Showing preview only (766K chars total). Download the full file or copy to clipboard to get everything.
Repository: zziz/pwc
Branch: master
Commit: 6805521215d9
Files: 5
Total size: 747.0 KB
Directory structure:
gitextract_pbxmyq_g/
├── CNAME
├── CONTRIBUTING.md
├── README.md
└── src/
├── README.md
└── pwc.csv
================================================
FILE CONTENTS
================================================
================================================
FILE: CNAME
================================================
www.paperake.com
================================================
FILE: CONTRIBUTING.md
================================================
### There are several ways that you can contribute
#### 1. Inspect repositories for paper and verify their correctness
- Open an issue
- Fix it and make a pull request
#### 2. Submit paper and its accompanying repository
- add it to pwc.csv in /src
- add it to README.md of this repository
- email it to me (fvzaur@gmail.com)
#### 3. Take a look at open issues and figure out how you can contribute
#### 4. Contribute to source code for curating Papers with Code
- Source code (PWC Engine) will be open gradually in upcoming months
#### For comments and suggestions for improving this repository, please do it [here](https://github.com/zziz/pwc/issues/1).
================================================
FILE: README.md
================================================
<div align="left">
<h1>
<img alt="HEADER" src="src/asset/header.jpg" width="900" height="300"></img>
</h1>
| [2018](#2018) | [2017](#2017) | [2016](#2016) | [2015](#2015) | [2014](#2014) | [2013](#2013) | 2012 | 2011 | 2010 | 2009 | 2008 | [](https://twitter.com/intent/tweet?text=Papers%20with%20code.%20Sorted%20by%20stars.%20Updated%20weekly.%20&url=https://github.com/zziz/pwc&via=fvzaur&hashtags=machinelearning,paper,code,github) | [Suggestions](https://github.com/zziz/pwc/issues/1) |
|:-------:|:-------:|:-------:|:-------:|:-------:|:-------:|:-------:|:-------:|:-------:|:-------:|:-------:|:-------:|:-------:|
This work is in continuous progress and update. We are adding new PWC everyday! Tweet me [@fvzaur](https://twitter.com/fvzaur)
Use [this](https://github.com/zziz/pwc/issues/11) thread to request us your favorite conference to be added to our watchlist and to PWC list.
#### Weekly updated pushed!
## 2018
| Title | Conf | Code | Stars |
|:--------|:--------:|:--------:|:--------:|
| [Video-to-Video Synthesis](https://arxiv.org/abs/1808.06601) | NIPS | [code](https://github.com/NVIDIA/vid2vid) | 5578 |
| [Deep Image Prior](http://openaccess.thecvf.com/content_cvpr_2018/papers/Ulyanov_Deep_Image_Prior_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/DmitryUlyanov/deep-image-prior) | 3736 |
| [StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Choi_StarGAN_Unified_Generative_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/yunjey/StarGAN) | 3405 |
| [Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network](http://openaccess.thecvf.com/content_ECCV_2018/html/Yao_Feng_Joint_3D_Face_ECCV_2018_paper.html) | ECCV | [code](https://github.com/YadiraF/PRNet) | 2434 |
| [Learning to See in the Dark](http://openaccess.thecvf.com/content_cvpr_2018/papers/Chen_Learning_to_See_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/cchen156/Learning-to-See-in-the-Dark) | 2326 |
| [Glow: Generative Flow with Invertible 1x1 Convolutions](http://arxiv.org/abs/1807.03039v2) | NIPS | [code](https://github.com/openai/glow) | 2088 |
| [Squeeze-and-Excitation Networks](http://openaccess.thecvf.com/content_cvpr_2018/papers/Hu_Squeeze-and-Excitation_Networks_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/hujie-frank/SENet) | 1477 |
| [Efficient Neural Architecture Search via Parameters Sharing](http://proceedings.mlr.press/v80/pham18a.html) | ICML | [code](https://github.com/carpedm20/ENAS-pytorch) | 1382 |
| [Multimodal Unsupervised Image-to-image Translation](http://openaccess.thecvf.com/content_ECCV_2018/html/Xun_Huang_Multimodal_Unsupervised_Image-to-image_ECCV_2018_paper.html) | ECCV | [code](https://github.com/NVlabs/MUNIT) | 1296 |
| [Non-Local Neural Networks](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_Non-Local_Neural_Networks_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/facebookresearch/video-nonlocal-net) | 992 |
| [Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?](http://openaccess.thecvf.com/content_cvpr_2018/papers/Hara_Can_Spatiotemporal_3D_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/kenshohara/3D-ResNets-PyTorch) | 924 |
| [Single-Shot Refinement Neural Network for Object Detection](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_Single-Shot_Refinement_Neural_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/sfzhang15/RefineDet) | 875 |
| [Image Generation From Scene Graphs](http://openaccess.thecvf.com/content_cvpr_2018/papers/Johnson_Image_Generation_From_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/google/sg2im) | 851 |
| [GANimation: Anatomically-aware Facial Animation from a Single Image](http://openaccess.thecvf.com/content_ECCV_2018/html/Albert_Pumarola_Anatomically_Coherent_Facial_ECCV_2018_paper.html) | ECCV | [code](https://github.com/albertpumarola/GANimation) | 772 |
| [Simple Baselines for Human Pose Estimation and Tracking](http://openaccess.thecvf.com/content_ECCV_2018/html/Bin_Xiao_Simple_Baselines_for_ECCV_2018_paper.html) | ECCV | [code](https://github.com/Microsoft/human-pose-estimation.pytorch) | 752 |
| [Visualizing the Loss Landscape of Neural Nets](http://arxiv.org/abs/1712.09913v2) | NIPS | [code](https://github.com/tomgoldstein/loss-landscape) | 724 |
| [Detect-and-Track: Efficient Pose Estimation in Videos](http://openaccess.thecvf.com/content_cvpr_2018/papers/Girdhar_Detect-and-Track_Efficient_Pose_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/facebookresearch/DetectAndTrack) | 650 |
| [Relation Networks for Object Detection](http://openaccess.thecvf.com/content_cvpr_2018/papers/Hu_Relation_Networks_for_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/msracver/Relation-Networks-for-Object-Detection) | 635 |
| [Generative Image Inpainting With Contextual Attention](http://openaccess.thecvf.com/content_cvpr_2018/papers/Yu_Generative_Image_Inpainting_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/JiahuiYu/generative_inpainting) | 609 |
| [PointCNN](http://arxiv.org/abs/1801.07791v3) | NIPS | [code](https://github.com/yangyanli/PointCNN) | 607 |
| [Look at Boundary: A Boundary-Aware Face Alignment Algorithm](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wu_Look_at_Boundary_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/wywu/LAB) | 575 |
| [Pelee: A Real-Time Object Detection System on Mobile Devices](nan) | NIPS | [code](https://github.com/Robert-JunWang/Pelee) | 548 |
| [Distractor-aware Siamese Networks for Visual Object Tracking](http://openaccess.thecvf.com/content_ECCV_2018/html/Zheng_Zhu_Distractor-aware_Siamese_Networks_ECCV_2018_paper.html) | ECCV | [code](https://github.com/foolwood/DaSiamRPN) | 545 |
| [Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples](http://proceedings.mlr.press/v80/athalye18a.html) | ICML | [code](https://github.com/anishathalye/obfuscated-gradients) | 535 |
| [Which Training Methods for GANs do actually Converge?](http://proceedings.mlr.press/v80/mescheder18a.html) | ICML | [code](https://github.com/LMescheder/GAN_stability) | 520 |
| [End-to-End Recovery of Human Shape and Pose](http://openaccess.thecvf.com/content_cvpr_2018/papers/Kanazawa_End-to-End_Recovery_of_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/akanazawa/hmr) | 502 |
| [Taskonomy: Disentangling Task Transfer Learning](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zamir_Taskonomy_Disentangling_Task_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/StanfordVL/taskonomy) | 502 |
| [Cascaded Pyramid Network for Multi-Person Pose Estimation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Chen_Cascaded_Pyramid_Network_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/chenyilun95/tf-cpn) | 497 |
| [Neural 3D Mesh Renderer](http://openaccess.thecvf.com/content_cvpr_2018/papers/Kato_Neural_3D_Mesh_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/hiroharu-kato/neural_renderer) | 489 |
| [Zero-Shot Recognition via Semantic Embeddings and Knowledge Graphs](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_Zero-Shot_Recognition_via_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/JudyYe/zero-shot-gcn) | 489 |
| [In-Place Activated BatchNorm for Memory-Optimized Training of DNNs](http://openaccess.thecvf.com/content_cvpr_2018/papers/Bulo_In-Place_Activated_BatchNorm_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/mapillary/inplace_abn) | 485 |
| [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_The_Unreasonable_Effectiveness_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/richzhang/PerceptualSimilarity) | 447 |
| [Frustum PointNets for 3D Object Detection From RGB-D Data](http://openaccess.thecvf.com/content_cvpr_2018/papers/Qi_Frustum_PointNets_for_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/charlesq34/frustum-pointnets) | 434 |
| [The Lovász-Softmax Loss: A Tractable Surrogate for the Optimization of the Intersection-Over-Union Measure in Neural Networks](http://openaccess.thecvf.com/content_cvpr_2018/papers/Berman_The_LovaSz-Softmax_Loss_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/bermanmaxim/LovaszSoftmax) | 416 |
| [ICNet for Real-Time Semantic Segmentation on High-Resolution Images](http://openaccess.thecvf.com/content_ECCV_2018/html/Hengshuang_Zhao_ICNet_for_Real-Time_ECCV_2018_paper.html) | ECCV | [code](https://github.com/hszhao/ICNet) | 415 |
| [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](http://openaccess.thecvf.com/content_cvpr_2018/papers/Sun_PWC-Net_CNNs_for_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/NVlabs/PWC-Net) | 398 |
| [Efficient Interactive Annotation of Segmentation Datasets With Polygon-RNN++](http://openaccess.thecvf.com/content_cvpr_2018/papers/Acuna_Efficient_Interactive_Annotation_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/fidler-lab/polyrnn-pp-pytorch) | 397 |
| [Gibson Env: Real-World Perception for Embodied Agents](http://openaccess.thecvf.com/content_cvpr_2018/papers/Xia_Gibson_Env_Real-World_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/StanfordVL/GibsonEnv) | 385 |
| [Acquisition of Localization Confidence for Accurate Object Detection](http://openaccess.thecvf.com/content_ECCV_2018/html/Borui_Jiang_Acquisition_of_Localization_ECCV_2018_paper.html) | ECCV | [code](https://github.com/vacancy/PreciseRoIPooling) | 384 |
| [Noise2Noise: Learning Image Restoration without Clean Data](http://proceedings.mlr.press/v80/lehtinen18a.html) | ICML | [code](https://github.com/yu4u/noise2noise) | 370 |
| [GeoNet: Geometric Neural Network for Joint Depth and Surface Normal Estimation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Qi_GeoNet_Geometric_Neural_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/yzcjtr/GeoNet) | 359 |
| [GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose](http://openaccess.thecvf.com/content_cvpr_2018/papers/Yin_GeoNet_Unsupervised_Learning_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/yzcjtr/GeoNet) | 359 |
| [A Style-Aware Content Loss for Real-time HD Style Transfer](http://openaccess.thecvf.com/content_ECCV_2018/html/Artsiom_Sanakoyeu_A_Style-aware_Content_ECCV_2018_paper.html) | ECCV | [code](https://github.com/CompVis/adaptive-style-transfer) | 349 |
| [Soccer on Your Tabletop](http://openaccess.thecvf.com/content_cvpr_2018/papers/Rematas_Soccer_on_Your_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/krematas/soccerontable) | 338 |
| [Pyramid Stereo Matching Network](http://openaccess.thecvf.com/content_cvpr_2018/papers/Chang_Pyramid_Stereo_Matching_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/JiaRenChang/PSMNet) | 335 |
| [Neural Baby Talk](http://openaccess.thecvf.com/content_cvpr_2018/papers/Lu_Neural_Baby_Talk_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/jiasenlu/NeuralBabyTalk) | 332 |
| [License Plate Detection and Recognition in Unconstrained Scenarios](http://openaccess.thecvf.com/content_ECCV_2018/html/Sergio_Silva_License_Plate_Detection_ECCV_2018_paper.html) | ECCV | [code](https://github.com/sergiomsilva/alpr-unconstrained) | 326 |
| [Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors](http://openaccess.thecvf.com/content_cvpr_2018/papers/Dong_Supervision-by-Registration_An_Unsupervised_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/facebookresearch/supervision-by-registration) | 326 |
