS Dataset: Pushing SLAM Towards All-weather Environments", - "authors": "Shibo Zhao, Yuanjun Gao, Tianhao Wu, Damanpreet Singh, Rushan Jiang, Haoxiang Sun, Mansi Sarawata, Yuheng Qiu, Warren Whittaker, Ian Higgins, Yi Du, Shaoshu Su, Can Xu, John Keller, Jay Karhade, Lucas Nogueira, Sourojit Saha, Ji Zhang, Wenshan Wang, Chen Wang, Sebastian Scherer", + "authors": [ + { + "first_name": "Shibo", + "last_name": "Zhao" + }, + { + "first_name": "Yuanjun", + "last_name": "Gao" + }, + { + "first_name": "Tianhao", + "last_name": "Wu" + }, + { + "first_name": "Damanpreet", + "last_name": "Singh" + }, + { + "first_name": "Rushan", + "last_name": "Jiang" + }, + { + "first_name": "Haoxiang", + "last_name": "Sun" + }, + { + "first_name": "Mansi", + "last_name": "Sarawata" + }, + { + "first_name": "Yuheng", + "last_name": "Qiu" + }, + { + "first_name": "Warren", + "last_name": "Whittaker" + }, + { + "first_name": "Ian", + "last_name": "Higgins" + }, + { + "first_name": "Yi", + "last_name": "Du" + }, + { + "first_name": "Shaoshu", + "last_name": "Su" + }, + { + "first_name": "Can", + "last_name": "Xu" + }, + { + "first_name": "John", + "last_name": "Keller" + }, + { + "first_name": "Jay", + "last_name": "Karhade" + }, + { + "first_name": "Lucas", + "last_name": "Nogueira" + }, + { + "first_name": "Sourojit", + "last_name": "Saha" + }, + { + "first_name": "Ji", + "last_name": "Zhang" + }, + { + "first_name": "Wenshan", + "last_name": "Wang" + }, + { + "first_name": "Chen", + "last_name": "Wang" + }, + { + "first_name": "Sebastian", + "last_name": "Scherer" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Named Entity Driven Zero-Shot Image Manipulation", - "authors": "Zhida Feng, Li Chen, Jing Tian, JiaXiang Liu, Shikun Feng", + "authors": [ + { + "first_name": "Zhida", + "last_name": "Feng" + }, + { + "first_name": "Li", + "last_name": "Chen" + }, + { + "first_name": "Jing", + "last_name": "Tian" + }, + { + "first_name": "JiaXiang", + "last_name": "Liu" + }, + { + "first_name": "Shikun", + "last_name": "Feng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Relational Matching for Weakly Semi-Supervised Oriented Object Detection", - "authors": "Wenhao Wu, Hau-San Wong, Si Wu, Tianyou Zhang", + "authors": [ + { + "first_name": "Wenhao", + "last_name": "Wu" + }, + { + "first_name": "Hau-San", + "last_name": "Wong" + }, + { + "first_name": "Si", + "last_name": "Wu" + }, + { + "first_name": "Tianyou", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Rethinking the Representation in Federated Unsupervised Learning with Non-IID Data", - "authors": "Xinting Liao, Weiming Liu, Chaochao Chen, Pengyang Zhou, Fengyuan Yu, Huabin Zhu, Binhui Yao, Tao Wang, Xiaolin Zheng, Yanchao Tan", + "authors": [ + { + "first_name": "Xinting", + "last_name": "Liao" + }, + { + "first_name": "Weiming", + "last_name": "Liu" + }, + { + "first_name": "Chaochao", + "last_name": "Chen" + }, + { + "first_name": "Pengyang", + "last_name": "Zhou" + }, + { + "first_name": "Fengyuan", + "last_name": "Yu" + }, + { + "first_name": "Huabin", + "last_name": "Zhu" + }, + { + "first_name": "Binhui", + "last_name": "Yao" + }, + { + "first_name": "Tao", + "last_name": "Wang" + }, + { + "first_name": "Xiaolin", + "last_name": "Zheng" + }, + { + "first_name": "Yanchao", + "last_name": "Tan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Distraction is All You Need: Memory-Efficient Image Immunization against Diffusion-Based Image Editing", - "authors": "Ling Lo, Cheng Yu Yeo, Hong-Han Shuai, Wen-Huang Cheng", + "authors": [ + { + "first_name": "Ling", + "last_name": "Lo" + }, + { + "first_name": "Cheng", + "last_name": "Yu Yeo" + }, + { + "first_name": "Hong-Han", + "last_name": "Shuai" + }, + { + "first_name": "Wen-Huang", + "last_name": "Cheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Knowledge-Enhanced Dual-stream Zero-shot Composed Image Retrieval", - "authors": "Yucheng Suo, Fan Ma, Linchao Zhu, Yi Yang", + "authors": [ + { + "first_name": "Yucheng", + "last_name": "Suo" + }, + { + "first_name": "Fan", + "last_name": "Ma" + }, + { + "first_name": "Linchao", + "last_name": "Zhu" + }, + { + "first_name": "Yi", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Taming Self-Training for Open-Vocabulary Object Detection", - "authors": "Shiyu Zhao, Samuel Schulter, Long Zhao, Zhixing Zhang, Vijay Kumar B G, Yumin Suh, Manmohan Chandraker, Dimitris N. Metaxas", + "authors": [ + { + "first_name": "Shiyu", + "last_name": "Zhao" + }, + { + "first_name": "Samuel", + "last_name": "Schulter" + }, + { + "first_name": "Long", + "last_name": "Zhao" + }, + { + "first_name": "Zhixing", + "last_name": "Zhang" + }, + { + "first_name": "Vijay", + "last_name": "Kumar B G" + }, + { + "first_name": "Yumin", + "last_name": "Suh" + }, + { + "first_name": "Manmohan", + "last_name": "Chandraker" + }, + { + "first_name": "Dimitris", + "last_name": "N. Metaxas" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Grounding and Enhancing Grid-based Models for Neural Fields", - "authors": "Zelin Zhao, Fenglei Fan, Wenlong Liao, Junchi Yan", + "authors": [ + { + "first_name": "Zelin", + "last_name": "Zhao" + }, + { + "first_name": "Fenglei", + "last_name": "Fan" + }, + { + "first_name": "Wenlong", + "last_name": "Liao" + }, + { + "first_name": "Junchi", + "last_name": "Yan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Bilateral Propagation Network for Depth Completion", - "authors": "Jie Tang, Fei-Peng Tian, Boshi An, Jian Li, Ping Tan", + "authors": [ + { + "first_name": "Jie", + "last_name": "Tang" + }, + { + "first_name": "Fei-Peng", + "last_name": "Tian" + }, + { + "first_name": "Boshi", + "last_name": "An" + }, + { + "first_name": "Jian", + "last_name": "Li" + }, + { + "first_name": "Ping", + "last_name": "Tan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ESR-NeRF: Emissive Source Reconstruction Using LDR Multi-view Images", - "authors": "Jinseo Jeong, Junseo Koo, Qimeng Zhang, Gunhee Kim", + "authors": [ + { + "first_name": "Jinseo", + "last_name": "Jeong" + }, + { + "first_name": "Junseo", + "last_name": "Koo" + }, + { + "first_name": "Qimeng", + "last_name": "Zhang" + }, + { + "first_name": "Gunhee", + "last_name": "Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Infer from What You Have Seen Before: Temporally-dependent Classifier for Semi-supervised Video Segmentation", - "authors": "Jiafan Zhuang, Zilei Wang, Yixin Zhang, Zhun Fan", + "authors": [ + { + "first_name": "Jiafan", + "last_name": "Zhuang" + }, + { + "first_name": "Zilei", + "last_name": "Wang" + }, + { + "first_name": "Yixin", + "last_name": "Zhang" + }, + { + "first_name": "Zhun", + "last_name": "Fan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Unleashing Channel Potential: Space-Frequency Selection Convolution for SAR Object Detection", - "authors": "Ke Li, Di Wang, Zhangyuan Hu, Wenxuan Zhu, Shaofeng Li, Quan Wang", + "authors": [ + { + "first_name": "Ke", + "last_name": "Li" + }, + { + "first_name": "Di", + "last_name": "Wang" + }, + { + "first_name": "Zhangyuan", + "last_name": "Hu" + }, + { + "first_name": "Wenxuan", + "last_name": "Zhu" + }, + { + "first_name": "Shaofeng", + "last_name": "Li" + }, + { + "first_name": "Quan", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "READ: Retrieval-Enhanced Asymmetric Diffusion for Motion Planning", - "authors": "Takeru Oba, Matthew Walter, Norimichi Ukita", + "authors": [ + { + "first_name": "Takeru", + "last_name": "Oba" + }, + { + "first_name": "Matthew", + "last_name": "Walter" + }, + { + "first_name": "Norimichi", + "last_name": "Ukita" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Video Frame Interpolation via Direct Synthesis with the Event-based Reference", - "authors": "Yuhan Liu, Yongjian Deng, Hao Chen, Zhen Yang", + "authors": [ + { + "first_name": "Yuhan", + "last_name": "Liu" + }, + { + "first_name": "Yongjian", + "last_name": "Deng" + }, + { + "first_name": "Hao", + "last_name": "Chen" + }, + { + "first_name": "Zhen", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DSL-FIQA: Assessing Facial Image Quality via Dual-Set Degradation Learning and Landmark-Guided Transformer", - "authors": "Wei-Ting Chen, Gurunandan Krishnan, Qiang Gao, Sy-Yen Kuo, Sizhou Ma, Jian Wang", + "authors": [ + { + "first_name": "Wei-Ting", + "last_name": "Chen" + }, + { + "first_name": "Gurunandan", + "last_name": "Krishnan" + }, + { + "first_name": "Qiang", + "last_name": "Gao" + }, + { + "first_name": "Sy-Yen", + "last_name": "Kuo" + }, + { + "first_name": "Sizhou", + "last_name": "Ma" + }, + { + "first_name": "Jian", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FMA-Net: Flow-Guided Dynamic Filtering and Iterative Feature Refinement with Multi-Attention for Joint Video Super-Resolution and Deblurring", - "authors": "Geunhyuk Youk, Jihyong Oh, Munchurl Kim", + "authors": [ + { + "first_name": "Geunhyuk", + "last_name": "Youk" + }, + { + "first_name": "Jihyong", + "last_name": "Oh" + }, + { + "first_name": "Munchurl", + "last_name": "Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "OVMR: Open-Vocabulary Recognition with Multi-Modal References", - "authors": "Zehong Ma, Shiliang Zhang, Longhui Wei, Qi Tian", + "authors": [ + { + "first_name": "Zehong", + "last_name": "Ma" + }, + { + "first_name": "Shiliang", + "last_name": "Zhang" + }, + { + "first_name": "Longhui", + "last_name": "Wei" + }, + { + "first_name": "Qi", + "last_name": "Tian" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation", - "authors": "Wenhao Li, Mengyuan Liu, Hong Liu, Pichao Wang, Jialun Cai, Nicu Sebe", + "authors": [ + { + "first_name": "Wenhao", + "last_name": "Li" + }, + { + "first_name": "Mengyuan", + "last_name": "Liu" + }, + { + "first_name": "Hong", + "last_name": "Liu" + }, + { + "first_name": "Pichao", + "last_name": "Wang" + }, + { + "first_name": "Jialun", + "last_name": "Cai" + }, + { + "first_name": "Nicu", + "last_name": "Sebe" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Boosting Diffusion Models with Moving Average Sampling in Frequency Domain", - "authors": "Yurui Qian, Qi Cai, Yingwei Pan, Yehao Li, Ting Yao, Qibin Sun, Tao Mei", + "authors": [ + { + "first_name": "Yurui", + "last_name": "Qian" + }, + { + "first_name": "Qi", + "last_name": "Cai" + }, + { + "first_name": "Yingwei", + "last_name": "Pan" + }, + { + "first_name": "Yehao", + "last_name": "Li" + }, + { + "first_name": "Ting", + "last_name": "Yao" + }, + { + "first_name": "Qibin", + "last_name": "Sun" + }, + { + "first_name": "Tao", + "last_name": "Mei" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GART: Gaussian Articulated Template Models", - "authors": "Jiahui Lei, Yufu Wang, Georgios Pavlakos, Lingjie Liu, Kostas Daniilidis", + "authors": [ + { + "first_name": "Jiahui", + "last_name": "Lei" + }, + { + "first_name": "Yufu", + "last_name": "Wang" + }, + { + "first_name": "Georgios", + "last_name": "Pavlakos" + }, + { + "first_name": "Lingjie", + "last_name": "Liu" + }, + { + "first_name": "Kostas", + "last_name": "Daniilidis" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Global and Local Prompts Cooperation via Optimal Transport for Federated Learning", - "authors": "Hongxia Li, Wei Huang, Jingya Wang, Ye Shi", + "authors": [ + { + "first_name": "Hongxia", + "last_name": "Li" + }, + { + "first_name": "Wei", + "last_name": "Huang" + }, + { + "first_name": "Jingya", + "last_name": "Wang" + }, + { + "first_name": "Ye", + "last_name": "Shi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Bi-Causal: Group Activity Recognition via Bidirectional Causality", - "authors": "Youliang Zhang, Wenxuan Liu, Danni Xu, Zhuo Zhou, Zheng Wang", + "authors": [ + { + "first_name": "Youliang", + "last_name": "Zhang" + }, + { + "first_name": "Wenxuan", + "last_name": "Liu" + }, + { + "first_name": "Danni", + "last_name": "Xu" + }, + { + "first_name": "Zhuo", + "last_name": "Zhou" + }, + { + "first_name": "Zheng", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Space-Time Diffusion Features for Zero-Shot Text-Driven Motion Transfer", - "authors": "Danah Yatim, Rafail Fridman, Omer Bar-Tal, Yoni Kasten, Tali Dekel", + "authors": [ + { + "first_name": "Danah", + "last_name": "Yatim" + }, + { + "first_name": "Rafail", + "last_name": "Fridman" + }, + { + "first_name": "Omer", + "last_name": "Bar-Tal" + }, + { + "first_name": "Yoni", + "last_name": "Kasten" + }, + { + "first_name": "Tali", + "last_name": "Dekel" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "KP-RED: Exploiting Semantic Keypoints for Joint 3D Shape Retrieval and Deformation", - "authors": "Ruida Zhang, Chenyangguang Zhang, Yan Di, Fabian Manhardt, Xingyu Liu, Federico Tombari, Xiangyang Ji", + "authors": [ + { + "first_name": "Ruida", + "last_name": "Zhang" + }, + { + "first_name": "Chenyangguang", + "last_name": "Zhang" + }, + { + "first_name": "Yan", + "last_name": "Di" + }, + { + "first_name": "Fabian", + "last_name": "Manhardt" + }, + { + "first_name": "Xingyu", + "last_name": "Liu" + }, + { + "first_name": "Federico", + "last_name": "Tombari" + }, + { + "first_name": "Xiangyang", + "last_name": "Ji" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning from One Continuous Video Stream", - "authors": "João Carreira, Michael King, Viorica Patraucean, Dilara Gokay, Catalin Ionescu, Yi Yang, Daniel Zoran, Joseph Heyward, Carl Doersch, Yusuf Aytar, Dima Damen, Andrew Zisserman", + "authors": [ + { + "first_name": "João", + "last_name": "Carreira" + }, + { + "first_name": "Michael", + "last_name": "King" + }, + { + "first_name": "Viorica", + "last_name": "Patraucean" + }, + { + "first_name": "Dilara", + "last_name": "Gokay" + }, + { + "first_name": "Catalin", + "last_name": "Ionescu" + }, + { + "first_name": "Yi", + "last_name": "Yang" + }, + { + "first_name": "Daniel", + "last_name": "Zoran" + }, + { + "first_name": "Joseph", + "last_name": "Heyward" + }, + { + "first_name": "Carl", + "last_name": "Doersch" + }, + { + "first_name": "Yusuf", + "last_name": "Aytar" + }, + { + "first_name": "Dima", + "last_name": "Damen" + }, + { + "first_name": "Andrew", + "last_name": "Zisserman" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "VGGSfM: Visual Geometry Grounded Deep Structure From Motion", - "authors": "Jianyuan Wang, Nikita Karaev, Christian Rupprecht, David Novotny", + "authors": [ + { + "first_name": "Jianyuan", + "last_name": "Wang" + }, + { + "first_name": "Nikita", + "last_name": "Karaev" + }, + { + "first_name": "Christian", + "last_name": "Rupprecht" + }, + { + "first_name": "David", + "last_name": "Novotny" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis", - "authors": "Dewei Zhou, You Li, Fan Ma, Xiaoting Zhang, Yi Yang", + "authors": [ + { + "first_name": "Dewei", + "last_name": "Zhou" + }, + { + "first_name": "You", + "last_name": "Li" + }, + { + "first_name": "Fan", + "last_name": "Ma" + }, + { + "first_name": "Xiaoting", + "last_name": "Zhang" + }, + { + "first_name": "Yi", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Distilling CLIP with Dual Guidance for Learning Discriminative Human Body Shape Representation", - "authors": "Feng Liu, Minchul Kim, Zhiyuan Ren, Xiaoming Liu", + "authors": [ + { + "first_name": "Feng", + "last_name": "Liu" + }, + { + "first_name": "Minchul", + "last_name": "Kim" + }, + { + "first_name": "Zhiyuan", + "last_name": "Ren" + }, + { + "first_name": "Xiaoming", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Retrieval-Augmented Open-Vocabulary Object Detection", - "authors": "Jooyeon Kim, Eulrang Cho, Sehyung Kim, Hyunwoo J. Kim", + "authors": [ + { + "first_name": "Jooyeon", + "last_name": "Kim" + }, + { + "first_name": "Eulrang", + "last_name": "Cho" + }, + { + "first_name": "Sehyung", + "last_name": "Kim" + }, + { + "first_name": "Hyunwoo", + "last_name": "J. Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MULTIFLOW: Shifting Towards Task-Agnostic Vision-Language Pruning", - "authors": "Matteo Farina, Massimiliano Mancini, Elia Cunegatti, Gaowen Liu, Giovanni Iacca, Elisa Ricci", + "authors": [ + { + "first_name": "Matteo", + "last_name": "Farina" + }, + { + "first_name": "Massimiliano", + "last_name": "Mancini" + }, + { + "first_name": "Elia", + "last_name": "Cunegatti" + }, + { + "first_name": "Gaowen", + "last_name": "Liu" + }, + { + "first_name": "Giovanni", + "last_name": "Iacca" + }, + { + "first_name": "Elisa", + "last_name": "Ricci" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Spin-UP: Spin Light for Natural Light Uncalibrated Photometric Stereo", - "authors": "Zongrui Li, Zhan Lu, Haojie Yan, Boxin Shi, Gang Pan, Qian Zheng, Xudong Jiang", + "authors": [ + { + "first_name": "Zongrui", + "last_name": "Li" + }, + { + "first_name": "Zhan", + "last_name": "Lu" + }, + { + "first_name": "Haojie", + "last_name": "Yan" + }, + { + "first_name": "Boxin", + "last_name": "Shi" + }, + { + "first_name": "Gang", + "last_name": "Pan" + }, + { + "first_name": "Qian", + "last_name": "Zheng" + }, + { + "first_name": "Xudong", + "last_name": "Jiang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LLaFS: When Large Language Models Meet Few-Shot Segmentation", - "authors": "Lanyun Zhu, Tianrun Chen, Deyi Ji, Jieping Ye, Jun Liu", + "authors": [ + { + "first_name": "Lanyun", + "last_name": "Zhu" + }, + { + "first_name": "Tianrun", + "last_name": "Chen" + }, + { + "first_name": "Deyi", + "last_name": "Ji" + }, + { + "first_name": "Jieping", + "last_name": "Ye" + }, + { + "first_name": "Jun", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Kernel Adaptive Convolution for Scene Text Detection via Distance Map Prediction", - "authors": "Jinzhi Zheng, Heng Fan, Libo Zhang", + "authors": [ + { + "first_name": "Jinzhi", + "last_name": "Zheng" + }, + { + "first_name": "Heng", + "last_name": "Fan" + }, + { + "first_name": "Libo", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PixelLM: Pixel Reasoning with Large Multimodal Model", - "authors": "Zhongwei Ren, Zhicheng Huang, Yunchao Wei, Yao Zhao, Dongmei Fu, Jiashi Feng, Xiaojie Jin", + "authors": [ + { + "first_name": "Zhongwei", + "last_name": "Ren" + }, + { + "first_name": "Zhicheng", + "last_name": "Huang" + }, + { + "first_name": "Yunchao", + "last_name": "Wei" + }, + { + "first_name": "Yao", + "last_name": "Zhao" + }, + { + "first_name": "Dongmei", + "last_name": "Fu" + }, + { + "first_name": "Jiashi", + "last_name": "Feng" + }, + { + "first_name": "Xiaojie", + "last_name": "Jin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MRFS: Mutually Reinforcing Image Fusion and Segmentation", - "authors": "Hao Zhang, Xuhui Zuo, Jie Jiang, Chunchao Guo, Jiayi Ma", + "authors": [ + { + "first_name": "Hao", + "last_name": "Zhang" + }, + { + "first_name": "Xuhui", + "last_name": "Zuo" + }, + { + "first_name": "Jie", + "last_name": "Jiang" + }, + { + "first_name": "Chunchao", + "last_name": "Guo" + }, + { + "first_name": "Jiayi", + "last_name": "Ma" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MemoNav: Working Memory Model for Visual Navigation", - "authors": "Hongxin Li, Zeyu Wang, Xu Yang, Yuran Yang, Shuqi Mei, Zhaoxiang Zhang", + "authors": [ + { + "first_name": "Hongxin", + "last_name": "Li" + }, + { + "first_name": "Zeyu", + "last_name": "Wang" + }, + { + "first_name": "Xu", + "last_name": "Yang" + }, + { + "first_name": "Yuran", + "last_name": "Yang" + }, + { + "first_name": "Shuqi", + "last_name": "Mei" + }, + { + "first_name": "Zhaoxiang", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Robust Depth Enhancement via Polarization Prompt Fusion Tuning", - "authors": "Kei Ikemura, Yiming Huang, Felix Heide, Zhaoxiang Zhang, Qifeng Chen, Chenyang Lei", + "authors": [ + { + "first_name": "Kei", + "last_name": "Ikemura" + }, + { + "first_name": "Yiming", + "last_name": "Huang" + }, + { + "first_name": "Felix", + "last_name": "Heide" + }, + { + "first_name": "Zhaoxiang", + "last_name": "Zhang" + }, + { + "first_name": "Qifeng", + "last_name": "Chen" + }, + { + "first_name": "Chenyang", + "last_name": "Lei" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "AssistGUI: Task-Oriented PC Graphical User Interface Automation", - "authors": "Difei Gao, Lei Ji, Zechen Bai, Mingyu Ouyang, Peiran Li, Dongxing Mao, Qinchen Wu, Weichen Zhang, Peiyi Wang, Xiangwu Guo, Hengxu Wang, Luowei Zhou, Mike Zheng Shou", + "authors": [ + { + "first_name": "Difei", + "last_name": "Gao" + }, + { + "first_name": "Lei", + "last_name": "Ji" + }, + { + "first_name": "Zechen", + "last_name": "Bai" + }, + { + "first_name": "Mingyu", + "last_name": "Ouyang" + }, + { + "first_name": "Peiran", + "last_name": "Li" + }, + { + "first_name": "Dongxing", + "last_name": "Mao" + }, + { + "first_name": "Qinchen", + "last_name": "Wu" + }, + { + "first_name": "Weichen", + "last_name": "Zhang" + }, + { + "first_name": "Peiyi", + "last_name": "Wang" + }, + { + "first_name": "Xiangwu", + "last_name": "Guo" + }, + { + "first_name": "Hengxu", + "last_name": "Wang" + }, + { + "first_name": "Luowei", + "last_name": "Zhou" + }, + { + "first_name": "Mike", + "last_name": "Zheng Shou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Adaptive Multi-Modal Cross-Entropy Loss for Stereo Matching", - "authors": "Peng Xu, Zhiyu Xiang, Chengyu Qiao, Jingyun Fu, Tianyu Pu", + "authors": [ + { + "first_name": "Peng", + "last_name": "Xu" + }, + { + "first_name": "Zhiyu", + "last_name": "Xiang" + }, + { + "first_name": "Chengyu", + "last_name": "Qiao" + }, + { + "first_name": "Jingyun", + "last_name": "Fu" + }, + { + "first_name": "Tianyu", + "last_name": "Pu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Unlocking the Potential of Prompt-Tuning in Bridging Generalized and Personalized Federated Learning", - "authors": "Wenlong Deng, Christos Thrampoulidis, Xiaoxiao Li", + "authors": [ + { + "first_name": "Wenlong", + "last_name": "Deng" + }, + { + "first_name": "Christos", + "last_name": "Thrampoulidis" + }, + { + "first_name": "Xiaoxiao", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Compact 3D Gaussian Representation for Radiance Field", - "authors": "Joo Chan Lee, Daniel Rho, Xiangyu Sun, Jong Hwan Ko, Eunbyung Park", + "authors": [ + { + "first_name": "Joo", + "last_name": "Chan Lee" + }, + { + "first_name": "Daniel", + "last_name": "Rho" + }, + { + "first_name": "Xiangyu", + "last_name": "Sun" + }, + { + "first_name": "Jong", + "last_name": "Hwan Ko" + }, + { + "first_name": "Eunbyung", + "last_name": "Park" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PaSCo: Urban 3D Panoptic Scene Completion with Uncertainty Awareness", - "authors": "Anh-Quan Cao, Angela Dai, Raoul de Charette", + "authors": [ + { + "first_name": "Anh-Quan", + "last_name": "Cao" + }, + { + "first_name": "Angela", + "last_name": "Dai" + }, + { + "first_name": "Raoul", + "last_name": "de Charette" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GALA: Generating Animatable Layered Assets from a Single Scan", - "authors": "Taeksoo Kim, Byungjun Kim, Shunsuke Saito, Hanbyul Joo", + "authors": [ + { + "first_name": "Taeksoo", + "last_name": "Kim" + }, + { + "first_name": "Byungjun", + "last_name": "Kim" + }, + { + "first_name": "Shunsuke", + "last_name": "Saito" + }, + { + "first_name": "Hanbyul", + "last_name": "Joo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LeGO: Leveraging a Surface Deformation Network for Animatable Stylized Face Generation with One Example", - "authors": "Soyeon Yoon, Kwan Yun, Kwanggyoon Seo, Sihun Cha, Jung Eun Yoo, Junyong Noh", + "authors": [ + { + "first_name": "Soyeon", + "last_name": "Yoon" + }, + { + "first_name": "Kwan", + "last_name": "Yun" + }, + { + "first_name": "Kwanggyoon", + "last_name": "Seo" + }, + { + "first_name": "Sihun", + "last_name": "Cha" + }, + { + "first_name": "Jung", + "last_name": "Eun Yoo" + }, + { + "first_name": "Junyong", + "last_name": "Noh" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Frequency-Adaptive Dilated Convolution for Semantic Segmentation", - "authors": "Linwei Chen, Lin Gu, Dezhi Zheng, Ying Fu", + "authors": [ + { + "first_name": "Linwei", + "last_name": "Chen" + }, + { + "first_name": "Lin", + "last_name": "Gu" + }, + { + "first_name": "Dezhi", + "last_name": "Zheng" + }, + { + "first_name": "Ying", + "last_name": "Fu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "3D Building Reconstruction from Monocular Remote Sensing Images with Multi-level Supervisions", - "authors": "Weijia Li, Haote Yang, Zhenghao Hu, Juepeng Zheng, Gui-Song Xia, Conghui He", + "authors": [ + { + "first_name": "Weijia", + "last_name": "Li" + }, + { + "first_name": "Haote", + "last_name": "Yang" + }, + { + "first_name": "Zhenghao", + "last_name": "Hu" + }, + { + "first_name": "Juepeng", + "last_name": "Zheng" + }, + { + "first_name": "Gui-Song", + "last_name": "Xia" + }, + { + "first_name": "Conghui", + "last_name": "He" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AI", - "authors": "Yandan Yang, Baoxiong Jia, Peiyuan Zhi, Siyuan Huang", + "authors": [ + { + "first_name": "Yandan", + "last_name": "Yang" + }, + { + "first_name": "Baoxiong", + "last_name": "Jia" + }, + { + "first_name": "Peiyuan", + "last_name": "Zhi" + }, + { + "first_name": "Siyuan", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Generative Latent Coding for Ultra-Low Bitrate Image Compression", - "authors": "Zhaoyang Jia, Jiahao Li, Bin Li, Houqiang Li, Yan Lu", + "authors": [ + { + "first_name": "Zhaoyang", + "last_name": "Jia" + }, + { + "first_name": "Jiahao", + "last_name": "Li" + }, + { + "first_name": "Bin", + "last_name": "Li" + }, + { + "first_name": "Houqiang", + "last_name": "Li" + }, + { + "first_name": "Yan", + "last_name": "Lu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Multiple View Geometry Transformers for 3D Human Pose Estimation", - "authors": "Ziwei Liao, Jialiang Zhu, Chunyu Wang, Han Hu, Steven L. Waslander", + "authors": [ + { + "first_name": "Ziwei", + "last_name": "Liao" + }, + { + "first_name": "Jialiang", + "last_name": "Zhu" + }, + { + "first_name": "Chunyu", + "last_name": "Wang" + }, + { + "first_name": "Han", + "last_name": "Hu" + }, + { + "first_name": "Steven", + "last_name": "L. Waslander" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusion", - "authors": "Hsuan- I Ho, Jie Song, Otmar Hilliges", + "authors": [ + { + "first_name": "Hsuan-", + "last_name": "I Ho" + }, + { + "first_name": "Jie", + "last_name": "Song" + }, + { + "first_name": "Otmar", + "last_name": "Hilliges" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Distributionally Generative Augmentation for Fair Facial Attribute Classification", - "authors": "Fengda Zhang, Qianpei He, Kun Kuang, Jiashuo Liu, Long Chen, Chao Wu, Jun Xiao, Hanwang Zhang", + "authors": [ + { + "first_name": "Fengda", + "last_name": "Zhang" + }, + { + "first_name": "Qianpei", + "last_name": "He" + }, + { + "first_name": "Kun", + "last_name": "Kuang" + }, + { + "first_name": "Jiashuo", + "last_name": "Liu" + }, + { + "first_name": "Long", + "last_name": "Chen" + }, + { + "first_name": "Chao", + "last_name": "Wu" + }, + { + "first_name": "Jun", + "last_name": "Xiao" + }, + { + "first_name": "Hanwang", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DynVideo-E: Harnessing Dynamic NeRF for Large-Scale Motion- and View-Change Human-Centric Video Editing", - "authors": "Jia-Wei Liu, Yan-Pei Cao, Jay Zhangjie Wu, Weijia Mao, Yuchao Gu, Rui Zhao, Jussi Keppo, Ying Shan, Mike Zheng Shou", + "authors": [ + { + "first_name": "Jia-Wei", + "last_name": "Liu" + }, + { + "first_name": "Yan-Pei", + "last_name": "Cao" + }, + { + "first_name": "Jay", + "last_name": "Zhangjie Wu" + }, + { + "first_name": "Weijia", + "last_name": "Mao" + }, + { + "first_name": "Yuchao", + "last_name": "Gu" + }, + { + "first_name": "Rui", + "last_name": "Zhao" + }, + { + "first_name": "Jussi", + "last_name": "Keppo" + }, + { + "first_name": "Ying", + "last_name": "Shan" + }, + { + "first_name": "Mike", + "last_name": "Zheng Shou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Real-Time Neural BRDF with Spherically Distributed Primitives", - "authors": "Yishun Dou, Zhong Zheng, Qiaoqiao Jin, Bingbing Ni, Yugang Chen, Junxiang Ke", + "authors": [ + { + "first_name": "Yishun", + "last_name": "Dou" + }, + { + "first_name": "Zhong", + "last_name": "Zheng" + }, + { + "first_name": "Qiaoqiao", + "last_name": "Jin" + }, + { + "first_name": "Bingbing", + "last_name": "Ni" + }, + { + "first_name": "Yugang", + "last_name": "Chen" + }, + { + "first_name": "Junxiang", + "last_name": "Ke" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Harnessing Meta-Learning for Improving Full-Frame Video Stabilization", - "authors": "Muhammad Kashif Ali, Eun Woo Im, Dongjin Kim, Tae Hyun Kim", + "authors": [ + { + "first_name": "Muhammad", + "last_name": "Kashif Ali" + }, + { + "first_name": "Eun", + "last_name": "Woo Im" + }, + { + "first_name": "Dongjin", + "last_name": "Kim" + }, + { + "first_name": "Tae", + "last_name": "Hyun Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models", - "authors": "Haoxin Chen, Yong Zhang, Xiaodong Cun, Menghan Xia, Xintao Wang, Chao Weng, Ying Shan", + "authors": [ + { + "first_name": "Haoxin", + "last_name": "Chen" + }, + { + "first_name": "Yong", + "last_name": "Zhang" + }, + { + "first_name": "Xiaodong", + "last_name": "Cun" + }, + { + "first_name": "Menghan", + "last_name": "Xia" + }, + { + "first_name": "Xintao", + "last_name": "Wang" + }, + { + "first_name": "Chao", + "last_name": "Weng" + }, + { + "first_name": "Ying", + "last_name": "Shan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "From SAM to CAMs: Exploring Segment Anything Model for Weakly Supervised Semantic Segmentation", - "authors": "Hyeokjun Kweon, Kuk-Jin Yoon", + "authors": [ + { + "first_name": "Hyeokjun", + "last_name": "Kweon" + }, + { + "first_name": "Kuk-Jin", + "last_name": "Yoon" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Boosting Flow-based Generative Super-Resolution Models via Learned Prior", - "authors": "Li-Yuan Tsao, Yi-Chen Lo, Chia-Che Chang, Hao-Wei Chen, Roy Tseng, Chien Feng, Chun-Yi Lee", + "authors": [ + { + "first_name": "Li-Yuan", + "last_name": "Tsao" + }, + { + "first_name": "Yi-Chen", + "last_name": "Lo" + }, + { + "first_name": "Chia-Che", + "last_name": "Chang" + }, + { + "first_name": "Hao-Wei", + "last_name": "Chen" + }, + { + "first_name": "Roy", + "last_name": "Tseng" + }, + { + "first_name": "Chien", + "last_name": "Feng" + }, + { + "first_name": "Chun-Yi", + "last_name": "Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "How to Handle Sketch-Abstraction in Sketch-Based Image Retrieval?", - "authors": "Subhadeep Koley, Ayan Kumar Bhunia, Aneeshan Sain, Pinaki Nath Chowdhury, Tao Xiang, Yi-Zhe Song", + "authors": [ + { + "first_name": "Subhadeep", + "last_name": "Koley" + }, + { + "first_name": "Ayan", + "last_name": "Kumar Bhunia" + }, + { + "first_name": "Aneeshan", + "last_name": "Sain" + }, + { + "first_name": "Pinaki", + "last_name": "Nath Chowdhury" + }, + { + "first_name": "Tao", + "last_name": "Xiang" + }, + { + "first_name": "Yi-Zhe", + "last_name": "Song" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "What You See is What You GAN: Rendering Every Pixel for High-Fidelity Geometry in 3D GANs", - "authors": "Alex Trevithick, Matthew Chan, Towaki Takikawa, Umar Iqbal, Shalini De Mello, Manmohan Chandraker, Ravi Ramamoorthi, Koki Nagano", + "authors": [ + { + "first_name": "Alex", + "last_name": "Trevithick" + }, + { + "first_name": "Matthew", + "last_name": "Chan" + }, + { + "first_name": "Towaki", + "last_name": "Takikawa" + }, + { + "first_name": "Umar", + "last_name": "Iqbal" + }, + { + "first_name": "Shalini", + "last_name": "De Mello" + }, + { + "first_name": "Manmohan", + "last_name": "Chandraker" + }, + { + "first_name": "Ravi", + "last_name": "Ramamoorthi" + }, + { + "first_name": "Koki", + "last_name": "Nagano" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer", - "authors": "Jiwoo Chung, Sangeek Hyun, Jae-Pil Heo", + "authors": [ + { + "first_name": "Jiwoo", + "last_name": "Chung" + }, + { + "first_name": "Sangeek", + "last_name": "Hyun" + }, + { + "first_name": "Jae-Pil", + "last_name": "Heo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards Robust Learning to Optimize with Theoretical Guarantees", - "authors": "Qingyu Song, Wei Lin, Juncheng Wang, Hong Xu", + "authors": [ + { + "first_name": "Qingyu", + "last_name": "Song" + }, + { + "first_name": "Wei", + "last_name": "Lin" + }, + { + "first_name": "Juncheng", + "last_name": "Wang" + }, + { + "first_name": "Hong", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Differentiable Neural Surface Refinement for Modeling Transparent Objects", - "authors": "Weijian Deng, Dylan Campbell, Chunyi Sun, Shubham Kanitkar, Matthew E. Shaffer, Stephen Gould", + "authors": [ + { + "first_name": "Weijian", + "last_name": "Deng" + }, + { + "first_name": "Dylan", + "last_name": "Campbell" + }, + { + "first_name": "Chunyi", + "last_name": "Sun" + }, + { + "first_name": "Shubham", + "last_name": "Kanitkar" + }, + { + "first_name": "Matthew", + "last_name": "E. Shaffer" + }, + { + "first_name": "Stephen", + "last_name": "Gould" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "OrthCaps: An Orthogonal CapsNet with Sparse Attention Routing and Pruning", - "authors": "Xinyu Geng, Jiaming Wang, Jiawei Gong, Yuerong Xue, Jun Xu, Fanglin Chen, Xiaolin Huang", + "authors": [ + { + "first_name": "Xinyu", + "last_name": "Geng" + }, + { + "first_name": "Jiaming", + "last_name": "Wang" + }, + { + "first_name": "Jiawei", + "last_name": "Gong" + }, + { + "first_name": "Yuerong", + "last_name": "Xue" + }, + { + "first_name": "Jun", + "last_name": "Xu" + }, + { + "first_name": "Fanglin", + "last_name": "Chen" + }, + { + "first_name": "Xiaolin", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ProS: Prompting-to-simulate Generalized knowledge for Universal Cross-Domain Retrieval", - "authors": "Kaipeng Fang, Jingkuan Song, Lianli Gao, Pengpeng Zeng, Zhi-Qi Cheng, Xiyao Li, Heng Tao Shen", + "authors": [ + { + "first_name": "Kaipeng", + "last_name": "Fang" + }, + { + "first_name": "Jingkuan", + "last_name": "Song" + }, + { + "first_name": "Lianli", + "last_name": "Gao" + }, + { + "first_name": "Pengpeng", + "last_name": "Zeng" + }, + { + "first_name": "Zhi-Qi", + "last_name": "Cheng" + }, + { + "first_name": "Xiyao", + "last_name": "Li" + }, + { + "first_name": "Heng", + "last_name": "Tao Shen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks", - "authors": "Bin Xiao, Haiping Wu, Weijian Xu, Xiyang Dai, Houdong Hu, Yumao Lu, Michael Zeng, Ce Liu, Lu Yuan", + "authors": [ + { + "first_name": "Bin", + "last_name": "Xiao" + }, + { + "first_name": "Haiping", + "last_name": "Wu" + }, + { + "first_name": "Weijian", + "last_name": "Xu" + }, + { + "first_name": "Xiyang", + "last_name": "Dai" + }, + { + "first_name": "Houdong", + "last_name": "Hu" + }, + { + "first_name": "Yumao", + "last_name": "Lu" + }, + { + "first_name": "Michael", + "last_name": "Zeng" + }, + { + "first_name": "Ce", + "last_name": "Liu" + }, + { + "first_name": "Lu", + "last_name": "Yuan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild", - "authors": "Weining Ren, Zihan Zhu, Boyang Sun, Jiaqi Chen, Marc Pollefeys, Songyou Peng", + "authors": [ + { + "first_name": "Weining", + "last_name": "Ren" + }, + { + "first_name": "Zihan", + "last_name": "Zhu" + }, + { + "first_name": "Boyang", + "last_name": "Sun" + }, + { + "first_name": "Jiaqi", + "last_name": "Chen" + }, + { + "first_name": "Marc", + "last_name": "Pollefeys" + }, + { + "first_name": "Songyou", + "last_name": "Peng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "3D Human Pose Perception from Egocentric Stereo Videos", - "authors": "Hiroyasu Akada, Jian Wang, Vladislav Golyanik, Christian Theobalt", + "authors": [ + { + "first_name": "Hiroyasu", + "last_name": "Akada" + }, + { + "first_name": "Jian", + "last_name": "Wang" + }, + { + "first_name": "Vladislav", + "last_name": "Golyanik" + }, + { + "first_name": "Christian", + "last_name": "Theobalt" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Grid Diffusion Models for Text-to-Video Generation", - "authors": "Taegyeong Lee, Soyeong Kwon, Taehwan Kim", + "authors": [ + { + "first_name": "Taegyeong", + "last_name": "Lee" + }, + { + "first_name": "Soyeong", + "last_name": "Kwon" + }, + { + "first_name": "Taehwan", + "last_name": "Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Boosting Object Detection with Zero-Shot Day-Night Domain Adaptation", - "authors": "Zhipeng Du, Miaojing Shi, Jiankang Deng", + "authors": [ + { + "first_name": "Zhipeng", + "last_name": "Du" + }, + { + "first_name": "Miaojing", + "last_name": "Shi" + }, + { + "first_name": "Jiankang", + "last_name": "Deng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching", - "authors": "Yixun Liang, Xin Yang, Jiantao Lin, Haodong Li, Xiaogang Xu, Yingcong Chen", + "authors": [ + { + "first_name": "Yixun", + "last_name": "Liang" + }, + { + "first_name": "Xin", + "last_name": "Yang" + }, + { + "first_name": "Jiantao", + "last_name": "Lin" + }, + { + "first_name": "Haodong", + "last_name": "Li" + }, + { + "first_name": "Xiaogang", + "last_name": "Xu" + }, + { + "first_name": "Yingcong", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PTM-VQA: Efficient Video Quality Assessment Leveraging Diverse PreTrained Models from the Wild", - "authors": "Kun Yuan, Hongbo Liu, Mading Li, Muyi Sun, Ming Sun, Jiachao Gong, Jinhua Hao, Chao Zhou, Yansong Tang", + "authors": [ + { + "first_name": "Kun", + "last_name": "Yuan" + }, + { + "first_name": "Hongbo", + "last_name": "Liu" + }, + { + "first_name": "Mading", + "last_name": "Li" + }, + { + "first_name": "Muyi", + "last_name": "Sun" + }, + { + "first_name": "Ming", + "last_name": "Sun" + }, + { + "first_name": "Jiachao", + "last_name": "Gong" + }, + { + "first_name": "Jinhua", + "last_name": "Hao" + }, + { + "first_name": "Chao", + "last_name": "Zhou" + }, + { + "first_name": "Yansong", + "last_name": "Tang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Versatile Medical Image Segmentation Learned from Multi-Source Datasets via Model Self-Disambiguation", - "authors": "Xiaoyang Chen, Hao Zheng, Yuemeng Li, Yuncong Ma, Liang Ma, Hongming Li, Yong Fan", + "authors": [ + { + "first_name": "Xiaoyang", + "last_name": "Chen" + }, + { + "first_name": "Hao", + "last_name": "Zheng" + }, + { + "first_name": "Yuemeng", + "last_name": "Li" + }, + { + "first_name": "Yuncong", + "last_name": "Ma" + }, + { + "first_name": "Liang", + "last_name": "Ma" + }, + { + "first_name": "Hongming", + "last_name": "Li" + }, + { + "first_name": "Yong", + "last_name": "Fan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Improving Generalization via Meta-Learning on Hard Samples", - "authors": "Nishant Jain, Arun S. Suggala, Pradeep Shenoy", + "authors": [ + { + "first_name": "Nishant", + "last_name": "Jain" + }, + { + "first_name": "Arun", + "last_name": "S. Suggala" + }, + { + "first_name": "Pradeep", + "last_name": "Shenoy" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Align and Aggregate: Compositional Reasoning with Video Alignment and Answer Aggregation for Video Question-Answering", - "authors": "Zhaohe Liao, Jiangtong Li, Li Niu, Liqing Zhang", + "authors": [ + { + "first_name": "Zhaohe", + "last_name": "Liao" + }, + { + "first_name": "Jiangtong", + "last_name": "Li" + }, + { + "first_name": "Li", + "last_name": "Niu" + }, + { + "first_name": "Liqing", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "REACTO: Reconstructing Articulated Objects from a Single Video", - "authors": "Chaoyue Song, Jiacheng Wei, Chuan Sheng Foo, Guosheng Lin, Fayao Liu", + "authors": [ + { + "first_name": "Chaoyue", + "last_name": "Song" + }, + { + "first_name": "Jiacheng", + "last_name": "Wei" + }, + { + "first_name": "Chuan", + "last_name": "Sheng Foo" + }, + { + "first_name": "Guosheng", + "last_name": "Lin" + }, + { + "first_name": "Fayao", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Egocentric Whole-Body Motion Capture with FisheyeViT and Diffusion-Based Motion Refinement", - "authors": "Jian Wang, Zhe Cao, Diogo Luvizon, Lingjie Liu, Kripasindhu Sarkar, Danhang Tang, Thabo Beeler, Christian Theobalt", + "authors": [ + { + "first_name": "Jian", + "last_name": "Wang" + }, + { + "first_name": "Zhe", + "last_name": "Cao" + }, + { + "first_name": "Diogo", + "last_name": "Luvizon" + }, + { + "first_name": "Lingjie", + "last_name": "Liu" + }, + { + "first_name": "Kripasindhu", + "last_name": "Sarkar" + }, + { + "first_name": "Danhang", + "last_name": "Tang" + }, + { + "first_name": "Thabo", + "last_name": "Beeler" + }, + { + "first_name": "Christian", + "last_name": "Theobalt" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Language Embedded 3D Gaussians for Open-Vocabulary Scene Understanding", - "authors": "Jin-Chuan Shi, Miao Wang, Hao-Bin Duan, Shao-Hua Guan", + "authors": [ + { + "first_name": "Jin-Chuan", + "last_name": "Shi" + }, + { + "first_name": "Miao", + "last_name": "Wang" + }, + { + "first_name": "Hao-Bin", + "last_name": "Duan" + }, + { + "first_name": "Shao-Hua", + "last_name": "Guan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards Automated Movie Trailer Generation", - "authors": "Dawit Mureja Argaw, Mattia Soldan, Alejandro Pardo, Chen Zhao, Fabian Caba Heilbron, Joon Son Chung, Bernard Ghanem", + "authors": [ + { + "first_name": "Dawit", + "last_name": "Mureja Argaw" + }, + { + "first_name": "Mattia", + "last_name": "Soldan" + }, + { + "first_name": "Alejandro", + "last_name": "Pardo" + }, + { + "first_name": "Chen", + "last_name": "Zhao" + }, + { + "first_name": "Fabian", + "last_name": "Caba Heilbron" + }, + { + "first_name": "Joon", + "last_name": "Son Chung" + }, + { + "first_name": "Bernard", + "last_name": "Ghanem" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Differentiable Information Bottleneck for Deterministic Multi-view Clustering", - "authors": "Xiaoqiang Yan, Zhixiang Jin, Fengshou Han, Yangdong Ye", + "authors": [ + { + "first_name": "Xiaoqiang", + "last_name": "Yan" + }, + { + "first_name": "Zhixiang", + "last_name": "Jin" + }, + { + "first_name": "Fengshou", + "last_name": "Han" + }, + { + "first_name": "Yangdong", + "last_name": "Ye" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Sheared Backpropagation for Fine-tuning Foundation Models", - "authors": "Zhiyuan Yu, Li Shen, Liang Ding, Xinmei Tian, Yixin Chen, Dacheng Tao", + "authors": [ + { + "first_name": "Zhiyuan", + "last_name": "Yu" + }, + { + "first_name": "Li", + "last_name": "Shen" + }, + { + "first_name": "Liang", + "last_name": "Ding" + }, + { + "first_name": "Xinmei", + "last_name": "Tian" + }, + { + "first_name": "Yixin", + "last_name": "Chen" + }, + { + "first_name": "Dacheng", + "last_name": "Tao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Action-slot: Visual Action-centric Representations for Multi-label Atomic Activity Recognition in Traffic Scenes", - "authors": "Chi-Hsi Kung, Shu-Wei Lu, Yi-Hsuan Tsai, Yi-Ting Chen", + "authors": [ + { + "first_name": "Chi-Hsi", + "last_name": "Kung" + }, + { + "first_name": "Shu-Wei", + "last_name": "Lu" + }, + { + "first_name": "Yi-Hsuan", + "last_name": "Tsai" + }, + { + "first_name": "Yi-Ting", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Animatable Gaussians: Learning Pose-dependent Gaussian Maps for High-fidelity Human Avatar Modeling", - "authors": "Zhe Li, Zerong Zheng, Lizhen Wang, Yebin Liu", + "authors": [ + { + "first_name": "Zhe", + "last_name": "Li" + }, + { + "first_name": "Zerong", + "last_name": "Zheng" + }, + { + "first_name": "Lizhen", + "last_name": "Wang" + }, + { + "first_name": "Yebin", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Latency Correction for Event-guided Deblurring and Frame Interpolation", - "authors": "Yixin Yang, Jinxiu Liang, Bohan Yu, Yan Chen, Jimmy S. Ren, Boxin Shi", + "authors": [ + { + "first_name": "Yixin", + "last_name": "Yang" + }, + { + "first_name": "Jinxiu", + "last_name": "Liang" + }, + { + "first_name": "Bohan", + "last_name": "Yu" + }, + { + "first_name": "Yan", + "last_name": "Chen" + }, + { + "first_name": "Jimmy", + "last_name": "S. Ren" + }, + { + "first_name": "Boxin", + "last_name": "Shi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Retraining-Free Model Quantization via One-Shot Weight-Coupling Learning", - "authors": "Chen Tang, Yuan Meng, Jiacheng Jiang, Shuzhao Xie, Rongwei Lu, Xinzhu Ma, Zhi Wang, Wenwu Zhu", + "authors": [ + { + "first_name": "Chen", + "last_name": "Tang" + }, + { + "first_name": "Yuan", + "last_name": "Meng" + }, + { + "first_name": "Jiacheng", + "last_name": "Jiang" + }, + { + "first_name": "Shuzhao", + "last_name": "Xie" + }, + { + "first_name": "Rongwei", + "last_name": "Lu" + }, + { + "first_name": "Xinzhu", + "last_name": "Ma" + }, + { + "first_name": "Zhi", + "last_name": "Wang" + }, + { + "first_name": "Wenwu", + "last_name": "Zhu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "EVCap: Retrieval-Augmented Image Captioning with External Visual-Name Memory for Open-World Comprehension", - "authors": "Jiaxuan Li, Duc Minh Vo, Akihiro Sugimoto, Hideki Nakayama", + "authors": [ + { + "first_name": "Jiaxuan", + "last_name": "Li" + }, + { + "first_name": "Duc", + "last_name": "Minh Vo" + }, + { + "first_name": "Akihiro", + "last_name": "Sugimoto" + }, + { + "first_name": "Hideki", + "last_name": "Nakayama" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction", - "authors": "Zechuan Zhang, Zongxin Yang, Yi Yang", + "authors": [ + { + "first_name": "Zechuan", + "last_name": "Zhang" + }, + { + "first_name": "Zongxin", + "last_name": "Yang" + }, + { + "first_name": "Yi", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "WinSyn: : A High Resolution Testbed for Synthetic Data", - "authors": "Tom Kelly, John Femiani, Peter Wonka", + "authors": [ + { + "first_name": "Tom", + "last_name": "Kelly" + }, + { + "first_name": "John", + "last_name": "Femiani" + }, + { + "first_name": "Peter", + "last_name": "Wonka" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Autoregressive Queries for Adaptive Tracking with Spatio-Temporal Transformers", - "authors": "Jinxia Xie, Bineng Zhong, Zhiyi Mo, Shengping Zhang, Liangtao Shi, Shuxiang Song, Rongrong Ji", + "authors": [ + { + "first_name": "Jinxia", + "last_name": "Xie" + }, + { + "first_name": "Bineng", + "last_name": "Zhong" + }, + { + "first_name": "Zhiyi", + "last_name": "Mo" + }, + { + "first_name": "Shengping", + "last_name": "Zhang" + }, + { + "first_name": "Liangtao", + "last_name": "Shi" + }, + { + "first_name": "Shuxiang", + "last_name": "Song" + }, + { + "first_name": "Rongrong", + "last_name": "Ji" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Misalignment-Robust Frequency Distribution Loss for Image Transformation", - "authors": "Zhangkai Ni, Juncheng Wu, Zian Wang, Wenhan Yang, Hanli Wang, Lin Ma", + "authors": [ + { + "first_name": "Zhangkai", + "last_name": "Ni" + }, + { + "first_name": "Juncheng", + "last_name": "Wu" + }, + { + "first_name": "Zian", + "last_name": "Wang" + }, + { + "first_name": "Wenhan", + "last_name": "Yang" + }, + { + "first_name": "Hanli", + "last_name": "Wang" + }, + { + "first_name": "Lin", + "last_name": "Ma" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Language-aware Visual Semantic Distillation for Video Question Answering", - "authors": "Bo Zou, Chao Yang, Yu Qiao, Chengbin Quan, Youjian Zhao", + "authors": [ + { + "first_name": "Bo", + "last_name": "Zou" + }, + { + "first_name": "Chao", + "last_name": "Yang" + }, + { + "first_name": "Yu", + "last_name": "Qiao" + }, + { + "first_name": "Chengbin", + "last_name": "Quan" + }, + { + "first_name": "Youjian", + "last_name": "Zhao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Lane2Seq: Towards Unified Lane Detection via Sequence Generation", - "authors": "Kunyang Zhou", + "authors": [ + { + "first_name": "Kunyang", + "last_name": "Zhou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Disentangled Prompt Representation for Domain Generalization", - "authors": "De Cheng, Zhipeng Xu, Xinyang Jiang, Nannan Wang, Dongsheng Li, Xinbo Gao", + "authors": [ + { + "first_name": "De", + "last_name": "Cheng" + }, + { + "first_name": "Zhipeng", + "last_name": "Xu" + }, + { + "first_name": "Xinyang", + "last_name": "Jiang" + }, + { + "first_name": "Nannan", + "last_name": "Wang" + }, + { + "first_name": "Dongsheng", + "last_name": "Li" + }, + { + "first_name": "Xinbo", + "last_name": "Gao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Abductive Ego-View Accident Video Understanding for Safe Driving Perception", - "authors": "Jianwu Fang, Lei-lei Li, Junfei Zhou, Junbin Xiao, Hongkai Yu, Chen Lv, Jianru Xue, Tat-Seng Chua", + "authors": [ + { + "first_name": "Jianwu", + "last_name": "Fang" + }, + { + "first_name": "Lei-lei", + "last_name": "Li" + }, + { + "first_name": "Junfei", + "last_name": "Zhou" + }, + { + "first_name": "Junbin", + "last_name": "Xiao" + }, + { + "first_name": "Hongkai", + "last_name": "Yu" + }, + { + "first_name": "Chen", + "last_name": "Lv" + }, + { + "first_name": "Jianru", + "last_name": "Xue" + }, + { + "first_name": "Tat-Seng", + "last_name": "Chua" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Cross-spectral Gated-RGB Stereo Depth Estimation", - "authors": "Samuel Brucker, Stefanie Walz, Mario Bijelic, Felix Heide", + "authors": [ + { + "first_name": "Samuel", + "last_name": "Brucker" + }, + { + "first_name": "Stefanie", + "last_name": "Walz" + }, + { + "first_name": "Mario", + "last_name": "Bijelic" + }, + { + "first_name": "Felix", + "last_name": "Heide" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "KVQ: Kwai Video Quality Assessment for Short-form Videos", - "authors": "Yiting Lu, Xin Li, Yajing Pei, Kun Yuan, Qizhi Xie, Yunpeng Qu, Ming Sun, Chao Zhou, Zhibo Chen", + "authors": [ + { + "first_name": "Yiting", + "last_name": "Lu" + }, + { + "first_name": "Xin", + "last_name": "Li" + }, + { + "first_name": "Yajing", + "last_name": "Pei" + }, + { + "first_name": "Kun", + "last_name": "Yuan" + }, + { + "first_name": "Qizhi", + "last_name": "Xie" + }, + { + "first_name": "Yunpeng", + "last_name": "Qu" + }, + { + "first_name": "Ming", + "last_name": "Sun" + }, + { + "first_name": "Chao", + "last_name": "Zhou" + }, + { + "first_name": "Zhibo", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Degrees of Freedom Matter: Inferring Dynamics from Point Trajectories", - "authors": "Yan Zhang, Sergey Prokudin, Marko Mihajlovic, Qianli Ma, Siyu Tang", + "authors": [ + { + "first_name": "Yan", + "last_name": "Zhang" + }, + { + "first_name": "Sergey", + "last_name": "Prokudin" + }, + { + "first_name": "Marko", + "last_name": "Mihajlovic" + }, + { + "first_name": "Qianli", + "last_name": "Ma" + }, + { + "first_name": "Siyu", + "last_name": "Tang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LEMON: Learning 3D Human-Object Interaction Relation from 2D Images", - "authors": "Yuhang Yang, Wei Zhai, Hongchen Luo, Yang Cao, Zheng-Jun Zha", + "authors": [ + { + "first_name": "Yuhang", + "last_name": "Yang" + }, + { + "first_name": "Wei", + "last_name": "Zhai" + }, + { + "first_name": "Hongchen", + "last_name": "Luo" + }, + { + "first_name": "Yang", + "last_name": "Cao" + }, + { + "first_name": "Zheng-Jun", + "last_name": "Zha" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Low-Latency Neural Stereo Streaming", - "authors": "Qiqi Hou, Farzad Farhadzadeh, Amir Said, Guillaume Sautiere, Hoang Le", + "authors": [ + { + "first_name": "Qiqi", + "last_name": "Hou" + }, + { + "first_name": "Farzad", + "last_name": "Farhadzadeh" + }, + { + "first_name": "Amir", + "last_name": "Said" + }, + { + "first_name": "Guillaume", + "last_name": "Sautiere" + }, + { + "first_name": "Hoang", + "last_name": "Le" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Understanding Video Transformers via Universal Concept Discovery", - "authors": "Matthew Kowal, Achal Dave, Rares Ambrus, Adrien Gaidon, Konstantinos G. Derpanis, Pavel Tokmakov", + "authors": [ + { + "first_name": "Matthew", + "last_name": "Kowal" + }, + { + "first_name": "Achal", + "last_name": "Dave" + }, + { + "first_name": "Rares", + "last_name": "Ambrus" + }, + { + "first_name": "Adrien", + "last_name": "Gaidon" + }, + { + "first_name": "Konstantinos", + "last_name": "G. Derpanis" + }, + { + "first_name": "Pavel", + "last_name": "Tokmakov" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Exploring the Transferability of Visual Prompting for Multimodal Large Language Models", - "authors": "Yichi Zhang, Yinpeng Dong, Siyuan Zhang, Tianzan Min, Hang Su, Jun Zhu", + "authors": [ + { + "first_name": "Yichi", + "last_name": "Zhang" + }, + { + "first_name": "Yinpeng", + "last_name": "Dong" + }, + { + "first_name": "Siyuan", + "last_name": "Zhang" + }, + { + "first_name": "Tianzan", + "last_name": "Min" + }, + { + "first_name": "Hang", + "last_name": "Su" + }, + { + "first_name": "Jun", + "last_name": "Zhu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PointOBB: Learning Oriented Object Detection via Single Point Supervision", - "authors": "Junwei Luo, Xue Yang, Yi Yu, Qingyun Li, Junchi Yan, Yansheng Li", + "authors": [ + { + "first_name": "Junwei", + "last_name": "Luo" + }, + { + "first_name": "Xue", + "last_name": "Yang" + }, + { + "first_name": "Yi", + "last_name": "Yu" + }, + { + "first_name": "Qingyun", + "last_name": "Li" + }, + { + "first_name": "Junchi", + "last_name": "Yan" + }, + { + "first_name": "Yansheng", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Intrinsic Image Diffusion for Indoor Single-view Material Estimation", - "authors": "Peter Kocsis, Vincent Sitzmann, Matthias Nießner", + "authors": [ + { + "first_name": "Peter", + "last_name": "Kocsis" + }, + { + "first_name": "Vincent", + "last_name": "Sitzmann" + }, + { + "first_name": "Matthias", + "last_name": "Nießner" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SHAP-EDITOR: Instruction-Guided Latent 3D Editing in Seconds", - "authors": "Minghao Chen, Junyu Xie, Iro Laina, Andrea Vedaldi", + "authors": [ + { + "first_name": "Minghao", + "last_name": "Chen" + }, + { + "first_name": "Junyu", + "last_name": "Xie" + }, + { + "first_name": "Iro", + "last_name": "Laina" + }, + { + "first_name": "Andrea", + "last_name": "Vedaldi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HyperSDFusion: Bridging Hierarchical Structures in Language and Geometry for Enhanced 3D Text2Shape Generation", - "authors": "Zhiying Leng, Tolga Birdal, Xiaohui Liang, Federico Tombari", + "authors": [ + { + "first_name": "Zhiying", + "last_name": "Leng" + }, + { + "first_name": "Tolga", + "last_name": "Birdal" + }, + { + "first_name": "Xiaohui", + "last_name": "Liang" + }, + { + "first_name": "Federico", + "last_name": "Tombari" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "OmniParser: A Unified Framework for Text Spotting Key Information Extraction and Table Recognition", - "authors": "Jianqiang Wan, Sibo Song, Wenwen Yu, Yuliang Liu, Wenqing Cheng, Fei Huang, Xiang Bai, Cong Yao, Zhibo Yang", + "authors": [ + { + "first_name": "Jianqiang", + "last_name": "Wan" + }, + { + "first_name": "Sibo", + "last_name": "Song" + }, + { + "first_name": "Wenwen", + "last_name": "Yu" + }, + { + "first_name": "Yuliang", + "last_name": "Liu" + }, + { + "first_name": "Wenqing", + "last_name": "Cheng" + }, + { + "first_name": "Fei", + "last_name": "Huang" + }, + { + "first_name": "Xiang", + "last_name": "Bai" + }, + { + "first_name": "Cong", + "last_name": "Yao" + }, + { + "first_name": "Zhibo", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Are Conventional SNNs Really Efficient? A Perspective from Network Quantization", - "authors": "Guobin Shen, Dongcheng Zhao, Tenglong Li, Jindong Li, Yi Zeng", + "authors": [ + { + "first_name": "Guobin", + "last_name": "Shen" + }, + { + "first_name": "Dongcheng", + "last_name": "Zhao" + }, + { + "first_name": "Tenglong", + "last_name": "Li" + }, + { + "first_name": "Jindong", + "last_name": "Li" + }, + { + "first_name": "Yi", + "last_name": "Zeng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Training Like a Medical Resident: Context-Prior Learning Toward Universal Medical Image Segmentation", - "authors": "Yunhe Gao", + "authors": [ + { + "first_name": "Yunhe", + "last_name": "Gao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Material Palette: Extraction of Materials from a Single Image", - "authors": "Ivan Lopes, Fabio Pizzati, Raoul de Charette", + "authors": [ + { + "first_name": "Ivan", + "last_name": "Lopes" + }, + { + "first_name": "Fabio", + "last_name": "Pizzati" + }, + { + "first_name": "Raoul", + "last_name": "de Charette" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Initialization Matters for Adversarial Transfer Learning", - "authors": "Andong Hua, Jindong Gu, Zhiyu Xue, Nicholas Carlini, Eric Wong, Yao Qin", + "authors": [ + { + "first_name": "Andong", + "last_name": "Hua" + }, + { + "first_name": "Jindong", + "last_name": "Gu" + }, + { + "first_name": "Zhiyu", + "last_name": "Xue" + }, + { + "first_name": "Nicholas", + "last_name": "Carlini" + }, + { + "first_name": "Eric", + "last_name": "Wong" + }, + { + "first_name": "Yao", + "last_name": "Qin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "RealCustom: Narrowing Real Text Word for Real-Time Open-Domain Text-to-Image Customization", - "authors": "Mengqi Huang, Zhendong Mao, Mingcong Liu, Qian He, Yongdong Zhang", + "authors": [ + { + "first_name": "Mengqi", + "last_name": "Huang" + }, + { + "first_name": "Zhendong", + "last_name": "Mao" + }, + { + "first_name": "Mingcong", + "last_name": "Liu" + }, + { + "first_name": "Qian", + "last_name": "He" + }, + { + "first_name": "Yongdong", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MicroDiffusion: Implicit Representation-Guided Diffusion for 3D Reconstruction from Limited 2D Microscopy Projections", - "authors": "Mude Hui, Zihao Wei, Hongru Zhu, Fei Xia, Yuyin Zhou", + "authors": [ + { + "first_name": "Mude", + "last_name": "Hui" + }, + { + "first_name": "Zihao", + "last_name": "Wei" + }, + { + "first_name": "Hongru", + "last_name": "Zhu" + }, + { + "first_name": "Fei", + "last_name": "Xia" + }, + { + "first_name": "Yuyin", + "last_name": "Zhou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Task-Conditioned Adaptation of Visual Features in Multi-Task Policy Learning", - "authors": "Pierre Marza, Laetitia Matignon, Olivier Simonin, Christian Wolf", + "authors": [ + { + "first_name": "Pierre", + "last_name": "Marza" + }, + { + "first_name": "Laetitia", + "last_name": "Matignon" + }, + { + "first_name": "Olivier", + "last_name": "Simonin" + }, + { + "first_name": "Christian", + "last_name": "Wolf" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "L0-Sampler: An L0 Model Guided Volume Sampling for NeRF", - "authors": "Liangchen Li, Juyong Zhang", + "authors": [ + { + "first_name": "Liangchen", + "last_name": "Li" + }, + { + "first_name": "Juyong", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Hybrid Proposal Refiner: Revisiting DETR Series from the Faster R-CNN Perspective", - "authors": "Jinjing Zhao, Fangyun Wei, Chang Xu", + "authors": [ + { + "first_name": "Jinjing", + "last_name": "Zhao" + }, + { + "first_name": "Fangyun", + "last_name": "Wei" + }, + { + "first_name": "Chang", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Practical Measurements of Translucent Materials with Inter-Pixel Translucency Prior", - "authors": "Zhenyu Chen, Jie Guo, Shuichang Lai, Ruoyu Fu, Mengxun Kong, Chen Wang, Hongyu Sun, Zhebin Zhang, Chen Li, Yanwen Guo", + "authors": [ + { + "first_name": "Zhenyu", + "last_name": "Chen" + }, + { + "first_name": "Jie", + "last_name": "Guo" + }, + { + "first_name": "Shuichang", + "last_name": "Lai" + }, + { + "first_name": "Ruoyu", + "last_name": "Fu" + }, + { + "first_name": "Mengxun", + "last_name": "Kong" + }, + { + "first_name": "Chen", + "last_name": "Wang" + }, + { + "first_name": "Hongyu", + "last_name": "Sun" + }, + { + "first_name": "Zhebin", + "last_name": "Zhang" + }, + { + "first_name": "Chen", + "last_name": "Li" + }, + { + "first_name": "Yanwen", + "last_name": "Guo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "TurboSL: Dense Accurate and Fast 3D by Neural Inverse Structured Light", - "authors": "Parsa Mirdehghan, Maxx Wu, Wenzheng Chen, David B. Lindell, Kiriakos N. Kutulakos", + "authors": [ + { + "first_name": "Parsa", + "last_name": "Mirdehghan" + }, + { + "first_name": "Maxx", + "last_name": "Wu" + }, + { + "first_name": "Wenzheng", + "last_name": "Chen" + }, + { + "first_name": "David", + "last_name": "B. Lindell" + }, + { + "first_name": "Kiriakos", + "last_name": "N. Kutulakos" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Text2QR: Harmonizing Aesthetic Customization and Scanning Robustness for Text-Guided QR Code Generation", - "authors": "Guangyang Wu, Xiaohong Liu, Jun Jia, Xuehao Cui, Guangtao Zhai", + "authors": [ + { + "first_name": "Guangyang", + "last_name": "Wu" + }, + { + "first_name": "Xiaohong", + "last_name": "Liu" + }, + { + "first_name": "Jun", + "last_name": "Jia" + }, + { + "first_name": "Xuehao", + "last_name": "Cui" + }, + { + "first_name": "Guangtao", + "last_name": "Zhai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GS-IR: 3D Gaussian Splatting for Inverse Rendering", - "authors": "Zhihao Liang, Qi Zhang, Ying Feng, Ying Shan, Kui Jia", + "authors": [ + { + "first_name": "Zhihao", + "last_name": "Liang" + }, + { + "first_name": "Qi", + "last_name": "Zhang" + }, + { + "first_name": "Ying", + "last_name": "Feng" + }, + { + "first_name": "Ying", + "last_name": "Shan" + }, + { + "first_name": "Kui", + "last_name": "Jia" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SynFog: A Photo-realistic Synthetic Fog Dataset based on End-to-end Imaging Simulation for Advancing Real-World Defogging in Autonomous Driving", - "authors": "Yiming Xie, Henglu Wei, Zhenyi Liu, Xiaoyu Wang, Xiangyang Ji", + "authors": [ + { + "first_name": "Yiming", + "last_name": "Xie" + }, + { + "first_name": "Henglu", + "last_name": "Wei" + }, + { + "first_name": "Zhenyi", + "last_name": "Liu" + }, + { + "first_name": "Xiaoyu", + "last_name": "Wang" + }, + { + "first_name": "Xiangyang", + "last_name": "Ji" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Video Harmonization with Triplet Spatio-Temporal Variation Patterns", - "authors": "Zonghui Guo, Xinyu Han, Jie Zhang, Shiguang Shan, Haiyong Zheng", + "authors": [ + { + "first_name": "Zonghui", + "last_name": "Guo" + }, + { + "first_name": "Xinyu", + "last_name": "Han" + }, + { + "first_name": "Jie", + "last_name": "Zhang" + }, + { + "first_name": "Shiguang", + "last_name": "Shan" + }, + { + "first_name": "Haiyong", + "last_name": "Zheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "TRINS: Towards Multimodal Language Models that Can Read", - "authors": "Ruiyi Zhang, Yanzhe Zhang, Jian Chen, Yufan Zhou, Jiuxiang Gu, Changyou Chen, Tong Sun", + "authors": [ + { + "first_name": "Ruiyi", + "last_name": "Zhang" + }, + { + "first_name": "Yanzhe", + "last_name": "Zhang" + }, + { + "first_name": "Jian", + "last_name": "Chen" + }, + { + "first_name": "Yufan", + "last_name": "Zhou" + }, + { + "first_name": "Jiuxiang", + "last_name": "Gu" + }, + { + "first_name": "Changyou", + "last_name": "Chen" + }, + { + "first_name": "Tong", + "last_name": "Sun" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Self-Supervised Representation Learning from Arbitrary Scenarios", - "authors": "Zhaowen Li, Yousong Zhu, Zhiyang Chen, Zongxin Gao, Rui Zhao, Chaoyang Zhao, Ming Tang, Jinqiao Wang", + "authors": [ + { + "first_name": "Zhaowen", + "last_name": "Li" + }, + { + "first_name": "Yousong", + "last_name": "Zhu" + }, + { + "first_name": "Zhiyang", + "last_name": "Chen" + }, + { + "first_name": "Zongxin", + "last_name": "Gao" + }, + { + "first_name": "Rui", + "last_name": "Zhao" + }, + { + "first_name": "Chaoyang", + "last_name": "Zhao" + }, + { + "first_name": "Ming", + "last_name": "Tang" + }, + { + "first_name": "Jinqiao", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Improved Zero-Shot Classification by Adapting VLMs with Text Descriptions", - "authors": "Oindrila Saha, Grant Van Horn, Subhransu Maji", + "authors": [ + { + "first_name": "Oindrila", + "last_name": "Saha" + }, + { + "first_name": "Grant", + "last_name": "Van Horn" + }, + { + "first_name": "Subhransu", + "last_name": "Maji" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Living Scenes: Multi-object Relocalization and Reconstruction in Changing 3D Environments", - "authors": "Liyuan Zhu, Shengyu Huang, Konrad Schindler, Iro Armeni", + "authors": [ + { + "first_name": "Liyuan", + "last_name": "Zhu" + }, + { + "first_name": "Shengyu", + "last_name": "Huang" + }, + { + "first_name": "Konrad", + "last_name": "Schindler" + }, + { + "first_name": "Iro", + "last_name": "Armeni" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CricaVPR: Cross-image Correlation-aware Representation Learning for Visual Place Recognition", - "authors": "Feng Lu, Xiangyuan Lan, Lijun Zhang, Dongmei Jiang, Yaowei Wang, Chun Yuan", + "authors": [ + { + "first_name": "Feng", + "last_name": "Lu" + }, + { + "first_name": "Xiangyuan", + "last_name": "Lan" + }, + { + "first_name": "Lijun", + "last_name": "Zhang" + }, + { + "first_name": "Dongmei", + "last_name": "Jiang" + }, + { + "first_name": "Yaowei", + "last_name": "Wang" + }, + { + "first_name": "Chun", + "last_name": "Yuan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ECLIPSE: A Resource-Efficient Text-to-Image Prior for Image Generations", - "authors": "Maitreya Patel, Changhoon Kim, Sheng Cheng, Chitta Baral, Yezhou Yang", + "authors": [ + { + "first_name": "Maitreya", + "last_name": "Patel" + }, + { + "first_name": "Changhoon", + "last_name": "Kim" + }, + { + "first_name": "Sheng", + "last_name": "Cheng" + }, + { + "first_name": "Chitta", + "last_name": "Baral" + }, + { + "first_name": "Yezhou", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Adaptive Bidirectional Displacement for Semi-Supervised Medical Image Segmentation", - "authors": "Hanyang Chi, Jian Pang, Bingfeng Zhang, Weifeng Liu", + "authors": [ + { + "first_name": "Hanyang", + "last_name": "Chi" + }, + { + "first_name": "Jian", + "last_name": "Pang" + }, + { + "first_name": "Bingfeng", + "last_name": "Zhang" + }, + { + "first_name": "Weifeng", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Accurate Training Data for Occupancy Map Prediction in Automated Driving Using Evidence Theory", - "authors": "Jonas Kälble, Sascha Wirges, Maxim Tatarchenko, Eddy Ilg", + "authors": [ + { + "first_name": "Jonas", + "last_name": "Kälble" + }, + { + "first_name": "Sascha", + "last_name": "Wirges" + }, + { + "first_name": "Maxim", + "last_name": "Tatarchenko" + }, + { + "first_name": "Eddy", + "last_name": "Ilg" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DiffusionLight: Light Probes for Free by Painting a Chrome Ball", - "authors": "Pakkapon Phongthawee, Worameth Chinchuthakun, Nontaphat Sinsunthithet, Varun Jampani, Amit Raj, Pramook Khungurn, Supasorn Suwajanakorn", + "authors": [ + { + "first_name": "Pakkapon", + "last_name": "Phongthawee" + }, + { + "first_name": "Worameth", + "last_name": "Chinchuthakun" + }, + { + "first_name": "Nontaphat", + "last_name": "Sinsunthithet" + }, + { + "first_name": "Varun", + "last_name": "Jampani" + }, + { + "first_name": "Amit", + "last_name": "Raj" + }, + { + "first_name": "Pramook", + "last_name": "Khungurn" + }, + { + "first_name": "Supasorn", + "last_name": "Suwajanakorn" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Instance-level Expert Knowledge and Aggregate Discriminative Attention for Radiology Report Generation", - "authors": "Shenshen Bu, Taiji Li, Yuedong Yang, Zhiming Dai", + "authors": [ + { + "first_name": "Shenshen", + "last_name": "Bu" + }, + { + "first_name": "Taiji", + "last_name": "Li" + }, + { + "first_name": "Yuedong", + "last_name": "Yang" + }, + { + "first_name": "Zhiming", + "last_name": "Dai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Task-Adaptive Saliency Guidance for Exemplar-free Class Incremental Learning", - "authors": "Xialei Liu, Jiang-Tian Zhai, Andrew D. Bagdanov, Ke Li, Ming-Ming Cheng", + "authors": [ + { + "first_name": "Xialei", + "last_name": "Liu" + }, + { + "first_name": "Jiang-Tian", + "last_name": "Zhai" + }, + { + "first_name": "Andrew", + "last_name": "D. Bagdanov" + }, + { + "first_name": "Ke", + "last_name": "Li" + }, + { + "first_name": "Ming-Ming", + "last_name": "Cheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Rethinking the Spatial Inconsistency in Classifier-Free Diffusion Guidance", - "authors": "Dazhong Shen, Guanglu Song, Zeyue Xue, Fu-Yun Wang, Yu Liu", + "authors": [ + { + "first_name": "Dazhong", + "last_name": "Shen" + }, + { + "first_name": "Guanglu", + "last_name": "Song" + }, + { + "first_name": "Zeyue", + "last_name": "Xue" + }, + { + "first_name": "Fu-Yun", + "last_name": "Wang" + }, + { + "first_name": "Yu", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Language-driven All-in-one Adverse Weather Removal", - "authors": "Hao Yang, Liyuan Pan, Yan Yang, Wei Liang", + "authors": [ + { + "first_name": "Hao", + "last_name": "Yang" + }, + { + "first_name": "Liyuan", + "last_name": "Pan" + }, + { + "first_name": "Yan", + "last_name": "Yang" + }, + { + "first_name": "Wei", + "last_name": "Liang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Each Test Image Deserves A Specific Prompt: Continual Test-Time Adaptation for 2D Medical Image Segmentation", - "authors": "Ziyang Chen, Yongsheng Pan, Yiwen Ye, Mengkang Lu, Yong Xia", + "authors": [ + { + "first_name": "Ziyang", + "last_name": "Chen" + }, + { + "first_name": "Yongsheng", + "last_name": "Pan" + }, + { + "first_name": "Yiwen", + "last_name": "Ye" + }, + { + "first_name": "Mengkang", + "last_name": "Lu" + }, + { + "first_name": "Yong", + "last_name": "Xia" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human Pose Estimation", - "authors": "Jihua Peng, Yanghong Zhou, P. Y. Mok", + "authors": [ + { + "first_name": "Jihua", + "last_name": "Peng" + }, + { + "first_name": "Yanghong", + "last_name": "Zhou" + }, + { + "first_name": "P.", + "last_name": "Y. Mok" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MAPLM: A Real-World Large-Scale Vision-Language Benchmark for Map and Traffic Scene Understanding", - "authors": "Xu Cao, Tong Zhou, Yunsheng Ma, Wenqian Ye, Can Cui, Kun Tang, Zhipeng Cao, Kaizhao Liang, Ziran Wang, James M. Rehg, Chao Zheng", + "authors": [ + { + "first_name": "Xu", + "last_name": "Cao" + }, + { + "first_name": "Tong", + "last_name": "Zhou" + }, + { + "first_name": "Yunsheng", + "last_name": "Ma" + }, + { + "first_name": "Wenqian", + "last_name": "Ye" + }, + { + "first_name": "Can", + "last_name": "Cui" + }, + { + "first_name": "Kun", + "last_name": "Tang" + }, + { + "first_name": "Zhipeng", + "last_name": "Cao" + }, + { + "first_name": "Kaizhao", + "last_name": "Liang" + }, + { + "first_name": "Ziran", + "last_name": "Wang" + }, + { + "first_name": "James", + "last_name": "M. Rehg" + }, + { + "first_name": "Chao", + "last_name": "Zheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World", - "authors": "Yifei Huang, Guo Chen, Jilan Xu, Mingfang Zhang, Lijin Yang, Baoqi Pei, Hongjie Zhang, Lu Dong, Yali Wang, Limin Wang, Yu Qiao", + "authors": [ + { + "first_name": "Yifei", + "last_name": "Huang" + }, + { + "first_name": "Guo", + "last_name": "Chen" + }, + { + "first_name": "Jilan", + "last_name": "Xu" + }, + { + "first_name": "Mingfang", + "last_name": "Zhang" + }, + { + "first_name": "Lijin", + "last_name": "Yang" + }, + { + "first_name": "Baoqi", + "last_name": "Pei" + }, + { + "first_name": "Hongjie", + "last_name": "Zhang" + }, + { + "first_name": "Lu", + "last_name": "Dong" + }, + { + "first_name": "Yali", + "last_name": "Wang" + }, + { + "first_name": "Limin", + "last_name": "Wang" + }, + { + "first_name": "Yu", + "last_name": "Qiao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Differentiable Micro-Mesh Construction", - "authors": "Yishun Dou, Zhong Zheng, Qiaoqiao Jin, Rui Shi, Yuhan Li, Bingbing Ni", + "authors": [ + { + "first_name": "Yishun", + "last_name": "Dou" + }, + { + "first_name": "Zhong", + "last_name": "Zheng" + }, + { + "first_name": "Qiaoqiao", + "last_name": "Jin" + }, + { + "first_name": "Rui", + "last_name": "Shi" + }, + { + "first_name": "Yuhan", + "last_name": "Li" + }, + { + "first_name": "Bingbing", + "last_name": "Ni" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Improved Implicit Neural Representation with Fourier Reparameterized Training", - "authors": "Kexuan Shi, Xingyu Zhou, Shuhang Gu", + "authors": [ + { + "first_name": "Kexuan", + "last_name": "Shi" + }, + { + "first_name": "Xingyu", + "last_name": "Zhou" + }, + { + "first_name": "Shuhang", + "last_name": "Gu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SNED: Superposition Network Architecture Search for Efficient Video Diffusion Model", - "authors": "Zhengang Li, Yan Kang, Yuchen Liu, Difan Liu, Tobias Hinz, Feng Liu, Yanzhi Wang", + "authors": [ + { + "first_name": "Zhengang", + "last_name": "Li" + }, + { + "first_name": "Yan", + "last_name": "Kang" + }, + { + "first_name": "Yuchen", + "last_name": "Liu" + }, + { + "first_name": "Difan", + "last_name": "Liu" + }, + { + "first_name": "Tobias", + "last_name": "Hinz" + }, + { + "first_name": "Feng", + "last_name": "Liu" + }, + { + "first_name": "Yanzhi", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship Detection", - "authors": "Jongha Kim, Jihwan Park, Jinyoung Park, Jinyoung Kim, Sehyung Kim, Hyunwoo J. Kim", + "authors": [ + { + "first_name": "Jongha", + "last_name": "Kim" + }, + { + "first_name": "Jihwan", + "last_name": "Park" + }, + { + "first_name": "Jinyoung", + "last_name": "Park" + }, + { + "first_name": "Jinyoung", + "last_name": "Kim" + }, + { + "first_name": "Sehyung", + "last_name": "Kim" + }, + { + "first_name": "Hyunwoo", + "last_name": "J. Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LeftRefill: Filling Right Canvas based on Left Reference through Generalized Text-to-Image Diffusion Model", - "authors": "Chenjie Cao, Yunuo Cai, Qiaole Dong, Yikai Wang, Yanwei Fu", + "authors": [ + { + "first_name": "Chenjie", + "last_name": "Cao" + }, + { + "first_name": "Yunuo", + "last_name": "Cai" + }, + { + "first_name": "Qiaole", + "last_name": "Dong" + }, + { + "first_name": "Yikai", + "last_name": "Wang" + }, + { + "first_name": "Yanwei", + "last_name": "Fu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Personalized Residuals for Concept-Driven Text-to-Image Generation", - "authors": "Cusuh Ham, Matthew Fisher, James Hays, Nicholas Kolkin, Yuchen Liu, Richard Zhang, Tobias Hinz", + "authors": [ + { + "first_name": "Cusuh", + "last_name": "Ham" + }, + { + "first_name": "Matthew", + "last_name": "Fisher" + }, + { + "first_name": "James", + "last_name": "Hays" + }, + { + "first_name": "Nicholas", + "last_name": "Kolkin" + }, + { + "first_name": "Yuchen", + "last_name": "Liu" + }, + { + "first_name": "Richard", + "last_name": "Zhang" + }, + { + "first_name": "Tobias", + "last_name": "Hinz" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Condition-Aware Neural Network for Controlled Image Generation", - "authors": "Han Cai, Muyang Li, Qinsheng Zhang, Ming-Yu Liu, Song Han", + "authors": [ + { + "first_name": "Han", + "last_name": "Cai" + }, + { + "first_name": "Muyang", + "last_name": "Li" + }, + { + "first_name": "Qinsheng", + "last_name": "Zhang" + }, + { + "first_name": "Ming-Yu", + "last_name": "Liu" + }, + { + "first_name": "Song", + "last_name": "Han" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Versatile Navigation Under Partial Observability via Value-guided Diffusion Policy", - "authors": "Gengyu Zhang, Hao Tang, Yan Yan", + "authors": [ + { + "first_name": "Gengyu", + "last_name": "Zhang" + }, + { + "first_name": "Hao", + "last_name": "Tang" + }, + { + "first_name": "Yan", + "last_name": "Yan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "All in One Framework for Multimodal Re-identification in the Wild", - "authors": "He Li, Mang Ye, Ming Zhang, Bo Du", + "authors": [ + { + "first_name": "He", + "last_name": "Li" + }, + { + "first_name": "Mang", + "last_name": "Ye" + }, + { + "first_name": "Ming", + "last_name": "Zhang" + }, + { + "first_name": "Bo", + "last_name": "Du" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Looking 3D: Anomaly Detection with 2D-3D Alignment", - "authors": "Ankan Bhunia, Changjian Li, Hakan Bilen", + "authors": [ + { + "first_name": "Ankan", + "last_name": "Bhunia" + }, + { + "first_name": "Changjian", + "last_name": "Li" + }, + { + "first_name": "Hakan", + "last_name": "Bilen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Purified and Unified Steganographic Network", - "authors": "Guobiao Li, Sheng Li, Zicong Luo, Zhenxing Qian, Xinpeng Zhang", + "authors": [ + { + "first_name": "Guobiao", + "last_name": "Li" + }, + { + "first_name": "Sheng", + "last_name": "Li" + }, + { + "first_name": "Zicong", + "last_name": "Luo" + }, + { + "first_name": "Zhenxing", + "last_name": "Qian" + }, + { + "first_name": "Xinpeng", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "VS: Reconstructing Clothed 3D Human from Single Image via Vertex Shift", - "authors": "Leyuan Liu, Yuhan Li, Yunqi Gao, Changxin Gao, Yuanyuan Liu, Jingying Chen", + "authors": [ + { + "first_name": "Leyuan", + "last_name": "Liu" + }, + { + "first_name": "Yuhan", + "last_name": "Li" + }, + { + "first_name": "Yunqi", + "last_name": "Gao" + }, + { + "first_name": "Changxin", + "last_name": "Gao" + }, + { + "first_name": "Yuanyuan", + "last_name": "Liu" + }, + { + "first_name": "Jingying", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PARA-Drive: Parallelized Architecture for Real-time Autonomous Driving", - "authors": "Xinshuo Weng, Boris Ivanovic, Yan Wang, Yue Wang, Marco Pavone", + "authors": [ + { + "first_name": "Xinshuo", + "last_name": "Weng" + }, + { + "first_name": "Boris", + "last_name": "Ivanovic" + }, + { + "first_name": "Yan", + "last_name": "Wang" + }, + { + "first_name": "Yue", + "last_name": "Wang" + }, + { + "first_name": "Marco", + "last_name": "Pavone" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "TEA: Test-time Energy Adaptation", - "authors": "Yige Yuan, Bingbing Xu, Liang Hou, Fei Sun, Huawei Shen, Xueqi Cheng", + "authors": [ + { + "first_name": "Yige", + "last_name": "Yuan" + }, + { + "first_name": "Bingbing", + "last_name": "Xu" + }, + { + "first_name": "Liang", + "last_name": "Hou" + }, + { + "first_name": "Fei", + "last_name": "Sun" + }, + { + "first_name": "Huawei", + "last_name": "Shen" + }, + { + "first_name": "Xueqi", + "last_name": "Cheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "NEAT: Distilling 3D Wireframes from Neural Attraction Fields", - "authors": "Nan Xue, Bin Tan, Yuxi Xiao, Liang Dong, Gui-Song Xia, Tianfu Wu, Yujun Shen", + "authors": [ + { + "first_name": "Nan", + "last_name": "Xue" + }, + { + "first_name": "Bin", + "last_name": "Tan" + }, + { + "first_name": "Yuxi", + "last_name": "Xiao" + }, + { + "first_name": "Liang", + "last_name": "Dong" + }, + { + "first_name": "Gui-Song", + "last_name": "Xia" + }, + { + "first_name": "Tianfu", + "last_name": "Wu" + }, + { + "first_name": "Yujun", + "last_name": "Shen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Prompt Augmentation for Self-supervised Text-guided Image Manipulation", - "authors": "Rumeysa Bodur, Binod Bhattarai, Tae-Kyun Kim", + "authors": [ + { + "first_name": "Rumeysa", + "last_name": "Bodur" + }, + { + "first_name": "Binod", + "last_name": "Bhattarai" + }, + { + "first_name": "Tae-Kyun", + "last_name": "Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Pink: Unveiling the Power of Referential Comprehension for Multi-modal LLMs", - "authors": "Shiyu Xuan, Qingpei Guo, Ming Yang, Shiliang Zhang", + "authors": [ + { + "first_name": "Shiyu", + "last_name": "Xuan" + }, + { + "first_name": "Qingpei", + "last_name": "Guo" + }, + { + "first_name": "Ming", + "last_name": "Yang" + }, + { + "first_name": "Shiliang", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LDP: Language-driven Dual-Pixel Image Defocus Deblurring Network", - "authors": "Hao Yang, Liyuan Pan, Yan Yang, Richard Hartley, Miaomiao Liu", + "authors": [ + { + "first_name": "Hao", + "last_name": "Yang" + }, + { + "first_name": "Liyuan", + "last_name": "Pan" + }, + { + "first_name": "Yan", + "last_name": "Yang" + }, + { + "first_name": "Richard", + "last_name": "Hartley" + }, + { + "first_name": "Miaomiao", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MMSum: A Dataset for Multimodal Summarization and Thumbnail Generation of Videos", - "authors": "Jielin Qiu, Jiacheng Zhu, William Han, Aditesh Kumar, Karthik Mittal, Claire Jin, Zhengyuan Yang, Linjie Li, Jianfeng Wang, Ding Zhao, Bo Li, Lijuan Wang", + "authors": [ + { + "first_name": "Jielin", + "last_name": "Qiu" + }, + { + "first_name": "Jiacheng", + "last_name": "Zhu" + }, + { + "first_name": "William", + "last_name": "Han" + }, + { + "first_name": "Aditesh", + "last_name": "Kumar" + }, + { + "first_name": "Karthik", + "last_name": "Mittal" + }, + { + "first_name": "Claire", + "last_name": "Jin" + }, + { + "first_name": "Zhengyuan", + "last_name": "Yang" + }, + { + "first_name": "Linjie", + "last_name": "Li" + }, + { + "first_name": "Jianfeng", + "last_name": "Wang" + }, + { + "first_name": "Ding", + "last_name": "Zhao" + }, + { + "first_name": "Bo", + "last_name": "Li" + }, + { + "first_name": "Lijuan", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data", - "authors": "Qifan Yu, Juncheng Li, Longhui Wei, Liang Pang, Wentao Ye, Bosheng Qin, Siliang Tang, Qi Tian, Yueting Zhuang", + "authors": [ + { + "first_name": "Qifan", + "last_name": "Yu" + }, + { + "first_name": "Juncheng", + "last_name": "Li" + }, + { + "first_name": "Longhui", + "last_name": "Wei" + }, + { + "first_name": "Liang", + "last_name": "Pang" + }, + { + "first_name": "Wentao", + "last_name": "Ye" + }, + { + "first_name": "Bosheng", + "last_name": "Qin" + }, + { + "first_name": "Siliang", + "last_name": "Tang" + }, + { + "first_name": "Qi", + "last_name": "Tian" + }, + { + "first_name": "Yueting", + "last_name": "Zhuang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Pre-trained Vision and Language Transformers Are Few-Shot Incremental Learners", - "authors": "Keon-Hee Park, Kyungwoo Song, Gyeong-Moon Park", + "authors": [ + { + "first_name": "Keon-Hee", + "last_name": "Park" + }, + { + "first_name": "Kyungwoo", + "last_name": "Song" + }, + { + "first_name": "Gyeong-Moon", + "last_name": "Park" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Guess The Unseen: Dynamic 3D Scene Reconstruction from Partial 2D Glimpses", - "authors": "Inhee Lee, Byungjun Kim, Hanbyul Joo", + "authors": [ + { + "first_name": "Inhee", + "last_name": "Lee" + }, + { + "first_name": "Byungjun", + "last_name": "Kim" + }, + { + "first_name": "Hanbyul", + "last_name": "Joo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "C^2RV: Cross-Regional and Cross-View Learning for Sparse-View CBCT Reconstruction", - "authors": "Yiqun Lin, Jiewen Yang, Hualiang Wang, Xinpeng Ding, Wei Zhao, Xiaomeng Li", + "authors": [ + { + "first_name": "Yiqun", + "last_name": "Lin" + }, + { + "first_name": "Jiewen", + "last_name": "Yang" + }, + { + "first_name": "Hualiang", + "last_name": "Wang" + }, + { + "first_name": "Xinpeng", + "last_name": "Ding" + }, + { + "first_name": "Wei", + "last_name": "Zhao" + }, + { + "first_name": "Xiaomeng", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HyperDreamBooth: HyperNetworks for Fast Personalization of Text-to-Image Models", - "authors": "Nataniel Ruiz, Yuanzhen Li, Varun Jampani, Wei Wei, Tingbo Hou, Yael Pritch, Neal Wadhwa, Michael Rubinstein, Kfir Aberman", + "authors": [ + { + "first_name": "Nataniel", + "last_name": "Ruiz" + }, + { + "first_name": "Yuanzhen", + "last_name": "Li" + }, + { + "first_name": "Varun", + "last_name": "Jampani" + }, + { + "first_name": "Wei", + "last_name": "Wei" + }, + { + "first_name": "Tingbo", + "last_name": "Hou" + }, + { + "first_name": "Yael", + "last_name": "Pritch" + }, + { + "first_name": "Neal", + "last_name": "Wadhwa" + }, + { + "first_name": "Michael", + "last_name": "Rubinstein" + }, + { + "first_name": "Kfir", + "last_name": "Aberman" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Language-guided Image Reflection Separation", - "authors": "Haofeng Zhong, Yuchen Hong, Shuchen Weng, Jinxiu Liang, Boxin Shi", + "authors": [ + { + "first_name": "Haofeng", + "last_name": "Zhong" + }, + { + "first_name": "Yuchen", + "last_name": "Hong" + }, + { + "first_name": "Shuchen", + "last_name": "Weng" + }, + { + "first_name": "Jinxiu", + "last_name": "Liang" + }, + { + "first_name": "Boxin", + "last_name": "Shi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HardMo: A Large-Scale Hardcase Dataset for Motion Capture", - "authors": "Jiaqi Liao, Chuanchen Luo, Yinuo Du, Yuxi Wang, Xucheng Yin, Man Zhang, Zhaoxiang Zhang, Junran Peng", + "authors": [ + { + "first_name": "Jiaqi", + "last_name": "Liao" + }, + { + "first_name": "Chuanchen", + "last_name": "Luo" + }, + { + "first_name": "Yinuo", + "last_name": "Du" + }, + { + "first_name": "Yuxi", + "last_name": "Wang" + }, + { + "first_name": "Xucheng", + "last_name": "Yin" + }, + { + "first_name": "Man", + "last_name": "Zhang" + }, + { + "first_name": "Zhaoxiang", + "last_name": "Zhang" + }, + { + "first_name": "Junran", + "last_name": "Peng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "View-Category Interactive Sharing Transformer for Incomplete Multi-View Multi-Label Learning", - "authors": "Shilong Ou, Zhe Xue, Yawen Li, Meiyu Liang, Yuanqiang Cai, Junjiang Wu", + "authors": [ + { + "first_name": "Shilong", + "last_name": "Ou" + }, + { + "first_name": "Zhe", + "last_name": "Xue" + }, + { + "first_name": "Yawen", + "last_name": "Li" + }, + { + "first_name": "Meiyu", + "last_name": "Liang" + }, + { + "first_name": "Yuanqiang", + "last_name": "Cai" + }, + { + "first_name": "Junjiang", + "last_name": "Wu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "The More You See in 2D the More You Perceive in 3D", - "authors": "Xinyang Han, Zelin Gao, Angjoo Kanazawa, Shubham Goel, Yossi Gandelsman", + "authors": [ + { + "first_name": "Xinyang", + "last_name": "Han" + }, + { + "first_name": "Zelin", + "last_name": "Gao" + }, + { + "first_name": "Angjoo", + "last_name": "Kanazawa" + }, + { + "first_name": "Shubham", + "last_name": "Goel" + }, + { + "first_name": "Yossi", + "last_name": "Gandelsman" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GLiDR: Topologically Regularized Graph Generative Network for Sparse LiDAR Point Clouds", - "authors": "Prashant Kumar, Kshitij Madhav Bhat, Vedang Bhupesh Shenvi Nadkarni, Prem Kalra", + "authors": [ + { + "first_name": "Prashant", + "last_name": "Kumar" + }, + { + "first_name": "Kshitij", + "last_name": "Madhav Bhat" + }, + { + "first_name": "Vedang", + "last_name": "Bhupesh Shenvi Nadkarni" + }, + { + "first_name": "Prem", + "last_name": "Kalra" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Separate and Conquer: Decoupling Co-occurrence via Decomposition and Representation for Weakly Supervised Semantic Segmentation", - "authors": "Zhiwei Yang, Kexue Fu, Minghong Duan, Linhao Qu, Shuo Wang, Zhijian Song", + "authors": [ + { + "first_name": "Zhiwei", + "last_name": "Yang" + }, + { + "first_name": "Kexue", + "last_name": "Fu" + }, + { + "first_name": "Minghong", + "last_name": "Duan" + }, + { + "first_name": "Linhao", + "last_name": "Qu" + }, + { + "first_name": "Shuo", + "last_name": "Wang" + }, + { + "first_name": "Zhijian", + "last_name": "Song" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "BiPer: Binary Neural Networks using a Periodic Function", - "authors": "Edwin Vargas, Claudia V. Correa, Carlos Hinojosa, Henry Arguello", + "authors": [ + { + "first_name": "Edwin", + "last_name": "Vargas" + }, + { + "first_name": "Claudia", + "last_name": "V. Correa" + }, + { + "first_name": "Carlos", + "last_name": "Hinojosa" + }, + { + "first_name": "Henry", + "last_name": "Arguello" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Unifying Automatic and Interactive Matting with Pretrained ViTs", - "authors": "Zixuan Ye, Wenze Liu, He Guo, Yujia Liang, Chaoyi Hong, Hao Lu, Zhiguo Cao", + "authors": [ + { + "first_name": "Zixuan", + "last_name": "Ye" + }, + { + "first_name": "Wenze", + "last_name": "Liu" + }, + { + "first_name": "He", + "last_name": "Guo" + }, + { + "first_name": "Yujia", + "last_name": "Liang" + }, + { + "first_name": "Chaoyi", + "last_name": "Hong" + }, + { + "first_name": "Hao", + "last_name": "Lu" + }, + { + "first_name": "Zhiguo", + "last_name": "Cao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Segment Any Event Streams via Weighted Adaptation of Pivotal Tokens", - "authors": "Zhiwen Chen, Zhiyu Zhu, Yifan Zhang, Junhui Hou, Guangming Shi, Jinjian Wu", + "authors": [ + { + "first_name": "Zhiwen", + "last_name": "Chen" + }, + { + "first_name": "Zhiyu", + "last_name": "Zhu" + }, + { + "first_name": "Yifan", + "last_name": "Zhang" + }, + { + "first_name": "Junhui", + "last_name": "Hou" + }, + { + "first_name": "Guangming", + "last_name": "Shi" + }, + { + "first_name": "Jinjian", + "last_name": "Wu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "AnyDoor: Zero-shot Object-level Image Customization", - "authors": "Xi Chen, Lianghua Huang, Yu Liu, Yujun Shen, Deli Zhao, Hengshuang Zhao", + "authors": [ + { + "first_name": "Xi", + "last_name": "Chen" + }, + { + "first_name": "Lianghua", + "last_name": "Huang" + }, + { + "first_name": "Yu", + "last_name": "Liu" + }, + { + "first_name": "Yujun", + "last_name": "Shen" + }, + { + "first_name": "Deli", + "last_name": "Zhao" + }, + { + "first_name": "Hengshuang", + "last_name": "Zhao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Commonsense Prototype for Outdoor Unsupervised 3D Object Detection", - "authors": "Hai Wu, Shijia Zhao, Xun Huang, Chenglu Wen, Xin Li, Cheng Wang", + "authors": [ + { + "first_name": "Hai", + "last_name": "Wu" + }, + { + "first_name": "Shijia", + "last_name": "Zhao" + }, + { + "first_name": "Xun", + "last_name": "Huang" + }, + { + "first_name": "Chenglu", + "last_name": "Wen" + }, + { + "first_name": "Xin", + "last_name": "Li" + }, + { + "first_name": "Cheng", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Lookahead Exploration with Neural Radiance Representation for Continuous Vision-Language Navigation", - "authors": "Zihan Wang, Xiangyang Li, Jiahao Yang, Yeqi Liu, Junjie Hu, Ming Jiang, Shuqiang Jiang", + "authors": [ + { + "first_name": "Zihan", + "last_name": "Wang" + }, + { + "first_name": "Xiangyang", + "last_name": "Li" + }, + { + "first_name": "Jiahao", + "last_name": "Yang" + }, + { + "first_name": "Yeqi", + "last_name": "Liu" + }, + { + "first_name": "Junjie", + "last_name": "Hu" + }, + { + "first_name": "Ming", + "last_name": "Jiang" + }, + { + "first_name": "Shuqiang", + "last_name": "Jiang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Clustering Propagation for Universal Medical Image Segmentation", - "authors": "Yuhang Ding, Liulei Li, Wenguan Wang, Yi Yang", + "authors": [ + { + "first_name": "Yuhang", + "last_name": "Ding" + }, + { + "first_name": "Liulei", + "last_name": "Li" + }, + { + "first_name": "Wenguan", + "last_name": "Wang" + }, + { + "first_name": "Yi", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MoPE-CLIP: Structured Pruning for Efficient Vision-Language Models with Module-wise Pruning Error Metric", - "authors": "Haokun Lin, Haoli Bai, Zhili Liu, Lu Hou, Muyi Sun, Linqi Song, Ying Wei, Zhenan Sun", + "authors": [ + { + "first_name": "Haokun", + "last_name": "Lin" + }, + { + "first_name": "Haoli", + "last_name": "Bai" + }, + { + "first_name": "Zhili", + "last_name": "Liu" + }, + { + "first_name": "Lu", + "last_name": "Hou" + }, + { + "first_name": "Muyi", + "last_name": "Sun" + }, + { + "first_name": "Linqi", + "last_name": "Song" + }, + { + "first_name": "Ying", + "last_name": "Wei" + }, + { + "first_name": "Zhenan", + "last_name": "Sun" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning Vision from Models Rivals Learning Vision from Data", - "authors": "Yonglong Tian, Lijie Fan, Kaifeng Chen, Dina Katabi, Dilip Krishnan, Phillip Isola", + "authors": [ + { + "first_name": "Yonglong", + "last_name": "Tian" + }, + { + "first_name": "Lijie", + "last_name": "Fan" + }, + { + "first_name": "Kaifeng", + "last_name": "Chen" + }, + { + "first_name": "Dina", + "last_name": "Katabi" + }, + { + "first_name": "Dilip", + "last_name": "Krishnan" + }, + { + "first_name": "Phillip", + "last_name": "Isola" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Leveraging Frame Affinity for sRGB-to-RAW Video De-rendering", - "authors": "Chen Zhang, Wencheng Han, Yang Zhou, Jianbing Shen, Cheng-zhong Xu, Wentao Liu", + "authors": [ + { + "first_name": "Chen", + "last_name": "Zhang" + }, + { + "first_name": "Wencheng", + "last_name": "Han" + }, + { + "first_name": "Yang", + "last_name": "Zhou" + }, + { + "first_name": "Jianbing", + "last_name": "Shen" + }, + { + "first_name": "Cheng-zhong", + "last_name": "Xu" + }, + { + "first_name": "Wentao", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Adapting Short-Term Transformers for Action Detection in Untrimmed Videos", - "authors": "Min Yang, Huan Gao, Ping Guo, Limin Wang", + "authors": [ + { + "first_name": "Min", + "last_name": "Yang" + }, + { + "first_name": "Huan", + "last_name": "Gao" + }, + { + "first_name": "Ping", + "last_name": "Guo" + }, + { + "first_name": "Limin", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "The Mirrored Influence Hypothesis: Efficient Data Influence Estimation by Harnessing Forward Passes", - "authors": "Myeongseob Ko, Feiyang Kang, Weiyan Shi, Ming Jin, Zhou Yu, Ruoxi Jia", + "authors": [ + { + "first_name": "Myeongseob", + "last_name": "Ko" + }, + { + "first_name": "Feiyang", + "last_name": "Kang" + }, + { + "first_name": "Weiyan", + "last_name": "Shi" + }, + { + "first_name": "Ming", + "last_name": "Jin" + }, + { + "first_name": "Zhou", + "last_name": "Yu" + }, + { + "first_name": "Ruoxi", + "last_name": "Jia" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SOAC: Spatio-Temporal Overlap-Aware Multi-Sensor Calibration using Neural Radiance Fields", - "authors": "Quentin Herau, Nathan Piasco, Moussab Bennehar, Luis Roldao, Dzmitry Tsishkou, Cyrille Migniot, Pascal Vasseur, Cédric Demonceaux", + "authors": [ + { + "first_name": "Quentin", + "last_name": "Herau" + }, + { + "first_name": "Nathan", + "last_name": "Piasco" + }, + { + "first_name": "Moussab", + "last_name": "Bennehar" + }, + { + "first_name": "Luis", + "last_name": "Roldao" + }, + { + "first_name": "Dzmitry", + "last_name": "Tsishkou" + }, + { + "first_name": "Cyrille", + "last_name": "Migniot" + }, + { + "first_name": "Pascal", + "last_name": "Vasseur" + }, + { + "first_name": "Cédric", + "last_name": "Demonceaux" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "G^3-LQ: Marrying Hyperbolic Alignment with Explicit Semantic-Geometric Modeling for 3D Visual Grounding", - "authors": "Yuan Wang, Yali Li, Shengjin Wang", + "authors": [ + { + "first_name": "Yuan", + "last_name": "Wang" + }, + { + "first_name": "Yali", + "last_name": "Li" + }, + { + "first_name": "Shengjin", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Garment Recovery with Shape and Deformation Priors", - "authors": "Ren Li, Corentin Dumery, Benoît Guillard, Pascal Fua", + "authors": [ + { + "first_name": "Ren", + "last_name": "Li" + }, + { + "first_name": "Corentin", + "last_name": "Dumery" + }, + { + "first_name": "Benoît", + "last_name": "Guillard" + }, + { + "first_name": "Pascal", + "last_name": "Fua" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Psychometry: An Omnifit Model for Image Reconstruction from Human Brain Activity", - "authors": "Ruijie Quan, Wenguan Wang, Zhibo Tian, Fan Ma, Yi Yang", + "authors": [ + { + "first_name": "Ruijie", + "last_name": "Quan" + }, + { + "first_name": "Wenguan", + "last_name": "Wang" + }, + { + "first_name": "Zhibo", + "last_name": "Tian" + }, + { + "first_name": "Fan", + "last_name": "Ma" + }, + { + "first_name": "Yi", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Exploring Regional Clues in CLIP for Zero-Shot Semantic Segmentation", - "authors": "Yi Zhang, Meng-Hao Guo, Miao Wang, Shi-Min Hu", + "authors": [ + { + "first_name": "Yi", + "last_name": "Zhang" + }, + { + "first_name": "Meng-Hao", + "last_name": "Guo" + }, + { + "first_name": "Miao", + "last_name": "Wang" + }, + { + "first_name": "Shi-Min", + "last_name": "Hu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Move as You Say Interact as You Can: Language-guided Human Motion Generation with Scene Affordance", - "authors": "Zan Wang, Yixin Chen, Baoxiong Jia, Puhao Li, Jinlu Zhang, Jingze Zhang, Tengyu Liu, Yixin Zhu, Wei Liang, Siyuan Huang", + "authors": [ + { + "first_name": "Zan", + "last_name": "Wang" + }, + { + "first_name": "Yixin", + "last_name": "Chen" + }, + { + "first_name": "Baoxiong", + "last_name": "Jia" + }, + { + "first_name": "Puhao", + "last_name": "Li" + }, + { + "first_name": "Jinlu", + "last_name": "Zhang" + }, + { + "first_name": "Jingze", + "last_name": "Zhang" + }, + { + "first_name": "Tengyu", + "last_name": "Liu" + }, + { + "first_name": "Yixin", + "last_name": "Zhu" + }, + { + "first_name": "Wei", + "last_name": "Liang" + }, + { + "first_name": "Siyuan", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Choose What You Need: Disentangled Representation Learning for Scene Text Recognition Removal and Editing", - "authors": "Boqiang Zhang, Hongtao Xie, Zuan Gao, Yuxin Wang", + "authors": [ + { + "first_name": "Boqiang", + "last_name": "Zhang" + }, + { + "first_name": "Hongtao", + "last_name": "Xie" + }, + { + "first_name": "Zuan", + "last_name": "Gao" + }, + { + "first_name": "Yuxin", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Generalizable Face Landmarking Guided by Conditional Face Warping", - "authors": "Jiayi Liang, Haotian Liu, Hongteng Xu, Dixin Luo", + "authors": [ + { + "first_name": "Jiayi", + "last_name": "Liang" + }, + { + "first_name": "Haotian", + "last_name": "Liu" + }, + { + "first_name": "Hongteng", + "last_name": "Xu" + }, + { + "first_name": "Dixin", + "last_name": "Luo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Sat2Scene: 3D Urban Scene Generation from Satellite Images with Diffusion", - "authors": "Zuoyue Li, Zhenqiang Li, Zhaopeng Cui, Marc Pollefeys, Martin R. Oswald", + "authors": [ + { + "first_name": "Zuoyue", + "last_name": "Li" + }, + { + "first_name": "Zhenqiang", + "last_name": "Li" + }, + { + "first_name": "Zhaopeng", + "last_name": "Cui" + }, + { + "first_name": "Marc", + "last_name": "Pollefeys" + }, + { + "first_name": "Martin", + "last_name": "R. Oswald" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Control4D: Efficient 4D Portrait Editing with Text", - "authors": "Ruizhi Shao, Jingxiang Sun, Cheng Peng, Zerong Zheng, Boyao Zhou, Hongwen Zhang, Yebin Liu", + "authors": [ + { + "first_name": "Ruizhi", + "last_name": "Shao" + }, + { + "first_name": "Jingxiang", + "last_name": "Sun" + }, + { + "first_name": "Cheng", + "last_name": "Peng" + }, + { + "first_name": "Zerong", + "last_name": "Zheng" + }, + { + "first_name": "Boyao", + "last_name": "Zhou" + }, + { + "first_name": "Hongwen", + "last_name": "Zhang" + }, + { + "first_name": "Yebin", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Symphonize 3D Semantic Scene Completion with Contextual Instance Queries", - "authors": "Haoyi Jiang, Tianheng Cheng, Naiyu Gao, Haoyang Zhang, Tianwei Lin, Wenyu Liu, Xinggang Wang", + "authors": [ + { + "first_name": "Haoyi", + "last_name": "Jiang" + }, + { + "first_name": "Tianheng", + "last_name": "Cheng" + }, + { + "first_name": "Naiyu", + "last_name": "Gao" + }, + { + "first_name": "Haoyang", + "last_name": "Zhang" + }, + { + "first_name": "Tianwei", + "last_name": "Lin" + }, + { + "first_name": "Wenyu", + "last_name": "Liu" + }, + { + "first_name": "Xinggang", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Loopy-SLAM: Dense Neural SLAM with Loop Closures", - "authors": "Lorenzo Liso, Erik Sandström, Vladimir Yugay, Luc Van Gool, Martin R. Oswald", + "authors": [ + { + "first_name": "Lorenzo", + "last_name": "Liso" + }, + { + "first_name": "Erik", + "last_name": "Sandström" + }, + { + "first_name": "Vladimir", + "last_name": "Yugay" + }, + { + "first_name": "Luc", + "last_name": "Van Gool" + }, + { + "first_name": "Martin", + "last_name": "R. Oswald" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CLIPtone: Unsupervised Learning for Text-based Image Tone Adjustment", - "authors": "Hyeongmin Lee, Kyoungkook Kang, Jungseul Ok, Sunghyun Cho", + "authors": [ + { + "first_name": "Hyeongmin", + "last_name": "Lee" + }, + { + "first_name": "Kyoungkook", + "last_name": "Kang" + }, + { + "first_name": "Jungseul", + "last_name": "Ok" + }, + { + "first_name": "Sunghyun", + "last_name": "Cho" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ToonerGAN: Reinforcing GANs for Obfuscating Automated Facial Indexing", - "authors": "Kartik Thakral, Shashikant Prasad, Stuti Aswani, Mayank Vatsa, Richa Singh", + "authors": [ + { + "first_name": "Kartik", + "last_name": "Thakral" + }, + { + "first_name": "Shashikant", + "last_name": "Prasad" + }, + { + "first_name": "Stuti", + "last_name": "Aswani" + }, + { + "first_name": "Mayank", + "last_name": "Vatsa" + }, + { + "first_name": "Richa", + "last_name": "Singh" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Content-Adaptive Non-Local Convolution for Remote Sensing Pansharpening", - "authors": "Yule Duan, Xiao Wu, Haoyu Deng, Liang-Jian Deng", + "authors": [ + { + "first_name": "Yule", + "last_name": "Duan" + }, + { + "first_name": "Xiao", + "last_name": "Wu" + }, + { + "first_name": "Haoyu", + "last_name": "Deng" + }, + { + "first_name": "Liang-Jian", + "last_name": "Deng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Codebook Transfer with Part-of-Speech for Vector-Quantized Image Modeling", - "authors": "Baoquan Zhang, Huaibin Wang, Chuyao Luo, Xutao Li, Guotao Liang, Yunming Ye, Xiaochen Qi, Yao He", + "authors": [ + { + "first_name": "Baoquan", + "last_name": "Zhang" + }, + { + "first_name": "Huaibin", + "last_name": "Wang" + }, + { + "first_name": "Chuyao", + "last_name": "Luo" + }, + { + "first_name": "Xutao", + "last_name": "Li" + }, + { + "first_name": "Guotao", + "last_name": "Liang" + }, + { + "first_name": "Yunming", + "last_name": "Ye" + }, + { + "first_name": "Xiaochen", + "last_name": "Qi" + }, + { + "first_name": "Yao", + "last_name": "He" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning Inclusion Matching for Animation Paint Bucket Colorization", - "authors": "Yuekun Dai, Shangchen Zhou, Qinyue Li, Chongyi Li, Chen Change Loy", + "authors": [ + { + "first_name": "Yuekun", + "last_name": "Dai" + }, + { + "first_name": "Shangchen", + "last_name": "Zhou" + }, + { + "first_name": "Qinyue", + "last_name": "Li" + }, + { + "first_name": "Chongyi", + "last_name": "Li" + }, + { + "first_name": "Chen", + "last_name": "Change Loy" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Editable Scene Simulation for Autonomous Driving via Collaborative LLM-Agents", - "authors": "Yuxi Wei, Zi Wang, Yifan Lu, Chenxin Xu, Changxing Liu, Hao Zhao, Siheng Chen, Yanfeng Wang", + "authors": [ + { + "first_name": "Yuxi", + "last_name": "Wei" + }, + { + "first_name": "Zi", + "last_name": "Wang" + }, + { + "first_name": "Yifan", + "last_name": "Lu" + }, + { + "first_name": "Chenxin", + "last_name": "Xu" + }, + { + "first_name": "Changxing", + "last_name": "Liu" + }, + { + "first_name": "Hao", + "last_name": "Zhao" + }, + { + "first_name": "Siheng", + "last_name": "Chen" + }, + { + "first_name": "Yanfeng", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation", - "authors": "Jiehong Lin, Lihua Liu, Dekun Lu, Kui Jia", + "authors": [ + { + "first_name": "Jiehong", + "last_name": "Lin" + }, + { + "first_name": "Lihua", + "last_name": "Liu" + }, + { + "first_name": "Dekun", + "last_name": "Lu" + }, + { + "first_name": "Kui", + "last_name": "Jia" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "InceptionNeXt: When Inception Meets ConvNeXt", - "authors": "Weihao Yu, Pan Zhou, Shuicheng Yan, Xinchao Wang", + "authors": [ + { + "first_name": "Weihao", + "last_name": "Yu" + }, + { + "first_name": "Pan", + "last_name": "Zhou" + }, + { + "first_name": "Shuicheng", + "last_name": "Yan" + }, + { + "first_name": "Xinchao", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SnAG: Scalable and Accurate Video Grounding", - "authors": "Fangzhou Mu, Sicheng Mo, Yin Li", + "authors": [ + { + "first_name": "Fangzhou", + "last_name": "Mu" + }, + { + "first_name": "Sicheng", + "last_name": "Mo" + }, + { + "first_name": "Yin", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformers", - "authors": "Ioannis Kakogeorgiou, Spyros Gidaris, Konstantinos Karantzalos, Nikos Komodakis", + "authors": [ + { + "first_name": "Ioannis", + "last_name": "Kakogeorgiou" + }, + { + "first_name": "Spyros", + "last_name": "Gidaris" + }, + { + "first_name": "Konstantinos", + "last_name": "Karantzalos" + }, + { + "first_name": "Nikos", + "last_name": "Komodakis" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LiveHPS: LiDAR-based Scene-level Human Pose and Shape Estimation in Free Environment", - "authors": "Yiming Ren, Xiao Han, Chengfeng Zhao, Jingya Wang, Lan Xu, Jingyi Yu, Yuexin Ma", + "authors": [ + { + "first_name": "Yiming", + "last_name": "Ren" + }, + { + "first_name": "Xiao", + "last_name": "Han" + }, + { + "first_name": "Chengfeng", + "last_name": "Zhao" + }, + { + "first_name": "Jingya", + "last_name": "Wang" + }, + { + "first_name": "Lan", + "last_name": "Xu" + }, + { + "first_name": "Jingyi", + "last_name": "Yu" + }, + { + "first_name": "Yuexin", + "last_name": "Ma" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Segment Every Out-of-Distribution Object", - "authors": "Wenjie Zhao, Jia Li, Xin Dong, Yu Xiang, Yunhui Guo", + "authors": [ + { + "first_name": "Wenjie", + "last_name": "Zhao" + }, + { + "first_name": "Jia", + "last_name": "Li" + }, + { + "first_name": "Xin", + "last_name": "Dong" + }, + { + "first_name": "Yu", + "last_name": "Xiang" + }, + { + "first_name": "Yunhui", + "last_name": "Guo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Building Vision-Language Models on Solid Foundations with Masked Distillation", - "authors": "Sepehr Sameni, Kushal Kafle, Hao Tan, Simon Jenni", + "authors": [ + { + "first_name": "Sepehr", + "last_name": "Sameni" + }, + { + "first_name": "Kushal", + "last_name": "Kafle" + }, + { + "first_name": "Hao", + "last_name": "Tan" + }, + { + "first_name": "Simon", + "last_name": "Jenni" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Wavelet-based Fourier Information Interaction with Frequency Diffusion Adjustment for Underwater Image Restoration", - "authors": "Chen Zhao, Weiling Cai, Chenyu Dong, Chengwei Hu", + "authors": [ + { + "first_name": "Chen", + "last_name": "Zhao" + }, + { + "first_name": "Weiling", + "last_name": "Cai" + }, + { + "first_name": "Chenyu", + "last_name": "Dong" + }, + { + "first_name": "Chengwei", + "last_name": "Hu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CroSel: Cross Selection of Confident Pseudo Labels for Partial-Label Learning", - "authors": "Shiyu Tian, Hongxin Wei, Yiqun Wang, Lei Feng", + "authors": [ + { + "first_name": "Shiyu", + "last_name": "Tian" + }, + { + "first_name": "Hongxin", + "last_name": "Wei" + }, + { + "first_name": "Yiqun", + "last_name": "Wang" + }, + { + "first_name": "Lei", + "last_name": "Feng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PoNQ: a Neural QEM-based Mesh Representation", - "authors": "Nissim Maruani, Maks Ovsjanikov, Pierre Alliez, Mathieu Desbrun", + "authors": [ + { + "first_name": "Nissim", + "last_name": "Maruani" + }, + { + "first_name": "Maks", + "last_name": "Ovsjanikov" + }, + { + "first_name": "Pierre", + "last_name": "Alliez" + }, + { + "first_name": "Mathieu", + "last_name": "Desbrun" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ModaVerse: Efficiently Transforming Modalities with LLMs", - "authors": "Xinyu Wang, Bohan Zhuang, Qi Wu", + "authors": [ + { + "first_name": "Xinyu", + "last_name": "Wang" + }, + { + "first_name": "Bohan", + "last_name": "Zhuang" + }, + { + "first_name": "Qi", + "last_name": "Wu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "TransLoc4D: Transformer-based 4D Radar Place Recognition", - "authors": "Guohao Peng, Heshan Li, Yangyang Zhao, Jun Zhang, Zhenyu Wu, Pengyu Zheng, Danwei Wang", + "authors": [ + { + "first_name": "Guohao", + "last_name": "Peng" + }, + { + "first_name": "Heshan", + "last_name": "Li" + }, + { + "first_name": "Yangyang", + "last_name": "Zhao" + }, + { + "first_name": "Jun", + "last_name": "Zhang" + }, + { + "first_name": "Zhenyu", + "last_name": "Wu" + }, + { + "first_name": "Pengyu", + "last_name": "Zheng" + }, + { + "first_name": "Danwei", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Frequency-aware Event-based Video Deblurring for Real-World Motion Blur", - "authors": "Taewoo Kim, Hoonhee Cho, Kuk-Jin Yoon", + "authors": [ + { + "first_name": "Taewoo", + "last_name": "Kim" + }, + { + "first_name": "Hoonhee", + "last_name": "Cho" + }, + { + "first_name": "Kuk-Jin", + "last_name": "Yoon" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Multiscale Vision Transformers Meet Bipartite Matching for Efficient Single-stage Action Localization", - "authors": "Ioanna Ntinou, Enrique Sanchez, Georgios Tzimiropoulos", + "authors": [ + { + "first_name": "Ioanna", + "last_name": "Ntinou" + }, + { + "first_name": "Enrique", + "last_name": "Sanchez" + }, + { + "first_name": "Georgios", + "last_name": "Tzimiropoulos" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Boosting Order-Preserving and Transferability for Neural Architecture Search: a Joint Architecture Refined Search and Fine-tuning Approach", - "authors": "Beichen Zhang, Xiaoxing Wang, Xiaohan Qin, Junchi Yan", + "authors": [ + { + "first_name": "Beichen", + "last_name": "Zhang" + }, + { + "first_name": "Xiaoxing", + "last_name": "Wang" + }, + { + "first_name": "Xiaohan", + "last_name": "Qin" + }, + { + "first_name": "Junchi", + "last_name": "Yan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Dr. Bokeh: DiffeRentiable Occlusion-aware Bokeh Rendering", - "authors": "Yichen Sheng, Zixun Yu, Lu Ling, Zhiwen Cao, Xuaner Zhang, Xin Lu, Ke Xian, Haiting Lin, Bedrich Benes", + "authors": [ + { + "first_name": "Yichen", + "last_name": "Sheng" + }, + { + "first_name": "Zixun", + "last_name": "Yu" + }, + { + "first_name": "Lu", + "last_name": "Ling" + }, + { + "first_name": "Zhiwen", + "last_name": "Cao" + }, + { + "first_name": "Xuaner", + "last_name": "Zhang" + }, + { + "first_name": "Xin", + "last_name": "Lu" + }, + { + "first_name": "Ke", + "last_name": "Xian" + }, + { + "first_name": "Haiting", + "last_name": "Lin" + }, + { + "first_name": "Bedrich", + "last_name": "Benes" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Unsegment Anything by Simulating Deformation", - "authors": "Jiahao Lu, Xingyi Yang, Xinchao Wang", + "authors": [ + { + "first_name": "Jiahao", + "last_name": "Lu" + }, + { + "first_name": "Xingyi", + "last_name": "Yang" + }, + { + "first_name": "Xinchao", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Transductive Zero-Shot and Few-Shot CLIP", - "authors": "Ségolène Martin, Yunshi Huang, Fereshteh Shakeri, Jean-Christophe Pesquet, Ismail Ben Ayed", + "authors": [ + { + "first_name": "Ségolène", + "last_name": "Martin" + }, + { + "first_name": "Yunshi", + "last_name": "Huang" + }, + { + "first_name": "Fereshteh", + "last_name": "Shakeri" + }, + { + "first_name": "Jean-Christophe", + "last_name": "Pesquet" + }, + { + "first_name": "Ismail", + "last_name": "Ben Ayed" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Deep Single Image Camera Calibration by Heatmap Regression to Recover Fisheye Images Under Manhattan World Assumption", - "authors": "Nobuhiko Wakai, Satoshi Sato, Yasunori Ishii, Takayoshi Yamashita", + "authors": [ + { + "first_name": "Nobuhiko", + "last_name": "Wakai" + }, + { + "first_name": "Satoshi", + "last_name": "Sato" + }, + { + "first_name": "Yasunori", + "last_name": "Ishii" + }, + { + "first_name": "Takayoshi", + "last_name": "Yamashita" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ID-Blau: Image Deblurring by Implicit Diffusion-based reBLurring AUgmentation", - "authors": "Jia-Hao Wu, Fu-Jen Tsai, Yan-Tsung Peng, Chung-Chi Tsai, Chia-Wen Lin, Yen-Yu Lin", + "authors": [ + { + "first_name": "Jia-Hao", + "last_name": "Wu" + }, + { + "first_name": "Fu-Jen", + "last_name": "Tsai" + }, + { + "first_name": "Yan-Tsung", + "last_name": "Peng" + }, + { + "first_name": "Chung-Chi", + "last_name": "Tsai" + }, + { + "first_name": "Chia-Wen", + "last_name": "Lin" + }, + { + "first_name": "Yen-Yu", + "last_name": "Lin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LAENeRF: Local Appearance Editing for Neural Radiance Fields", - "authors": "Lukas Radl, Michael Steiner, Andreas Kurz, Markus Steinberger", + "authors": [ + { + "first_name": "Lukas", + "last_name": "Radl" + }, + { + "first_name": "Michael", + "last_name": "Steiner" + }, + { + "first_name": "Andreas", + "last_name": "Kurz" + }, + { + "first_name": "Markus", + "last_name": "Steinberger" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CSTA: CNN-based Spatiotemporal Attention for Video Summarization", - "authors": "Jaewon Son, Jaehun Park, Kwangsu Kim", + "authors": [ + { + "first_name": "Jaewon", + "last_name": "Son" + }, + { + "first_name": "Jaehun", + "last_name": "Park" + }, + { + "first_name": "Kwangsu", + "last_name": "Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Adversarial Score Distillation: When score distillation meets GAN", - "authors": "Min Wei, Jingkai Zhou, Junyao Sun, Xuesong Zhang", + "authors": [ + { + "first_name": "Min", + "last_name": "Wei" + }, + { + "first_name": "Jingkai", + "last_name": "Zhou" + }, + { + "first_name": "Junyao", + "last_name": "Sun" + }, + { + "first_name": "Xuesong", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Decentralized Directed Collaboration for Personalized Federated Learning", - "authors": "Yingqi Liu, Yifan Shi, Qinglun Li, Baoyuan Wu, Xueqian Wang, Li Shen", + "authors": [ + { + "first_name": "Yingqi", + "last_name": "Liu" + }, + { + "first_name": "Yifan", + "last_name": "Shi" + }, + { + "first_name": "Qinglun", + "last_name": "Li" + }, + { + "first_name": "Baoyuan", + "last_name": "Wu" + }, + { + "first_name": "Xueqian", + "last_name": "Wang" + }, + { + "first_name": "Li", + "last_name": "Shen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Vector Graphics Generation via Mutually Impulsed Dual-domain Diffusion", - "authors": "Zhongyin Zhao, Ye Chen, Zhangli Hu, Xuanhong Chen, Bingbing Ni", + "authors": [ + { + "first_name": "Zhongyin", + "last_name": "Zhao" + }, + { + "first_name": "Ye", + "last_name": "Chen" + }, + { + "first_name": "Zhangli", + "last_name": "Hu" + }, + { + "first_name": "Xuanhong", + "last_name": "Chen" + }, + { + "first_name": "Bingbing", + "last_name": "Ni" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PEM: Prototype-based Efficient MaskFormer for Image Segmentation", - "authors": "Niccolò Cavagnero, Gabriele Rosi, Claudia Cuttano, Francesca Pistilli, Marco Ciccone, Giuseppe Averta, Fabio Cermelli", + "authors": [ + { + "first_name": "Niccolò", + "last_name": "Cavagnero" + }, + { + "first_name": "Gabriele", + "last_name": "Rosi" + }, + { + "first_name": "Claudia", + "last_name": "Cuttano" + }, + { + "first_name": "Francesca", + "last_name": "Pistilli" + }, + { + "first_name": "Marco", + "last_name": "Ciccone" + }, + { + "first_name": "Giuseppe", + "last_name": "Averta" + }, + { + "first_name": "Fabio", + "last_name": "Cermelli" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Referring Expression Counting", - "authors": "Siyang Dai, Jun Liu, Ngai-Man Cheung", + "authors": [ + { + "first_name": "Siyang", + "last_name": "Dai" + }, + { + "first_name": "Jun", + "last_name": "Liu" + }, + { + "first_name": "Ngai-Man", + "last_name": "Cheung" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ScoreHypo: Probabilistic Human Mesh Estimation with Hypothesis Scoring", - "authors": "Yuan Xu, Xiaoxuan Ma, Jiajun Su, Wentao Zhu, Yu Qiao, Yizhou Wang", + "authors": [ + { + "first_name": "Yuan", + "last_name": "Xu" + }, + { + "first_name": "Xiaoxuan", + "last_name": "Ma" + }, + { + "first_name": "Jiajun", + "last_name": "Su" + }, + { + "first_name": "Wentao", + "last_name": "Zhu" + }, + { + "first_name": "Yu", + "last_name": "Qiao" + }, + { + "first_name": "Yizhou", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GES : Generalized Exponential Splatting for Efficient Radiance Field Rendering", - "authors": "Abdullah Hamdi, Luke Melas-Kyriazi, Jinjie Mai, Guocheng Qian, Ruoshi Liu, Carl Vondrick, Bernard Ghanem, Andrea Vedaldi", + "authors": [ + { + "first_name": "Abdullah", + "last_name": "Hamdi" + }, + { + "first_name": "Luke", + "last_name": "Melas-Kyriazi" + }, + { + "first_name": "Jinjie", + "last_name": "Mai" + }, + { + "first_name": "Guocheng", + "last_name": "Qian" + }, + { + "first_name": "Ruoshi", + "last_name": "Liu" + }, + { + "first_name": "Carl", + "last_name": "Vondrick" + }, + { + "first_name": "Bernard", + "last_name": "Ghanem" + }, + { + "first_name": "Andrea", + "last_name": "Vedaldi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning to Predict Activity Progress by Self-Supervised Video Alignment", - "authors": "Gerard Donahue, Ehsan Elhamifar", + "authors": [ + { + "first_name": "Gerard", + "last_name": "Donahue" + }, + { + "first_name": "Ehsan", + "last_name": "Elhamifar" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "VicTR: Video-conditioned Text Representations for Activity Recognition", - "authors": "Kumara Kahatapitiya, Anurag Arnab, Arsha Nagrani, Michael S. Ryoo", + "authors": [ + { + "first_name": "Kumara", + "last_name": "Kahatapitiya" + }, + { + "first_name": "Anurag", + "last_name": "Arnab" + }, + { + "first_name": "Arsha", + "last_name": "Nagrani" + }, + { + "first_name": "Michael", + "last_name": "S. Ryoo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Label-Efficient Group Robustness via Out-of-Distribution Concept Curation", - "authors": "Yiwei Yang, Anthony Z. Liu, Robert Wolfe, Aylin Caliskan, Bill Howe", + "authors": [ + { + "first_name": "Yiwei", + "last_name": "Yang" + }, + { + "first_name": "Anthony", + "last_name": "Z. Liu" + }, + { + "first_name": "Robert", + "last_name": "Wolfe" + }, + { + "first_name": "Aylin", + "last_name": "Caliskan" + }, + { + "first_name": "Bill", + "last_name": "Howe" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MMCert: Provable Defense against Adversarial Attacks to Multi-modal Models", - "authors": "Yanting Wang, Hongye Fu, Wei Zou, Jinyuan Jia", + "authors": [ + { + "first_name": "Yanting", + "last_name": "Wang" + }, + { + "first_name": "Hongye", + "last_name": "Fu" + }, + { + "first_name": "Wei", + "last_name": "Zou" + }, + { + "first_name": "Jinyuan", + "last_name": "Jia" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "3DToonify: Creating Your High-Fidelity 3D Stylized Avatar Easily from 2D Portrait Images", - "authors": "Yifang Men, Hanxi Liu, Yuan Yao, Miaomiao Cui, Xuansong Xie, Zhouhui Lian", + "authors": [ + { + "first_name": "Yifang", + "last_name": "Men" + }, + { + "first_name": "Hanxi", + "last_name": "Liu" + }, + { + "first_name": "Yuan", + "last_name": "Yao" + }, + { + "first_name": "Miaomiao", + "last_name": "Cui" + }, + { + "first_name": "Xuansong", + "last_name": "Xie" + }, + { + "first_name": "Zhouhui", + "last_name": "Lian" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "NAYER: Noisy Layer Data Generation for Efficient and Effective Data-free Knowledge Distillation", - "authors": "Minh-Tuan Tran, Trung Le, Xuan-May Le, Mehrtash Harandi, Quan Hung Tran, Dinh Phung", + "authors": [ + { + "first_name": "Minh-Tuan", + "last_name": "Tran" + }, + { + "first_name": "Trung", + "last_name": "Le" + }, + { + "first_name": "Xuan-May", + "last_name": "Le" + }, + { + "first_name": "Mehrtash", + "last_name": "Harandi" + }, + { + "first_name": "Quan", + "last_name": "Hung Tran" + }, + { + "first_name": "Dinh", + "last_name": "Phung" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning", - "authors": "Siddharth Srivastava, Gaurav Sharma", + "authors": [ + { + "first_name": "Siddharth", + "last_name": "Srivastava" + }, + { + "first_name": "Gaurav", + "last_name": "Sharma" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Investigating Compositional Challenges in Vision-Language Models for Visual Grounding", - "authors": "Yunan Zeng, Yan Huang, Jinjin Zhang, Zequn Jie, Zhenhua Chai, Liang Wang", + "authors": [ + { + "first_name": "Yunan", + "last_name": "Zeng" + }, + { + "first_name": "Yan", + "last_name": "Huang" + }, + { + "first_name": "Jinjin", + "last_name": "Zhang" + }, + { + "first_name": "Zequn", + "last_name": "Jie" + }, + { + "first_name": "Zhenhua", + "last_name": "Chai" + }, + { + "first_name": "Liang", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "6D-Diff: A Keypoint Diffusion Framework for 6D Object Pose Estimation", - "authors": "Li Xu, Haoxuan Qu, Yujun Cai, Jun Liu", + "authors": [ + { + "first_name": "Li", + "last_name": "Xu" + }, + { + "first_name": "Haoxuan", + "last_name": "Qu" + }, + { + "first_name": "Yujun", + "last_name": "Cai" + }, + { + "first_name": "Jun", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Generative Region-Language Pretraining for Open-Ended Object Detection", - "authors": "Chuang Lin, Yi Jiang, Lizhen Qu, Zehuan Yuan, Jianfei Cai", + "authors": [ + { + "first_name": "Chuang", + "last_name": "Lin" + }, + { + "first_name": "Yi", + "last_name": "Jiang" + }, + { + "first_name": "Lizhen", + "last_name": "Qu" + }, + { + "first_name": "Zehuan", + "last_name": "Yuan" + }, + { + "first_name": "Jianfei", + "last_name": "Cai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Enhancing Post-training Quantization Calibration through Contrastive Learning", - "authors": "Yuzhang Shang, Gaowen Liu, Ramana Rao Kompella, Yan Yan", + "authors": [ + { + "first_name": "Yuzhang", + "last_name": "Shang" + }, + { + "first_name": "Gaowen", + "last_name": "Liu" + }, + { + "first_name": "Ramana", + "last_name": "Rao Kompella" + }, + { + "first_name": "Yan", + "last_name": "Yan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Efficient Model Stealing Defense with Noise Transition Matrix", - "authors": "Dong-Dong Wu, Chilin Fu, Weichang Wu, Wenwen Xia, Xiaolu Zhang, Jun Zhou, Min-Ling Zhang", + "authors": [ + { + "first_name": "Dong-Dong", + "last_name": "Wu" + }, + { + "first_name": "Chilin", + "last_name": "Fu" + }, + { + "first_name": "Weichang", + "last_name": "Wu" + }, + { + "first_name": "Wenwen", + "last_name": "Xia" + }, + { + "first_name": "Xiaolu", + "last_name": "Zhang" + }, + { + "first_name": "Jun", + "last_name": "Zhou" + }, + { + "first_name": "Min-Ling", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MeshPose: Unifying DensePose and 3D Body Mesh Reconstruction", - "authors": "Eric-Tuan Le, Antonis Kakolyris, Petros Koutras, Himmy Tam, Efstratios Skordos, George Papandreou, Riza Alp Güler, Iasonas Kokkinos", + "authors": [ + { + "first_name": "Eric-Tuan", + "last_name": "Le" + }, + { + "first_name": "Antonis", + "last_name": "Kakolyris" + }, + { + "first_name": "Petros", + "last_name": "Koutras" + }, + { + "first_name": "Himmy", + "last_name": "Tam" + }, + { + "first_name": "Efstratios", + "last_name": "Skordos" + }, + { + "first_name": "George", + "last_name": "Papandreou" + }, + { + "first_name": "Riza", + "last_name": "Alp Güler" + }, + { + "first_name": "Iasonas", + "last_name": "Kokkinos" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Unsupervised Salient Instance Detection", - "authors": "Xin Tian, Ke Xu, Rynson