cv.md

Computer Vision

Including Classification, Recognition, Detection, Captioning, GAN and etc.

Datasets

• [2018 CVPR] Referring Relationships, [paper], [bibtex], [homepage], sources: [StanfordVL/ReferringRelationships].
• [2019 CVPR] From Recognition to Cognition: Visual Commonsense Reasoning, [paper], [bibtex], [homepage], [leaderboard], [dataset], sources: [rowanz/r2c].

Image Processing

• [2018 IJCAI] DehazeGAN: When Image Dehazing Meets Differential Programming, [paper].
• [2018 AAAI] Towards Perceptual Image Dehazing by Physics-based Disentanglement and Adversarial Training, [paper].

Image Classification/Recognition and Object Detection

• [2012 NIPS] ImageNet Classification with Deep Convolutional Neural Networks, AlexNet, [paper].
• [2014 ArXiv] Very Deep Convolutional Networks for Large-Scale Image Recognition, VGG, [paper].
• [2015 CVPR] Going Deeper with Convolutions, GoogLeNet, [paper].
• [2015 ICCV] Learning Spatiotemporal Features with 3D Convolutional Networks, [paper], [bibtex], [homepage], sources: [facebook/C3D], [hx173149/C3D-tensorflow].
• [2015 ICML] Siamese Neural Networks for One-shot Image Recognition, [paper], sources: [Goldesel23/Siamese-Networks-for-One-Shot-Learning].
• [2017 CVPR] Feature Pyramid Networks for Object Detection, [paper], [bibtex], sources: [unsky/FPN], [DetectionTeamUCAS/FPN_Tensorflow], [yangxue0827/FPN_Tensorflow].
• [2017 ICCV] Mask R-CNN, [paper], [tutorial], [video], sources: [matterport/Mask_RCNN], [CharlesShang/FastMaskRCNN], [facebookresearch/Detectron].
• [2017 ICCV] Focal Loss for Dense Object Detection, [paper], [bibtex], sources: [unsky/focal-loss], [ailias/Focal-Loss-implement-on-Tensorflow].
• [2017 CVPR] Densely Connected Convolutional Networks, [paper], sources: [liuzhuang13/DenseNet].
• [2018 CVPR] Zero-shot Recognition via Semantic Embeddings and Knowledge Graphs, [paper], [blog], sources: [JudyYe/zero-shot-gcn].
• [2018 ECCV] DOCK: Detecting Objects by Transferring Common-sense Knowledge, [paper], [bibtex], sources: [kkanshul/dock].

Instance/Semantic Description/Segmentation

• [2015 IPMI] Predicting Semantic Descriptions from Medical Images with Convolutional Neural Networks, [paper], [bibtex].
• [2017 CVPR] PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation, [paper], sources: [charlesq34/pointnet].
• [2018 ICML] Attention-based Deep Multiple Instance Learning, [paper], [bibtex], sources: [AMLab-Amsterdam/AttentionDeepMIL].

Image/Video Captioning

• [2017 PAMI] Show and Tell: Lessons learned from the 2015 MSCOCO Image Captioning Challenge, [paper], sources: [tensorflow/models/im2txt].
• [2018 ACL] Conceptual Captions: A Cleaned, Hypernymed, Image Alt-text Dataset For Automatic Image Captioning, [paper], [bibtex], [homepage], sources: [google-research-datasets/conceptual-captions].

Action Recognition

• [2016 CVPR] Dynamic Image Networks for Action Recognition, [paper], [bibtex], sources: [hbilen/dynamic-image-nets].
• [2016 CVPR] End-to-end Learning of Action Detection from Frame Glimpses in Videos, [paper], sources: [syyeung/frameglimpses].
• [2017 PAMI] Action Recognition with Dynamic Image Networks, [paper], [bibtex], sources: [hbilen/dynamic-image-nets].

Generative Adversarial Network (GAN)

• [2014 NIPS] Generative Adversarial Nets, [paper], sources: [goodfeli/adversarial], [aymericdamien/TensorFlow-Examples].
• [2016 ICLR] Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks, [paper], sources: [Newmu/dcgan_code].
• [2017 AAAI] SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient, [paper], sources:[LantaoYu/SeqGAN].
• [2017 ICCV] CycleGAN: Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks, [paper], [bibtex], [homepage], sources: [junyanz/pytorch-CycleGAN-and-pix2pix], [junyanz/CycleGAN], [xhujoy/CycleGAN-tensorflow].
• [2018 ICLR] CausalGAN: Learning Causal Implicit Generative Models with Adversarial Training, [paper], [bibtex], sources: [mkocaoglu/CausalGAN].
• [2018 ICLR] Progressive Growing of GANs for Improved Quality, Stability, and Variation, [paper], [bibtex], sources: [tkarras/progressive_growing_of_gans].
• [2018 ArXiv] A Style-Based Generator Architecture for Generative Adversarial Networks, [paper], [bibtex], [blog], sources: [NVlabs/stylegan], [Puzer/stylegan-encoder].
• [2018 ArXiv] XGAN: Unsupervised Image-to-Image Translation for Many-to-Many Mappings, [paper], [bibtex], [Cartoon Dataset].

Multi-tasks and Multi-model

• [2018 ICLR] Beyond Shared Hierarchies: Deep Multitask Learning Through Soft Layer Ordering, [paper], [bibtex].

Unassorted Research Works

• [2014 ECCV] Visualizing and Understanding Convolutional Networks, [paper].
• [2016 NIPS] Matching Networks for One Shot Learning, [paper], source: [AntreasAntoniou/MatchingNetworks], [BoyuanJiang/matching-networks-pytorch].
• [2017 ICLR] Adversarially Learned Inference, [paper], [bibtex], sources: [IshmaelBelghazi/ALI], [otenim/ALI-Keras2], [edgarriba/ali-pytorch].