| [Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images](http://openaccess.thecvf.com/content_ECCV_2018/html/Nanyang_Wang_Pixel2Mesh_Generating_3D_ECCV_2018_paper.html) | ECCV | [code](https://github.com/nywang16/Pixel2Mesh) | 323 |
| [Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning](http://openaccess.thecvf.com/content_cvpr_2018/papers/Mascharka_Transparency_by_Design_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/davidmascharka/tbd-nets) | 317 |
| [Fast End-to-End Trainable Guided Filter](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wu_Fast_End-to-End_Trainable_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/wuhuikai/DeepGuidedFilter) | 312 |
| [Deep Clustering for Unsupervised Learning of Visual Features](http://openaccess.thecvf.com/content_ECCV_2018/html/Mathilde_Caron_Deep_Clustering_for_ECCV_2018_paper.html) | ECCV | [code](https://github.com/facebookresearch/deepcluster) | 302 |
| [Deep Photo Enhancer: Unpaired Learning for Image Enhancement From Photographs With GANs](http://openaccess.thecvf.com/content_cvpr_2018/papers/Chen_Deep_Photo_Enhancer_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/nothinglo/Deep-Photo-Enhancer) | 294 |
| [Neural Relational Inference for Interacting Systems](http://proceedings.mlr.press/v80/kipf18a.html) | ICML | [code](https://github.com/ethanfetaya/NRI) | 289 |
| [Adversarially Regularized Autoencoders](http://proceedings.mlr.press/v80/zhao18b.html) | ICML | [code](https://github.com/jakezhaojb/ARAE) | 282 |
| [Learning to Adapt Structured Output Space for Semantic Segmentation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Tsai_Learning_to_Adapt_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/wasidennis/AdaptSegNet) | 280 |
| [Convolutional Neural Networks With Alternately Updated Clique](http://openaccess.thecvf.com/content_cvpr_2018/papers/Yang_Convolutional_Neural_Networks_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/iboing/CliqueNet) | 272 |
| [Learning to Segment Every Thing](http://openaccess.thecvf.com/content_cvpr_2018/papers/Hu_Learning_to_Segment_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/ronghanghu/seg_every_thing) | 269 |
| [Supervising Unsupervised Learning](http://arxiv.org/abs/1709.05262v2) | NIPS | [code](https://github.com/quinnliu/machineLearning) | 262 |
| [LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Hui_LiteFlowNet_A_Lightweight_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/twhui/LiteFlowNet) | 261 |
| [Bilinear Attention Networks](http://arxiv.org/abs/1805.07932v1) | NIPS | [code](https://github.com/jnhwkim/ban-vqa) | 258 |
| [ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation](http://openaccess.thecvf.com/content_ECCV_2018/html/Sachin_Mehta_ESPNet_Efficient_Spatial_ECCV_2018_paper.html) | ECCV | [code](https://github.com/sacmehta/ESPNet) | 254 |
| [An intriguing failing of convolutional neural networks and the CoordConv solution](https://arxiv.org/abs/1807.03247) | NIPS | [code](https://github.com/mkocabas/CoordConv-pytorch) | 249 |
| [End-to-End Learning of Motion Representation for Video Understanding](http://openaccess.thecvf.com/content_cvpr_2018/papers/Fan_End-to-End_Learning_of_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/LijieFan/tvnet) | 238 |
| [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](http://openaccess.thecvf.com/content_ECCV_2018/html/Yulun_Zhang_Image_Super-Resolution_Using_ECCV_2018_paper.html) | ECCV | [code](https://github.com/yulunzhang/RCAN) | 234 |
| [Iterative Visual Reasoning Beyond Convolutions](http://openaccess.thecvf.com/content_cvpr_2018/papers/Chen_Iterative_Visual_Reasoning_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/endernewton/iter-reason) | 228 |
| [Semi-Parametric Image Synthesis](http://openaccess.thecvf.com/content_cvpr_2018/papers/Qi_Semi-Parametric_Image_Synthesis_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/xjqicuhk/SIMS) | 226 |
| [Compressed Video Action Recognition](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wu_Compressed_Video_Action_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/chaoyuaw/pytorch-coviar) | 225 |
| [Style Aggregated Network for Facial Landmark Detection](http://openaccess.thecvf.com/content_cvpr_2018/papers/Dong_Style_Aggregated_Network_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/D-X-Y/SAN) | 223 |
| [Pose-Robust Face Recognition via Deep Residual Equivariant Mapping](http://openaccess.thecvf.com/content_cvpr_2018/papers/Cao_Pose-Robust_Face_Recognition_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/penincillin/DREAM) | 220 |
| [Multi-Content GAN for Few-Shot Font Style Transfer](http://openaccess.thecvf.com/content_cvpr_2018/papers/Azadi_Multi-Content_GAN_for_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/azadis/MC-GAN) | 218 |
| [GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models](http://proceedings.mlr.press/v80/you18a.html) | ICML | [code](https://github.com/JiaxuanYou/graph-generation) | 214 |
| [Referring Relationships](http://openaccess.thecvf.com/content_cvpr_2018/papers/Krishna_Referring_Relationships_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/StanfordVL/ReferringRelationships) | 210 |
| [MoCoGAN: Decomposing Motion and Content for Video Generation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Tulyakov_MoCoGAN_Decomposing_Motion_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/sergeytulyakov/mocogan) | 205 |
| [Latent Alignment and Variational Attention](http://arxiv.org/abs/1807.03756v1) | NIPS | [code](https://github.com/harvardnlp/var-attn) | 204 |
| [LayoutNet: Reconstructing the 3D Room Layout From a Single RGB Image](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zou_LayoutNet_Reconstructing_the_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/zouchuhang/LayoutNet) | 202 |
| [Large-Scale Point Cloud Semantic Segmentation With Superpoint Graphs](http://openaccess.thecvf.com/content_cvpr_2018/papers/Landrieu_Large-Scale_Point_Cloud_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/loicland/superpoint_graph) | 197 |
| [An End-to-End TextSpotter With Explicit Alignment and Attention](http://openaccess.thecvf.com/content_cvpr_2018/papers/He_An_End-to-End_TextSpotter_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/tonghe90/textspotter) | 195 |
| [DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks](http://openaccess.thecvf.com/content_cvpr_2018/papers/Kupyn_DeblurGAN_Blind_Motion_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/RaphaelMeudec/deblur-gan) | 189 |
| [SPLATNet: Sparse Lattice Networks for Point Cloud Processing](http://openaccess.thecvf.com/content_cvpr_2018/papers/Su_SPLATNet_Sparse_Lattice_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/NVlabs/splatnet) | 188 |
| [Attentive Generative Adversarial Network for Raindrop Removal From a Single Image](http://openaccess.thecvf.com/content_cvpr_2018/papers/Qian_Attentive_Generative_Adversarial_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/rui1996/DeRaindrop) | 186 |
| [Single View Stereo Matching](http://openaccess.thecvf.com/content_cvpr_2018/papers/Luo_Single_View_Stereo_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/lawy623/SVS) | 182 |
| [MegaDepth: Learning Single-View Depth Prediction From Internet Photos](http://openaccess.thecvf.com/content_cvpr_2018/papers/Li_MegaDepth_Learning_Single-View_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/lixx2938/MegaDepth) | 181 |
| [ECO: Efficient Convolutional Network for Online Video Understanding](http://openaccess.thecvf.com/content_ECCV_2018/html/Mohammadreza_Zolfaghari_ECO_Efficient_Convolutional_ECCV_2018_paper.html) | ECCV | [code](https://github.com/mzolfaghari/ECO-efficient-video-understanding) | 180 |
| [Unsupervised Feature Learning via Non-Parametric Instance Discrimination](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wu_Unsupervised_Feature_Learning_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/zhirongw/lemniscate.pytorch) | 180 |
| [ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositing](http://openaccess.thecvf.com/content_cvpr_2018/papers/Lin_ST-GAN_Spatial_Transformer_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/chenhsuanlin/spatial-transformer-GAN) | 179 |
| [Video Based Reconstruction of 3D People Models](http://openaccess.thecvf.com/content_cvpr_2018/papers/Alldieck_Video_Based_Reconstruction_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/thmoa/videoavatars) | 179 |
| [Social GAN: Socially Acceptable Trajectories With Generative Adversarial Networks](http://openaccess.thecvf.com/content_cvpr_2018/papers/Gupta_Social_GAN_Socially_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/agrimgupta92/sgan) | 178 |
| [Learning Category-Specific Mesh Reconstruction from Image Collections](http://openaccess.thecvf.com/content_ECCV_2018/html/Angjoo_Kanazawa_Learning_Category-Specific_Mesh_ECCV_2018_paper.html) | ECCV | [code](https://github.com/akanazawa/cmr) | 176 |
| [Realistic Evaluation of Deep Semi-Supervised Learning Algorithms](http://arxiv.org/abs/1804.09170v2) | NIPS | [code](https://github.com/brain-research/realistic-ssl-evaluation) | 175 |
| [BSN: Boundary Sensitive Network for Temporal Action Proposal Generation](http://openaccess.thecvf.com/content_ECCV_2018/html/Tianwei_Lin_BSN_Boundary_Sensitive_ECCV_2018_paper.html) | ECCV | [code](https://github.com/wzmsltw/BSN-boundary-sensitive-network) | 175 |
| [Group Normalization](http://openaccess.thecvf.com/content_ECCV_2018/html/Yuxin_Wu_Group_Normalization_ECCV_2018_paper.html) | ECCV | [code](https://github.com/shaohua0116/Group-Normalization-Tensorflow) | 175 |
| [Real-Time Seamless Single Shot 6D Object Pose Prediction](http://openaccess.thecvf.com/content_cvpr_2018/papers/Tekin_Real-Time_Seamless_Single_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/Microsoft/singleshotpose) | 174 |
| [MVSNet: Depth Inference for Unstructured Multi-view Stereo](http://openaccess.thecvf.com/content_ECCV_2018/html/Yao_Yao_MVSNet_Depth_Inference_ECCV_2018_paper.html) | ECCV | [code](https://github.com/YoYo000/MVSNet) | 174 |
| [Neural Motifs: Scene Graph Parsing With Global Context](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zellers_Neural_Motifs_Scene_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/rowanz/neural-motifs) | 171 |
| [Learning a Single Convolutional Super-Resolution Network for Multiple Degradations](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_Learning_a_Single_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/cszn/SRMD) | 169 |
| [Optimizing Video Object Detection via a Scale-Time Lattice](http://openaccess.thecvf.com/content_cvpr_2018/papers/Chen_Optimizing_Video_Object_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/hellock/scale-time-lattice) | 168 |
| [MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network](http://openaccess.thecvf.com/content_ECCV_2018/html/Muhammed_Kocabas_MultiPoseNet_Fast_Multi-Person_ECCV_2018_paper.html) | ECCV | [code](https://github.com/salihkaragoz/pose-residual-network-pytorch) | 167 |
| [Unsupervised Cross-Dataset Person Re-Identification by Transfer Learning of Spatial-Temporal Patterns](http://openaccess.thecvf.com/content_cvpr_2018/papers/Lv_Unsupervised_Cross-Dataset_Person_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/ahangchen/TFusion) | 166 |
| [Weakly Supervised Instance Segmentation Using Class Peak Response](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhou_Weakly_Supervised_Instance_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/ZhouYanzhao/PRM) | 166 |
| [PlaneNet: Piece-Wise Planar Reconstruction From a Single RGB Image](http://openaccess.thecvf.com/content_cvpr_2018/papers/Liu_PlaneNet_Piece-Wise_Planar_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/art-programmer/PlaneNet) | 164 |
| [Residual Dense Network for Image Super-Resolution](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_Residual_Dense_Network_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/yulunzhang/RDN) | 163 |
| [Embodied Question Answering](http://openaccess.thecvf.com/content_cvpr_2018/papers/Das_Embodied_Question_Answering_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/facebookresearch/EmbodiedQA) | 162 |
| [Evolved Policy Gradients](http://arxiv.org/abs/1802.04821v2) | NIPS | [code](https://github.com/openai/EPG) | 160 |
| [Camera Style Adaptation for Person Re-Identification](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhong_Camera_Style_Adaptation_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/zhunzhong07/CamStyle) | 159 |