Lau", + "authors": [ + { + "first_name": "Xin", + "last_name": "Tian" + }, + { + "first_name": "Ke", + "last_name": "Xu" + }, + { + "first_name": "Rynson", + "last_name": "Lau" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Enhancing Visual Document Understanding with Contrastive Learning in Large Visual-Language Models", - "authors": "Xin Li, Yunfei Wu, Xinghua Jiang, Zhihao Guo, Mingming Gong, Haoyu Cao, Yinsong Liu, Deqiang Jiang, Xing Sun", + "authors": [ + { + "first_name": "Xin", + "last_name": "Li" + }, + { + "first_name": "Yunfei", + "last_name": "Wu" + }, + { + "first_name": "Xinghua", + "last_name": "Jiang" + }, + { + "first_name": "Zhihao", + "last_name": "Guo" + }, + { + "first_name": "Mingming", + "last_name": "Gong" + }, + { + "first_name": "Haoyu", + "last_name": "Cao" + }, + { + "first_name": "Yinsong", + "last_name": "Liu" + }, + { + "first_name": "Deqiang", + "last_name": "Jiang" + }, + { + "first_name": "Xing", + "last_name": "Sun" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Move Anything with Layered Scene Diffusion", - "authors": "Jiawei Ren, Mengmeng Xu, Jui-Chieh Wu, Ziwei Liu, Tao Xiang, Antoine Toisoul", + "authors": [ + { + "first_name": "Jiawei", + "last_name": "Ren" + }, + { + "first_name": "Mengmeng", + "last_name": "Xu" + }, + { + "first_name": "Jui-Chieh", + "last_name": "Wu" + }, + { + "first_name": "Ziwei", + "last_name": "Liu" + }, + { + "first_name": "Tao", + "last_name": "Xiang" + }, + { + "first_name": "Antoine", + "last_name": "Toisoul" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting", - "authors": "Chi Yan, Delin Qu, Dan Xu, Bin Zhao, Zhigang Wang, Dong Wang, Xuelong Li", + "authors": [ + { + "first_name": "Chi", + "last_name": "Yan" + }, + { + "first_name": "Delin", + "last_name": "Qu" + }, + { + "first_name": "Dan", + "last_name": "Xu" + }, + { + "first_name": "Bin", + "last_name": "Zhao" + }, + { + "first_name": "Zhigang", + "last_name": "Wang" + }, + { + "first_name": "Dong", + "last_name": "Wang" + }, + { + "first_name": "Xuelong", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering", - "authors": "Tao Lu, Mulin Yu, Linning Xu, Yuanbo Xiangli, Limin Wang, Dahua Lin, Bo Dai", + "authors": [ + { + "first_name": "Tao", + "last_name": "Lu" + }, + { + "first_name": "Mulin", + "last_name": "Yu" + }, + { + "first_name": "Linning", + "last_name": "Xu" + }, + { + "first_name": "Yuanbo", + "last_name": "Xiangli" + }, + { + "first_name": "Limin", + "last_name": "Wang" + }, + { + "first_name": "Dahua", + "last_name": "Lin" + }, + { + "first_name": "Bo", + "last_name": "Dai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Data Valuation and Detections in Federated Learning", - "authors": "Wenqian Li, Shuran Fu, Fengrui Zhang, Yan Pang", + "authors": [ + { + "first_name": "Wenqian", + "last_name": "Li" + }, + { + "first_name": "Shuran", + "last_name": "Fu" + }, + { + "first_name": "Fengrui", + "last_name": "Zhang" + }, + { + "first_name": "Yan", + "last_name": "Pang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Classes Are Not Equal: An Empirical Study on Image Recognition Fairness", - "authors": "Jiequan Cui, Beier Zhu, Xin Wen, Xiaojuan Qi, Bei Yu, Hanwang Zhang", + "authors": [ + { + "first_name": "Jiequan", + "last_name": "Cui" + }, + { + "first_name": "Beier", + "last_name": "Zhu" + }, + { + "first_name": "Xin", + "last_name": "Wen" + }, + { + "first_name": "Xiaojuan", + "last_name": "Qi" + }, + { + "first_name": "Bei", + "last_name": "Yu" + }, + { + "first_name": "Hanwang", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Human Gaussian Splatting: Real-time Rendering of Animatable Avatars", - "authors": "Arthur Moreau, Jifei Song, Helisa Dhamo, Richard Shaw, Yiren Zhou, Eduardo Pérez-Pellitero", + "authors": [ + { + "first_name": "Arthur", + "last_name": "Moreau" + }, + { + "first_name": "Jifei", + "last_name": "Song" + }, + { + "first_name": "Helisa", + "last_name": "Dhamo" + }, + { + "first_name": "Richard", + "last_name": "Shaw" + }, + { + "first_name": "Yiren", + "last_name": "Zhou" + }, + { + "first_name": "Eduardo", + "last_name": "Pérez-Pellitero" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Multi-Scale 3D Gaussian Splatting for Anti-Aliased Rendering", - "authors": "Zhiwen Yan, Weng Fei Low, Yu Chen, Gim Hee Lee", + "authors": [ + { + "first_name": "Zhiwen", + "last_name": "Yan" + }, + { + "first_name": "Weng", + "last_name": "Fei Low" + }, + { + "first_name": "Yu", + "last_name": "Chen" + }, + { + "first_name": "Gim", + "last_name": "Hee Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "A Bayesian Approach to OOD Robustness in Image Classification", - "authors": "Prakhar Kaushik, Adam Kortylewski, Alan Yuille", + "authors": [ + { + "first_name": "Prakhar", + "last_name": "Kaushik" + }, + { + "first_name": "Adam", + "last_name": "Kortylewski" + }, + { + "first_name": "Alan", + "last_name": "Yuille" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision Language Audio and Action", - "authors": "Jiasen Lu, Christopher Clark, Sangho Lee, Zichen Zhang, Savya Khosla, Ryan Marten, Derek Hoiem, Aniruddha Kembhavi", + "authors": [ + { + "first_name": "Jiasen", + "last_name": "Lu" + }, + { + "first_name": "Christopher", + "last_name": "Clark" + }, + { + "first_name": "Sangho", + "last_name": "Lee" + }, + { + "first_name": "Zichen", + "last_name": "Zhang" + }, + { + "first_name": "Savya", + "last_name": "Khosla" + }, + { + "first_name": "Ryan", + "last_name": "Marten" + }, + { + "first_name": "Derek", + "last_name": "Hoiem" + }, + { + "first_name": "Aniruddha", + "last_name": "Kembhavi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Joint Reconstruction of 3D Human and Object via Contact-Based Refinement Transformer", - "authors": "Hyeongjin Nam, Daniel Sungho Jung, Gyeongsik Moon, Kyoung Mu Lee", + "authors": [ + { + "first_name": "Hyeongjin", + "last_name": "Nam" + }, + { + "first_name": "Daniel", + "last_name": "Sungho Jung" + }, + { + "first_name": "Gyeongsik", + "last_name": "Moon" + }, + { + "first_name": "Kyoung", + "last_name": "Mu Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "TIM: A Time Interval Machine for Audio-Visual Action Recognition", - "authors": "Jacob Chalk, Jaesung Huh, Evangelos Kazakos, Andrew Zisserman, Dima Damen", + "authors": [ + { + "first_name": "Jacob", + "last_name": "Chalk" + }, + { + "first_name": "Jaesung", + "last_name": "Huh" + }, + { + "first_name": "Evangelos", + "last_name": "Kazakos" + }, + { + "first_name": "Andrew", + "last_name": "Zisserman" + }, + { + "first_name": "Dima", + "last_name": "Damen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "The Devil is in the Details: StyleFeatureEditor for Detail-Rich StyleGAN Inversion and High Quality Image Editing", - "authors": "Denis Bobkov, Vadim Titov, Aibek Alanov, Dmitry Vetrov", + "authors": [ + { + "first_name": "Denis", + "last_name": "Bobkov" + }, + { + "first_name": "Vadim", + "last_name": "Titov" + }, + { + "first_name": "Aibek", + "last_name": "Alanov" + }, + { + "first_name": "Dmitry", + "last_name": "Vetrov" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Unbiased Estimator for Distorted Conics in Camera Calibration", - "authors": "Chaehyeon Song, Jaeho Shin, Myung-Hwan Jeon, Jongwoo Lim, Ayoung Kim", + "authors": [ + { + "first_name": "Chaehyeon", + "last_name": "Song" + }, + { + "first_name": "Jaeho", + "last_name": "Shin" + }, + { + "first_name": "Myung-Hwan", + "last_name": "Jeon" + }, + { + "first_name": "Jongwoo", + "last_name": "Lim" + }, + { + "first_name": "Ayoung", + "last_name": "Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MultiPhys: Multi-Person Physics-aware 3D Motion Estimation", - "authors": "Nicolas Ugrinovic, Boxiao Pan, Georgios Pavlakos, Despoina Paschalidou, Bokui Shen, Jordi Sanchez-Riera, Francesc Moreno-Noguer, Leonidas Guibas", + "authors": [ + { + "first_name": "Nicolas", + "last_name": "Ugrinovic" + }, + { + "first_name": "Boxiao", + "last_name": "Pan" + }, + { + "first_name": "Georgios", + "last_name": "Pavlakos" + }, + { + "first_name": "Despoina", + "last_name": "Paschalidou" + }, + { + "first_name": "Bokui", + "last_name": "Shen" + }, + { + "first_name": "Jordi", + "last_name": "Sanchez-Riera" + }, + { + "first_name": "Francesc", + "last_name": "Moreno-Noguer" + }, + { + "first_name": "Leonidas", + "last_name": "Guibas" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Multi-Level Neural Scene Graphs for Dynamic Urban Environments", - "authors": "Tobias Fischer, Lorenzo Porzi, Samuel Rota Bulo, Marc Pollefeys, Peter Kontschieder", + "authors": [ + { + "first_name": "Tobias", + "last_name": "Fischer" + }, + { + "first_name": "Lorenzo", + "last_name": "Porzi" + }, + { + "first_name": "Samuel", + "last_name": "Rota Bulo" + }, + { + "first_name": "Marc", + "last_name": "Pollefeys" + }, + { + "first_name": "Peter", + "last_name": "Kontschieder" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Would Deep Generative Models Amplify Bias in Future Models?", - "authors": "Tianwei Chen, Yusuke Hirota, Mayu Otani, Noa Garcia, Yuta Nakashima", + "authors": [ + { + "first_name": "Tianwei", + "last_name": "Chen" + }, + { + "first_name": "Yusuke", + "last_name": "Hirota" + }, + { + "first_name": "Mayu", + "last_name": "Otani" + }, + { + "first_name": "Noa", + "last_name": "Garcia" + }, + { + "first_name": "Yuta", + "last_name": "Nakashima" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Bayes' Rays: Uncertainty Quantification for Neural Radiance Fields", - "authors": "Lily Goli, Cody Reading, Silvia Sellán, Alec Jacobson, Andrea Tagliasacchi", + "authors": [ + { + "first_name": "Lily", + "last_name": "Goli" + }, + { + "first_name": "Cody", + "last_name": "Reading" + }, + { + "first_name": "Silvia", + "last_name": "Sellán" + }, + { + "first_name": "Alec", + "last_name": "Jacobson" + }, + { + "first_name": "Andrea", + "last_name": "Tagliasacchi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "NIVeL: Neural Implicit Vector Layers for Text-to-Vector Generation", - "authors": "Vikas Thamizharasan, Difan Liu, Matthew Fisher, Nanxuan Zhao, Evangelos Kalogerakis, Michal Lukac", + "authors": [ + { + "first_name": "Vikas", + "last_name": "Thamizharasan" + }, + { + "first_name": "Difan", + "last_name": "Liu" + }, + { + "first_name": "Matthew", + "last_name": "Fisher" + }, + { + "first_name": "Nanxuan", + "last_name": "Zhao" + }, + { + "first_name": "Evangelos", + "last_name": "Kalogerakis" + }, + { + "first_name": "Michal", + "last_name": "Lukac" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Driving-Video Dehazing with Non-Aligned Regularization for Safety Assistance", - "authors": "Junkai Fan, Jiangwei Weng, Kun Wang, Yijun Yang, Jianjun Qian, Jun Li, Jian Yang", + "authors": [ + { + "first_name": "Junkai", + "last_name": "Fan" + }, + { + "first_name": "Jiangwei", + "last_name": "Weng" + }, + { + "first_name": "Kun", + "last_name": "Wang" + }, + { + "first_name": "Yijun", + "last_name": "Yang" + }, + { + "first_name": "Jianjun", + "last_name": "Qian" + }, + { + "first_name": "Jun", + "last_name": "Li" + }, + { + "first_name": "Jian", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Is Vanilla MLP in Neural Radiance Field Enough for Few-shot View Synthesis?", - "authors": "Hanxin Zhu, Tianyu He, Xin Li, Bingchen Li, Zhibo Chen", + "authors": [ + { + "first_name": "Hanxin", + "last_name": "Zhu" + }, + { + "first_name": "Tianyu", + "last_name": "He" + }, + { + "first_name": "Xin", + "last_name": "Li" + }, + { + "first_name": "Bingchen", + "last_name": "Li" + }, + { + "first_name": "Zhibo", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CVT-xRF: Contrastive In-Voxel Transformer for 3D Consistent Radiance Fields from Sparse Inputs", - "authors": "Yingji Zhong, Lanqing Hong, Zhenguo Li, Dan Xu", + "authors": [ + { + "first_name": "Yingji", + "last_name": "Zhong" + }, + { + "first_name": "Lanqing", + "last_name": "Hong" + }, + { + "first_name": "Zhenguo", + "last_name": "Li" + }, + { + "first_name": "Dan", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "OAKINK2: A Dataset of Bimanual Hands-Object Manipulation in Complex Task Completion", - "authors": "Xinyu Zhan, Lixin Yang, Yifei Zhao, Kangrui Mao, Hanlin Xu, Zenan Lin, Kailin Li, Cewu Lu", + "authors": [ + { + "first_name": "Xinyu", + "last_name": "Zhan" + }, + { + "first_name": "Lixin", + "last_name": "Yang" + }, + { + "first_name": "Yifei", + "last_name": "Zhao" + }, + { + "first_name": "Kangrui", + "last_name": "Mao" + }, + { + "first_name": "Hanlin", + "last_name": "Xu" + }, + { + "first_name": "Zenan", + "last_name": "Lin" + }, + { + "first_name": "Kailin", + "last_name": "Li" + }, + { + "first_name": "Cewu", + "last_name": "Lu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CogAgent: A Visual Language Model for GUI Agents", - "authors": "Wenyi Hong, Weihan Wang, Qingsong Lv, Jiazheng Xu, Wenmeng Yu, Junhui Ji, Yan Wang, Zihan Wang, Yuxiao Dong, Ming Ding, Jie Tang", + "authors": [ + { + "first_name": "Wenyi", + "last_name": "Hong" + }, + { + "first_name": "Weihan", + "last_name": "Wang" + }, + { + "first_name": "Qingsong", + "last_name": "Lv" + }, + { + "first_name": "Jiazheng", + "last_name": "Xu" + }, + { + "first_name": "Wenmeng", + "last_name": "Yu" + }, + { + "first_name": "Junhui", + "last_name": "Ji" + }, + { + "first_name": "Yan", + "last_name": "Wang" + }, + { + "first_name": "Zihan", + "last_name": "Wang" + }, + { + "first_name": "Yuxiao", + "last_name": "Dong" + }, + { + "first_name": "Ming", + "last_name": "Ding" + }, + { + "first_name": "Jie", + "last_name": "Tang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Text-Guided 3D Face Synthesis - From Generation to Editing", - "authors": "Yunjie Wu, Yapeng Meng, Zhipeng Hu, Lincheng Li, Haoqian Wu, Kun Zhou, Weiwei Xu, Xin Yu", + "authors": [ + { + "first_name": "Yunjie", + "last_name": "Wu" + }, + { + "first_name": "Yapeng", + "last_name": "Meng" + }, + { + "first_name": "Zhipeng", + "last_name": "Hu" + }, + { + "first_name": "Lincheng", + "last_name": "Li" + }, + { + "first_name": "Haoqian", + "last_name": "Wu" + }, + { + "first_name": "Kun", + "last_name": "Zhou" + }, + { + "first_name": "Weiwei", + "last_name": "Xu" + }, + { + "first_name": "Xin", + "last_name": "Yu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "AIDE: An Automatic Data Engine for Object Detection in Autonomous Driving", - "authors": "Mingfu Liang, Jong-Chyi Su, Samuel Schulter, Sparsh Garg, Shiyu Zhao, Ying Wu, Manmohan Chandraker", + "authors": [ + { + "first_name": "Mingfu", + "last_name": "Liang" + }, + { + "first_name": "Jong-Chyi", + "last_name": "Su" + }, + { + "first_name": "Samuel", + "last_name": "Schulter" + }, + { + "first_name": "Sparsh", + "last_name": "Garg" + }, + { + "first_name": "Shiyu", + "last_name": "Zhao" + }, + { + "first_name": "Ying", + "last_name": "Wu" + }, + { + "first_name": "Manmohan", + "last_name": "Chandraker" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Multiplane Prior Guided Few-Shot Aerial Scene Rendering", - "authors": "Zihan Gao, Licheng Jiao, Lingling Li, Xu Liu, Fang Liu, Puhua Chen, Yuwei Guo", + "authors": [ + { + "first_name": "Zihan", + "last_name": "Gao" + }, + { + "first_name": "Licheng", + "last_name": "Jiao" + }, + { + "first_name": "Lingling", + "last_name": "Li" + }, + { + "first_name": "Xu", + "last_name": "Liu" + }, + { + "first_name": "Fang", + "last_name": "Liu" + }, + { + "first_name": "Puhua", + "last_name": "Chen" + }, + { + "first_name": "Yuwei", + "last_name": "Guo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MAS: Multi-view Ancestral Sampling for 3D Motion Generation Using 2D Diffusion", - "authors": "Roy Kapon, Guy Tevet, Daniel Cohen-Or, Amit H. Bermano", + "authors": [ + { + "first_name": "Roy", + "last_name": "Kapon" + }, + { + "first_name": "Guy", + "last_name": "Tevet" + }, + { + "first_name": "Daniel", + "last_name": "Cohen-Or" + }, + { + "first_name": "Amit", + "last_name": "H. Bermano" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Smart Help: Strategic Opponent Modeling for Proactive and Adaptive Robot Assistance in Households", - "authors": "Zhihao Cao, Zidong Wang, Siwen Xie, Anji Liu, Lifeng Fan", + "authors": [ + { + "first_name": "Zhihao", + "last_name": "Cao" + }, + { + "first_name": "Zidong", + "last_name": "Wang" + }, + { + "first_name": "Siwen", + "last_name": "Xie" + }, + { + "first_name": "Anji", + "last_name": "Liu" + }, + { + "first_name": "Lifeng", + "last_name": "Fan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Bilateral Event Mining and Complementary for Event Stream Super-Resolution", - "authors": "Zhilin Huang, Quanmin Liang, Yijie Yu, Chujun Qin, Xiawu Zheng, Kai Huang, Zikun Zhou, Wenming Yang", + "authors": [ + { + "first_name": "Zhilin", + "last_name": "Huang" + }, + { + "first_name": "Quanmin", + "last_name": "Liang" + }, + { + "first_name": "Yijie", + "last_name": "Yu" + }, + { + "first_name": "Chujun", + "last_name": "Qin" + }, + { + "first_name": "Xiawu", + "last_name": "Zheng" + }, + { + "first_name": "Kai", + "last_name": "Huang" + }, + { + "first_name": "Zikun", + "last_name": "Zhou" + }, + { + "first_name": "Wenming", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Online Task-Free Continual Generative and Discriminative Learning via Dynamic Cluster Memory", - "authors": "Fei Ye, Adrian G. Bors", + "authors": [ + { + "first_name": "Fei", + "last_name": "Ye" + }, + { + "first_name": "Adrian", + "last_name": "G. Bors" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Rapid Motor Adaptation for Robotic Manipulator Arms", - "authors": "Yichao Liang, Kevin Ellis, João Henriques", + "authors": [ + { + "first_name": "Yichao", + "last_name": "Liang" + }, + { + "first_name": "Kevin", + "last_name": "Ellis" + }, + { + "first_name": "João", + "last_name": "Henriques" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SANeRF-HQ: Segment Anything for NeRF in High Quality", - "authors": "Yichen Liu, Benran Hu, Chi-Keung Tang, Yu-Wing Tai", + "authors": [ + { + "first_name": "Yichen", + "last_name": "Liu" + }, + { + "first_name": "Benran", + "last_name": "Hu" + }, + { + "first_name": "Chi-Keung", + "last_name": "Tang" + }, + { + "first_name": "Yu-Wing", + "last_name": "Tai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DSGG: Dense Relation Transformer for an End-to-end Scene Graph Generation", - "authors": "Zeeshan Hayder, Xuming He", + "authors": [ + { + "first_name": "Zeeshan", + "last_name": "Hayder" + }, + { + "first_name": "Xuming", + "last_name": "He" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary", - "authors": "Leheng Zhang, Yawei Li, Xingyu Zhou, Xiaorui Zhao, Shuhang Gu", + "authors": [ + { + "first_name": "Leheng", + "last_name": "Zhang" + }, + { + "first_name": "Yawei", + "last_name": "Li" + }, + { + "first_name": "Xingyu", + "last_name": "Zhou" + }, + { + "first_name": "Xiaorui", + "last_name": "Zhao" + }, + { + "first_name": "Shuhang", + "last_name": "Gu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Object Dynamics Modeling with Hierarchical Point Cloud-based Representations", - "authors": "Chanho Kim, Li Fuxin", + "authors": [ + { + "first_name": "Chanho", + "last_name": "Kim" + }, + { + "first_name": "Li", + "last_name": "Fuxin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "WWW: A Unified Framework for Explaining What Where and Why of Neural Networks by Interpretation of Neuron Concepts", - "authors": "Yong Hyun Ahn, Hyeon Bae Kim, Seong Tae Kim", + "authors": [ + { + "first_name": "Yong", + "last_name": "Hyun Ahn" + }, + { + "first_name": "Hyeon", + "last_name": "Bae Kim" + }, + { + "first_name": "Seong", + "last_name": "Tae Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery", - "authors": "Xin Guo, Jiangwei Lao, Bo Dang, Yingying Zhang, Lei Yu, Lixiang Ru, Liheng Zhong, Ziyuan Huang, Kang Wu, Dingxiang Hu, Huimei He, Jian Wang, Jingdong Chen, Ming Yang, Yongjun Zhang, Yansheng Li", + "authors": [ + { + "first_name": "Xin", + "last_name": "Guo" + }, + { + "first_name": "Jiangwei", + "last_name": "Lao" + }, + { + "first_name": "Bo", + "last_name": "Dang" + }, + { + "first_name": "Yingying", + "last_name": "Zhang" + }, + { + "first_name": "Lei", + "last_name": "Yu" + }, + { + "first_name": "Lixiang", + "last_name": "Ru" + }, + { + "first_name": "Liheng", + "last_name": "Zhong" + }, + { + "first_name": "Ziyuan", + "last_name": "Huang" + }, + { + "first_name": "Kang", + "last_name": "Wu" + }, + { + "first_name": "Dingxiang", + "last_name": "Hu" + }, + { + "first_name": "Huimei", + "last_name": "He" + }, + { + "first_name": "Jian", + "last_name": "Wang" + }, + { + "first_name": "Jingdong", + "last_name": "Chen" + }, + { + "first_name": "Ming", + "last_name": "Yang" + }, + { + "first_name": "Yongjun", + "last_name": "Zhang" + }, + { + "first_name": "Yansheng", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CaKDP: Category-aware Knowledge Distillation and Pruning Framework for Lightweight 3D Object Detection", - "authors": "Haonan Zhang, Longjun Liu, Yuqi Huang, Zhao Yang, Xinyu Lei, Bihan Wen", + "authors": [ + { + "first_name": "Haonan", + "last_name": "Zhang" + }, + { + "first_name": "Longjun", + "last_name": "Liu" + }, + { + "first_name": "Yuqi", + "last_name": "Huang" + }, + { + "first_name": "Zhao", + "last_name": "Yang" + }, + { + "first_name": "Xinyu", + "last_name": "Lei" + }, + { + "first_name": "Bihan", + "last_name": "Wen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Mixed-Precision Quantization for Federated Learning on Resource-Constrained Heterogeneous Devices", - "authors": "Huancheng Chen, Haris Vikalo", + "authors": [ + { + "first_name": "Huancheng", + "last_name": "Chen" + }, + { + "first_name": "Haris", + "last_name": "Vikalo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CFAT: Unleashing Triangular Windows for Image Super-resolution", - "authors": "Abhisek Ray, Gaurav Kumar, Maheshkumar H. Kolekar", + "authors": [ + { + "first_name": "Abhisek", + "last_name": "Ray" + }, + { + "first_name": "Gaurav", + "last_name": "Kumar" + }, + { + "first_name": "Maheshkumar", + "last_name": "H. Kolekar" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ICP-Flow: LiDAR Scene Flow Estimation with ICP", - "authors": "Yancong Lin, Holger Caesar", + "authors": [ + { + "first_name": "Yancong", + "last_name": "Lin" + }, + { + "first_name": "Holger", + "last_name": "Caesar" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer", - "authors": "Jianjian Cao, Peng Ye, Shengze Li, Chong Yu, Yansong Tang, Jiwen Lu, Tao Chen", + "authors": [ + { + "first_name": "Jianjian", + "last_name": "Cao" + }, + { + "first_name": "Peng", + "last_name": "Ye" + }, + { + "first_name": "Shengze", + "last_name": "Li" + }, + { + "first_name": "Chong", + "last_name": "Yu" + }, + { + "first_name": "Yansong", + "last_name": "Tang" + }, + { + "first_name": "Jiwen", + "last_name": "Lu" + }, + { + "first_name": "Tao", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "G-NeRF: Geometry-enhanced Novel View Synthesis from Single-View Images", - "authors": "Zixiong Huang, Qi Chen, Libo Sun, Yifan Yang, Naizhou Wang, Qi Wu, Mingkui Tan", + "authors": [ + { + "first_name": "Zixiong", + "last_name": "Huang" + }, + { + "first_name": "Qi", + "last_name": "Chen" + }, + { + "first_name": "Libo", + "last_name": "Sun" + }, + { + "first_name": "Yifan", + "last_name": "Yang" + }, + { + "first_name": "Naizhou", + "last_name": "Wang" + }, + { + "first_name": "Qi", + "last_name": "Wu" + }, + { + "first_name": "Mingkui", + "last_name": "Tan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Neural Fields as Distributions: Signal Processing Beyond Euclidean Space", - "authors": "Daniel Rebain, Soroosh Yazdani, Kwang Moo Yi, Andrea Tagliasacchi", + "authors": [ + { + "first_name": "Daniel", + "last_name": "Rebain" + }, + { + "first_name": "Soroosh", + "last_name": "Yazdani" + }, + { + "first_name": "Kwang", + "last_name": "Moo Yi" + }, + { + "first_name": "Andrea", + "last_name": "Tagliasacchi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Rolling Shutter Correction with Intermediate Distortion Flow Estimation", - "authors": "Mingdeng Cao, Sidi Yang, Yujiu Yang, Yinqiang Zheng", + "authors": [ + { + "first_name": "Mingdeng", + "last_name": "Cao" + }, + { + "first_name": "Sidi", + "last_name": "Yang" + }, + { + "first_name": "Yujiu", + "last_name": "Yang" + }, + { + "first_name": "Yinqiang", + "last_name": "Zheng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Style Blind Domain Generalized Semantic Segmentation via Covariance Alignment and Semantic Consistence Contrastive Learning", - "authors": "Woo-Jin Ahn, Geun-Yeong Yang, Hyun-Duck Choi, Myo-Taeg Lim", + "authors": [ + { + "first_name": "Woo-Jin", + "last_name": "Ahn" + }, + { + "first_name": "Geun-Yeong", + "last_name": "Yang" + }, + { + "first_name": "Hyun-Duck", + "last_name": "Choi" + }, + { + "first_name": "Myo-Taeg", + "last_name": "Lim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Attack To Defend: Exploiting Adversarial Attacks for Detecting Poisoned Models", - "authors": "Samar Fares, Karthik Nandakumar", + "authors": [ + { + "first_name": "Samar", + "last_name": "Fares" + }, + { + "first_name": "Karthik", + "last_name": "Nandakumar" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "X-3D: Explicit 3D Structure Modeling for Point Cloud Recognition", - "authors": "Shuofeng Sun, Yongming Rao, Jiwen Lu, Haibin Yan", + "authors": [ + { + "first_name": "Shuofeng", + "last_name": "Sun" + }, + { + "first_name": "Yongming", + "last_name": "Rao" + }, + { + "first_name": "Jiwen", + "last_name": "Lu" + }, + { + "first_name": "Haibin", + "last_name": "Yan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SpiderMatch: 3D Shape Matching with Global Optimality and Geometric Consistency", - "authors": "Paul Roetzer, Florian Bernard", + "authors": [ + { + "first_name": "Paul", + "last_name": "Roetzer" + }, + { + "first_name": "Florian", + "last_name": "Bernard" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learning", - "authors": "Siteng Huang, Biao Gong, Yutong Feng, Min Zhang, Yiliang Lv, Donglin Wang", + "authors": [ + { + "first_name": "Siteng", + "last_name": "Huang" + }, + { + "first_name": "Biao", + "last_name": "Gong" + }, + { + "first_name": "Yutong", + "last_name": "Feng" + }, + { + "first_name": "Min", + "last_name": "Zhang" + }, + { + "first_name": "Yiliang", + "last_name": "Lv" + }, + { + "first_name": "Donglin", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "One More Step: A Versatile Plug-and-Play Module for Rectifying Diffusion Schedule Flaws and Enhancing Low-Frequency Controls", - "authors": "Minghui Hu, Jianbin Zheng, Chuanxia Zheng, Chaoyue Wang, Dacheng Tao, Tat-Jen Cham", + "authors": [ + { + "first_name": "Minghui", + "last_name": "Hu" + }, + { + "first_name": "Jianbin", + "last_name": "Zheng" + }, + { + "first_name": "Chuanxia", + "last_name": "Zheng" + }, + { + "first_name": "Chaoyue", + "last_name": "Wang" + }, + { + "first_name": "Dacheng", + "last_name": "Tao" + }, + { + "first_name": "Tat-Jen", + "last_name": "Cham" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Enhancing Multimodal Cooperation via Sample-level Modality Valuation", - "authors": "Yake Wei, Ruoxuan Feng, Zihe Wang, Di Hu", + "authors": [ + { + "first_name": "Yake", + "last_name": "Wei" + }, + { + "first_name": "Ruoxuan", + "last_name": "Feng" + }, + { + "first_name": "Zihe", + "last_name": "Wang" + }, + { + "first_name": "Di", + "last_name": "Hu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Evidential Active Recognition: Intelligent and Prudent Open-World Embodied Perception", - "authors": "Lei Fan, Mingfu Liang, Yunxuan Li, Gang Hua, Ying Wu", + "authors": [ + { + "first_name": "Lei", + "last_name": "Fan" + }, + { + "first_name": "Mingfu", + "last_name": "Liang" + }, + { + "first_name": "Yunxuan", + "last_name": "Li" + }, + { + "first_name": "Gang", + "last_name": "Hua" + }, + { + "first_name": "Ying", + "last_name": "Wu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SatSynth: Augmenting Image-Mask Pairs through Diffusion Models for Aerial Semantic Segmentation", - "authors": "Aysim Toker, Marvin Eisenberger, Daniel Cremers, Laura Leal-Taixé", + "authors": [ + { + "first_name": "Aysim", + "last_name": "Toker" + }, + { + "first_name": "Marvin", + "last_name": "Eisenberger" + }, + { + "first_name": "Daniel", + "last_name": "Cremers" + }, + { + "first_name": "Laura", + "last_name": "Leal-Taixé" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "XScale-NVS: Cross-Scale Novel View Synthesis with Hash Featurized Manifold", - "authors": "Guangyu Wang, Jinzhi Zhang, Fan Wang, Ruqi Huang, Lu Fang", + "authors": [ + { + "first_name": "Guangyu", + "last_name": "Wang" + }, + { + "first_name": "Jinzhi", + "last_name": "Zhang" + }, + { + "first_name": "Fan", + "last_name": "Wang" + }, + { + "first_name": "Ruqi", + "last_name": "Huang" + }, + { + "first_name": "Lu", + "last_name": "Fang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Ink Dot-Oriented Differentiable Optimization for Neural Image Halftoning", - "authors": "Hao Jiang, Bingfeng Zhou, Yadong Mu", + "authors": [ + { + "first_name": "Hao", + "last_name": "Jiang" + }, + { + "first_name": "Bingfeng", + "last_name": "Zhou" + }, + { + "first_name": "Yadong", + "last_name": "Mu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "The Unreasonable Effectiveness of Pre-Trained Features for Camera Pose Refinement", - "authors": "Gabriele Trivigno, Carlo Masone, Barbara Caputo, Torsten Sattler", + "authors": [ + { + "first_name": "Gabriele", + "last_name": "Trivigno" + }, + { + "first_name": "Carlo", + "last_name": "Masone" + }, + { + "first_name": "Barbara", + "last_name": "Caputo" + }, + { + "first_name": "Torsten", + "last_name": "Sattler" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Scalable 3D Registration via Truncated Entry-wise Absolute Residuals", - "authors": "Tianyu Huang, Liangzu Peng, Rene Vidal, Yun-Hui Liu", + "authors": [ + { + "first_name": "Tianyu", + "last_name": "Huang" + }, + { + "first_name": "Liangzu", + "last_name": "Peng" + }, + { + "first_name": "Rene", + "last_name": "Vidal" + }, + { + "first_name": "Yun-Hui", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ExtraNeRF: Visibility-Aware View Extrapolation of Neural Radiance Fields with Diffusion Models", - "authors": "Meng-Li Shih, Wei-Chiu Ma, Lorenzo Boyice, Aleksander Holynski, Forrester Cole, Brian Curless, Janne Kontkanen", + "authors": [ + { + "first_name": "Meng-Li", + "last_name": "Shih" + }, + { + "first_name": "Wei-Chiu", + "last_name": "Ma" + }, + { + "first_name": "Lorenzo", + "last_name": "Boyice" + }, + { + "first_name": "Aleksander", + "last_name": "Holynski" + }, + { + "first_name": "Forrester", + "last_name": "Cole" + }, + { + "first_name": "Brian", + "last_name": "Curless" + }, + { + "first_name": "Janne", + "last_name": "Kontkanen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Equivariant Plug-and-Play Image Reconstruction", - "authors": "Matthieu Terris, Thomas Moreau, Nelly Pustelnik, Julian Tachella", + "authors": [ + { + "first_name": "Matthieu", + "last_name": "Terris" + }, + { + "first_name": "Thomas", + "last_name": "Moreau" + }, + { + "first_name": "Nelly", + "last_name": "Pustelnik" + }, + { + "first_name": "Julian", + "last_name": "Tachella" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor", - "authors": "Shuyang Sun, Runjia Li, Philip Torr, Xiuye Gu, Siyang Li", + "authors": [ + { + "first_name": "Shuyang", + "last_name": "Sun" + }, + { + "first_name": "Runjia", + "last_name": "Li" + }, + { + "first_name": "Philip", + "last_name": "Torr" + }, + { + "first_name": "Xiuye", + "last_name": "Gu" + }, + { + "first_name": "Siyang", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LP++: A Surprisingly Strong Linear Probe for Few-Shot CLIP", - "authors": "Yunshi Huang, Fereshteh Shakeri, Jose Dolz, Malik Boudiaf, Houda Bahig, Ismail Ben Ayed", + "authors": [ + { + "first_name": "Yunshi", + "last_name": "Huang" + }, + { + "first_name": "Fereshteh", + "last_name": "Shakeri" + }, + { + "first_name": "Jose", + "last_name": "Dolz" + }, + { + "first_name": "Malik", + "last_name": "Boudiaf" + }, + { + "first_name": "Houda", + "last_name": "Bahig" + }, + { + "first_name": "Ismail", + "last_name": "Ben Ayed" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Active Generalized Category Discovery", - "authors": "Shijie Ma, Fei Zhu, Zhun Zhong, Xu-Yao Zhang, Cheng-Lin Liu", + "authors": [ + { + "first_name": "Shijie", + "last_name": "Ma" + }, + { + "first_name": "Fei", + "last_name": "Zhu" + }, + { + "first_name": "Zhun", + "last_name": "Zhong" + }, + { + "first_name": "Xu-Yao", + "last_name": "Zhang" + }, + { + "first_name": "Cheng-Lin", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HIVE: Harnessing Human Feedback for Instructional Visual Editing", - "authors": "Shu Zhang, Xinyi Yang, Yihao Feng, Can Qin, Chia-Chih Chen, Ning Yu, Zeyuan Chen, Huan Wang, Silvio Savarese, Stefano Ermon, Caiming Xiong, Ran Xu", + "authors": [ + { + "first_name": "Shu", + "last_name": "Zhang" + }, + { + "first_name": "Xinyi", + "last_name": "Yang" + }, + { + "first_name": "Yihao", + "last_name": "Feng" + }, + { + "first_name": "Can", + "last_name": "Qin" + }, + { + "first_name": "Chia-Chih", + "last_name": "Chen" + }, + { + "first_name": "Ning", + "last_name": "Yu" + }, + { + "first_name": "Zeyuan", + "last_name": "Chen" + }, + { + "first_name": "Huan", + "last_name": "Wang" + }, + { + "first_name": "Silvio", + "last_name": "Savarese" + }, + { + "first_name": "Stefano", + "last_name": "Ermon" + }, + { + "first_name": "Caiming", + "last_name": "Xiong" + }, + { + "first_name": "Ran", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "StrokeFaceNeRF: Stroke-based Facial Appearance Editing in Neural Radiance Field", - "authors": "Xiao-Juan Li, Dingxi Zhang, Shu-Yu Chen, Feng-Lin Liu", + "authors": [ + { + "first_name": "Xiao-Juan", + "last_name": "Li" + }, + { + "first_name": "Dingxi", + "last_name": "Zhang" + }, + { + "first_name": "Shu-Yu", + "last_name": "Chen" + }, + { + "first_name": "Feng-Lin", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FlowVQTalker: High-Quality Emotional Talking Face Generation through Normalizing Flow and Quantization", - "authors": "Shuai Tan, Bin Ji, Ye Pan", + "authors": [ + { + "first_name": "Shuai", + "last_name": "Tan" + }, + { + "first_name": "Bin", + "last_name": "Ji" + }, + { + "first_name": "Ye", + "last_name": "Pan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning from Observer Gaze: Zero-Shot Attention Prediction Oriented by Human-Object Interaction Recognition", - "authors": "Yuchen Zhou, Linkai Liu, Chao Gou", + "authors": [ + { + "first_name": "Yuchen", + "last_name": "Zhou" + }, + { + "first_name": "Linkai", + "last_name": "Liu" + }, + { + "first_name": "Chao", + "last_name": "Gou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ProxyCap: Real-time Monocular Full-body Capture in World Space via Human-Centric Proxy-to-Motion Learning", - "authors": "Yuxiang Zhang, Hongwen Zhang, Liangxiao Hu, Jiajun Zhang, Hongwei Yi, Shengping Zhang, Yebin Liu", + "authors": [ + { + "first_name": "Yuxiang", + "last_name": "Zhang" + }, + { + "first_name": "Hongwen", + "last_name": "Zhang" + }, + { + "first_name": "Liangxiao", + "last_name": "Hu" + }, + { + "first_name": "Jiajun", + "last_name": "Zhang" + }, + { + "first_name": "Hongwei", + "last_name": "Yi" + }, + { + "first_name": "Shengping", + "last_name": "Zhang" + }, + { + "first_name": "Yebin", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "OpenBias: Open-set Bias Detection in Text-to-Image Generative Models", - "authors": "Moreno D'Incà, Elia Peruzzo, Massimiliano Mancini, Dejia Xu, Vidit Goel, Xingqian Xu, Zhangyang Wang, Humphrey Shi, Nicu Sebe", + "authors": [ + { + "first_name": "Moreno", + "last_name": "D'Incà" + }, + { + "first_name": "Elia", + "last_name": "Peruzzo" + }, + { + "first_name": "Massimiliano", + "last_name": "Mancini" + }, + { + "first_name": "Dejia", + "last_name": "Xu" + }, + { + "first_name": "Vidit", + "last_name": "Goel" + }, + { + "first_name": "Xingqian", + "last_name": "Xu" + }, + { + "first_name": "Zhangyang", + "last_name": "Wang" + }, + { + "first_name": "Humphrey", + "last_name": "Shi" + }, + { + "first_name": "Nicu", + "last_name": "Sebe" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "On the Robustness of Language Guidance for Low-Level Vision Tasks: Findings from Depth Estimation", - "authors": "Agneet Chatterjee, Tejas Gokhale, Chitta Baral, Yezhou Yang", + "authors": [ + { + "first_name": "Agneet", + "last_name": "Chatterjee" + }, + { + "first_name": "Tejas", + "last_name": "Gokhale" + }, + { + "first_name": "Chitta", + "last_name": "Baral" + }, + { + "first_name": "Yezhou", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANs", - "authors": "Yanwu Xu, Yang Zhao, Zhisheng Xiao, Tingbo Hou", + "authors": [ + { + "first_name": "Yanwu", + "last_name": "Xu" + }, + { + "first_name": "Yang", + "last_name": "Zhao" + }, + { + "first_name": "Zhisheng", + "last_name": "Xiao" + }, + { + "first_name": "Tingbo", + "last_name": "Hou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "3DiffTection: 3D Object Detection with Geometry-Aware Diffusion Features", - "authors": "Chenfeng Xu, Huan Ling, Sanja Fidler, Or Litany", + "authors": [ + { + "first_name": "Chenfeng", + "last_name": "Xu" + }, + { + "first_name": "Huan", + "last_name": "Ling" + }, + { + "first_name": "Sanja", + "last_name": "Fidler" + }, + { + "first_name": "Or", + "last_name": "Litany" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3D", - "authors": "Mukund Varma T, Peihao Wang, Zhiwen Fan, Zhangyang Wang, Hao Su, Ravi Ramamoorthi", + "authors": [ + { + "first_name": "Mukund", + "last_name": "Varma T" + }, + { + "first_name": "Peihao", + "last_name": "Wang" + }, + { + "first_name": "Zhiwen", + "last_name": "Fan" + }, + { + "first_name": "Zhangyang", + "last_name": "Wang" + }, + { + "first_name": "Hao", + "last_name": "Su" + }, + { + "first_name": "Ravi", + "last_name": "Ramamoorthi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LowRankOcc: Tensor Decomposition and Low-Rank Recovery for Vision-based 3D Semantic Occupancy Prediction", - "authors": "Linqing Zhao, Xiuwei Xu, Ziwei Wang, Yunpeng Zhang, Borui Zhang, Wenzhao Zheng, Dalong Du, Jie Zhou, Jiwen Lu", + "authors": [ + { + "first_name": "Linqing", + "last_name": "Zhao" + }, + { + "first_name": "Xiuwei", + "last_name": "Xu" + }, + { + "first_name": "Ziwei", + "last_name": "Wang" + }, + { + "first_name": "Yunpeng", + "last_name": "Zhang" + }, + { + "first_name": "Borui", + "last_name": "Zhang" + }, + { + "first_name": "Wenzhao", + "last_name": "Zheng" + }, + { + "first_name": "Dalong", + "last_name": "Du" + }, + { + "first_name": "Jie", + "last_name": "Zhou" + }, + { + "first_name": "Jiwen", + "last_name": "Lu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Multiway Point Cloud Mosaicking with Diffusion and Global Optimization", - "authors": "Shengze Jin, Iro Armeni, Marc Pollefeys, Daniel Barath", + "authors": [ + { + "first_name": "Shengze", + "last_name": "Jin" + }, + { + "first_name": "Iro", + "last_name": "Armeni" + }, + { + "first_name": "Marc", + "last_name": "Pollefeys" + }, + { + "first_name": "Daniel", + "last_name": "Barath" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Novel View Synthesis with View-Dependent Effects from a Single Image", - "authors": "Juan Luis Gonzalez Bello, Munchurl Kim", + "authors": [ + { + "first_name": "Juan", + "last_name": "Luis Gonzalez Bello" + }, + { + "first_name": "Munchurl", + "last_name": "Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Point2RBox: Combine Knowledge from Synthetic Visual Patterns for End-to-end Oriented Object Detection with Single Point Supervision", - "authors": "Yi Yu, Xue Yang, Qingyun Li, Feipeng Da, Jifeng Dai, Yu Qiao, Junchi Yan", + "authors": [ + { + "first_name": "Yi", + "last_name": "Yu" + }, + { + "first_name": "Xue", + "last_name": "Yang" + }, + { + "first_name": "Qingyun", + "last_name": "Li" + }, + { + "first_name": "Feipeng", + "last_name": "Da" + }, + { + "first_name": "Jifeng", + "last_name": "Dai" + }, + { + "first_name": "Yu", + "last_name": "Qiao" + }, + { + "first_name": "Junchi", + "last_name": "Yan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "PBWR: Parametric-Building-Wireframe Reconstruction from Aerial LiDAR Point Clouds", - "authors": "Shangfeng Huang, Ruisheng Wang, Bo Guo, Hongxin Yang", + "authors": [ + { + "first_name": "Shangfeng", + "last_name": "Huang" + }, + { + "first_name": "Ruisheng", + "last_name": "Wang" + }, + { + "first_name": "Bo", + "last_name": "Guo" + }, + { + "first_name": "Hongxin", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Spectrum AUC Difference (SAUCD): Human-aligned 3D Shape Evaluation", - "authors": "Tianyu Luan, Zhong Li, Lele Chen, Xuan Gong, Lichang Chen, Yi Xu, Junsong Yuan", + "authors": [ + { + "first_name": "Tianyu", + "last_name": "Luan" + }, + { + "first_name": "Zhong", + "last_name": "Li" + }, + { + "first_name": "Lele", + "last_name": "Chen" + }, + { + "first_name": "Xuan", + "last_name": "Gong" + }, + { + "first_name": "Lichang", + "last_name": "Chen" + }, + { + "first_name": "Yi", + "last_name": "Xu" + }, + { + "first_name": "Junsong", + "last_name": "Yuan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "HRVDA: High-Resolution Visual Document Assistant", - "authors": "Chaohu Liu, Kun Yin, Haoyu Cao, Xinghua Jiang, Xin Li, Yinsong Liu, Deqiang Jiang, Xing Sun, Linli Xu", + "authors": [ + { + "first_name": "Chaohu", + "last_name": "Liu" + }, + { + "first_name": "Kun", + "last_name": "Yin" + }, + { + "first_name": "Haoyu", + "last_name": "Cao" + }, + { + "first_name": "Xinghua", + "last_name": "Jiang" + }, + { + "first_name": "Xin", + "last_name": "Li" + }, + { + "first_name": "Yinsong", + "last_name": "Liu" + }, + { + "first_name": "Deqiang", + "last_name": "Jiang" + }, + { + "first_name": "Xing", + "last_name": "Sun" + }, + { + "first_name": "Linli", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning for Transductive Threshold Calibration in Open-World Recognition", - "authors": "Qin Zhang, Dongsheng An, Tianjun Xiao, Tong He, Qingming Tang, Ying Nian Wu, Joseph Tighe, Yifan Xing", + "authors": [ + { + "first_name": "Qin", + "last_name": "Zhang" + }, + { + "first_name": "Dongsheng", + "last_name": "An" + }, + { + "first_name": "Tianjun", + "last_name": "Xiao" + }, + { + "first_name": "Tong", + "last_name": "He" + }, + { + "first_name": "Qingming", + "last_name": "Tang" + }, + { + "first_name": "Ying", + "last_name": "Nian Wu" + }, + { + "first_name": "Joseph", + "last_name": "Tighe" + }, + { + "first_name": "Yifan", + "last_name": "Xing" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Weakly-Supervised Emotion Transition Learning for Diverse 3D Co-speech Gesture Generation", - "authors": "Xingqun Qi, Jiahao Pan, Peng Li, Ruibin Yuan, Xiaowei Chi, Mengfei Li, Wenhan Luo, Wei Xue, Shanghang Zhang, Qifeng Liu, Yike Guo", + "authors": [ + { + "first_name": "Xingqun", + "last_name": "Qi" + }, + { + "first_name": "Jiahao", + "last_name": "Pan" + }, + { + "first_name": "Peng", + "last_name": "Li" + }, + { + "first_name": "Ruibin", + "last_name": "Yuan" + }, + { + "first_name": "Xiaowei", + "last_name": "Chi" + }, + { + "first_name": "Mengfei", + "last_name": "Li" + }, + { + "first_name": "Wenhan", + "last_name": "Luo" + }, + { + "first_name": "Wei", + "last_name": "Xue" + }, + { + "first_name": "Shanghang", + "last_name": "Zhang" + }, + { + "first_name": "Qifeng", + "last_name": "Liu" + }, + { + "first_name": "Yike", + "last_name": "Guo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Multi-Session SLAM with Differentiable Wide-Baseline Pose Optimization", - "authors": "Lahav Lipson, Jia Deng", + "authors": [ + { + "first_name": "Lahav", + "last_name": "Lipson" + }, + { + "first_name": "Jia", + "last_name": "Deng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "A Dual-Augmentor Framework for Domain Generalization in 3D Human Pose Estimation", - "authors": "Qucheng Peng, Ce Zheng, Chen Chen", + "authors": [ + { + "first_name": "Qucheng", + "last_name": "Peng" + }, + { + "first_name": "Ce", + "last_name": "Zheng" + }, + { + "first_name": "Chen", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Improving Out-of-Distribution Generalization in Graphs via Hierarchical Semantic Environments", - "authors": "Yinhua Piao, Sangseon Lee, Yijingxiu Lu, Sun Kim", + "authors": [ + { + "first_name": "Yinhua", + "last_name": "Piao" + }, + { + "first_name": "Sangseon", + "last_name": "Lee" + }, + { + "first_name": "Yijingxiu", + "last_name": "Lu" + }, + { + "first_name": "Sun", + "last_name": "Kim" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CN-RMA: Combined Network with Ray Marching Aggregation for 3D Indoor Object Detection from Multi-view Images", - "authors": "Guanlin Shen, Jingwei Huang, Zhihua Hu, Bin Wang", + "authors": [ + { + "first_name": "Guanlin", + "last_name": "Shen" + }, + { + "first_name": "Jingwei", + "last_name": "Huang" + }, + { + "first_name": "Zhihua", + "last_name": "Hu" + }, + { + "first_name": "Bin", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ACT-Diffusion: Efficient Adversarial Consistency Training for One-step Diffusion Models", - "authors": "Fei Kong, Jinhao Duan, Lichao Sun, Hao Cheng, Renjing Xu, Hengtao Shen, Xiaofeng Zhu, Xiaoshuang Shi, Kaidi Xu", + "authors": [ + { + "first_name": "Fei", + "last_name": "Kong" + }, + { + "first_name": "Jinhao", + "last_name": "Duan" + }, + { + "first_name": "Lichao", + "last_name": "Sun" + }, + { + "first_name": "Hao", + "last_name": "Cheng" + }, + { + "first_name": "Renjing", + "last_name": "Xu" + }, + { + "first_name": "Hengtao", + "last_name": "Shen" + }, + { + "first_name": "Xiaofeng", + "last_name": "Zhu" + }, + { + "first_name": "Xiaoshuang", + "last_name": "Shi" + }, + { + "first_name": "Kaidi", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Spectral Meets Spatial: Harmonising 3D Shape Matching and Interpolation", - "authors": "Dongliang Cao, Marvin Eisenberger, Nafie El Amrani, Daniel Cremers, Florian Bernard", + "authors": [ + { + "first_name": "Dongliang", + "last_name": "Cao" + }, + { + "first_name": "Marvin", + "last_name": "Eisenberger" + }, + { + "first_name": "Nafie", + "last_name": "El Amrani" + }, + { + "first_name": "Daniel", + "last_name": "Cremers" + }, + { + "first_name": "Florian", + "last_name": "Bernard" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Emu Edit: Precise Image Editing via Recognition and Generation Tasks", - "authors": "Shelly Sheynin, Adam Polyak, Uriel Singer, Yuval Kirstain, Amit Zohar, Oron Ashual, Devi Parikh, Yaniv Taigman", + "authors": [ + { + "first_name": "Shelly", + "last_name": "Sheynin" + }, + { + "first_name": "Adam", + "last_name": "Polyak" + }, + { + "first_name": "Uriel", + "last_name": "Singer" + }, + { + "first_name": "Yuval", + "last_name": "Kirstain" + }, + { + "first_name": "Amit", + "last_name": "Zohar" + }, + { + "first_name": "Oron", + "last_name": "Ashual" + }, + { + "first_name": "Devi", + "last_name": "Parikh" + }, + { + "first_name": "Yaniv", + "last_name": "Taigman" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Face2Diffusion for Fast and Editable Face Personalization", - "authors": "Kaede Shiohara, Toshihiko Yamasaki", + "authors": [ + { + "first_name": "Kaede", + "last_name": "Shiohara" + }, + { + "first_name": "Toshihiko", + "last_name": "Yamasaki" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Causal-CoG: A Causal-Effect Look at Context Generation for Boosting Multi-modal Language Models", - "authors": "Shitian Zhao, Zhuowan Li, Yadong Lu, Alan Yuille, Yan Wang", + "authors": [ + { + "first_name": "Shitian", + "last_name": "Zhao" + }, + { + "first_name": "Zhuowan", + "last_name": "Li" + }, + { + "first_name": "Yadong", + "last_name": "Lu" + }, + { + "first_name": "Alan", + "last_name": "Yuille" + }, + { + "first_name": "Yan", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds", - "authors": "Tianrui Lou, Xiaojun Jia, Jindong Gu, Li Liu, Siyuan Liang, Bangyan He, Xiaochun Cao", + "authors": [ + { + "first_name": "Tianrui", + "last_name": "Lou" + }, + { + "first_name": "Xiaojun", + "last_name": "Jia" + }, + { + "first_name": "Jindong", + "last_name": "Gu" + }, + { + "first_name": "Li", + "last_name": "Liu" + }, + { + "first_name": "Siyuan", + "last_name": "Liang" + }, + { + "first_name": "Bangyan", + "last_name": "He" + }, + { + "first_name": "Xiaochun", + "last_name": "Cao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SG-BEV: Satellite-Guided BEV Fusion for Cross-View Semantic Segmentation", - "authors": "Junyan Ye, Qiyan Luo, Jinhua Yu, Huaping Zhong, Zhimeng Zheng, Conghui He, Weijia Li", + "authors": [ + { + "first_name": "Junyan", + "last_name": "Ye" + }, + { + "first_name": "Qiyan", + "last_name": "Luo" + }, + { + "first_name": "Jinhua", + "last_name": "Yu" + }, + { + "first_name": "Huaping", + "last_name": "Zhong" + }, + { + "first_name": "Zhimeng", + "last_name": "Zheng" + }, + { + "first_name": "Conghui", + "last_name": "He" + }, + { + "first_name": "Weijia", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Brush2Prompt: Contextual Prompt Generator for Object Inpainting", - "authors": "Mang Tik Chiu, Yuqian Zhou, Lingzhi Zhang, Zhe Lin, Connelly Barnes, Sohrab Amirghodsi, Eli Shechtman, Humphrey Shi", + "authors": [ + { + "first_name": "Mang", + "last_name": "Tik Chiu" + }, + { + "first_name": "Yuqian", + "last_name": "Zhou" + }, + { + "first_name": "Lingzhi", + "last_name": "Zhang" + }, + { + "first_name": "Zhe", + "last_name": "Lin" + }, + { + "first_name": "Connelly", + "last_name": "Barnes" + }, + { + "first_name": "Sohrab", + "last_name": "Amirghodsi" + }, + { + "first_name": "Eli", + "last_name": "Shechtman" + }, + { + "first_name": "Humphrey", + "last_name": "Shi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Joint-Task Regularization for Partially Labeled Multi-Task Learning", - "authors": "Kento Nishi, Junsik Kim, Wanhua Li, Hanspeter Pfister", + "authors": [ + { + "first_name": "Kento", + "last_name": "Nishi" + }, + { + "first_name": "Junsik", + "last_name": "Kim" + }, + { + "first_name": "Wanhua", + "last_name": "Li" + }, + { + "first_name": "Hanspeter", + "last_name": "Pfister" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Shallow-Deep Collaborative Learning for Unsupervised Visible-Infrared Person Re-Identification", - "authors": "Bin Yang, Jun Chen, Mang Ye", + "authors": [ + { + "first_name": "Bin", + "last_name": "Yang" + }, + { + "first_name": "Jun", + "last_name": "Chen" + }, + { + "first_name": "Mang", + "last_name": "Ye" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Dancing with Still Images: Video Distillation via Static-Dynamic Disentanglement", - "authors": "Ziyu Wang, Yue Xu, Cewu Lu, Yong-Lu Li", + "authors": [ + { + "first_name": "Ziyu", + "last_name": "Wang" + }, + { + "first_name": "Yue", + "last_name": "Xu" + }, + { + "first_name": "Cewu", + "last_name": "Lu" + }, + { + "first_name": "Yong-Lu", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Context-Aware Integration of Language and Visual References for Natural Language Tracking", - "authors": "Yanyan Shao, Shuting He, Qi Ye, Yuchao Feng, Wenhan Luo, Jiming Chen", + "authors": [ + { + "first_name": "Yanyan", + "last_name": "Shao" + }, + { + "first_name": "Shuting", + "last_name": "He" + }, + { + "first_name": "Qi", + "last_name": "Ye" + }, + { + "first_name": "Yuchao", + "last_name": "Feng" + }, + { + "first_name": "Wenhan", + "last_name": "Luo" + }, + { + "first_name": "Jiming", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "An Edit Friendly DDPM Noise Space: Inversion and Manipulations", - "authors": "Inbar Huberman-Spiegelglas, Vladimir Kulikov, Tomer Michaeli", + "authors": [ + { + "first_name": "Inbar", + "last_name": "Huberman-Spiegelglas" + }, + { + "first_name": "Vladimir", + "last_name": "Kulikov" + }, + { + "first_name": "Tomer", + "last_name": "Michaeli" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry", - "authors": "Weirong Chen, Le Chen, Rui Wang, Marc Pollefeys", + "authors": [ + { + "first_name": "Weirong", + "last_name": "Chen" + }, + { + "first_name": "Le", + "last_name": "Chen" + }, + { + "first_name": "Rui", + "last_name": "Wang" + }, + { + "first_name": "Marc", + "last_name": "Pollefeys" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "RoDLA: Benchmarking the Robustness of Document Layout Analysis Models", - "authors": "Yufan Chen, Jiaming Zhang, Kunyu Peng, Junwei Zheng, Ruiping Liu, Philip Torr, Rainer Stiefelhagen", + "authors": [ + { + "first_name": "Yufan", + "last_name": "Chen" + }, + { + "first_name": "Jiaming", + "last_name": "Zhang" + }, + { + "first_name": "Kunyu", + "last_name": "Peng" + }, + { + "first_name": "Junwei", + "last_name": "Zheng" + }, + { + "first_name": "Ruiping", + "last_name": "Liu" + }, + { + "first_name": "Philip", + "last_name": "Torr" + }, + { + "first_name": "Rainer", + "last_name": "Stiefelhagen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio Video Point Cloud Time-Series and Image Recognition", - "authors": "Xiaohan Ding, Yiyuan Zhang, Yixiao Ge, Sijie Zhao, Lin Song, Xiangyu Yue, Ying Shan", + "authors": [ + { + "first_name": "Xiaohan", + "last_name": "Ding" + }, + { + "first_name": "Yiyuan", + "last_name": "Zhang" + }, + { + "first_name": "Yixiao", + "last_name": "Ge" + }, + { + "first_name": "Sijie", + "last_name": "Zhao" + }, + { + "first_name": "Lin", + "last_name": "Song" + }, + { + "first_name": "Xiangyu", + "last_name": "Yue" + }, + { + "first_name": "Ying", + "last_name": "Shan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Unveiling the Unknown: Unleashing the Power of Unknown to Known in Open-Set Source-Free Domain Adaptation", - "authors": "Fuli Wan, Han Zhao, Xu Yang, Cheng Deng", + "authors": [ + { + "first_name": "Fuli", + "last_name": "Wan" + }, + { + "first_name": "Han", + "last_name": "Zhao" + }, + { + "first_name": "Xu", + "last_name": "Yang" + }, + { + "first_name": "Cheng", + "last_name": "Deng" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "BilevelPruning: Unified Dynamic and Static Channel Pruning for Convolutional Neural Networks", - "authors": "Shangqian Gao, Yanfu Zhang, Feihu Huang, Heng Huang", + "authors": [ + { + "first_name": "Shangqian", + "last_name": "Gao" + }, + { + "first_name": "Yanfu", + "last_name": "Zhang" + }, + { + "first_name": "Feihu", + "last_name": "Huang" + }, + { + "first_name": "Heng", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "IDGuard: Robust General Identity-centric POI Proactive Defense Against Face Editing Abuse", - "authors": "Yunshu Dai, Jianwei Fei, Fangjun Huang", + "authors": [ + { + "first_name": "Yunshu", + "last_name": "Dai" + }, + { + "first_name": "Jianwei", + "last_name": "Fei" + }, + { + "first_name": "Fangjun", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SwiftBrush: One-Step Text-to-Image Diffusion Model with Variational Score Distillation", - "authors": "Thuan Hoang Nguyen, Anh Tran", + "authors": [ + { + "first_name": "Thuan", + "last_name": "Hoang Nguyen" + }, + { + "first_name": "Anh", + "last_name": "Tran" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DEADiff: An Efficient Stylization Diffusion Model with Disentangled Representations", - "authors": "Tianhao Qi, Shancheng Fang, Yanze Wu, Hongtao Xie, Jiawei Liu, Lang Chen, Qian He, Yongdong Zhang", + "authors": [ + { + "first_name": "Tianhao", + "last_name": "Qi" + }, + { + "first_name": "Shancheng", + "last_name": "Fang" + }, + { + "first_name": "Yanze", + "last_name": "Wu" + }, + { + "first_name": "Hongtao", + "last_name": "Xie" + }, + { + "first_name": "Jiawei", + "last_name": "Liu" + }, + { + "first_name": "Lang", + "last_name": "Chen" + }, + { + "first_name": "Qian", + "last_name": "He" + }, + { + "first_name": "Yongdong", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Instance-Adaptive and Geometric-Aware Keypoint Learning for Category-Level 6D Object Pose Estimation", - "authors": "Xiao Lin, Wenfei Yang, Yuan Gao, Tianzhu Zhang", + "authors": [ + { + "first_name": "Xiao", + "last_name": "Lin" + }, + { + "first_name": "Wenfei", + "last_name": "Yang" + }, + { + "first_name": "Yuan", + "last_name": "Gao" + }, + { + "first_name": "Tianzhu", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Universal Semi-Supervised Domain Adaptation by Mitigating Common-Class Bias", - "authors": "Wenyu Zhang, Qingmu Liu, Felix Ong Wei Cong, Mohamed Ragab, Chuan-Sheng Foo", + "authors": [ + { + "first_name": "Wenyu", + "last_name": "Zhang" + }, + { + "first_name": "Qingmu", + "last_name": "Liu" + }, + { + "first_name": "Felix", + "last_name": "Ong Wei Cong" + }, + { + "first_name": "Mohamed", + "last_name": "Ragab" + }, + { + "first_name": "Chuan-Sheng", + "last_name": "Foo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Exact Fusion via Feature Distribution Matching for Few-shot Image Generation", - "authors": "Yingbo Zhou, Yutong Ye, Pengyu Zhang, Xian Wei, Mingsong Chen", + "authors": [ + { + "first_name": "Yingbo", + "last_name": "Zhou" + }, + { + "first_name": "Yutong", + "last_name": "Ye" + }, + { + "first_name": "Pengyu", + "last_name": "Zhang" + }, + { + "first_name": "Xian", + "last_name": "Wei" + }, + { + "first_name": "Mingsong", + "last_name": "Chen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CoDeF: Content Deformation Fields for Temporally Consistent Video Processing", - "authors": "Hao Ouyang, Qiuyu Wang, Yuxi Xiao, Qingyan Bai, Juntao Zhang, Kecheng Zheng, Xiaowei Zhou, Qifeng Chen, Yujun Shen", + "authors": [ + { + "first_name": "Hao", + "last_name": "Ouyang" + }, + { + "first_name": "Qiuyu", + "last_name": "Wang" + }, + { + "first_name": "Yuxi", + "last_name": "Xiao" + }, + { + "first_name": "Qingyan", + "last_name": "Bai" + }, + { + "first_name": "Juntao", + "last_name": "Zhang" + }, + { + "first_name": "Kecheng", + "last_name": "Zheng" + }, + { + "first_name": "Xiaowei", + "last_name": "Zhou" + }, + { + "first_name": "Qifeng", + "last_name": "Chen" + }, + { + "first_name": "Yujun", + "last_name": "Shen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "QUADify: Extracting Meshes with Pixel-level Details and Materials from Images", - "authors": "Maximilian Frühauf, Hayko Riemenschneider, Markus Gross, Christopher Schroers", + "authors": [ + { + "first_name": "Maximilian", + "last_name": "Frühauf" + }, + { + "first_name": "Hayko", + "last_name": "Riemenschneider" + }, + { + "first_name": "Markus", + "last_name": "Gross" + }, + { + "first_name": "Christopher", + "last_name": "Schroers" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "RecDiffusion: Rectangling for Image Stitching with Diffusion Models", - "authors": "Tianhao Zhou, Haipeng Li, Ziyi Wang, Ao Luo, Chen-Lin Zhang, Jiajun Li, Bing Zeng, Shuaicheng Liu", + "authors": [ + { + "first_name": "Tianhao", + "last_name": "Zhou" + }, + { + "first_name": "Haipeng", + "last_name": "Li" + }, + { + "first_name": "Ziyi", + "last_name": "Wang" + }, + { + "first_name": "Ao", + "last_name": "Luo" + }, + { + "first_name": "Chen-Lin", + "last_name": "Zhang" + }, + { + "first_name": "Jiajun", + "last_name": "Li" + }, + { + "first_name": "Bing", + "last_name": "Zeng" + }, + { + "first_name": "Shuaicheng", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Eclipse: Disambiguating Illumination and Materials using Unintended Shadows", - "authors": "Dor Verbin, Ben Mildenhall, Peter Hedman, Jonathan T. Barron, Todd Zickler, Pratul P. Srinivasan", + "authors": [ + { + "first_name": "Dor", + "last_name": "Verbin" + }, + { + "first_name": "Ben", + "last_name": "Mildenhall" + }, + { + "first_name": "Peter", + "last_name": "Hedman" + }, + { + "first_name": "Jonathan", + "last_name": "T. Barron" + }, + { + "first_name": "Todd", + "last_name": "Zickler" + }, + { + "first_name": "Pratul", + "last_name": "P. Srinivasan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields", - "authors": "Shijie Zhou, Haoran Chang, Sicheng Jiang, Zhiwen Fan, Zehao Zhu, Dejia Xu, Pradyumna Chari, Suya You, Zhangyang Wang, Achuta Kadambi", + "authors": [ + { + "first_name": "Shijie", + "last_name": "Zhou" + }, + { + "first_name": "Haoran", + "last_name": "Chang" + }, + { + "first_name": "Sicheng", + "last_name": "Jiang" + }, + { + "first_name": "Zhiwen", + "last_name": "Fan" + }, + { + "first_name": "Zehao", + "last_name": "Zhu" + }, + { + "first_name": "Dejia", + "last_name": "Xu" + }, + { + "first_name": "Pradyumna", + "last_name": "Chari" + }, + { + "first_name": "Suya", + "last_name": "You" + }, + { + "first_name": "Zhangyang", + "last_name": "Wang" + }, + { + "first_name": "Achuta", + "last_name": "Kadambi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Balancing Act: Distribution-Guided Debiasing in Diffusion Models", - "authors": "Rishubh Parihar, Abhijnya Bhat, Abhipsa Basu, Saswat Mallick, Jogendra Nath Kundu, R. Venkatesh Babu", + "authors": [ + { + "first_name": "Rishubh", + "last_name": "Parihar" + }, + { + "first_name": "Abhijnya", + "last_name": "Bhat" + }, + { + "first_name": "Abhipsa", + "last_name": "Basu" + }, + { + "first_name": "Saswat", + "last_name": "Mallick" + }, + { + "first_name": "Jogendra", + "last_name": "Nath Kundu" + }, + { + "first_name": "R.", + "last_name": "Venkatesh Babu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Viewpoint-Aware Visual Grounding in 3D Scenes", - "authors": "Xiangxi Shi, Zhonghua Wu, Stefan Lee", + "authors": [ + { + "first_name": "Xiangxi", + "last_name": "Shi" + }, + { + "first_name": "Zhonghua", + "last_name": "Wu" + }, + { + "first_name": "Stefan", + "last_name": "Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "4K4D: Real-Time 4D View Synthesis at 4K Resolution", - "authors": "Zhen Xu, Sida Peng, Haotong Lin, Guangzhao He, Jiaming Sun, Yujun Shen, Hujun Bao, Xiaowei Zhou", + "authors": [ + { + "first_name": "Zhen", + "last_name": "Xu" + }, + { + "first_name": "Sida", + "last_name": "Peng" + }, + { + "first_name": "Haotong", + "last_name": "Lin" + }, + { + "first_name": "Guangzhao", + "last_name": "He" + }, + { + "first_name": "Jiaming", + "last_name": "Sun" + }, + { + "first_name": "Yujun", + "last_name": "Shen" + }, + { + "first_name": "Hujun", + "last_name": "Bao" + }, + { + "first_name": "Xiaowei", + "last_name": "Zhou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "View-decoupled Transformer for Person Re-identification under Aerial-ground Camera Network", - "authors": "Quan Zhang, Lei Wang, Vishal M. Patel, Xiaohua Xie, Jianhaung Lai", + "authors": [ + { + "first_name": "Quan", + "last_name": "Zhang" + }, + { + "first_name": "Lei", + "last_name": "Wang" + }, + { + "first_name": "Vishal", + "last_name": "M. Patel" + }, + { + "first_name": "Xiaohua", + "last_name": "Xie" + }, + { + "first_name": "Jianhaung", + "last_name": "Lai" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CRKD: Enhanced Camera-Radar Object Detection with Cross-modality Knowledge Distillation", - "authors": "Lingjun Zhao, Jingyu Song, Katherine A. Skinner", + "authors": [ + { + "first_name": "Lingjun", + "last_name": "Zhao" + }, + { + "first_name": "Jingyu", + "last_name": "Song" + }, + { + "first_name": "Katherine", + "last_name": "A. Skinner" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Differentiable Point-based Inverse Rendering", - "authors": "Hoon-Gyu Chung, Seokjun Choi, Seung-Hwan Baek", + "authors": [ + { + "first_name": "Hoon-Gyu", + "last_name": "Chung" + }, + { + "first_name": "Seokjun", + "last_name": "Choi" + }, + { + "first_name": "Seung-Hwan", + "last_name": "Baek" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "OED: Towards One-stage End-to-End Dynamic Scene Graph Generation", - "authors": "Guan Wang, Zhimin Li, Qingchao Chen, Yang Liu", + "authors": [ + { + "first_name": "Guan", + "last_name": "Wang" + }, + { + "first_name": "Zhimin", + "last_name": "Li" + }, + { + "first_name": "Qingchao", + "last_name": "Chen" + }, + { + "first_name": "Yang", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CoG-DQA: Chain-of-Guiding Learning with Large Language Models for Diagram Question Answering", - "authors": "Shaowei Wang, Lingling Zhang, Longji Zhu, Tao Qin, Kim-Hui Yap, Xinyu Zhang, Jun Liu", + "authors": [ + { + "first_name": "Shaowei", + "last_name": "Wang" + }, + { + "first_name": "Lingling", + "last_name": "Zhang" + }, + { + "first_name": "Longji", + "last_name": "Zhu" + }, + { + "first_name": "Tao", + "last_name": "Qin" + }, + { + "first_name": "Kim-Hui", + "last_name": "Yap" + }, + { + "first_name": "Xinyu", + "last_name": "Zhang" + }, + { + "first_name": "Jun", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Transferable and Principled Efficiency for Open-Vocabulary Segmentation", - "authors": "Jingxuan Xu, Wuyang Chen, Yao Zhao, Yunchao Wei", + "authors": [ + { + "first_name": "Jingxuan", + "last_name": "Xu" + }, + { + "first_name": "Wuyang", + "last_name": "Chen" + }, + { + "first_name": "Yao", + "last_name": "Zhao" + }, + { + "first_name": "Yunchao", + "last_name": "Wei" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "A Unified and Interpretable Emotion Representation and Expression Generation", - "authors": "Reni Paskaleva, Mykyta Holubakha, Andela Ilic, Saman Motamed, Luc Van Gool, Danda Paudel", + "authors": [ + { + "first_name": "Reni", + "last_name": "Paskaleva" + }, + { + "first_name": "Mykyta", + "last_name": "Holubakha" + }, + { + "first_name": "Andela", + "last_name": "Ilic" + }, + { + "first_name": "Saman", + "last_name": "Motamed" + }, + { + "first_name": "Luc", + "last_name": "Van Gool" + }, + { + "first_name": "Danda", + "last_name": "Paudel" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution", - "authors": "Shangchen Zhou, Peiqing Yang, Jianyi Wang, Yihang Luo, Chen Change Loy", + "authors": [ + { + "first_name": "Shangchen", + "last_name": "Zhou" + }, + { + "first_name": "Peiqing", + "last_name": "Yang" + }, + { + "first_name": "Jianyi", + "last_name": "Wang" + }, + { + "first_name": "Yihang", + "last_name": "Luo" + }, + { + "first_name": "Chen", + "last_name": "Change Loy" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "EvDiG: Event-guided Direct and Global Components Separation", - "authors": "Xinyu Zhou, Peiqi Duan, Boyu Li, Chu Zhou, Chao Xu, Boxin Shi", + "authors": [ + { + "first_name": "Xinyu", + "last_name": "Zhou" + }, + { + "first_name": "Peiqi", + "last_name": "Duan" + }, + { + "first_name": "Boyu", + "last_name": "Li" + }, + { + "first_name": "Chu", + "last_name": "Zhou" + }, + { + "first_name": "Chao", + "last_name": "Xu" + }, + { + "first_name": "Boxin", + "last_name": "Shi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DeIL: Direct-and-Inverse CLIP for Open-World Few-Shot Learning", - "authors": "Shuai Shao, Yu Bai, Yan Wang, Baodi Liu, Yicong Zhou", + "authors": [ + { + "first_name": "Shuai", + "last_name": "Shao" + }, + { + "first_name": "Yu", + "last_name": "Bai" + }, + { + "first_name": "Yan", + "last_name": "Wang" + }, + { + "first_name": "Baodi", + "last_name": "Liu" + }, + { + "first_name": "Yicong", + "last_name": "Zhou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "4D-DRESS: A 4D Dataset of Real-World Human Clothing With Semantic Annotations", - "authors": "Wenbo Wang, Hsuan-I Ho, Chen Guo, Boxiang Rong, Artur Grigorev, Jie Song, Juan Jose Zarate, Otmar Hilliges", + "authors": [ + { + "first_name": "Wenbo", + "last_name": "Wang" + }, + { + "first_name": "Hsuan-I", + "last_name": "Ho" + }, + { + "first_name": "Chen", + "last_name": "Guo" + }, + { + "first_name": "Boxiang", + "last_name": "Rong" + }, + { + "first_name": "Artur", + "last_name": "Grigorev" + }, + { + "first_name": "Jie", + "last_name": "Song" + }, + { + "first_name": "Juan", + "last_name": "Jose Zarate" + }, + { + "first_name": "Otmar", + "last_name": "Hilliges" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Feedback-Guided Autonomous Driving", - "authors": "Jimuyang Zhang, Zanming Huang, Arijit Ray, Eshed Ohn-Bar", + "authors": [ + { + "first_name": "Jimuyang", + "last_name": "Zhang" + }, + { + "first_name": "Zanming", + "last_name": "Huang" + }, + { + "first_name": "Arijit", + "last_name": "Ray" + }, + { + "first_name": "Eshed", + "last_name": "Ohn-Bar" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Large Language Models are Good Prompt Learners for Low-Shot Image Classification", - "authors": "Zhaoheng Zheng, Jingmin Wei, Xuefeng Hu, Haidong Zhu, Ram Nevatia", + "authors": [ + { + "first_name": "Zhaoheng", + "last_name": "Zheng" + }, + { + "first_name": "Jingmin", + "last_name": "Wei" + }, + { + "first_name": "Xuefeng", + "last_name": "Hu" + }, + { + "first_name": "Haidong", + "last_name": "Zhu" + }, + { + "first_name": "Ram", + "last_name": "Nevatia" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Specularity Factorization for Low-Light Enhancement", - "authors": "Saurabh Saini, P J Narayanan", + "authors": [ + { + "first_name": "Saurabh", + "last_name": "Saini" + }, + { + "first_name": "P", + "last_name": "J Narayanan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models", - "authors": "Xianfang Zeng, Xin Chen, Zhongqi Qi, Wen Liu, Zibo Zhao, Zhibin Wang, Bin Fu, Yong Liu, Gang Yu", + "authors": [ + { + "first_name": "Xianfang", + "last_name": "Zeng" + }, + { + "first_name": "Xin", + "last_name": "Chen" + }, + { + "first_name": "Zhongqi", + "last_name": "Qi" + }, + { + "first_name": "Wen", + "last_name": "Liu" + }, + { + "first_name": "Zibo", + "last_name": "Zhao" + }, + { + "first_name": "Zhibin", + "last_name": "Wang" + }, + { + "first_name": "Bin", + "last_name": "Fu" + }, + { + "first_name": "Yong", + "last_name": "Liu" + }, + { + "first_name": "Gang", + "last_name": "Yu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "VILA: On Pre-training for Visual Language Models", - "authors": "Ji Lin, Hongxu Yin, Wei Ping, Pavlo Molchanov, Mohammad Shoeybi, Song Han", + "authors": [ + { + "first_name": "Ji", + "last_name": "Lin" + }, + { + "first_name": "Hongxu", + "last_name": "Yin" + }, + { + "first_name": "Wei", + "last_name": "Ping" + }, + { + "first_name": "Pavlo", + "last_name": "Molchanov" + }, + { + "first_name": "Mohammad", + "last_name": "Shoeybi" + }, + { + "first_name": "Song", + "last_name": "Han" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DiLiGenRT: A Photometric Stereo Dataset with Quantified Roughness and Translucency", - "authors": "Heng Guo, Jieji Ren, Feishi Wang, Boxin Shi, Mingjun Ren, Yasuyuki Matsushita", + "authors": [ + { + "first_name": "Heng", + "last_name": "Guo" + }, + { + "first_name": "Jieji", + "last_name": "Ren" + }, + { + "first_name": "Feishi", + "last_name": "Wang" + }, + { + "first_name": "Boxin", + "last_name": "Shi" + }, + { + "first_name": "Mingjun", + "last_name": "Ren" + }, + { + "first_name": "Yasuyuki", + "last_name": "Matsushita" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "De-Diffusion Makes Text a Strong Cross-Modal Interface", - "authors": "Chen Wei, Chenxi Liu, Siyuan Qiao, Zhishuai Zhang, Alan Yuille, Jiahui Yu", + "authors": [ + { + "first_name": "Chen", + "last_name": "Wei" + }, + { + "first_name": "Chenxi", + "last_name": "Liu" + }, + { + "first_name": "Siyuan", + "last_name": "Qiao" + }, + { + "first_name": "Zhishuai", + "last_name": "Zhang" + }, + { + "first_name": "Alan", + "last_name": "Yuille" + }, + { + "first_name": "Jiahui", + "last_name": "Yu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "End-to-End Spatio-Temporal Action Localisation with Video Transformers", - "authors": "Alexey A. Gritsenko, Xuehan Xiong, Josip Djolonga, Mostafa Dehghani, Chen Sun, Mario Lucic, Cordelia Schmid, Anurag Arnab", + "authors": [ + { + "first_name": "Alexey", + "last_name": "A. Gritsenko" + }, + { + "first_name": "Xuehan", + "last_name": "Xiong" + }, + { + "first_name": "Josip", + "last_name": "Djolonga" + }, + { + "first_name": "Mostafa", + "last_name": "Dehghani" + }, + { + "first_name": "Chen", + "last_name": "Sun" + }, + { + "first_name": "Mario", + "last_name": "Lucic" + }, + { + "first_name": "Cordelia", + "last_name": "Schmid" + }, + { + "first_name": "Anurag", + "last_name": "Arnab" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Text-Guided Variational Image Generation for Industrial Anomaly Detection and Segmentation", - "authors": "Mingyu Lee, Jongwon Choi", + "authors": [ + { + "first_name": "Mingyu", + "last_name": "Lee" + }, + { + "first_name": "Jongwon", + "last_name": "Choi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Self-Adaptive Reality-Guided Diffusion for Artifact-Free Super-Resolution", - "authors": "Qingping Zheng, Ling Zheng, Yuanfan Guo, Ying Li, Songcen Xu, Jiankang Deng, Hang Xu", + "authors": [ + { + "first_name": "Qingping", + "last_name": "Zheng" + }, + { + "first_name": "Ling", + "last_name": "Zheng" + }, + { + "first_name": "Yuanfan", + "last_name": "Guo" + }, + { + "first_name": "Ying", + "last_name": "Li" + }, + { + "first_name": "Songcen", + "last_name": "Xu" + }, + { + "first_name": "Jiankang", + "last_name": "Deng" + }, + { + "first_name": "Hang", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames", - "authors": "Shuming Liu, Chen-Lin Zhang, Chen Zhao, Bernard Ghanem", + "authors": [ + { + "first_name": "Shuming", + "last_name": "Liu" + }, + { + "first_name": "Chen-Lin", + "last_name": "Zhang" + }, + { + "first_name": "Chen", + "last_name": "Zhao" + }, + { + "first_name": "Bernard", + "last_name": "Ghanem" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Multimodal Representation Learning by Alternating Unimodal Adaptation", - "authors": "Xiaohui Zhang, Jaehong Yoon, Mohit Bansal, Huaxiu Yao", + "authors": [ + { + "first_name": "Xiaohui", + "last_name": "Zhang" + }, + { + "first_name": "Jaehong", + "last_name": "Yoon" + }, + { + "first_name": "Mohit", + "last_name": "Bansal" + }, + { + "first_name": "Huaxiu", + "last_name": "Yao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MS-MANO: Enabling Hand Pose Tracking with Biomechanical Constraints", - "authors": "Pengfei Xie, Wenqiang Xu, Tutian Tang, Zhenjun Yu, Cewu Lu", + "authors": [ + { + "first_name": "Pengfei", + "last_name": "Xie" + }, + { + "first_name": "Wenqiang", + "last_name": "Xu" + }, + { + "first_name": "Tutian", + "last_name": "Tang" + }, + { + "first_name": "Zhenjun", + "last_name": "Yu" + }, + { + "first_name": "Cewu", + "last_name": "Lu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Generate Like Experts: Multi-Stage Font Generation by Incorporating Font Transfer Process into Diffusion Models", - "authors": "Bin Fu, Fanghua Yu, Anran Liu, Zixuan Wang, Jie Wen, Junjun He, Yu Qiao", + "authors": [ + { + "first_name": "Bin", + "last_name": "Fu" + }, + { + "first_name": "Fanghua", + "last_name": "Yu" + }, + { + "first_name": "Anran", + "last_name": "Liu" + }, + { + "first_name": "Zixuan", + "last_name": "Wang" + }, + { + "first_name": "Jie", + "last_name": "Wen" + }, + { + "first_name": "Junjun", + "last_name": "He" + }, + { + "first_name": "Yu", + "last_name": "Qiao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Pre-training Vision Models with Mandelbulb Variations", - "authors": "Benjamin Naoto Chiche, Yuto Horikawa, Ryo Fujita", + "authors": [ + { + "first_name": "Benjamin", + "last_name": "Naoto Chiche" + }, + { + "first_name": "Yuto", + "last_name": "Horikawa" + }, + { + "first_name": "Ryo", + "last_name": "Fujita" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Diffuse Attend and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusion", - "authors": "Junjiao Tian, Lavisha Aggarwal, Andrea Colaco, Zsolt Kira, Mar Gonzalez-Franco", + "authors": [ + { + "first_name": "Junjiao", + "last_name": "Tian" + }, + { + "first_name": "Lavisha", + "last_name": "Aggarwal" + }, + { + "first_name": "Andrea", + "last_name": "Colaco" + }, + { + "first_name": "Zsolt", + "last_name": "Kira" + }, + { + "first_name": "Mar", + "last_name": "Gonzalez-Franco" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "TransNeXt: Robust Foveal Visual Perception for Vision Transformers", - "authors": "Dai Shi", + "authors": [ + { + "first_name": "Dai", + "last_name": "Shi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Implicit Discriminative Knowledge Learning for Visible-Infrared Person Re-Identification", - "authors": "Kaijie Ren, Lei Zhang", + "authors": [ + { + "first_name": "Kaijie", + "last_name": "Ren" + }, + { + "first_name": "Lei", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Modeling Dense Multimodal Interactions Between Biological Pathways and Histology for Survival Prediction", - "authors": "Guillaume Jaume, Anurag Vaidya, Richard J. Chen, Drew F.K. Williamson, Paul Pu Liang, Faisal Mahmood", + "authors": [ + { + "first_name": "Guillaume", + "last_name": "Jaume" + }, + { + "first_name": "Anurag", + "last_name": "Vaidya" + }, + { + "first_name": "Richard", + "last_name": "J. Chen" + }, + { + "first_name": "Drew", + "last_name": "F.K. Williamson" + }, + { + "first_name": "Paul", + "last_name": "Pu Liang" + }, + { + "first_name": "Faisal", + "last_name": "Mahmood" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Mining Supervision for Dynamic Regions in Self-Supervised Monocular Depth Estimation", - "authors": "Hoang Chuong Nguyen, Tianyu Wang, Jose M. Alvarez, Miaomiao Liu", + "authors": [ + { + "first_name": "Hoang", + "last_name": "Chuong Nguyen" + }, + { + "first_name": "Tianyu", + "last_name": "Wang" + }, + { + "first_name": "Jose", + "last_name": "M. Alvarez" + }, + { + "first_name": "Miaomiao", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Gradient Alignment for Cross-Domain Face Anti-Spoofing", - "authors": "Binh M. Le, Simon S. Woo", + "authors": [ + { + "first_name": "Binh", + "last_name": "M. Le" + }, + { + "first_name": "Simon", + "last_name": "S. Woo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Physics-guided Shape-from-Template: Monocular Video Perception through Neural Surrogate Models", - "authors": "David Stotko, Nils Wandel, Reinhard Klein", + "authors": [ + { + "first_name": "David", + "last_name": "Stotko" + }, + { + "first_name": "Nils", + "last_name": "Wandel" + }, + { + "first_name": "Reinhard", + "last_name": "Klein" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "S2MVTC: a Simple yet Efficient Scalable Multi-View Tensor Clustering", - "authors": "Zhen Long, Qiyuan Wang, Yazhou Ren, Yipeng Liu, Ce Zhu", + "authors": [ + { + "first_name": "Zhen", + "last_name": "Long" + }, + { + "first_name": "Qiyuan", + "last_name": "Wang" + }, + { + "first_name": "Yazhou", + "last_name": "Ren" + }, + { + "first_name": "Yipeng", + "last_name": "Liu" + }, + { + "first_name": "Ce", + "last_name": "Zhu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "OpticalDR: A Deep Optical Imaging Model for Privacy-Protective Depression Recognition", - "authors": "Yuchen Pan, Junjun Jiang, Kui Jiang, Zhihao Wu, Keyuan Yu, Xianming Liu", + "authors": [ + { + "first_name": "Yuchen", + "last_name": "Pan" + }, + { + "first_name": "Junjun", + "last_name": "Jiang" + }, + { + "first_name": "Kui", + "last_name": "Jiang" + }, + { + "first_name": "Zhihao", + "last_name": "Wu" + }, + { + "first_name": "Keyuan", + "last_name": "Yu" + }, + { + "first_name": "Xianming", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Observation-Guided Diffusion Probabilistic Models", - "authors": "Junoh Kang, Jinyoung Choi, Sungik Choi, Bohyung Han", + "authors": [ + { + "first_name": "Junoh", + "last_name": "Kang" + }, + { + "first_name": "Jinyoung", + "last_name": "Choi" + }, + { + "first_name": "Sungik", + "last_name": "Choi" + }, + { + "first_name": "Bohyung", + "last_name": "Han" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "You'll Never Walk Alone: A Sketch and Text Duet for Fine-Grained Image Retrieval", - "authors": "Subhadeep Koley, Ayan Kumar Bhunia, Aneeshan Sain, Pinaki Nath Chowdhury, Tao Xiang, Yi-Zhe Song", + "authors": [ + { + "first_name": "Subhadeep", + "last_name": "Koley" + }, + { + "first_name": "Ayan", + "last_name": "Kumar Bhunia" + }, + { + "first_name": "Aneeshan", + "last_name": "Sain" + }, + { + "first_name": "Pinaki", + "last_name": "Nath Chowdhury" + }, + { + "first_name": "Tao", + "last_name": "Xiang" + }, + { + "first_name": "Yi-Zhe", + "last_name": "Song" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Spatial-Aware Regression for Keypoint Localization", - "authors": "Dongkai Wang, Shiliang Zhang", + "authors": [ + { + "first_name": "Dongkai", + "last_name": "Wang" + }, + { + "first_name": "Shiliang", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "S2MAE: A Spatial-Spectral Pretraining Foundation Model for Spectral Remote Sensing Data", - "authors": "Xuyang Li, Danfeng Hong, Jocelyn Chanussot", + "authors": [ + { + "first_name": "Xuyang", + "last_name": "Li" + }, + { + "first_name": "Danfeng", + "last_name": "Hong" + }, + { + "first_name": "Jocelyn", + "last_name": "Chanussot" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "EFormer: Enhanced Transformer towards Semantic-Contour Features of Foreground for Portraits Matting", - "authors": "Zitao Wang, Qiguang Miao, Yue Xi, Peipei Zhao", + "authors": [ + { + "first_name": "Zitao", + "last_name": "Wang" + }, + { + "first_name": "Qiguang", + "last_name": "Miao" + }, + { + "first_name": "Yue", + "last_name": "Xi" + }, + { + "first_name": "Peipei", + "last_name": "Zhao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MultiPly: Reconstruction of Multiple People from Monocular Video in the Wild", - "authors": "Zeren Jiang, Chen Guo, Manuel Kaufmann, Tianjian Jiang, Julien Valentin, Otmar Hilliges, Jie Song", + "authors": [ + { + "first_name": "Zeren", + "last_name": "Jiang" + }, + { + "first_name": "Chen", + "last_name": "Guo" + }, + { + "first_name": "Manuel", + "last_name": "Kaufmann" + }, + { + "first_name": "Tianjian", + "last_name": "Jiang" + }, + { + "first_name": "Julien", + "last_name": "Valentin" + }, + { + "first_name": "Otmar", + "last_name": "Hilliges" + }, + { + "first_name": "Jie", + "last_name": "Song" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Unsupervised 3D Structure Inference from Category-Specific Image Collections", - "authors": "Weikang Wang, Dongliang Cao, Florian Bernard", + "authors": [ + { + "first_name": "Weikang", + "last_name": "Wang" + }, + { + "first_name": "Dongliang", + "last_name": "Cao" + }, + { + "first_name": "Florian", + "last_name": "Bernard" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DiG-IN: Diffusion Guidance for Investigating Networks - Uncovering Classifier Differences Neuron Visualisations and Visual Counterfactual Explanations", - "authors": "Maximilian Augustin, Yannic Neuhaus, Matthias Hein", + "authors": [ + { + "first_name": "Maximilian", + "last_name": "Augustin" + }, + { + "first_name": "Yannic", + "last_name": "Neuhaus" + }, + { + "first_name": "Matthias", + "last_name": "Hein" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "RepViT: Revisiting Mobile CNN From ViT Perspective", - "authors": "Ao Wang, Hui Chen, Zijia Lin, Jungong Han, Guiguang Ding", + "authors": [ + { + "first_name": "Ao", + "last_name": "Wang" + }, + { + "first_name": "Hui", + "last_name": "Chen" + }, + { + "first_name": "Zijia", + "last_name": "Lin" + }, + { + "first_name": "Jungong", + "last_name": "Han" + }, + { + "first_name": "Guiguang", + "last_name": "Ding" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MonoNPHM: Dynamic Head Reconstruction from Monocular Videos", - "authors": "Simon Giebenhain, Tobias Kirschstein, Markos Georgopoulos, Martin Rünz, Lourdes Agapito, Matthias Nießner", + "authors": [ + { + "first_name": "Simon", + "last_name": "Giebenhain" + }, + { + "first_name": "Tobias", + "last_name": "Kirschstein" + }, + { + "first_name": "Markos", + "last_name": "Georgopoulos" + }, + { + "first_name": "Martin", + "last_name": "Rünz" + }, + { + "first_name": "Lourdes", + "last_name": "Agapito" + }, + { + "first_name": "Matthias", + "last_name": "Nießner" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Realigning Confidence with Temporal Saliency Information for Point-Level Weakly-Supervised Temporal Action Localization", - "authors": "Ziying Xia, Jian Cheng, Siyu Liu, Yongxiang Hu, Shiguang Wang, Yijie Zhang, Liwan Dang", + "authors": [ + { + "first_name": "Ziying", + "last_name": "Xia" + }, + { + "first_name": "Jian", + "last_name": "Cheng" + }, + { + "first_name": "Siyu", + "last_name": "Liu" + }, + { + "first_name": "Yongxiang", + "last_name": "Hu" + }, + { + "first_name": "Shiguang", + "last_name": "Wang" + }, + { + "first_name": "Yijie", + "last_name": "Zhang" + }, + { + "first_name": "Liwan", + "last_name": "Dang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ConsistNet: Enforcing 3D Consistency for Multi-view Images Diffusion", - "authors": "Jiayu Yang, Ziang Cheng, Yunfei Duan, Pan Ji, Hongdong Li", + "authors": [ + { + "first_name": "Jiayu", + "last_name": "Yang" + }, + { + "first_name": "Ziang", + "last_name": "Cheng" + }, + { + "first_name": "Yunfei", + "last_name": "Duan" + }, + { + "first_name": "Pan", + "last_name": "Ji" + }, + { + "first_name": "Hongdong", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GenN2N: Generative NeRF2NeRF Translation", - "authors": "Xiangyue Liu, Han Xue, Kunming Luo, Ping Tan, Li Yi", + "authors": [ + { + "first_name": "Xiangyue", + "last_name": "Liu" + }, + { + "first_name": "Han", + "last_name": "Xue" + }, + { + "first_name": "Kunming", + "last_name": "Luo" + }, + { + "first_name": "Ping", + "last_name": "Tan" + }, + { + "first_name": "Li", + "last_name": "Yi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Theoretically Achieving Continuous Representation of Oriented Bounding Boxes", - "authors": "Zikai Xiao, Guoye Yang, Xue Yang, Taijiang Mu, Junchi Yan, Shimin Hu", + "authors": [ + { + "first_name": "Zikai", + "last_name": "Xiao" + }, + { + "first_name": "Guoye", + "last_name": "Yang" + }, + { + "first_name": "Xue", + "last_name": "Yang" + }, + { + "first_name": "Taijiang", + "last_name": "Mu" + }, + { + "first_name": "Junchi", + "last_name": "Yan" + }, + { + "first_name": "Shimin", + "last_name": "Hu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Universal Robustness via Median Randomized Smoothing for Real-World Super-Resolution", - "authors": "Zakariya Chaouai, Mohamed Tamaazousti", + "authors": [ + { + "first_name": "Zakariya", + "last_name": "Chaouai" + }, + { + "first_name": "Mohamed", + "last_name": "Tamaazousti" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "One-dimensional Adapter to Rule Them All: Concepts Diffusion Models and Erasing Applications", - "authors": "Mengyao Lyu, Yuhong Yang, Haiwen Hong, Hui Chen, Xuan Jin, Yuan He, Hui Xue, Jungong Han, Guiguang Ding", + "authors": [ + { + "first_name": "Mengyao", + "last_name": "Lyu" + }, + { + "first_name": "Yuhong", + "last_name": "Yang" + }, + { + "first_name": "Haiwen", + "last_name": "Hong" + }, + { + "first_name": "Hui", + "last_name": "Chen" + }, + { + "first_name": "Xuan", + "last_name": "Jin" + }, + { + "first_name": "Yuan", + "last_name": "He" + }, + { + "first_name": "Hui", + "last_name": "Xue" + }, + { + "first_name": "Jungong", + "last_name": "Han" + }, + { + "first_name": "Guiguang", + "last_name": "Ding" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Learning Large-Factor EM Image Super-Resolution with Generative Priors", - "authors": "Jiateng Shou, Zeyu Xiao, Shiyu Deng, Wei Huang, Peiyao Shi, Ruobing Zhang, Zhiwei Xiong, Feng Wu", + "authors": [ + { + "first_name": "Jiateng", + "last_name": "Shou" + }, + { + "first_name": "Zeyu", + "last_name": "Xiao" + }, + { + "first_name": "Shiyu", + "last_name": "Deng" + }, + { + "first_name": "Wei", + "last_name": "Huang" + }, + { + "first_name": "Peiyao", + "last_name": "Shi" + }, + { + "first_name": "Ruobing", + "last_name": "Zhang" + }, + { + "first_name": "Zhiwei", + "last_name": "Xiong" + }, + { + "first_name": "Feng", + "last_name": "Wu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DIMAT: Decentralized Iterative Merging-And-Training for Deep Learning Models", - "authors": "Nastaran Saadati, Minh Pham, Nasla Saleem, Joshua R. Waite, Aditya Balu, Zhanong Jiang, Chinmay Hegde, Soumik Sarkar", + "authors": [ + { + "first_name": "Nastaran", + "last_name": "Saadati" + }, + { + "first_name": "Minh", + "last_name": "Pham" + }, + { + "first_name": "Nasla", + "last_name": "Saleem" + }, + { + "first_name": "Joshua", + "last_name": "R. Waite" + }, + { + "first_name": "Aditya", + "last_name": "Balu" + }, + { + "first_name": "Zhanong", + "last_name": "Jiang" + }, + { + "first_name": "Chinmay", + "last_name": "Hegde" + }, + { + "first_name": "Soumik", + "last_name": "Sarkar" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "MMA: Multi-Modal Adapter for Vision-Language Models", - "authors": "Lingxiao Yang, Ru-Yuan Zhang, Yanchen Wang, Xiaohua Xie", + "authors": [ + { + "first_name": "Lingxiao", + "last_name": "Yang" + }, + { + "first_name": "Ru-Yuan", + "last_name": "Zhang" + }, + { + "first_name": "Yanchen", + "last_name": "Wang" + }, + { + "first_name": "Xiaohua", + "last_name": "Xie" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Kandinsky Conformal Prediction: Efficient Calibration of Image Segmentation Algorithms", - "authors": "Joren Brunekreef, Eric Marcus, Ray Sheombarsing, Jan-Jakob Sonke, Jonas Teuwen", + "authors": [ + { + "first_name": "Joren", + "last_name": "Brunekreef" + }, + { + "first_name": "Eric", + "last_name": "Marcus" + }, + { + "first_name": "Ray", + "last_name": "Sheombarsing" + }, + { + "first_name": "Jan-Jakob", + "last_name": "Sonke" + }, + { + "first_name": "Jonas", + "last_name": "Teuwen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Diversity-aware Channel Pruning for StyleGAN Compression", - "authors": "Jiwoo Chung, Sangeek Hyun, Sang-Heon Shim, Jae-Pil Heo", + "authors": [ + { + "first_name": "Jiwoo", + "last_name": "Chung" + }, + { + "first_name": "Sangeek", + "last_name": "Hyun" + }, + { + "first_name": "Sang-Heon", + "last_name": "Shim" + }, + { + "first_name": "Jae-Pil", + "last_name": "Heo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "BioCLIP: A Vision Foundation Model for the Tree of Life", - "authors": "Samuel Stevens, Jiaman Wu, Matthew J Thompson, Elizabeth G Campolongo, Chan Hee Song, David Edward Carlyn, Li Dong, Wasila M Dahdul, Charles Stewart, Tanya Berger-Wolf, Wei-Lun Chao, Yu Su", + "authors": [ + { + "first_name": "Samuel", + "last_name": "Stevens" + }, + { + "first_name": "Jiaman", + "last_name": "Wu" + }, + { + "first_name": "Matthew", + "last_name": "J Thompson" + }, + { + "first_name": "Elizabeth", + "last_name": "G Campolongo" + }, + { + "first_name": "Chan", + "last_name": "Hee Song" + }, + { + "first_name": "David", + "last_name": "Edward Carlyn" + }, + { + "first_name": "Li", + "last_name": "Dong" + }, + { + "first_name": "Wasila", + "last_name": "M Dahdul" + }, + { + "first_name": "Charles", + "last_name": "Stewart" + }, + { + "first_name": "Tanya", + "last_name": "Berger-Wolf" + }, + { + "first_name": "Wei-Lun", + "last_name": "Chao" + }, + { + "first_name": "Yu", + "last_name": "Su" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models", - "authors": "Rongjie Li, Songyang Zhang, Dahua Lin, Kai Chen, Xuming He", + "authors": [ + { + "first_name": "Rongjie", + "last_name": "Li" + }, + { + "first_name": "Songyang", + "last_name": "Zhang" + }, + { + "first_name": "Dahua", + "last_name": "Lin" + }, + { + "first_name": "Kai", + "last_name": "Chen" + }, + { + "first_name": "Xuming", + "last_name": "He" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Deep Imbalanced Regression via Hierarchical Classification Adjustment", - "authors": "Haipeng Xiong, Angela Yao", + "authors": [ + { + "first_name": "Haipeng", + "last_name": "Xiong" + }, + { + "first_name": "Angela", + "last_name": "Yao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Adaptive Fusion of Single-View and Multi-View Depth for Autonomous Driving", - "authors": "Junda Cheng, Wei Yin, Kaixuan Wang, Xiaozhi Chen, Shijie Wang, Xin Yang", + "authors": [ + { + "first_name": "Junda", + "last_name": "Cheng" + }, + { + "first_name": "Wei", + "last_name": "Yin" + }, + { + "first_name": "Kaixuan", + "last_name": "Wang" + }, + { + "first_name": "Xiaozhi", + "last_name": "Chen" + }, + { + "first_name": "Shijie", + "last_name": "Wang" + }, + { + "first_name": "Xin", + "last_name": "Yang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Neural Clustering based Visual Representation Learning", - "authors": "Guikun Chen, Xia Li, Yi Yang, Wenguan Wang", + "authors": [ + { + "first_name": "Guikun", + "last_name": "Chen" + }, + { + "first_name": "Xia", + "last_name": "Li" + }, + { + "first_name": "Yi", + "last_name": "Yang" + }, + { + "first_name": "Wenguan", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Continual Self-supervised Learning: Towards Universal Multi-modal Medical Data Representation Learning", - "authors": "Yiwen Ye, Yutong Xie, Jianpeng Zhang, Ziyang Chen, Qi Wu, Yong Xia", + "authors": [ + { + "first_name": "Yiwen", + "last_name": "Ye" + }, + { + "first_name": "Yutong", + "last_name": "Xie" + }, + { + "first_name": "Jianpeng", + "last_name": "Zhang" + }, + { + "first_name": "Ziyang", + "last_name": "Chen" + }, + { + "first_name": "Qi", + "last_name": "Wu" + }, + { + "first_name": "Yong", + "last_name": "Xia" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Sparse Semi-DETR: Sparse Learnable Queries for Semi-Supervised Object Detection", - "authors": "Tahira Shehzadi, Khurram Azeem Hashmi, Didier Stricker, Muhammad Zeshan Afzal", + "authors": [ + { + "first_name": "Tahira", + "last_name": "Shehzadi" + }, + { + "first_name": "Khurram", + "last_name": "Azeem Hashmi" + }, + { + "first_name": "Didier", + "last_name": "Stricker" + }, + { + "first_name": "Muhammad", + "last_name": "Zeshan Afzal" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Towards Efficient Replay in Federated Incremental Learning", - "authors": "Yichen Li, Qunwei Li, Haozhao Wang, Ruixuan Li, Wenliang Zhong, Guannan Zhang", + "authors": [ + { + "first_name": "Yichen", + "last_name": "Li" + }, + { + "first_name": "Qunwei", + "last_name": "Li" + }, + { + "first_name": "Haozhao", + "last_name": "Wang" + }, + { + "first_name": "Ruixuan", + "last_name": "Li" + }, + { + "first_name": "Wenliang", + "last_name": "Zhong" + }, + { + "first_name": "Guannan", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SimAC: A Simple Anti-Customization Method for Protecting Face Privacy against Text-to-Image Synthesis of Diffusion Models", - "authors": "Feifei Wang, Zhentao Tan, Tianyi Wei, Yue Wu, Qidong Huang", + "authors": [ + { + "first_name": "Feifei", + "last_name": "Wang" + }, + { + "first_name": "Zhentao", + "last_name": "Tan" + }, + { + "first_name": "Tianyi", + "last_name": "Wei" + }, + { + "first_name": "Yue", + "last_name": "Wu" + }, + { + "first_name": "Qidong", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Total-Decom: Decomposed 3D Scene Reconstruction with Minimal Interaction", - "authors": "Xiaoyang Lyu, Chirui Chang, Peng Dai, Yang-Tian Sun, Xiaojuan Qi", + "authors": [ + { + "first_name": "Xiaoyang", + "last_name": "Lyu" + }, + { + "first_name": "Chirui", + "last_name": "Chang" + }, + { + "first_name": "Peng", + "last_name": "Dai" + }, + { + "first_name": "Yang-Tian", + "last_name": "Sun" + }, + { + "first_name": "Xiaojuan", + "last_name": "Qi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Accelerating Neural Field Training via Soft Mining", - "authors": "Shakiba Kheradmand, Daniel Rebain, Gopal Sharma, Hossam Isack, Abhishek Kar, Andrea Tagliasacchi, Kwang Moo Yi", + "authors": [ + { + "first_name": "Shakiba", + "last_name": "Kheradmand" + }, + { + "first_name": "Daniel", + "last_name": "Rebain" + }, + { + "first_name": "Gopal", + "last_name": "Sharma" + }, + { + "first_name": "Hossam", + "last_name": "Isack" + }, + { + "first_name": "Abhishek", + "last_name": "Kar" + }, + { + "first_name": "Andrea", + "last_name": "Tagliasacchi" + }, + { + "first_name": "Kwang", + "last_name": "Moo Yi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Ensemble Diversity Facilitates Adversarial Transferability", - "authors": "Bowen Tang, Zheng Wang, Yi Bin, Qi Dou, Yang Yang, Heng Tao Shen", + "authors": [ + { + "first_name": "Bowen", + "last_name": "Tang" + }, + { + "first_name": "Zheng", + "last_name": "Wang" + }, + { + "first_name": "Yi", + "last_name": "Bin" + }, + { + "first_name": "Qi", + "last_name": "Dou" + }, + { + "first_name": "Yang", + "last_name": "Yang" + }, + { + "first_name": "Heng", + "last_name": "Tao Shen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Fair-VPT: Fair Visual Prompt Tuning for Image Classification", - "authors": "Sungho Park, Hyeran Byun", + "authors": [ + { + "first_name": "Sungho", + "last_name": "Park" + }, + { + "first_name": "Hyeran", + "last_name": "Byun" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Uncertainty-Aware Source-Free Adaptive Image Super-Resolution with Wavelet Augmentation Transformer", - "authors": "Yuang Ai, Xiaoqiang Zhou, Huaibo Huang, Lei Zhang, Ran He", + "authors": [ + { + "first_name": "Yuang", + "last_name": "Ai" + }, + { + "first_name": "Xiaoqiang", + "last_name": "Zhou" + }, + { + "first_name": "Huaibo", + "last_name": "Huang" + }, + { + "first_name": "Lei", + "last_name": "Zhang" + }, + { + "first_name": "Ran", + "last_name": "He" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Gear-NeRF: Free-Viewpoint Rendering and Tracking with Motion-aware Spatio-Temporal Sampling", - "authors": "Xinhang Liu, Yu-Wing Tai, Chi-Keung Tang, Pedro Miraldo, Suhas Lohit, Moitreya Chatterjee", + "authors": [ + { + "first_name": "Xinhang", + "last_name": "Liu" + }, + { + "first_name": "Yu-Wing", + "last_name": "Tai" + }, + { + "first_name": "Chi-Keung", + "last_name": "Tang" + }, + { + "first_name": "Pedro", + "last_name": "Miraldo" + }, + { + "first_name": "Suhas", + "last_name": "Lohit" + }, + { + "first_name": "Moitreya", + "last_name": "Chatterjee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "CaDeT: a Causal Disentanglement Approach for Robust Trajectory Prediction in Autonomous Driving", - "authors": "Mozhgan Pourkeshavarz, Junrui Zhang, Amir Rasouli", + "authors": [ + { + "first_name": "Mozhgan", + "last_name": "Pourkeshavarz" + }, + { + "first_name": "Junrui", + "last_name": "Zhang" + }, + { + "first_name": "Amir", + "last_name": "Rasouli" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis", - "authors": "Zhan Li, Zhang Chen, Zhong Li, Yi Xu", + "authors": [ + { + "first_name": "Zhan", + "last_name": "Li" + }, + { + "first_name": "Zhang", + "last_name": "Chen" + }, + { + "first_name": "Zhong", + "last_name": "Li" + }, + { + "first_name": "Yi", + "last_name": "Xu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Instruct-Imagen: Image Generation with Multi-modal Instruction", - "authors": "Hexiang Hu, Kelvin C.K. Chan, Yu-Chuan Su, Wenhu Chen, Yandong Li, Kihyuk Sohn, Yang Zhao, Xue Ben, Boqing Gong, William Cohen, Ming-Wei Chang, Xuhui Jia", + "authors": [ + { + "first_name": "Hexiang", + "last_name": "Hu" + }, + { + "first_name": "Kelvin", + "last_name": "C.K. Chan" + }, + { + "first_name": "Yu-Chuan", + "last_name": "Su" + }, + { + "first_name": "Wenhu", + "last_name": "Chen" + }, + { + "first_name": "Yandong", + "last_name": "Li" + }, + { + "first_name": "Kihyuk", + "last_name": "Sohn" + }, + { + "first_name": "Yang", + "last_name": "Zhao" + }, + { + "first_name": "Xue", + "last_name": "Ben" + }, + { + "first_name": "Boqing", + "last_name": "Gong" + }, + { + "first_name": "William", + "last_name": "Cohen" + }, + { + "first_name": "Ming-Wei", + "last_name": "Chang" + }, + { + "first_name": "Xuhui", + "last_name": "Jia" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Prompting Vision Foundation Models for Pathology Image Analysis", - "authors": "Chong Yin, Siqi Liu, Kaiyang Zhou, Vincent Wai-Sun Wong, Pong C. Yuen", + "authors": [ + { + "first_name": "Chong", + "last_name": "Yin" + }, + { + "first_name": "Siqi", + "last_name": "Liu" + }, + { + "first_name": "Kaiyang", + "last_name": "Zhou" + }, + { + "first_name": "Vincent", + "last_name": "Wai-Sun Wong" + }, + { + "first_name": "Pong", + "last_name": "C. Yuen" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Rethinking Few-shot 3D Point Cloud Semantic Segmentation", - "authors": "Zhaochong An, Guolei Sun, Yun Liu, Fayao Liu, Zongwei Wu, Dan Wang, Luc Van Gool, Serge Belongie", + "authors": [ + { + "first_name": "Zhaochong", + "last_name": "An" + }, + { + "first_name": "Guolei", + "last_name": "Sun" + }, + { + "first_name": "Yun", + "last_name": "Liu" + }, + { + "first_name": "Fayao", + "last_name": "Liu" + }, + { + "first_name": "Zongwei", + "last_name": "Wu" + }, + { + "first_name": "Dan", + "last_name": "Wang" + }, + { + "first_name": "Luc", + "last_name": "Van Gool" + }, + { + "first_name": "Serge", + "last_name": "Belongie" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SEED-Bench: Benchmarking Multimodal Large Language Models", - "authors": "Bohao Li, Yuying Ge, Yixiao Ge, Guangzhi Wang, Rui Wang, Ruimao Zhang, Ying Shan", + "authors": [ + { + "first_name": "Bohao", + "last_name": "Li" + }, + { + "first_name": "Yuying", + "last_name": "Ge" + }, + { + "first_name": "Yixiao", + "last_name": "Ge" + }, + { + "first_name": "Guangzhi", + "last_name": "Wang" + }, + { + "first_name": "Rui", + "last_name": "Wang" + }, + { + "first_name": "Ruimao", + "last_name": "Zhang" + }, + { + "first_name": "Ying", + "last_name": "Shan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "BrainWash: A Poisoning Attack to Forget in Continual Learning", - "authors": "Ali Abbasi, Parsa Nooralinejad, Hamed Pirsiavash, Soheil Kolouri", + "authors": [ + { + "first_name": "Ali", + "last_name": "Abbasi" + }, + { + "first_name": "Parsa", + "last_name": "Nooralinejad" + }, + { + "first_name": "Hamed", + "last_name": "Pirsiavash" + }, + { + "first_name": "Soheil", + "last_name": "Kolouri" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "GreedyViG: Dynamic Axial Graph Construction for Efficient Vision GNNs", - "authors": "Mustafa Munir, William Avery, Md Mostafijur Rahman, Radu Marculescu", + "authors": [ + { + "first_name": "Mustafa", + "last_name": "Munir" + }, + { + "first_name": "William", + "last_name": "Avery" + }, + { + "first_name": "Md", + "last_name": "Mostafijur Rahman" + }, + { + "first_name": "Radu", + "last_name": "Marculescu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Relightable and Animatable Neural Avatar from Sparse-View Video", - "authors": "Zhen Xu, Sida Peng, Chen Geng, Linzhan Mou, Zihan Yan, Jiaming Sun, Hujun Bao, Xiaowei Zhou", + "authors": [ + { + "first_name": "Zhen", + "last_name": "Xu" + }, + { + "first_name": "Sida", + "last_name": "Peng" + }, + { + "first_name": "Chen", + "last_name": "Geng" + }, + { + "first_name": "Linzhan", + "last_name": "Mou" + }, + { + "first_name": "Zihan", + "last_name": "Yan" + }, + { + "first_name": "Jiaming", + "last_name": "Sun" + }, + { + "first_name": "Hujun", + "last_name": "Bao" + }, + { + "first_name": "Xiaowei", + "last_name": "Zhou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FreePoint: Unsupervised Point Cloud Instance Segmentation", - "authors": "Zhikai Zhang, Jian Ding, Li Jiang, Dengxin Dai, Guisong Xia", + "authors": [ + { + "first_name": "Zhikai", + "last_name": "Zhang" + }, + { + "first_name": "Jian", + "last_name": "Ding" + }, + { + "first_name": "Li", + "last_name": "Jiang" + }, + { + "first_name": "Dengxin", + "last_name": "Dai" + }, + { + "first_name": "Guisong", + "last_name": "Xia" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Pose Adapted Shape Learning for Large-Pose Face Reenactment", - "authors": "Gee-Sern Jison Hsu, Jie-Ying Zhang, Huang Yu Hsiang, Wei-Jie Hong", + "authors": [ + { + "first_name": "Gee-Sern", + "last_name": "Jison Hsu" + }, + { + "first_name": "Jie-Ying", + "last_name": "Zhang" + }, + { + "first_name": "Huang", + "last_name": "Yu Hsiang" + }, + { + "first_name": "Wei-Jie", + "last_name": "Hong" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Object Pose Estimation via the Aggregation of Diffusion Features", - "authors": "Tianfu Wang, Guosheng Hu, Hongguang Wang", + "authors": [ + { + "first_name": "Tianfu", + "last_name": "Wang" + }, + { + "first_name": "Guosheng", + "last_name": "Hu" + }, + { + "first_name": "Hongguang", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Circuit Design and Efficient Simulation of Quantum Inner Product and Empirical Studies of Its Effect on Near-Term Hybrid Quantum-Classic Machine Learning", - "authors": "Hao Xiong, Yehui Tang, Xinyu Ye, Junchi Yan", + "authors": [ + { + "first_name": "Hao", + "last_name": "Xiong" + }, + { + "first_name": "Yehui", + "last_name": "Tang" + }, + { + "first_name": "Xinyu", + "last_name": "Ye" + }, + { + "first_name": "Junchi", + "last_name": "Yan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "How to Make Cross Encoder a Good Teacher for Efficient Image-Text Retrieval?", - "authors": "Yuxin Chen, Zongyang Ma, Ziqi Zhang, Zhongang Qi, Chunfeng Yuan, Bing Li, Junfu Pu, Ying Shan, Xiaojuan Qi, Weiming Hu", + "authors": [ + { + "first_name": "Yuxin", + "last_name": "Chen" + }, + { + "first_name": "Zongyang", + "last_name": "Ma" + }, + { + "first_name": "Ziqi", + "last_name": "Zhang" + }, + { + "first_name": "Zhongang", + "last_name": "Qi" + }, + { + "first_name": "Chunfeng", + "last_name": "Yuan" + }, + { + "first_name": "Bing", + "last_name": "Li" + }, + { + "first_name": "Junfu", + "last_name": "Pu" + }, + { + "first_name": "Ying", + "last_name": "Shan" + }, + { + "first_name": "Xiaojuan", + "last_name": "Qi" + }, + { + "first_name": "Weiming", + "last_name": "Hu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Diffeomorphic Template Registration for Atmospheric Turbulence Mitigation", - "authors": "Dong Lao, Congli Wang, Alex Wong, Stefano Soatto", + "authors": [ + { + "first_name": "Dong", + "last_name": "Lao" + }, + { + "first_name": "Congli", + "last_name": "Wang" + }, + { + "first_name": "Alex", + "last_name": "Wong" + }, + { + "first_name": "Stefano", + "last_name": "Soatto" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Selective Nonlinearities Removal from Digital Signals", - "authors": "Krzysztof A. Maliszewski, Magdalena A. Urba?ska, Varvara Vetrova, Sylwia M. Kolenderska", + "authors": [ + { + "first_name": "Krzysztof", + "last_name": "A. Maliszewski" + }, + { + "first_name": "Magdalena", + "last_name": "A. Urba?ska" + }, + { + "first_name": "Varvara", + "last_name": "Vetrova" + }, + { + "first_name": "Sylwia", + "last_name": "M. Kolenderska" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "NB-GTR: Narrow-Band Guided Turbulence Removal", - "authors": "Yifei Xia, Chu Zhou, Chengxuan Zhu, Minggui Teng, Chao Xu, Boxin Shi", + "authors": [ + { + "first_name": "Yifei", + "last_name": "Xia" + }, + { + "first_name": "Chu", + "last_name": "Zhou" + }, + { + "first_name": "Chengxuan", + "last_name": "Zhu" + }, + { + "first_name": "Minggui", + "last_name": "Teng" + }, + { + "first_name": "Chao", + "last_name": "Xu" + }, + { + "first_name": "Boxin", + "last_name": "Shi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Can Biases in ImageNet Models Explain Generalization?", - "authors": "Paul Gavrikov, Janis Keuper", + "authors": [ + { + "first_name": "Paul", + "last_name": "Gavrikov" + }, + { + "first_name": "Janis", + "last_name": "Keuper" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "NRDF: Neural Riemannian Distance Fields for Learning Articulated Pose Priors", - "authors": "Yannan He, Garvita Tiwari, Tolga Birdal, Jan Eric Lenssen, Gerard Pons-Moll", + "authors": [ + { + "first_name": "Yannan", + "last_name": "He" + }, + { + "first_name": "Garvita", + "last_name": "Tiwari" + }, + { + "first_name": "Tolga", + "last_name": "Birdal" + }, + { + "first_name": "Jan", + "last_name": "Eric Lenssen" + }, + { + "first_name": "Gerard", + "last_name": "Pons-Moll" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "RepAn: Enhanced Annealing through Re-parameterization", - "authors": "Xiang Fei, Xiawu Zheng, Yan Wang, Fei Chao, Chenglin Wu, Liujuan Cao", + "authors": [ + { + "first_name": "Xiang", + "last_name": "Fei" + }, + { + "first_name": "Xiawu", + "last_name": "Zheng" + }, + { + "first_name": "Yan", + "last_name": "Wang" + }, + { + "first_name": "Fei", + "last_name": "Chao" + }, + { + "first_name": "Chenglin", + "last_name": "Wu" + }, + { + "first_name": "Liujuan", + "last_name": "Cao" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Generative Quanta Color Imaging", - "authors": "Vishal Purohit, Junjie Luo, Yiheng Chi, Qi Guo, Stanley H. Chan, Qiang Qiu", + "authors": [ + { + "first_name": "Vishal", + "last_name": "Purohit" + }, + { + "first_name": "Junjie", + "last_name": "Luo" + }, + { + "first_name": "Yiheng", + "last_name": "Chi" + }, + { + "first_name": "Qi", + "last_name": "Guo" + }, + { + "first_name": "Stanley", + "last_name": "H. Chan" + }, + { + "first_name": "Qiang", + "last_name": "Qiu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers", - "authors": "Tsai-Shien Chen, Aliaksandr Siarohin, Willi Menapace, Ekaterina Deyneka, Hsiang-wei Chao, Byung Eun Jeon, Yuwei Fang, Hsin-Ying Lee, Jian Ren, Ming-Hsuan Yang, Sergey Tulyakov", + "authors": [ + { + "first_name": "Tsai-Shien", + "last_name": "Chen" + }, + { + "first_name": "Aliaksandr", + "last_name": "Siarohin" + }, + { + "first_name": "Willi", + "last_name": "Menapace" + }, + { + "first_name": "Ekaterina", + "last_name": "Deyneka" + }, + { + "first_name": "Hsiang-wei", + "last_name": "Chao" + }, + { + "first_name": "Byung", + "last_name": "Eun Jeon" + }, + { + "first_name": "Yuwei", + "last_name": "Fang" + }, + { + "first_name": "Hsin-Ying", + "last_name": "Lee" + }, + { + "first_name": "Jian", + "last_name": "Ren" + }, + { + "first_name": "Ming-Hsuan", + "last_name": "Yang" + }, + { + "first_name": "Sergey", + "last_name": "Tulyakov" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Overload: Latency Attacks on Object Detection for Edge Devices", - "authors": "Erh-Chung Chen, Pin-Yu Chen, I-Hsin Chung, Che-Rung Lee", + "authors": [ + { + "first_name": "Erh-Chung", + "last_name": "Chen" + }, + { + "first_name": "Pin-Yu", + "last_name": "Chen" + }, + { + "first_name": "I-Hsin", + "last_name": "Chung" + }, + { + "first_name": "Che-Rung", + "last_name": "Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DreamControl: Control-Based Text-to-3D Generation with 3D Self-Prior", - "authors": "Tianyu Huang, Yihan Zeng, Zhilu Zhang, Wan Xu, Hang Xu, Songcen Xu, Rynson W.H. Lau, Wangmeng Zuo", + "authors": [ + { + "first_name": "Tianyu", + "last_name": "Huang" + }, + { + "first_name": "Yihan", + "last_name": "Zeng" + }, + { + "first_name": "Zhilu", + "last_name": "Zhang" + }, + { + "first_name": "Wan", + "last_name": "Xu" + }, + { + "first_name": "Hang", + "last_name": "Xu" + }, + { + "first_name": "Songcen", + "last_name": "Xu" + }, + { + "first_name": "Rynson", + "last_name": "W.H. Lau" + }, + { + "first_name": "Wangmeng", + "last_name": "Zuo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Infrared Small Target Detection with Scale and Location Sensitivity", - "authors": "Qiankun Liu, Rui Liu, Bolun Zheng, Hongkui Wang, Ying Fu", + "authors": [ + { + "first_name": "Qiankun", + "last_name": "Liu" + }, + { + "first_name": "Rui", + "last_name": "Liu" + }, + { + "first_name": "Bolun", + "last_name": "Zheng" + }, + { + "first_name": "Hongkui", + "last_name": "Wang" + }, + { + "first_name": "Ying", + "last_name": "Fu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Self-supervised Debiasing Using Low Rank Regularization", - "authors": "Geon Yeong Park, Chanyong Jung, Sangmin Lee, Jong Chul Ye, Sang Wan Lee", + "authors": [ + { + "first_name": "Geon", + "last_name": "Yeong Park" + }, + { + "first_name": "Chanyong", + "last_name": "Jung" + }, + { + "first_name": "Sangmin", + "last_name": "Lee" + }, + { + "first_name": "Jong", + "last_name": "Chul Ye" + }, + { + "first_name": "Sang", + "last_name": "Wan Lee" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "ODIN: A Single Model for 2D and 3D Segmentation", - "authors": "Ayush Jain, Pushkal Katara, Nikolaos Gkanatsios, Adam W. Harley, Gabriel Sarch, Kriti Aggarwal, Vishrav Chaudhary, Katerina Fragkiadaki", + "authors": [ + { + "first_name": "Ayush", + "last_name": "Jain" + }, + { + "first_name": "Pushkal", + "last_name": "Katara" + }, + { + "first_name": "Nikolaos", + "last_name": "Gkanatsios" + }, + { + "first_name": "Adam", + "last_name": "W. Harley" + }, + { + "first_name": "Gabriel", + "last_name": "Sarch" + }, + { + "first_name": "Kriti", + "last_name": "Aggarwal" + }, + { + "first_name": "Vishrav", + "last_name": "Chaudhary" + }, + { + "first_name": "Katerina", + "last_name": "Fragkiadaki" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SD4Match: Learning to Prompt Stable Diffusion Model for Semantic Matching", - "authors": "Xinghui Li, Jingyi Lu, Kai Han, Victor Adrian Prisacariu", + "authors": [ + { + "first_name": "Xinghui", + "last_name": "Li" + }, + { + "first_name": "Jingyi", + "last_name": "Lu" + }, + { + "first_name": "Kai", + "last_name": "Han" + }, + { + "first_name": "Victor", + "last_name": "Adrian Prisacariu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "InitNO: Boosting Text-to-Image Diffusion Models via Initial Noise Optimization", - "authors": "Xiefan Guo, Jinlin Liu, Miaomiao Cui, Jiankai Li, Hongyu Yang, Di Huang", + "authors": [ + { + "first_name": "Xiefan", + "last_name": "Guo" + }, + { + "first_name": "Jinlin", + "last_name": "Liu" + }, + { + "first_name": "Miaomiao", + "last_name": "Cui" + }, + { + "first_name": "Jiankai", + "last_name": "Li" + }, + { + "first_name": "Hongyu", + "last_name": "Yang" + }, + { + "first_name": "Di", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Neural Video Compression with Feature Modulation", - "authors": "Jiahao Li, Bin Li, Yan Lu", + "authors": [ + { + "first_name": "Jiahao", + "last_name": "Li" + }, + { + "first_name": "Bin", + "last_name": "Li" + }, + { + "first_name": "Yan", + "last_name": "Lu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Data Poisoning based Backdoor Attacks to Contrastive Learning", - "authors": "Jinghuai Zhang, Hongbin Liu, Jinyuan Jia, Neil Zhenqiang Gong", + "authors": [ + { + "first_name": "Jinghuai", + "last_name": "Zhang" + }, + { + "first_name": "Hongbin", + "last_name": "Liu" + }, + { + "first_name": "Jinyuan", + "last_name": "Jia" + }, + { + "first_name": "Neil", + "last_name": "Zhenqiang Gong" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Multimodal Sense-Informed Forecasting of 3D Human Motions", - "authors": "Zhenyu Lou, Qiongjie Cui, Haofan Wang, Xu Tang, Hong Zhou", + "authors": [ + { + "first_name": "Zhenyu", + "last_name": "Lou" + }, + { + "first_name": "Qiongjie", + "last_name": "Cui" + }, + { + "first_name": "Haofan", + "last_name": "Wang" + }, + { + "first_name": "Xu", + "last_name": "Tang" + }, + { + "first_name": "Hong", + "last_name": "Zhou" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "FlowerFormer: Empowering Neural Architecture Encoding using a Flow-aware Graph Transformer", - "authors": "Dongyeong Hwang, Hyunju Kim, Sunwoo Kim, Kijung Shin", + "authors": [ + { + "first_name": "Dongyeong", + "last_name": "Hwang" + }, + { + "first_name": "Hyunju", + "last_name": "Kim" + }, + { + "first_name": "Sunwoo", + "last_name": "Kim" + }, + { + "first_name": "Kijung", + "last_name": "Shin" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "EmoGen: Emotional Image Content Generation with Text-to-Image Diffusion Models", - "authors": "Jingyuan Yang, Jiawei Feng, Hui Huang", + "authors": [ + { + "first_name": "Jingyuan", + "last_name": "Yang" + }, + { + "first_name": "Jiawei", + "last_name": "Feng" + }, + { + "first_name": "Hui", + "last_name": "Huang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Finding Lottery Tickets in Vision Models via Data-driven Spectral Foresight Pruning", - "authors": "Leonardo Iurada, Marco Ciccone, Tatiana Tommasi", + "authors": [ + { + "first_name": "Leonardo", + "last_name": "Iurada" + }, + { + "first_name": "Marco", + "last_name": "Ciccone" + }, + { + "first_name": "Tatiana", + "last_name": "Tommasi" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "InNeRF360: Text-Guided 3D-Consistent Object Inpainting on 360-degree Neural Radiance Fields", - "authors": "Dongqing Wang, Tong Zhang, Alaa Abboud, Sabine Süsstrunk", + "authors": [ + { + "first_name": "Dongqing", + "last_name": "Wang" + }, + { + "first_name": "Tong", + "last_name": "Zhang" + }, + { + "first_name": "Alaa", + "last_name": "Abboud" + }, + { + "first_name": "Sabine", + "last_name": "Süsstrunk" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Neural Implicit Representation for Building Digital Twins of Unknown Articulated Objects", - "authors": "Yijia Weng, Bowen Wen, Jonathan Tremblay, Valts Blukis, Dieter Fox, Leonidas Guibas, Stan Birchfield", + "authors": [ + { + "first_name": "Yijia", + "last_name": "Weng" + }, + { + "first_name": "Bowen", + "last_name": "Wen" + }, + { + "first_name": "Jonathan", + "last_name": "Tremblay" + }, + { + "first_name": "Valts", + "last_name": "Blukis" + }, + { + "first_name": "Dieter", + "last_name": "Fox" + }, + { + "first_name": "Leonidas", + "last_name": "Guibas" + }, + { + "first_name": "Stan", + "last_name": "Birchfield" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Progressive Semantic-Guided Vision Transformer for Zero-Shot Learning", - "authors": "Shiming Chen, Wenjin Hou, Salman Khan, Fahad Shahbaz Khan", + "authors": [ + { + "first_name": "Shiming", + "last_name": "Chen" + }, + { + "first_name": "Wenjin", + "last_name": "Hou" + }, + { + "first_name": "Salman", + "last_name": "Khan" + }, + { + "first_name": "Fahad", + "last_name": "Shahbaz Khan" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detection", - "authors": "Junbo Yin, Jianbing Shen, Runnan Chen, Wei Li, Ruigang Yang, Pascal Frossard, Wenguan Wang", + "authors": [ + { + "first_name": "Junbo", + "last_name": "Yin" + }, + { + "first_name": "Jianbing", + "last_name": "Shen" + }, + { + "first_name": "Runnan", + "last_name": "Chen" + }, + { + "first_name": "Wei", + "last_name": "Li" + }, + { + "first_name": "Ruigang", + "last_name": "Yang" + }, + { + "first_name": "Pascal", + "last_name": "Frossard" + }, + { + "first_name": "Wenguan", + "last_name": "Wang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Building Bridges across Spatial and Temporal Resolutions: Reference-Based Super-Resolution via Change Priors and Conditional Diffusion Model", - "authors": "Runmin Dong, Shuai Yuan, Bin Luo, Mengxuan Chen, Jinxiao Zhang, Lixian Zhang, Weijia Li, Juepeng Zheng, Haohuan Fu", + "authors": [ + { + "first_name": "Runmin", + "last_name": "Dong" + }, + { + "first_name": "Shuai", + "last_name": "Yuan" + }, + { + "first_name": "Bin", + "last_name": "Luo" + }, + { + "first_name": "Mengxuan", + "last_name": "Chen" + }, + { + "first_name": "Jinxiao", + "last_name": "Zhang" + }, + { + "first_name": "Lixian", + "last_name": "Zhang" + }, + { + "first_name": "Weijia", + "last_name": "Li" + }, + { + "first_name": "Juepeng", + "last_name": "Zheng" + }, + { + "first_name": "Haohuan", + "last_name": "Fu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Vanishing-Point-Guided Video Semantic Segmentation of Driving Scenes", - "authors": "Diandian Guo, Deng-Ping Fan, Tongyu Lu, Christos Sakaridis, Luc Van Gool", + "authors": [ + { + "first_name": "Diandian", + "last_name": "Guo" + }, + { + "first_name": "Deng-Ping", + "last_name": "Fan" + }, + { + "first_name": "Tongyu", + "last_name": "Lu" + }, + { + "first_name": "Christos", + "last_name": "Sakaridis" + }, + { + "first_name": "Luc", + "last_name": "Van Gool" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Enhancing Intrinsic Features for Debiasing via Investigating Class-Discerning Common Attributes in Bias-Contrastive Pair", - "authors": "Jeonghoon Park, Chaeyeon Chung, Jaegul Choo", + "authors": [ + { + "first_name": "Jeonghoon", + "last_name": "Park" + }, + { + "first_name": "Chaeyeon", + "last_name": "Chung" + }, + { + "first_name": "Jaegul", + "last_name": "Choo" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "LAMP: Learn A Motion Pattern for Few-Shot Video Generation", - "authors": "Ruiqi Wu, Liangyu Chen, Tong Yang, Chunle Guo, Chongyi Li, Xiangyu Zhang", + "authors": [ + { + "first_name": "Ruiqi", + "last_name": "Wu" + }, + { + "first_name": "Liangyu", + "last_name": "Chen" + }, + { + "first_name": "Tong", + "last_name": "Yang" + }, + { + "first_name": "Chunle", + "last_name": "Guo" + }, + { + "first_name": "Chongyi", + "last_name": "Li" + }, + { + "first_name": "Xiangyu", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Compositional Chain-of-Thought Prompting for Large Multimodal Models", - "authors": "Chancharik Mitra, Brandon Huang, Trevor Darrell, Roei Herzig", + "authors": [ + { + "first_name": "Chancharik", + "last_name": "Mitra" + }, + { + "first_name": "Brandon", + "last_name": "Huang" + }, + { + "first_name": "Trevor", + "last_name": "Darrell" + }, + { + "first_name": "Roei", + "last_name": "Herzig" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Diffusion Time-step Curriculum for One Image to 3D Generation", - "authors": "Xuanyu Yi, Zike Wu, Qingshan Xu, Pan Zhou, Joo-Hwee Lim, Hanwang Zhang", + "authors": [ + { + "first_name": "Xuanyu", + "last_name": "Yi" + }, + { + "first_name": "Zike", + "last_name": "Wu" + }, + { + "first_name": "Qingshan", + "last_name": "Xu" + }, + { + "first_name": "Pan", + "last_name": "Zhou" + }, + { + "first_name": "Joo-Hwee", + "last_name": "Lim" + }, + { + "first_name": "Hanwang", + "last_name": "Zhang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Language-driven Object Fusion into Neural Radiance Fields with Pose-Conditioned Dataset Updates", - "authors": "Ka Chun Shum, Jaeyeon Kim, Binh-Son Hua, Duc Thanh Nguyen, Sai-Kit Yeung", + "authors": [ + { + "first_name": "Ka", + "last_name": "Chun Shum" + }, + { + "first_name": "Jaeyeon", + "last_name": "Kim" + }, + { + "first_name": "Binh-Son", + "last_name": "Hua" + }, + { + "first_name": "Duc", + "last_name": "Thanh Nguyen" + }, + { + "first_name": "Sai-Kit", + "last_name": "Yeung" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Adaptive Hyper-graph Aggregation for Modality-Agnostic Federated Learning", - "authors": "Fan Qi, Shuai Li", + "authors": [ + { + "first_name": "Fan", + "last_name": "Qi" + }, + { + "first_name": "Shuai", + "last_name": "Li" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "SPIN: Simultaneous Perception Interaction and Navigation", - "authors": "Shagun Uppal, Ananye Agarwal, Haoyu Xiong, Kenneth Shaw, Deepak Pathak", + "authors": [ + { + "first_name": "Shagun", + "last_name": "Uppal" + }, + { + "first_name": "Ananye", + "last_name": "Agarwal" + }, + { + "first_name": "Haoyu", + "last_name": "Xiong" + }, + { + "first_name": "Kenneth", + "last_name": "Shaw" + }, + { + "first_name": "Deepak", + "last_name": "Pathak" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "DREAM: Diffusion Rectification and Estimation-Adaptive Models", - "authors": "Jinxin Zhou, Tianyu Ding, Tianyi Chen, Jiachen Jiang, Ilya Zharkov, Zhihui Zhu, Luming Liang", + "authors": [ + { + "first_name": "Jinxin", + "last_name": "Zhou" + }, + { + "first_name": "Tianyu", + "last_name": "Ding" + }, + { + "first_name": "Tianyi", + "last_name": "Chen" + }, + { + "first_name": "Jiachen", + "last_name": "Jiang" + }, + { + "first_name": "Ilya", + "last_name": "Zharkov" + }, + { + "first_name": "Zhihui", + "last_name": "Zhu" + }, + { + "first_name": "Luming", + "last_name": "Liang" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1 }, { "title": "Exploring the Potential of Large Foundation Models for Open-Vocabulary HOI Detection", - "authors": "Ting Lei, Shaofeng Yin, Yang Liu", + "authors": [ + { + "first_name": "Ting", + "last_name": "Lei" + }, + { + "first_name": "Shaofeng", + "last_name": "Yin" + }, + { + "first_name": "Yang", + "last_name": "Liu" + } + ], "publication": "IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)", "pubTime": "2024", "pubType": 1