| [Weakly and Semi Supervised Human Body Part Parsing via Pose-Guided Knowledge Transfer](http://openaccess.thecvf.com/content_cvpr_2018/papers/Fang_Weakly_and_Semi_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/MVIG-SJTU/WSHP) | 159 |
| [Scale-Recurrent Network for Deep Image Deblurring](http://openaccess.thecvf.com/content_cvpr_2018/papers/Tao_Scale-Recurrent_Network_for_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/jiangsutx/SRN-Deblur) | 159 |
| [Unsupervised Learning of Monocular Depth Estimation and Visual Odometry With Deep Feature Reconstruction](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhan_Unsupervised_Learning_of_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/Huangying-Zhan/Depth-VO-Feat) | 158 |
| [Relational recurrent neural networks](https://arxiv.org/abs/1806.01822) | NIPS | [code](https://github.com/L0SG/relational-rnn-pytorch) | 157 |
| [Densely Connected Pyramid Dehazing Network](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_Densely_Connected_Pyramid_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/hezhangsprinter/DCPDN) | 155 |
| [Image Inpainting for Irregular Holes Using Partial Convolutions](http://openaccess.thecvf.com/content_ECCV_2018/html/Guilin_Liu_Image_Inpainting_for_ECCV_2018_paper.html) | ECCV | [code](https://github.com/naoto0804/pytorch-inpainting-with-partial-conv) | 153 |
| [SO-Net: Self-Organizing Network for Point Cloud Analysis](http://openaccess.thecvf.com/content_cvpr_2018/papers/Li_SO-Net_Self-Organizing_Network_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/lijx10/SO-Net) | 152 |
| [Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling](http://openaccess.thecvf.com/content_cvpr_2018/papers/Sun_Pix3D_Dataset_and_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/xingyuansun/pix3d) | 152 |
| [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_ShuffleNet_An_Extremely_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/camel007/Caffe-ShuffleNet) | 152 |
| [DenseASPP for Semantic Segmentation in Street Scenes](http://openaccess.thecvf.com/content_cvpr_2018/papers/Yang_DenseASPP_for_Semantic_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/DeepMotionAIResearch/DenseASPP) | 151 |
| [Facelet-Bank for Fast Portrait Manipulation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Chen_Facelet-Bank_for_Fast_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/yingcong/Facelet_Bank) | 150 |
| [Self-Imitation Learning](http://proceedings.mlr.press/v80/oh18b.html) | ICML | [code](https://github.com/junhyukoh/self-imitation-learning) | 145 |
| [Graph R-CNN for Scene Graph Generation](http://openaccess.thecvf.com/content_ECCV_2018/html/Jianwei_Yang_Graph_R-CNN_for_ECCV_2018_paper.html) | ECCV | [code](https://github.com/jwyang/graph-rcnn.pytorch) | 144 |
| [A Closer Look at Spatiotemporal Convolutions for Action Recognition](http://openaccess.thecvf.com/content_cvpr_2018/papers/Tran_A_Closer_Look_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/irhumshafkat/R2Plus1D-PyTorch) | 143 |
| [Cross-Domain Weakly-Supervised Object Detection Through Progressive Domain Adaptation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Inoue_Cross-Domain_Weakly-Supervised_Object_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/naoto0804/cross-domain-detection) | 143 |
| [Quantized Densely Connected U-Nets for Efficient Landmark Localization](http://openaccess.thecvf.com/content_ECCV_2018/html/Zhiqiang_Tang_Quantized_Densely_Connected_ECCV_2018_paper.html) | ECCV | [code](https://github.com/zhiqiangdon/CU-Net) | 143 |
| [Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Deraining](http://openaccess.thecvf.com/content_ECCV_2018/html/Xia_Li_Recurrent_Squeeze-and-Excitation_Context_ECCV_2018_paper.html) | ECCV | [code](https://github.com/XiaLiPKU/RESCAN) | 142 |
| [Two-Stream Convolutional Networks for Dynamic Texture Synthesis](http://openaccess.thecvf.com/content_cvpr_2018/papers/Tesfaldet_Two-Stream_Convolutional_Networks_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/ryersonvisionlab/two-stream-dyntex-synth) | 141 |
| [Integral Human Pose Regression](http://openaccess.thecvf.com/content_ECCV_2018/html/Xiao_Sun_Integral_Human_Pose_ECCV_2018_paper.html) | ECCV | [code](https://github.com/JimmySuen/integral-human-pose) | 141 |
| [Adaptive Affinity Fields for Semantic Segmentation](http://openaccess.thecvf.com/content_ECCV_2018/html/Jyh-Jing_Hwang_Adaptive_Affinity_Field_ECCV_2018_paper.html) | ECCV | [code](https://github.com/twke18/Adaptive_Affinity_Fields) | 141 |
| [LSTM Pose Machines](http://openaccess.thecvf.com/content_cvpr_2018/papers/Luo_LSTM_Pose_Machines_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/lawy623/LSTM_Pose_Machines) | 141 |
| [Structure Inference Net: Object Detection Using Scene-Level Context and Instance-Level Relationships](http://openaccess.thecvf.com/content_cvpr_2018/papers/Liu_Structure_Inference_Net_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/choasup/SIN) | 140 |
| [Recovering Realistic Texture in Image Super-Resolution by Deep Spatial Feature Transform](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_Recovering_Realistic_Texture_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/xinntao/CVPR18-SFTGAN) | 139 |
| [Image-Image Domain Adaptation With Preserved Self-Similarity and Domain-Dissimilarity for Person Re-Identification](http://openaccess.thecvf.com/content_cvpr_2018/papers/Deng_Image-Image_Domain_Adaptation_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/Simon4Yan/Learning-via-Translation) | 137 |
| [Learning to Compare: Relation Network for Few-Shot Learning](http://openaccess.thecvf.com/content_cvpr_2018/papers/Sung_Learning_to_Compare_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/lzrobots/LearningToCompare_ZSL) | 135 |
| [CosFace: Large Margin Cosine Loss for Deep Face Recognition](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_CosFace_Large_Margin_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/yule-li/CosFace) | 135 |
| [Deep Depth Completion of a Single RGB-D Image](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_Deep_Depth_Completion_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/yindaz/DeepCompletionRelease) | 134 |
| [Deep Back-Projection Networks for Super-Resolution](http://openaccess.thecvf.com/content_cvpr_2018/papers/Haris_Deep_Back-Projection_Networks_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/alterzero/DBPN-Pytorch) | 132 |
| [Context Embedding Networks](http://openaccess.thecvf.com/content_cvpr_2018/papers/Kim_Context_Embedding_Networks_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/thunlp/CANE) | 131 |
| [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](http://openaccess.thecvf.com/content_cvpr_2018/papers/Kendall_Multi-Task_Learning_Using_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/alexgkendall/multitaskvision) | 131 |
| [Perturbative Neural Networks](http://openaccess.thecvf.com/content_cvpr_2018/papers/Juefei-Xu_Perturbative_Neural_Networks_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/juefeix/pnn.pytorch) | 130 |
| [Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis](http://proceedings.mlr.press/v80/wang18h.html) | ICML | [code](https://github.com/syang1993/gst-tacotron) | 129 |
| [Fast and Accurate Online Video Object Segmentation via Tracking Parts](http://openaccess.thecvf.com/content_cvpr_2018/papers/Cheng_Fast_and_Accurate_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/JingchunCheng/FAVOS) | 129 |
| [Nonlinear 3D Face Morphable Model](http://openaccess.thecvf.com/content_cvpr_2018/papers/Tran_Nonlinear_3D_Face_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/tranluan/Nonlinear_Face_3DMM) | 128 |
| [BodyNet: Volumetric Inference of 3D Human Body Shapes](http://openaccess.thecvf.com/content_ECCV_2018/html/Gul_Varol_BodyNet_Volumetric_Inference_ECCV_2018_paper.html) | ECCV | [code](https://github.com/gulvarol/bodynet) | 126 |
| [3D-CODED: 3D Correspondences by Deep Deformation](http://openaccess.thecvf.com/content_ECCV_2018/html/Thibault_Groueix_Shape_correspondences_from_ECCV_2018_paper.html) | ECCV | [code](https://github.com/ThibaultGROUEIX/3D-CODED) | 125 |
| [DeepMVS: Learning Multi-View Stereopsis](http://openaccess.thecvf.com/content_cvpr_2018/papers/Huang_DeepMVS_Learning_Multi-View_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/phuang17/DeepMVS) | 125 |
| [Hierarchical Imitation and Reinforcement Learning](http://proceedings.mlr.press/v80/le18a.html) | ICML | [code](https://github.com/hoangminhle/hierarchical_IL_RL) | 124 |
| [Domain Adaptive Faster R-CNN for Object Detection in the Wild](http://openaccess.thecvf.com/content_cvpr_2018/papers/Chen_Domain_Adaptive_Faster_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/yuhuayc/da-faster-rcnn) | 123 |
| [L4: Practical loss-based stepsize adaptation for deep learning](http://arxiv.org/abs/1802.05074v4) | NIPS | [code](https://github.com/martius-lab/l4-optimizer) | 123 |
| [A Generative Adversarial Approach for Zero-Shot Learning From Noisy Texts](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhu_A_Generative_Adversarial_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/EthanZhu90/ZSL_GAN_CVPR18) | 122 |
| [Recurrent Relational Networks](http://arxiv.org/abs/1711.08028v2) | NIPS | [code](https://github.com/rasmusbergpalm/recurrent-relational-networks) | 121 |
| [Gated Path Planning Networks](http://proceedings.mlr.press/v80/lee18c.html) | ICML | [code](https://github.com/lileee/gated-path-planning-networks) | 121 |
| [PSANet: Point-wise Spatial Attention Network for Scene Parsing](http://openaccess.thecvf.com/content_ECCV_2018/html/Hengshuang_Zhao_PSANet_Point-wise_Spatial_ECCV_2018_paper.html) | ECCV | [code](https://github.com/hszhao/PSANet) | 121 |
| [Rethinking Feature Distribution for Loss Functions in Image Classification](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wan_Rethinking_Feature_Distribution_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/WeitaoVan/L-GM-loss) | 120 |
| [Density-Aware Single Image De-Raining Using a Multi-Stream Dense Network](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_Density-Aware_Single_Image_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/hezhangsprinter/DID-MDN) | 118 |
| [FOTS: Fast Oriented Text Spotting With a Unified Network](http://openaccess.thecvf.com/content_cvpr_2018/papers/Liu_FOTS_Fast_Oriented_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/jiangxiluning/FOTS.PyTorch) | 118 |
| [ELEGANT: Exchanging Latent Encodings with GAN for Transferring Multiple Face Attributes](http://openaccess.thecvf.com/content_ECCV_2018/html/Taihong_Xiao_ELEGANT_Exchanging_Latent_ECCV_2018_paper.html) | ECCV | [code](https://github.com/Prinsphield/ELEGANT) | 117 |
| [PU-Net: Point Cloud Upsampling Network](http://openaccess.thecvf.com/content_cvpr_2018/papers/Yu_PU-Net_Point_Cloud_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/yulequan/PU-Net) | 117 |
| [PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning](http://openaccess.thecvf.com/content_cvpr_2018/papers/Mallya_PackNet_Adding_Multiple_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/arunmallya/packnet) | 117 |
| [Long-term Tracking in the Wild: a Benchmark](http://openaccess.thecvf.com/content_ECCV_2018/html/Efstratios_Gavves_Long-term_Tracking_in_ECCV_2018_paper.html) | ECCV | [code](https://github.com/oxuva/long-term-tracking-benchmark) | 116 |
| [Factoring Shape, Pose, and Layout From the 2D Image of a 3D Scene](http://openaccess.thecvf.com/content_cvpr_2018/papers/Tulsiani_Factoring_Shape_Pose_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/shubhtuls/factored3d) | 114 |
| [Repulsion Loss: Detecting Pedestrians in a Crowd](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_Repulsion_Loss_Detecting_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/bailvwangzi/repulsion_loss_ssd) | 113 |
| [Unsupervised Attention-guided Image-to-Image Translation](https://arxiv.org/abs/1806.02311) | NIPS | [code](https://github.com/AlamiMejjati/Unsupervised-Attention-guided-Image-to-Image-Translation) | 110 |
| [Attention-based Deep Multiple Instance Learning](http://proceedings.mlr.press/v80/ilse18a.html) | ICML | [code](https://github.com/AMLab-Amsterdam/AttentionDeepMIL) | 109 |
| [Learning Blind Video Temporal Consistency](http://openaccess.thecvf.com/content_ECCV_2018/html/Wei-Sheng_Lai_Real-Time_Blind_Video_ECCV_2018_paper.html) | ECCV | [code](https://github.com/phoenix104104/fast_blind_video_consistency) | 109 |
| [Noisy Natural Gradient as Variational Inference](http://proceedings.mlr.press/v80/zhang18l.html) | ICML | [code](https://github.com/wlwkgus/NoisyNaturalGradient) | 108 |
| [End-to-End Weakly-Supervised Semantic Alignment](http://openaccess.thecvf.com/content_cvpr_2018/papers/Rocco_End-to-End_Weakly-Supervised_Semantic_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/ignacio-rocco/weakalign) | 106 |
| [Decoupled Networks](http://openaccess.thecvf.com/content_cvpr_2018/papers/Liu_Decoupled_Networks_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/wy1iu/DCNets) | 105 |
| [LiDAR-Video Driving Dataset: Learning Driving Policies Effectively](http://openaccess.thecvf.com/content_cvpr_2018/papers/Chen_LiDAR-Video_Driving_Dataset_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/driving-behavior/DBNet) | 104 |
| [MAttNet: Modular Attention Network for Referring Expression Comprehension](http://openaccess.thecvf.com/content_cvpr_2018/papers/Yu_MAttNet_Modular_Attention_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/lichengunc/MAttNet) | 104 |
| [LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks](http://openaccess.thecvf.com/content_ECCV_2018/html/Dongqing_Zhang_Optimized_Quantization_for_ECCV_2018_paper.html) | ECCV | [code](https://github.com/Microsoft/LQ-Nets) | 103 |
| [FSRNet: End-to-End Learning Face Super-Resolution With Facial Priors](http://openaccess.thecvf.com/content_cvpr_2018/papers/Chen_FSRNet_End-to-End_Learning_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/tyshiwo/FSRNet) | 100 |
| [Deep Mutual Learning](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_Deep_Mutual_Learning_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/YingZhangDUT/Deep-Mutual-Learning) | 100 |
| [Macro-Micro Adversarial Network for Human Parsing](http://openaccess.thecvf.com/content_ECCV_2018/html/Yawei_Luo_Macro-Micro_Adversarial_Network_ECCV_2018_paper.html) | ECCV | [code](https://github.com/RoyalVane/MMAN) | 98 |
| [ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans](http://openaccess.thecvf.com/content_cvpr_2018/papers/Dai_ScanComplete_Large-Scale_Scene_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/angeladai/ScanComplete) | 97 |
| [Learning Depth From Monocular Videos Using Direct Methods](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_Learning_Depth_From_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/MightyChaos/LKVOLearner) | 97 |
| [VITON: An Image-Based Virtual Try-On Network](http://openaccess.thecvf.com/content_cvpr_2018/papers/Han_VITON_An_Image-Based_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/xthan/VITON) | 95 |
| [Cascade R-CNN: Delving Into High Quality Object Detection](http://openaccess.thecvf.com/content_cvpr_2018/papers/Cai_Cascade_R-CNN_Delving_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/guoruoqian/cascade-rcnn_Pytorch) | 93 |
| [Learning Human-Object Interactions by Graph Parsing Neural Networks](http://openaccess.thecvf.com/content_ECCV_2018/html/Siyuan_Qi_Learning_Human-Object_Interactions_ECCV_2018_paper.html) | ECCV | [code](https://github.com/SiyuanQi/gpnn) | 93 |
| [Future Frame Prediction for Anomaly Detection – A New Baseline](http://openaccess.thecvf.com/content_cvpr_2018/papers/Liu_Future_Frame_Prediction_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/StevenLiuWen/ano_pred_cvpr2018) | 92 |
| [Multi-view to Novel view: Synthesizing novel views with Self-Learned Confidence](http://openaccess.thecvf.com/content_ECCV_2018/html/Shao-Hua_Sun_Multi-view_to_Novel_ECCV_2018_paper.html) | ECCV | [code](https://github.com/shaohua0116/Multiview2Novelview) | 92 |
| [Tell Me Where to Look: Guided Attention Inference Network](http://openaccess.thecvf.com/content_cvpr_2018/papers/Li_Tell_Me_Where_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/alokwhitewolf/Guided-Attention-Inference-Network) | 91 |
| [Neural Kinematic Networks for Unsupervised Motion Retargetting](http://openaccess.thecvf.com/content_cvpr_2018/papers/Villegas_Neural_Kinematic_Networks_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/rubenvillegas/cvpr2018nkn) | 90 |
| [Learning SO(3) Equivariant Representations with Spherical CNNs](http://openaccess.thecvf.com/content_ECCV_2018/html/Carlos_Esteves_Learning_SO3_Equivariant_ECCV_2018_paper.html) | ECCV | [code](https://github.com/daniilidis-group/spherical-cnn) | 89 |
| [One-Shot Unsupervised Cross Domain Translation](http://arxiv.org/abs/1806.06029v1) | NIPS | [code](https://github.com/sagiebenaim/OneShotTranslation) | 89 |
| [Synthesizing Images of Humans in Unseen Poses](http://openaccess.thecvf.com/content_cvpr_2018/papers/Balakrishnan_Synthesizing_Images_of_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/balakg/posewarp-cvpr2018) | 88 |
| [Depth-aware CNN for RGB-D Segmentation](http://openaccess.thecvf.com/content_ECCV_2018/html/Weiyue_Wang_Depth-aware_CNN_for_ECCV_2018_paper.html) | ECCV | [code](https://github.com/laughtervv/DepthAwareCNN) | 88 |
| [Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weights](http://openaccess.thecvf.com/content_ECCV_2018/html/Arun_Mallya_Piggyback_Adapting_a_ECCV_2018_paper.html) | ECCV | [code](https://github.com/arunmallya/piggyback) | 88 |
| [Knowledge Aided Consistency for Weakly Supervised Phrase Grounding](http://openaccess.thecvf.com/content_cvpr_2018/papers/Chen_Knowledge_Aided_Consistency_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/kanchen-usc/KAC-Net) | 87 |
| [CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes](http://openaccess.thecvf.com/content_cvpr_2018/papers/Li_CSRNet_Dilated_Convolutional_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/leeyeehoo/CSRNet-pytorch) | 87 |
| [Neural Arithmetic Logic Units](http://arxiv.org/abs/1808.00508v1) | NIPS | [code](https://github.com/llSourcell/Neural_Arithmetic_Logic_Units) | 87 |
| [A PID Controller Approach for Stochastic Optimization of Deep Networks](http://openaccess.thecvf.com/content_cvpr_2018/papers/An_A_PID_Controller_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/tensorboy/PIDOptimizer) | 87 |
| [VITAL: VIsual Tracking via Adversarial Learning](http://openaccess.thecvf.com/content_cvpr_2018/papers/Song_VITAL_VIsual_Tracking_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/ybsong00/Vital_release) | 86 |
| [Learning Spatial-Temporal Regularized Correlation Filters for Visual Tracking](http://openaccess.thecvf.com/content_cvpr_2018/papers/Li_Learning_Spatial-Temporal_Regularized_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/lifeng9472/STRCF) | 86 |
| [Recurrent Pixel Embedding for Instance Grouping](http://openaccess.thecvf.com/content_cvpr_2018/papers/Kong_Recurrent_Pixel_Embedding_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/aimerykong/Recurrent-Pixel-Embedding-for-Instance-Grouping) | 85 |
| [SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_SGPN_Similarity_Group_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/laughtervv/SGPN) | 84 |
| [Multi-Scale Location-Aware Kernel Representation for Object Detection](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_Multi-Scale_Location-Aware_Kernel_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/Hwang64/MLKP) | 84 |
| [Repeatability Is Not Enough: Learning Affine Regions via Discriminability](http://openaccess.thecvf.com/content_ECCV_2018/html/Dmytro_Mishkin_Repeatability_Is_Not_ECCV_2018_paper.html) | ECCV | [code](https://github.com/ducha-aiki/affnet) | 84 |
| [“Zero-Shot” Super-Resolution Using Deep Internal Learning](http://openaccess.thecvf.com/content_cvpr_2018/papers/Shocher_Zero-Shot_Super-Resolution_Using_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/assafshocher/ZSSR) | 84 |
| [DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistency](http://openaccess.thecvf.com/content_ECCV_2018/html/Yuliang_Zou_DF-Net_Unsupervised_Joint_ECCV_2018_paper.html) | ECCV | [code](https://github.com/vt-vl-lab/DF-Net) | 82 |
| [Multi-View Consistency as Supervisory Signal for Learning Shape and Pose Prediction](http://openaccess.thecvf.com/content_cvpr_2018/papers/Tulsiani_Multi-View_Consistency_as_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/shubhtuls/mvcSnP) | 80 |
| [Factorizable Net: An Efficient Subgraph-based Framework for Scene Graph Generation](http://openaccess.thecvf.com/content_ECCV_2018/html/Yikang_LI_Factorizable_Net_An_ECCV_2018_paper.html) | ECCV | [code](https://github.com/yikang-li/FactorizableNet) | 78 |
| [Generalizing A Person Retrieval Model Hetero- and Homogeneously](http://openaccess.thecvf.com/content_ECCV_2018/html/Zhun_Zhong_Generalizing_A_Person_ECCV_2018_paper.html) | ECCV | [code](https://github.com/zhunzhong07/HHL) | 78 |
| [Crafting a Toolchain for Image Restoration by Deep Reinforcement Learning](http://openaccess.thecvf.com/content_cvpr_2018/papers/Yu_Crafting_a_Toolchain_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/yuke93/RL-Restore) | 77 |
| [Pairwise Confusion for Fine-Grained Visual Classification](http://openaccess.thecvf.com/content_ECCV_2018/html/Abhimanyu_Dubey_Improving_Fine-Grained_Visual_ECCV_2018_paper.html) | ECCV | [code](https://github.com/abhimanyudubey/confusion) | 77 |
| [Learning to Reweight Examples for Robust Deep Learning](http://proceedings.mlr.press/v80/ren18a.html) | ICML | [code](https://github.com/danieltan07/learning-to-reweight-examples) | 76 |
| [Improving Generalization via Scalable Neighborhood Component Analysis](http://openaccess.thecvf.com/content_ECCV_2018/html/Zhirong_Wu_Improving_Embedding_Generalization_ECCV_2018_paper.html) | ECCV | [code](https://github.com/Microsoft/snca.pytorch) | 76 |
| [SparseMAP: Differentiable Sparse Structured Inference](http://proceedings.mlr.press/v80/niculae18a.html) | ICML | [code](https://github.com/vene/sparsemap) | 75 |
| [PDE-Net: Learning PDEs from Data](http://proceedings.mlr.press/v80/long18a.html) | ICML | [code](https://github.com/ZichaoLong/PDE-Net) | 75 |
| [Pose-Normalized Image Generation for Person Re-identification](http://openaccess.thecvf.com/content_ECCV_2018/html/Xuelin_Qian_Pose-Normalized_Image_Generation_ECCV_2018_paper.html) | ECCV | [code](https://github.com/naiq/PN_GAN) | 75 |
| [Disentangled Person Image Generation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Ma_Disentangled_Person_Image_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/charliememory/Disentangled-Person-Image-Generation) | 75 |
| [Learning to Navigate for Fine-grained Classification](http://openaccess.thecvf.com/content_ECCV_2018/html/Ze_Yang_Learning_to_Navigate_ECCV_2018_paper.html) | ECCV | [code](https://github.com/yangze0930/NTS-Net) | 74 |
| [Superpixel Sampling Networks](http://openaccess.thecvf.com/content_ECCV_2018/html/Varun_Jampani_Superpixel_Sampling_Networks_ECCV_2018_paper.html) | ECCV | [code](https://github.com/NVlabs/ssn_superpixels) | 74 |
| [Shift-Net: Image Inpainting via Deep Feature Rearrangement](http://openaccess.thecvf.com/content_ECCV_2018/html/Zhaoyi_Yan_Shift-Net_Image_Inpainting_ECCV_2018_paper.html) | ECCV | [code](https://github.com/Zhaoyi-Yan/Shift-Net_pytorch) | 74 |
| [3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation](http://openaccess.thecvf.com/content_ECCV_2018/html/Angela_Dai_3DMV_Joint_3D-Multi-View_ECCV_2018_paper.html) | ECCV | [code](https://github.com/angeladai/3DMV) | 74 |
| [Ordinal Depth Supervision for 3D Human Pose Estimation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Pavlakos_Ordinal_Depth_Supervision_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/geopavlakos/ordinal-pose3d) | 74 |
| [Path-Level Network Transformation for Efficient Architecture Search](http://proceedings.mlr.press/v80/cai18a.html) | ICML | [code](https://github.com/han-cai/PathLevel-EAS) | 73 |
| [Diverse Image-to-Image Translation via Disentangled Representations](http://openaccess.thecvf.com/content_ECCV_2018/html/Hsin-Ying_Lee_Diverse_Image-to-Image_Translation_ECCV_2018_paper.html) | ECCV | [code](https://github.com/taki0112/DRIT-Tensorflow) | 72 |
| [Visual Feature Attribution Using Wasserstein GANs](http://openaccess.thecvf.com/content_cvpr_2018/papers/Baumgartner_Visual_Feature_Attribution_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/orobix/Visual-Feature-Attribution-Using-Wasserstein-GANs-Pytorch) | 72 |
| [Real-World Anomaly Detection in Surveillance Videos](http://openaccess.thecvf.com/content_cvpr_2018/papers/Sultani_Real-World_Anomaly_Detection_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/WaqasSultani/AnomalyDetectionCVPR2018) | 72 |
| [Self-Supervised Adversarial Hashing Networks for Cross-Modal Retrieval](http://openaccess.thecvf.com/content_cvpr_2018/papers/Li_Self-Supervised_Adversarial_Hashing_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/lelan-li/SSAH) | 72 |
| [Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image](http://openaccess.thecvf.com/content_ECCV_2018/html/Siyuan_Huang_Monocular_Scene_Parsing_ECCV_2018_paper.html) | ECCV | [code](https://github.com/thusiyuan/holistic_scene_parsing) | 72 |
| [Learning to Find Good Correspondences](http://openaccess.thecvf.com/content_cvpr_2018/papers/Yi_Learning_to_Find_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/vcg-uvic/learned-correspondence-release) | 72 |
| [Learning Less Is More - 6D Camera Localization via 3D Surface Regression](http://openaccess.thecvf.com/content_cvpr_2018/papers/Brachmann_Learning_Less_Is_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/vislearn/LessMore) | 72 |
| [Object Level Visual Reasoning in Videos](http://openaccess.thecvf.com/content_ECCV_2018/html/Fabien_Baradel_Object_Level_Visual_ECCV_2018_paper.html) | ECCV | [code](https://github.com/fabienbaradel/object_level_visual_reasoning) | 71 |
| [Weakly-Supervised Semantic Segmentation Network With Deep Seeded Region Growing](http://openaccess.thecvf.com/content_cvpr_2018/papers/Huang_Weakly-Supervised_Semantic_Segmentation_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/speedinghzl/DSRG) | 71 |
| [Avatar-Net: Multi-Scale Zero-Shot Style Transfer by Feature Decoration](http://openaccess.thecvf.com/content_cvpr_2018/papers/Sheng_Avatar-Net_Multi-Scale_Zero-Shot_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/LucasSheng/avatar-net) | 71 |
| [Fast and Accurate Single Image Super-Resolution via Information Distillation Network](http://openaccess.thecvf.com/content_cvpr_2018/papers/Hui_Fast_and_Accurate_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/Zheng222/IDN-Caffe) | 71 |
| [Regularizing RNNs for Caption Generation by Reconstructing the Past With the Present](http://openaccess.thecvf.com/content_cvpr_2018/papers/Chen_Regularizing_RNNs_for_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/chenxinpeng/ARNet) | 70 |
| [Multi-Shot Pedestrian Re-Identification via Sequential Decision Making](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_Multi-Shot_Pedestrian_Re-Identification_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/TuSimple/rl-multishot-reid) | 70 |
| [PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition](http://openaccess.thecvf.com/content_cvpr_2018/papers/Uy_PointNetVLAD_Deep_Point_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/mikacuy/pointnetvlad) | 69 |
| [Progressive Neural Architecture Search](http://openaccess.thecvf.com/content_ECCV_2018/html/Chenxi_Liu_Progressive_Neural_Architecture_ECCV_2018_paper.html) | ECCV | [code](https://github.com/titu1994/progressive-neural-architecture-search) | 68 |
| [Generative Neural Machine Translation](http://arxiv.org/abs/1806.05138v1) | NIPS | [code](https://github.com/ZhenYangIACAS/NMT_GAN) | 68 |
| [Learning Latent Super-Events to Detect Multiple Activities in Videos](http://openaccess.thecvf.com/content_cvpr_2018/papers/Piergiovanni_Learning_Latent_Super-Events_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/piergiaj/super-events-cvpr18) | 67 |
| [Generate to Adapt: Aligning Domains Using Generative Adversarial Networks](http://openaccess.thecvf.com/content_cvpr_2018/papers/Sankaranarayanan_Generate_to_Adapt_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/yogeshbalaji/Generate_To_Adapt) | 67 |
| [Adversarial Feature Augmentation for Unsupervised Domain Adaptation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Volpi_Adversarial_Feature_Augmentation_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/ricvolpi/adversarial-feature-augmentation) | 67 |
| [Learning Attentions: Residual Attentional Siamese Network for High Performance Online Visual Tracking](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_Learning_Attentions_Residual_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/foolwood/RASNet) | 67 |
| [Pointwise Convolutional Neural Networks](http://openaccess.thecvf.com/content_cvpr_2018/papers/Hua_Pointwise_Convolutional_Neural_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/scenenn/pointwise) | 67 |
| [Optimizing the Latent Space of Generative Networks](http://proceedings.mlr.press/v80/bojanowski18a.html) | ICML | [code](https://github.com/tneumann/minimal_glo) | 66 |
| [Part-Aligned Bilinear Representations for Person Re-Identification](http://openaccess.thecvf.com/content_ECCV_2018/html/Yumin_Suh_Part-Aligned_Bilinear_Representations_ECCV_2018_paper.html) | ECCV | [code](https://github.com/yuminsuh/part_bilinear_reid) | 64 |
| [Geometry-Aware Learning of Maps for Camera Localization](http://openaccess.thecvf.com/content_cvpr_2018/papers/Brahmbhatt_Geometry-Aware_Learning_of_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/samarth-robo/MapNet) | 63 |
| [Fighting Fake News: Image Splice Detection via Learned Self-Consistency](http://openaccess.thecvf.com/content_ECCV_2018/html/Jacob_Huh_Fighting_Fake_News_ECCV_2018_paper.html) | ECCV | [code](https://github.com/minyoungg/selfconsistency) | 62 |
| [Isolating Sources of Disentanglement in Variational Autoencoders](http://arxiv.org/abs/1802.04942v2) | NIPS | [code](https://github.com/rtqichen/beta-tcvae) | 62 |
| [Neural Program Synthesis from Diverse Demonstration Videos](http://proceedings.mlr.press/v80/sun18a.html) | ICML | [code](https://github.com/shaohua0116/demo2program) | 62 |
| [Learning Rigidity in Dynamic Scenes with a Moving Camera for 3D Motion Field Estimation](http://openaccess.thecvf.com/content_ECCV_2018/html/Zhaoyang_Lv_Learning_Rigidity_in_ECCV_2018_paper.html) | ECCV | [code](https://github.com/NVlabs/learningrigidity) | 61 |
| [Rotation-Sensitive Regression for Oriented Scene Text Detection](http://openaccess.thecvf.com/content_cvpr_2018/papers/Liao_Rotation-Sensitive_Regression_for_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/MhLiao/RRD) | 61 |
| [Human Semantic Parsing for Person Re-Identification](http://openaccess.thecvf.com/content_cvpr_2018/papers/Kalayeh_Human_Semantic_Parsing_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/emrahbasaran/SPReID) | 61 |
| [Unsupervised Discovery of Object Landmarks as Structural Representations](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_Unsupervised_Discovery_of_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/YutingZhang/lmdis-rep) | 61 |
| [IQA: Visual Question Answering in Interactive Environments](http://openaccess.thecvf.com/content_cvpr_2018/papers/Gordon_IQA_Visual_Question_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/danielgordon10/thor-iqa-cvpr-2018) | 60 |
| [Hierarchical Long-term Video Prediction without Supervision](http://proceedings.mlr.press/v80/wichers18a.html) | ICML | [code](https://github.com/brain-research/long-term-video-prediction-without-supervision) | 60 |
| [Unsupervised Domain Adaptation for 3D Keypoint Estimation via View Consistency](http://openaccess.thecvf.com/content_ECCV_2018/html/Xingyi_Zhou_Unsupervised_Domain_Adaptation_ECCV_2018_paper.html) | ECCV | [code](https://github.com/xingyizhou/3DKeypoints-DA) | 60 |
| [Exploit the Unknown Gradually: One-Shot Video-Based Person Re-Identification by Stepwise Learning](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wu_Exploit_the_Unknown_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/Yu-Wu/Exploit-Unknown-Gradually) | 59 |
| [Neural Style Transfer via Meta Networks](http://openaccess.thecvf.com/content_cvpr_2018/papers/Shen_Neural_Style_Transfer_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/FalongShen/styletransfer) | 59 |
| [Frame-Recurrent Video Super-Resolution](http://openaccess.thecvf.com/content_cvpr_2018/papers/Sajjadi_Frame-Recurrent_Video_Super-Resolution_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/msmsajjadi/FRVSR) | 58 |
| [PlaneMatch: Patch Coplanarity Prediction for Robust RGB-D Reconstruction](http://openaccess.thecvf.com/content_ECCV_2018/html/Yifei_Shi_PlaneMatch_Patch_Coplanarity_ECCV_2018_paper.html) | ECCV | [code](https://github.com/yifeishi/PlaneMatch) | 57 |
| [CBAM: Convolutional Block Attention Module](http://openaccess.thecvf.com/content_ECCV_2018/html/Sanghyun_Woo_Convolutional_Block_Attention_ECCV_2018_paper.html) | ECCV | [code](https://github.com/Youngkl0726/Convolutional-Block-Attention-Module) | 57 |
| [Decorrelated Batch Normalization](http://openaccess.thecvf.com/content_cvpr_2018/papers/Huang_Decorrelated_Batch_Normalization_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/umich-vl/DecorrelatedBN) | 57 |
| [Learning Conditioned Graph Structures for Interpretable Visual Question Answering](nan) | NIPS | [code](https://github.com/aimbrain/vqa-project) | 57 |
| [Hierarchical Bilinear Pooling for Fine-Grained Visual Recognition](http://openaccess.thecvf.com/content_ECCV_2018/html/Chaojian_Yu_Hierarchical_Bilinear_Pooling_ECCV_2018_paper.html) | ECCV | [code](https://github.com/ChaojianYu/Hierarchical-Bilinear-Pooling) | 57 |
| [Leveraging Unlabeled Data for Crowd Counting by Learning to Rank](http://openaccess.thecvf.com/content_cvpr_2018/papers/Liu_Leveraging_Unlabeled_Data_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/xialeiliu/CrowdCountingCVPR18) | 56 |
| [Deep Marching Cubes: Learning Explicit Surface Representations](http://openaccess.thecvf.com/content_cvpr_2018/papers/Liao_Deep_Marching_Cubes_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/yiyiliao/deep_marching_cubes) | 56 |
| [Learning From Synthetic Data: Addressing Domain Shift for Semantic Segmentation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Sankaranarayanan_Learning_From_Synthetic_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/swamiviv/LSD-seg) | 56 |
| [LF-Net: Learning Local Features from Images](https://arxiv.org/abs/1805.09662) | NIPS | [code](https://github.com/vcg-uvic/lf-net-release) | 55 |
| [Semi-supervised Adversarial Learning to Generate Photorealistic Face Images of New Identities from 3D Morphable Model](http://openaccess.thecvf.com/content_ECCV_2018/html/Baris_Gecer_Semi-supervised_Adversarial_Learning_ECCV_2018_paper.html) | ECCV | [code](https://github.com/barisgecer/facegan) | 55 |
| [Discriminability Objective for Training Descriptive Captions](http://openaccess.thecvf.com/content_cvpr_2018/papers/Luo_Discriminability_Objective_for_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/ruotianluo/DiscCaptioning) | 54 |
| [BlockDrop: Dynamic Inference Paths in Residual Networks](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wu_BlockDrop_Dynamic_Inference_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/Tushar-N/blockdrop) | 54 |
| [Conditional Probability Models for Deep Image Compression](http://openaccess.thecvf.com/content_cvpr_2018/papers/Mentzer_Conditional_Probability_Models_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/fab-jul/imgcomp-cvpr) | 54 |
| [Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Peng_Jointly_Optimize_Data_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/zhiqiangdon/pose-adv-aug) | 54 |
| [Learning towards Minimum Hyperspherical Energy](http://arxiv.org/abs/1805.09298v4) | NIPS | [code](https://github.com/wy1iu/MHE) | 54 |
| [DeepVS: A Deep Learning Based Video Saliency Prediction Approach](http://openaccess.thecvf.com/content_ECCV_2018/html/Lai_Jiang_DeepVS_A_Deep_ECCV_2018_paper.html) | ECCV | [code](https://github.com/remega/OMCNN_2CLSTM) | 53 |
| [Learning Efficient Single-stage Pedestrian Detectors by Asymptotic Localization Fitting](http://openaccess.thecvf.com/content_ECCV_2018/html/Wei_Liu_Learning_Efficient_Single-stage_ECCV_2018_paper.html) | ECCV | [code](https://github.com/liuwei16/ALFNet) | 52 |
| [Learning Pixel-Level Semantic Affinity With Image-Level Supervision for Weakly Supervised Semantic Segmentation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Ahn_Learning_Pixel-Level_Semantic_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/jiwoon-ahn/psa) | 52 |
| [Wasserstein Introspective Neural Networks](http://openaccess.thecvf.com/content_cvpr_2018/papers/Lee_Wasserstein_Introspective_Neural_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/kjunelee/WINN) | 51 |
| [SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis](http://openaccess.thecvf.com/content_cvpr_2018/papers/Chen_SketchyGAN_Towards_Diverse_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/wchen342/SketchyGAN) | 51 |
| [Self-produced Guidance for Weakly-supervised Object Localization](http://openaccess.thecvf.com/content_ECCV_2018/html/Xiaolin_Zhang_Self-produced_Guidance_for_ECCV_2018_paper.html) | ECCV | [code](https://github.com/xiaomengyc/SPG) | 51 |
| [Measuring abstract reasoning in neural networks](http://proceedings.mlr.press/v80/santoro18a.html) | ICML | [code](https://github.com/deepmind/abstract-reasoning-matrices) | 51 |
| [A Unified Feature Disentangler for Multi-Domain Image Translation and Manipulation](https://arxiv.org/abs/1809.01361) | NIPS | [code](https://github.com/XenderLiu/UFDN) | 51 |
| [RayNet: Learning Volumetric 3D Reconstruction With Ray Potentials](http://openaccess.thecvf.com/content_cvpr_2018/papers/Paschalidou_RayNet_Learning_Volumetric_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/paschalidoud/raynet) | 51 |
| [Coloring with Words: Guiding Image Colorization Through Text-based Palette Generation](http://openaccess.thecvf.com/content_ECCV_2018/html/Hyojin_Bahng_Coloring_with_Words_ECCV_2018_paper.html) | ECCV | [code](https://github.com/awesome-davian/Text2Colors) | 50 |
| [Efficient end-to-end learning for quantizable representations](http://proceedings.mlr.press/v80/jeong18a.html) | ICML | [code](https://github.com/maestrojeong/Deep-Hash-Table-ICML18) | 50 |
| [Visual Question Generation as Dual Task of Visual Question Answering](http://openaccess.thecvf.com/content_cvpr_2018/papers/Li_Visual_Question_Generation_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/yikang-li/iQAN) | 50 |
| [Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam](http://proceedings.mlr.press/v80/khan18a.html) | ICML | [code](https://github.com/emtiyaz/vadam) | 49 |
| [Surface Networks](http://openaccess.thecvf.com/content_cvpr_2018/papers/Kostrikov_Surface_Networks_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/jiangzhongshi/SurfaceNetworks) | 48 |
| [Deep k-Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutions](http://proceedings.mlr.press/v80/wu18h.html) | ICML | [code](https://github.com/Sandbox3aster/Deep-K-Means-pytorch) | 48 |
| [Stacked Cross Attention for Image-Text Matching](http://openaccess.thecvf.com/content_ECCV_2018/html/Kuang-Huei_Lee_Stacked_Cross_Attention_ECCV_2018_paper.html) | ECCV | [code](https://github.com/kuanghuei/SCAN) | 48 |
| [Actor and Observer: Joint Modeling of First and Third-Person Videos](http://openaccess.thecvf.com/content_cvpr_2018/papers/Sigurdsson_Actor_and_Observer_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/gsig/actor-observer) | 48 |
| [Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Jiang_Super_SloMo_High_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/TheFairBear/Super-SlowMo) | 47 |
| [Learning-based Video Motion Magnification](http://openaccess.thecvf.com/content_ECCV_2018/html/Tae-Hyun_Oh_Learning-based_Video_Motion_ECCV_2018_paper.html) | ECCV | [code](https://github.com/12dmodel/deep_motion_mag) | 47 |
| [Pose Partition Networks for Multi-Person Pose Estimation](http://openaccess.thecvf.com/content_ECCV_2018/html/Xuecheng_Nie_Pose_Partition_Networks_ECCV_2018_paper.html) | ECCV | [code](https://github.com/NieXC/pytorch-ppn) | 47 |
| [Neural Autoregressive Flows](http://proceedings.mlr.press/v80/huang18d.html) | ICML | [code](https://github.com/CW-Huang/NAF) | 47 |
| [Weakly- and Semi-Supervised Panoptic Segmentation](http://openaccess.thecvf.com/content_ECCV_2018/html/Anurag_Arnab_Weakly-_and_Semi-Supervised_ECCV_2018_paper.html) | ECCV | [code](https://github.com/qizhuli/Weakly-Supervised-Panoptic-Segmentation) | 46 |
| [Video Re-localization](http://openaccess.thecvf.com/content_ECCV_2018/html/Yang_Feng_Video_Re-localization_via_ECCV_2018_paper.html) | ECCV | [code](https://github.com/fengyang0317/video_reloc) | 46 |
| [Real-time 'Actor-Critic' Tracking](http://openaccess.thecvf.com/content_ECCV_2018/html/Boyu_Chen_Real-time_Actor-Critic_Tracking_ECCV_2018_paper.html) | ECCV | [code](https://github.com/bychen515/ACT) | 46 |
| [Black-box Adversarial Attacks with Limited Queries and Information](http://proceedings.mlr.press/v80/ilyas18a.html) | ICML | [code](https://github.com/labsix/limited-blackbox-attacks) | 46 |
| [Hyperbolic Entailment Cones for Learning Hierarchical Embeddings](http://proceedings.mlr.press/v80/ganea18a.html) | ICML | [code](https://github.com/dalab/hyperbolic_cones) | 46 |
| [Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Xu_Structured_Attention_Guided_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/danxuhk/StructuredAttentionDepthEstimation) | 46 |
| [Differentiable Compositional Kernel Learning for Gaussian Processes](http://proceedings.mlr.press/v80/sun18e.html) | ICML | [code](https://github.com/ssydasheng/Neural-Kernel-Network) | 45 |
| [Visualizing and Understanding Atari Agents](http://proceedings.mlr.press/v80/greydanus18a.html) | ICML | [code](https://github.com/greydanus/visualize_atari) | 45 |
| [Image Manipulation with Perceptual Discriminators](http://openaccess.thecvf.com/content_ECCV_2018/html/Diana_Sungatullina_Image_Manipulation_with_ECCV_2018_paper.html) | ECCV | [code](https://github.com/egorzakharov/PerceptualGAN) | 45 |
| [Learning Intrinsic Image Decomposition From Watching the World](http://openaccess.thecvf.com/content_cvpr_2018/papers/Li_Learning_Intrinsic_Image_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/lixx2938/unsupervised-learning-intrinsic-images) | 45 |
| [Overcoming Catastrophic Forgetting with Hard Attention to the Task](http://proceedings.mlr.press/v80/serra18a.html) | ICML | [code](https://github.com/joansj/hat) | 44 |
| [Learning Pose Specific Representations by Predicting Different Views](http://openaccess.thecvf.com/content_cvpr_2018/papers/Poier_Learning_Pose_Specific_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/poier/PreView) | 44 |
| [Zero-Shot Object Detection](http://openaccess.thecvf.com/content_ECCV_2018/html/Ankan_Bansal_Zero-Shot_Object_Detection_ECCV_2018_paper.html) | ECCV | [code](https://github.com/salman-h-khan/ZSD_Release) | 43 |
| [Mean Field Multi-Agent Reinforcement Learning](http://proceedings.mlr.press/v80/yang18d.html) | ICML | [code](https://github.com/mlii/mfrl) | 43 |
| [Partial Adversarial Domain Adaptation](http://openaccess.thecvf.com/content_ECCV_2018/html/Zhangjie_Cao_Partial_Adversarial_Domain_ECCV_2018_paper.html) | ECCV | [code](https://github.com/thuml/PADA) | 43 |
| [Mutual Learning to Adapt for Joint Human Parsing and Pose Estimation](http://openaccess.thecvf.com/content_ECCV_2018/html/Xuecheng_Nie_Mutual_Learning_to_ECCV_2018_paper.html) | ECCV | [code](https://github.com/NieXC/pytorch-mula) | 43 |
| [Robust Classification With Convolutional Prototype Learning](http://openaccess.thecvf.com/content_cvpr_2018/papers/Yang_Robust_Classification_With_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/YangHM/Convolutional-Prototype-Learning) | 43 |
| [SimplE Embedding for Link Prediction in Knowledge Graphs](http://arxiv.org/abs/1802.04868v1) | NIPS | [code](https://github.com/Mehran-k/SimplE) | 42 |
| [PredRNN++: Towards A Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learning](http://proceedings.mlr.press/v80/wang18b.html) | ICML | [code](https://github.com/Yunbo426/predrnn-pp) | 42 |
| [Learning to Blend Photos](http://openaccess.thecvf.com/content_ECCV_2018/html/Wei-Chih_Hung_Learning_to_Blend_ECCV_2018_paper.html) | ECCV | [code](https://github.com/hfslyc/LearnToBlend) | 42 |
| [Mask-Guided Contrastive Attention Model for Person Re-Identification](http://openaccess.thecvf.com/content_cvpr_2018/papers/Song_Mask-Guided_Contrastive_Attention_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/developfeng/MGCAM) | 41 |
| [Link Prediction Based on Graph Neural Networks](http://arxiv.org/abs/1802.09691v2) | NIPS | [code](https://github.com/muhanzhang/SEAL) | 41 |
| [Generalisation in humans and deep neural networks](http://arxiv.org/abs/1808.08750v1) | NIPS | [code](https://github.com/rgeirhos/generalisation-humans-DNNs) | 41 |
| [Towards Binary-Valued Gates for Robust LSTM Training](http://proceedings.mlr.press/v80/li18c.html) | ICML | [code](https://github.com/zhuohan123/g2-lstm) | 41 |
| [Multi-scale Residual Network for Image Super-Resolution](http://openaccess.thecvf.com/content_ECCV_2018/html/Juncheng_Li_Multi-scale_Residual_Network_ECCV_2018_paper.html) | ECCV | [code](https://github.com/MIVRC/MSRN-PyTorch) | 41 |
| [Fully Motion-Aware Network for Video Object Detection](http://openaccess.thecvf.com/content_ECCV_2018/html/Shiyao_Wang_Fully_Motion-Aware_Network_ECCV_2018_paper.html) | ECCV | [code](https://github.com/wangshy31/MANet_for_Video_Object_Detection) | 41 |
| [Interpretable Convolutional Neural Networks](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_Interpretable_Convolutional_Neural_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/seongjunyun/CNN-with-Dual-Local-and-Global-Attention) | 40 |
| [Generative Adversarial Perturbations](http://openaccess.thecvf.com/content_cvpr_2018/papers/Poursaeed_Generative_Adversarial_Perturbations_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/OmidPoursaeed/Generative_Adversarial_Perturbations) | 40 |
| [The Sound of Pixels](http://openaccess.thecvf.com/content_ECCV_2018/html/Hang_Zhao_The_Sound_of_ECCV_2018_paper.html) | ECCV | [code](https://github.com/roudimit/MUSIC_dataset) | 40 |
| [Towards Faster Training of Global Covariance Pooling Networks by Iterative Matrix Square Root Normalization](http://openaccess.thecvf.com/content_cvpr_2018/papers/Li_Towards_Faster_Training_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/jiangtaoxie/fast-MPN-COV) | 40 |
| [Choose Your Neuron: Incorporating Domain Knowledge through Neuron-Importance](http://openaccess.thecvf.com/content_ECCV_2018/html/Ramprasaath_Ramasamy_Selvaraju_Choose_Your_Neuron_ECCV_2018_paper.html) | ECCV | [code](https://github.com/ramprs/neuron-importance-zsl) | 40 |
| [Multi-View Silhouette and Depth Decomposition for High Resolution 3D Object Representation](https://arxiv.org/abs/1802.09987) | NIPS | [code](https://github.com/EdwardSmith1884/Multi-View-Silhouette-and-Depth-Decomposition-for-High-Resolution-3D-Object-Representation) | 40 |
| [Learning Warped Guidance for Blind Face Restoration](http://openaccess.thecvf.com/content_ECCV_2018/html/Xiaoming_Li_Learning_Warped_Guidance_ECCV_2018_paper.html) | ECCV | [code](https://github.com/csxmli2016/GFRNet) | 39 |
| [Adversarial Complementary Learning for Weakly Supervised Object Localization](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_Adversarial_Complementary_Learning_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/xiaomengyc/ACoL) | 39 |
| [Learning Semantic Representations for Unsupervised Domain Adaptation](http://proceedings.mlr.press/v80/xie18c.html) | ICML | [code](https://github.com/Mid-Push/Moving-Semantic-Transfer-Network) | 39 |
| [Neural Architecture Search with Bayesian Optimisation and Optimal Transport](https://arxiv.org/abs/1802.07191) | NIPS | [code](https://github.com/kirthevasank/nasbot) | 39 |
| [Mutual Information Neural Estimation](http://proceedings.mlr.press/v80/belghazi18a.html) | ICML | [code](https://github.com/MasanoriYamada/Mine_pytorch) | 39 |
| [NetGAN: Generating Graphs via Random Walks](http://proceedings.mlr.press/v80/bojchevski18a.html) | ICML | [code](https://github.com/danielzuegner/netgan) | 39 |
| [Learning to Evaluate Image Captioning](http://openaccess.thecvf.com/content_cvpr_2018/papers/Cui_Learning_to_Evaluate_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/richardaecn/cvpr18-caption-eval) | 38 |
| [Hyperbolic Neural Networks](http://arxiv.org/abs/1805.09112v2) | NIPS | [code](https://github.com/dalab/hyperbolic_nn) | 37 |
| [Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation](http://openaccess.thecvf.com/content_ECCV_2018/html/Helge_Rhodin_Unsupervised_Geometry-Aware_Representation_ECCV_2018_paper.html) | ECCV | [code](https://github.com/hrhodin/UnsupervisedGeometryAwareRepresentationLearning) | 37 |
| [Adversarially Learned One-Class Classifier for Novelty Detection](http://openaccess.thecvf.com/content_cvpr_2018/papers/Sabokrou_Adversarially_Learned_One-Class_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/khalooei/ALOCC-CVPR2018) | 37 |
| [Disentangling by Factorising](http://proceedings.mlr.press/v80/kim18b.html) | ICML | [code](https://github.com/1Konny/FactorVAE) | 37 |
| [Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples](http://proceedings.mlr.press/v80/weiss18a.html) | ICML | [code](https://github.com/tech-srl/lstar_extraction) | 37 |
| [Tangent Convolutions for Dense Prediction in 3D](http://openaccess.thecvf.com/content_cvpr_2018/papers/Tatarchenko_Tangent_Convolutions_for_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/tatarchm/tangent_conv) | 37 |
| [Few-Shot Image Recognition by Predicting Parameters From Activations](http://openaccess.thecvf.com/content_cvpr_2018/papers/Qiao_Few-Shot_Image_Recognition_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/joe-siyuan-qiao/FewShot-CVPR) | 37 |
| [Real-Time Monocular Depth Estimation Using Synthetic Data With Domain Adaptation via Image Style Transfer](http://openaccess.thecvf.com/content_cvpr_2018/papers/Atapour-Abarghouei_Real-Time_Monocular_Depth_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/atapour/monocularDepth-Inference) | 37 |
| [Generalizing to Unseen Domains via Adversarial Data Augmentation](http://arxiv.org/abs/1805.12018v1) | NIPS | [code](https://github.com/ricvolpi/generalize-unseen-domains) | 36 |
| [SeGAN: Segmenting and Generating the Invisible](http://openaccess.thecvf.com/content_cvpr_2018/papers/Ehsani_SeGAN_Segmenting_and_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/ehsanik/SeGAN) | 36 |
| [Graphical Generative Adversarial Networks](http://arxiv.org/abs/1804.03429v1) | NIPS | [code](https://github.com/zhenxuan00/graphical-gan) | 36 |
| [PieAPP: Perceptual Image-Error Assessment Through Pairwise Preference](http://openaccess.thecvf.com/content_cvpr_2018/papers/Prashnani_PieAPP_Perceptual_Image-Error_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/prashnani/PerceptualImageError) | 36 |
| [Gated Fusion Network for Single Image Dehazing](http://openaccess.thecvf.com/content_cvpr_2018/papers/Ren_Gated_Fusion_Network_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/rwenqi/GFN-dehazing) | 35 |
| [Neural Code Comprehension: A Learnable Representation of Code Semantics](http://arxiv.org/abs/1806.07336v2) | NIPS | [code](https://github.com/spcl/ncc) | 35 |
| [Eye In-Painting With Exemplar Generative Adversarial Networks](http://openaccess.thecvf.com/content_cvpr_2018/papers/Dolhansky_Eye_In-Painting_With_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/zhangqianhui/Exemplar-GAN-Eye-Inpainting-Tensorflow) | 35 |
| [Deep One-Class Classification](http://proceedings.mlr.press/v80/ruff18a.html) | ICML | [code](https://github.com/lukasruff/Deep-SVDD) | 34 |
| [Deep Regression Tracking with Shrinkage Loss](http://openaccess.thecvf.com/content_ECCV_2018/html/Xiankai_Lu_Deep_Regression_Tracking_ECCV_2018_paper.html) | ECCV | [code](https://github.com/chaoma99/DSLT) | 34 |
| [Deflecting Adversarial Attacks With Pixel Deflection](http://openaccess.thecvf.com/content_cvpr_2018/papers/Prakash_Deflecting_Adversarial_Attacks_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/iamaaditya/pixel-deflection) | 34 |
| [Learning Visual Question Answering by Bootstrapping Hard Attention](http://openaccess.thecvf.com/content_ECCV_2018/html/Mateusz_Malinowski_Learning_Visual_Question_ECCV_2018_paper.html) | ECCV | [code](https://github.com/gnouhp/PyTorch-AdaHAN) | 33 |
| [Human-Centric Indoor Scene Synthesis Using Stochastic Grammar](http://openaccess.thecvf.com/content_cvpr_2018/papers/Qi_Human-Centric_Indoor_Scene_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/SiyuanQi/human-centric-scene-synthesis) | 33 |
| [Improved Fusion of Visual and Language Representations by Dense Symmetric Co-Attention for Visual Question Answering](http://openaccess.thecvf.com/content_cvpr_2018/papers/Nguyen_Improved_Fusion_of_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/cvlab-tohoku/Dense-CoAttention-Network) | 33 |
| [CleanNet: Transfer Learning for Scalable Image Classifier Training With Label Noise](http://openaccess.thecvf.com/content_cvpr_2018/papers/Lee_CleanNet_Transfer_Learning_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/kuanghuei/clean-net) | 33 |
| [Speaker-Follower Models for Vision-and-Language Navigation](https://arxiv.org/abs/1806.02724) | NIPS | [code](https://github.com/ronghanghu/speaker_follower) | 33 |
| [Improving Shape Deformation in Unsupervised Image-to-Image Translation](http://openaccess.thecvf.com/content_ECCV_2018/html/Aaron_Gokaslan_Improving_Shape_Deformation_ECCV_2018_paper.html) | ECCV | [code](https://github.com/brownvc/ganimorph) | 33 |
| [Learning Single-View 3D Reconstruction with Limited Pose Supervision](http://openaccess.thecvf.com/content_ECCV_2018/html/Guandao_Yang_A_Unified_Framework_ECCV_2018_paper.html) | ECCV | [code](https://github.com/stevenygd/3d-recon) | 33 |
| [3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data](https://arxiv.org/abs/1807.02547) | NIPS | [code](https://github.com/mariogeiger/se3cnn) | 33 |
| [Adversarial Logit Pairing](http://arxiv.org/abs/1803.06373v1) | NIPS | [code](https://github.com/labsix/adversarial-logit-pairing-analysis) | 32 |
| [Attention in Convolutional LSTM for Gesture Recognition](https://nips.cc/Conferences/2018/Schedule?showEvent=11207) | NIPS | [code](https://github.com/GuangmingZhu/AttentionConvLSTM) | 32 |
| [Graph-Cut RANSAC](http://openaccess.thecvf.com/content_cvpr_2018/papers/Barath_Graph-Cut_RANSAC_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/danini/graph-cut-ransac) | 32 |
| [Neural Guided Constraint Logic Programming for Program Synthesis](http://arxiv.org/abs/1809.02840v2) | NIPS | [code](https://github.com/xuexue/neuralkanren) | 32 |
| [Learning Dynamic Memory Networks for Object Tracking](http://openaccess.thecvf.com/content_ECCV_2018/html/Tianyu_Yang_Learning_Dynamic_Memory_ECCV_2018_paper.html) | ECCV | [code](https://github.com/skyoung/MemTrack) | 32 |
| [GeoDesc: Learning Local Descriptors by Integrating Geometry Constraints](http://openaccess.thecvf.com/content_ECCV_2018/html/Zixin_Luo_Learning_Local_Descriptors_ECCV_2018_paper.html) | ECCV | [code](https://github.com/lzx551402/geodesc) | 32 |
| [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](nan) | NIPS | [code](https://github.com/pokaxpoka/deep_Mahalanobis_detector) | 32 |
| [Flow-Grounded Spatial-Temporal Video Prediction from Still Images](http://openaccess.thecvf.com/content_ECCV_2018/html/Yijun_Li_Flow-Grounded_Spatial-Temporal_Video_ECCV_2018_paper.html) | ECCV | [code](https://github.com/Yijunmaverick/FlowGrounded-VideoPrediction) | 32 |
| [Bidirectional Feature Pyramid Network with Recurrent Attention Residual Modules for Shadow Detection](http://openaccess.thecvf.com/content_ECCV_2018/html/Lei_Zhu_Bi-directional_Feature_Pyramid_ECCV_2018_paper.html) | ECCV | [code](https://github.com/zijundeng/BDRAR) | 32 |
| [On the Robustness of Semantic Segmentation Models to Adversarial Attacks](http://openaccess.thecvf.com/content_cvpr_2018/papers/Arnab_On_the_Robustness_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/hmph/adversarial-attacks) | 31 |
| [Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning](http://openaccess.thecvf.com/content_cvpr_2018/papers/Cui_Large_Scale_Fine-Grained_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/richardaecn/cvpr18-inaturalist-transfer) | 31 |
| [SketchyScene: Richly-Annotated Scene Sketches](http://openaccess.thecvf.com/content_ECCV_2018/html/Changqing_Zou_SketchyScene_Richly-Annotated_Scene_ECCV_2018_paper.html) | ECCV | [code](https://github.com/SketchyScene/SketchyScene) | 31 |
| [Deep Randomized Ensembles for Metric Learning](http://openaccess.thecvf.com/content_ECCV_2018/html/Hong_Xuan_Randomized_Ensemble_Embeddings_ECCV_2018_paper.html) | ECCV | [code](https://github.com/littleredxh/DREML) | 30 |
| [Deep High Dynamic Range Imaging with Large Foreground Motions](http://openaccess.thecvf.com/content_ECCV_2018/html/Shangzhe_Wu_Deep_High_Dynamic_ECCV_2018_paper.html) | ECCV | [code](https://github.com/elliottwu/DeepHDR) | 30 |
| [Revisiting Video Saliency: A Large-Scale Benchmark and a New Model](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_Revisiting_Video_Saliency_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/wenguanwang/DHF1K) | 30 |
| [Blazingly Fast Video Object Segmentation With Pixel-Wise Metric Learning](http://openaccess.thecvf.com/content_cvpr_2018/papers/Chen_Blazingly_Fast_Video_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/yuhuayc/fast-vos) | 30 |
| [Deep Model-Based 6D Pose Refinement in RGB](http://openaccess.thecvf.com/content_ECCV_2018/html/Fabian_Manhardt_Deep_Model-Based_6D_ECCV_2018_paper.html) | ECCV | [code](https://github.com/fabi92/eccv18-rgb_pose_refinement) | 30 |
| [TOM-Net: Learning Transparent Object Matting From a Single Image](http://openaccess.thecvf.com/content_cvpr_2018/papers/Chen_TOM-Net_Learning_Transparent_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/guanyingc/TOM-Net) | 30 |
| [Quaternion Convolutional Neural Networks](http://openaccess.thecvf.com/content_ECCV_2018/html/Xuanyu_Zhu_Quaternion_Convolutional_Neural_ECCV_2018_paper.html) | ECCV | [code](https://github.com/TParcollet/Quaternion-Convolutional-Neural-Networks-for-End-to-End-Automatic-Speech-Recognition) | 30 |
| [Densely Connected Attention Propagation for Reading Comprehension](https://nips.cc/Conferences/2018/Schedule?showEvent=11481) | NIPS | [code](https://github.com/vanzytay/NIPS2018_DECAPROP) | 30 |
| [A Trilateral Weighted Sparse Coding Scheme for Real-World Image Denoising](http://openaccess.thecvf.com/content_ECCV_2018/html/XU_JUN_A_Trilateral_Weighted_ECCV_2018_paper.html) | ECCV | [code](https://github.com/csjunxu/TWSC-ECCV2018) | 30 |
| [Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings](http://proceedings.mlr.press/v80/co-reyes18a.html) | ICML | [code](https://github.com/wyndwarrior/Sectar) | 29 |
| [Video Rain Streak Removal by Multiscale Convolutional Sparse Coding](http://openaccess.thecvf.com/content_cvpr_2018/papers/Li_Video_Rain_Streak_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/MinghanLi/MS-CSC-Rain-Streak-Removal) | 29 |
| [Recurrent Scene Parsing With Perspective Understanding in the Loop](http://openaccess.thecvf.com/content_cvpr_2018/papers/Kong_Recurrent_Scene_Parsing_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/aimerykong/Recurrent-Scene-Parsing-with-Perspective-Understanding-in-the-loop) | 29 |
| [Single Shot Scene Text Retrieval](http://openaccess.thecvf.com/content_ECCV_2018/html/Lluis_Gomez_Single_Shot_Scene_ECCV_2018_paper.html) | ECCV | [code](https://github.com/lluisgomez/single-shot-str) | 29 |
| [Toward Characteristic-Preserving Image-based Virtual Try-On Network](http://openaccess.thecvf.com/content_ECCV_2018/html/Bochao_Wang_Toward_Characteristic-Preserving_Image-based_ECCV_2018_paper.html) | ECCV | [code](https://github.com/sergeywong/cp-vton) | 29 |
| [Explainable Neural Computation via Stack Neural Module Networks](http://openaccess.thecvf.com/content_ECCV_2018/html/Ronghang_Hu_Explainable_Neural_Computation_ECCV_2018_paper.html) | ECCV | [code](https://github.com/ronghanghu/snmn) | 29 |
| [Exploring Disentangled Feature Representation Beyond Face Identification](http://openaccess.thecvf.com/content_cvpr_2018/papers/Liu_Exploring_Disentangled_Feature_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/sciencefans/D2AE-Face-Generator) | 29 |
| [Controllable Video Generation With Sparse Trajectories](http://openaccess.thecvf.com/content_cvpr_2018/papers/Hao_Controllable_Video_Generation_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/zekunhao1995/ControllableVideoGen) | 28 |
| [Layer-structured 3D Scene Inference via View Synthesis](http://openaccess.thecvf.com/content_ECCV_2018/html/Shubham_Tulsiani_Layer-structured_3D_Scene_ECCV_2018_paper.html) | ECCV | [code](https://github.com/google/layered-scene-inference) | 28 |
| [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](http://openaccess.thecvf.com/content_ECCV_2018/html/Liang-Chieh_Chen_Encoder-Decoder_with_Atrous_ECCV_2018_paper.html) | ECCV | [code](https://github.com/qixuxiang/deeplabv3plus) | 28 |
| [PiCANet: Learning Pixel-Wise Contextual Attention for Saliency Detection](http://openaccess.thecvf.com/content_cvpr_2018/papers/Liu_PiCANet_Learning_Pixel-Wise_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/Ugness/PiCANet-Implementation) | 28 |
| [Learning Rich Features for Image Manipulation Detection](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhou_Learning_Rich_Features_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/LarryJiang134/Image_manipulation_detection) | 27 |
| [Fast Video Object Segmentation by Reference-Guided Mask Propagation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Oh_Fast_Video_Object_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/seoungwugoh/RGMP) | 27 |
| [3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration](http://openaccess.thecvf.com/content_ECCV_2018/html/Zi_Jian_Yew_3DFeat-Net_Weakly_Supervised_ECCV_2018_paper.html) | ECCV | [code](https://github.com/yewzijian/3DFeatNet) | 27 |
| [Who Let the Dogs Out? Modeling Dog Behavior From Visual Data](http://openaccess.thecvf.com/content_cvpr_2018/papers/Ehsani_Who_Let_the_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/ehsanik/dogTorch) | 27 |
| [EC-Net: an Edge-aware Point set Consolidation Network](http://openaccess.thecvf.com/content_ECCV_2018/html/Lequan_Yu_EC-Net_an_Edge-aware_ECCV_2018_paper.html) | ECCV | [code](https://github.com/yulequan/EC-Net) | 27 |
| [Interpretable Intuitive Physics Model](http://openaccess.thecvf.com/content_ECCV_2018/html/Tian_Ye_Interpretable_Intuitive_Physics_ECCV_2018_paper.html) | ECCV | [code](https://github.com/tianye95/interpretable-intuitive-physics-model) | 27 |
| [Learning a Discriminative Feature Network for Semantic Segmentation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Yu_Learning_a_Discriminative_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/lxtGH/dfn_seg) | 26 |
| [Partial Transfer Learning With Selective Adversarial Networks](http://openaccess.thecvf.com/content_cvpr_2018/papers/Cao_Partial_Transfer_Learning_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/thuml/SAN) | 26 |
| [Cross-Modal Deep Variational Hand Pose Estimation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Spurr_Cross-Modal_Deep_Variational_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/spurra/vae-hands-3d) | 26 |
| [Between-Class Learning for Image Classification](http://openaccess.thecvf.com/content_cvpr_2018/papers/Tokozume_Between-Class_Learning_for_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/mil-tokyo/bc_learning_image) | 26 |
| [AON: Towards Arbitrarily-Oriented Text Recognition](http://openaccess.thecvf.com/content_cvpr_2018/papers/Cheng_AON_Towards_Arbitrarily-Oriented_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/huizhang0110/AON) | 26 |
| [Conditional Image-to-Image Translation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Lin_Conditional_Image-to-Image_Translation_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/znxlwm/pytorch-Conditional-image-to-image-translation) | 25 |
| [Learning Convolutional Networks for Content-Weighted Image Compression](http://openaccess.thecvf.com/content_cvpr_2018/papers/Li_Learning_Convolutional_Networks_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/limuhit/ImageCompression) | 25 |
| [Diversity Regularized Spatiotemporal Attention for Video-Based Person Re-Identification](http://openaccess.thecvf.com/content_cvpr_2018/papers/Li_Diversity_Regularized_Spatiotemporal_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/ShuangLI59/Diversity-Regularized-Spatiotemporal-Attention) | 25 |
| [Dynamic Multimodal Instance Segmentation Guided by Natural Language Queries](http://openaccess.thecvf.com/content_ECCV_2018/html/Edgar_Margffoy-Tuay_Dynamic_Multimodal_Instance_ECCV_2018_paper.html) | ECCV | [code](https://github.com/BCV-Uniandes/query-objseg) | 25 |
| [CBMV: A Coalesced Bidirectional Matching Volume for Disparity Estimation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Batsos_CBMV_A_Coalesced_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/kbatsos/CBMV) | 25 |
| [Deep Texture Manifold for Ground Terrain Recognition](http://openaccess.thecvf.com/content_cvpr_2018/papers/Xue_Deep_Texture_Manifold_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/jiaxue1993/Deep-Encoding-Pooling-Network-DEP-) | 25 |
| [Audio-Visual Event Localization in Unconstrained Videos](http://openaccess.thecvf.com/content_ECCV_2018/html/Yapeng_Tian_Audio-Visual_Event_Localization_ECCV_2018_paper.html) | ECCV | [code](https://github.com/YapengTian/AVE-ECCV18) | 25 |
| [First Order Generative Adversarial Networks](http://proceedings.mlr.press/v80/seward18a.html) | ICML | [code](https://github.com/zalandoresearch/first_order_gan) | 25 |
| [Visual Coreference Resolution in Visual Dialog using Neural Module Networks](http://openaccess.thecvf.com/content_ECCV_2018/html/Satwik_Kottur_Visual_Coreference_Resolution_ECCV_2018_paper.html) | ECCV | [code](https://github.com/facebookresearch/corefnmn) | 25 |
| [SYQ: Learning Symmetric Quantization for Efficient Deep Neural Networks](http://openaccess.thecvf.com/content_cvpr_2018/papers/Faraone_SYQ_Learning_Symmetric_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/julianfaraone/SYQ) | 24 |
| [Deep Reinforcement Learning of Marked Temporal Point Processes](http://arxiv.org/abs/1805.09360v1) | NIPS | [code](https://github.com/Networks-Learning/tpprl) | 24 |
| [Explicit Inductive Bias for Transfer Learning with Convolutional Networks](http://proceedings.mlr.press/v80/li18a.html) | ICML | [code](https://github.com/holyseven/TransferLearningClassification) | 24 |
| [LEGO: Learning Edge With Geometry All at Once by Watching Videos](http://openaccess.thecvf.com/content_cvpr_2018/papers/Yang_LEGO_Learning_Edge_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/zhenheny/LEGO) | 24 |
| [Verisimilar Image Synthesis for Accurate Detection and Recognition of Texts in Scenes](http://openaccess.thecvf.com/content_ECCV_2018/html/Fangneng_Zhan_Verisimilar_Image_Synthesis_ECCV_2018_paper.html) | ECCV | [code](https://github.com/fnzhan/Verisimilar-Image-Synthesis-for-Accurate-Detection-and-Recognition-of-Texts-in-Scenes) | 24 |
| [Multi-Agent Diverse Generative Adversarial Networks](http://openaccess.thecvf.com/content_cvpr_2018/papers/Ghosh_Multi-Agent_Diverse_Generative_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/arnabgho/MADGAN) | 23 |
| [Face Aging With Identity-Preserved Conditional Generative Adversarial Networks](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_Face_Aging_With_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/dawei6875797/Face-Aging-with-Identity-Preserved-Conditional-Generative-Adversarial-Networks) | 23 |
| [Learning to Separate Object Sounds by Watching Unlabeled Video](http://openaccess.thecvf.com/content_ECCV_2018/html/Ruohan_Gao_Learning_to_Separate_ECCV_2018_paper.html) | ECCV | [code](https://github.com/rhgao/separating-object-sounds) | 23 |
| [Exploiting the Potential of Standard Convolutional Autoencoders for Image Restoration by Evolutionary Search](http://proceedings.mlr.press/v80/suganuma18a.html) | ICML | [code](https://github.com/sg-nm/Evolutionary-Autoencoders) | 23 |
| [To Trust Or Not To Trust A Classifier](http://arxiv.org/abs/1805.11783v1) | NIPS | [code](https://github.com/google/TrustScore) | 23 |
| [Im2Flow: Motion Hallucination From Static Images for Action Recognition](http://openaccess.thecvf.com/content_cvpr_2018/papers/Gao_Im2Flow_Motion_Hallucination_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/rhgao/Im2Flow) | 22 |
| [ISTA-Net: Interpretable Optimization-Inspired Deep Network for Image Compressive Sensing](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_ISTA-Net_Interpretable_Optimization-Inspired_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/jianzhangcs/ISTA-Net) | 22 |
| [Hallucinated-IQA: No-Reference Image Quality Assessment via Adversarial Learning](http://openaccess.thecvf.com/content_cvpr_2018/papers/Lin_Hallucinated-IQA_No-Reference_Image_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/kwanyeelin/HIQA) | 22 |
| [Anonymous Walk Embeddings](http://proceedings.mlr.press/v80/ivanov18a.html) | ICML | [code](https://github.com/nd7141/AWE) | 22 |
| [Learning to Multitask](http://arxiv.org/abs/1805.07541v1) | NIPS | [code](https://github.com/jfutoma/MGP-RNN) | 22 |
| [CondenseNet: An Efficient DenseNet Using Learned Group Convolutions](http://openaccess.thecvf.com/content_cvpr_2018/papers/Huang_CondenseNet_An_Efficient_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/markdtw/condensenet-tensorflow) | 22 |
| [HashGAN: Deep Learning to Hash With Pair Conditional Wasserstein GAN](http://openaccess.thecvf.com/content_cvpr_2018/papers/Cao_HashGAN_Deep_Learning_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/thuml/HashGAN) | 22 |
| [Hierarchical Relational Networks for Group Activity Recognition and Retrieval](http://openaccess.thecvf.com/content_ECCV_2018/html/Mostafa_Ibrahim_Hierarchical_Relational_Networks_ECCV_2018_paper.html) | ECCV | [code](https://github.com/mostafa-saad/hierarchical-relational-network) | 22 |
| [Collaborative and Adversarial Network for Unsupervised Domain Adaptation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_Collaborative_and_Adversarial_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/mahfuj9346449/iCAN) | 22 |
| [Geometry-Aware Scene Text Detection With Instance Transformation Network](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_Geometry-Aware_Scene_Text_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/zlmzju/itn) | 22 |
| [Learning to Promote Saliency Detectors](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zeng_Learning_to_Promote_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/zengxianyu/lps) | 21 |
| [CSGNet: Neural Shape Parser for Constructive Solid Geometry](http://openaccess.thecvf.com/content_cvpr_2018/papers/Sharma_CSGNet_Neural_Shape_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/Hippogriff/CSGNet) | 21 |
| [Local Spectral Graph Convolution for Point Set Feature Learning](http://openaccess.thecvf.com/content_ECCV_2018/html/Chu_Wang_Local_Spectral_Graph_ECCV_2018_paper.html) | ECCV | [code](https://github.com/fate3439/LocalSpecGCN) | 21 |
| [HiDDeN: Hiding Data with Deep Networks](http://openaccess.thecvf.com/content_ECCV_2018/html/Jiren_Zhu_HiDDeN_Hiding_Data_ECCV_2018_paper.html) | ECCV | [code](https://github.com/jirenz/HiDDeN) | 21 |
| [GraphBit: Bitwise Interaction Mining via Deep Reinforcement Learning](http://openaccess.thecvf.com/content_cvpr_2018/papers/Duan_GraphBit_Bitwise_Interaction_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/duanyq14/GraphBit) | 20 |
| [Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_Stacked_Conditional_Generative_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/DeepInsight-PCALab/ST-CGAN) | 20 |
| [Fully-Convolutional Point Networks for Large-Scale Point Clouds](http://openaccess.thecvf.com/content_ECCV_2018/html/Dario_Rethage_Fully-Convolutional_Point_Networks_ECCV_2018_paper.html) | ECCV | [code](https://github.com/drethage/fully-convolutional-point-network) | 20 |
| [Learning Superpixels With Segmentation-Aware Affinity Loss](http://openaccess.thecvf.com/content_cvpr_2018/papers/Tu_Learning_Superpixels_With_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/wctu/SEAL) | 20 |
| [Zero-Shot Visual Recognition Using Semantics-Preserving Adversarial Embedding Networks](http://openaccess.thecvf.com/content_cvpr_2018/papers/Chen_Zero-Shot_Visual_Recognition_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/zjuchenlong/sp-aen.cvpr18) | 20 |
| [Crowd Counting With Deep Negative Correlation Learning](http://openaccess.thecvf.com/content_cvpr_2018/papers/Shi_Crowd_Counting_With_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/shizenglin/Deep-NCL) | 20 |
| [Dimensionality-Driven Learning with Noisy Labels](http://proceedings.mlr.press/v80/ma18d.html) | ICML | [code](https://github.com/xingjunm/dimensionality-driven-learning) | 20 |
| [Objects that Sound](http://openaccess.thecvf.com/content_ECCV_2018/html/Relja_Arandjelovic_Objects_that_Sound_ECCV_2018_paper.html) | ECCV | [code](https://github.com/rohitrango/objects-that-sound) | 20 |
| [Deep Expander Networks: Efficient Deep Networks from Graph Theory](http://openaccess.thecvf.com/content_ECCV_2018/html/Ameya_Prabhu_Deep_Expander_Networks_ECCV_2018_paper.html) | ECCV | [code](https://github.com/DrImpossible/Deep-Expander-Networks) | 19 |
| [Low-Shot Learning With Large-Scale Diffusion](http://openaccess.thecvf.com/content_cvpr_2018/papers/Douze_Low-Shot_Learning_With_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/facebookresearch/low-shot-with-diffusion) | 19 |
| [Low-Shot Learning With Imprinted Weights](http://openaccess.thecvf.com/content_cvpr_2018/papers/Qi_Low-Shot_Learning_With_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/YU1ut/imprinted-weights) | 19 |
| [Cross-Domain Self-Supervised Multi-Task Feature Learning Using Synthetic Imagery](http://openaccess.thecvf.com/content_cvpr_2018/papers/Ren_Cross-Domain_Self-Supervised_Multi-Task_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/jason718/game-feature-learning) | 19 |
| [Learning Descriptor Networks for 3D Shape Synthesis and Analysis](http://openaccess.thecvf.com/content_cvpr_2018/papers/Xie_Learning_Descriptor_Networks_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/jianwen-xie/3DDescriptorNet) | 19 |
| [Disentangling Factors of Variation with Cycle-Consistent Variational Auto-Encoders](http://openaccess.thecvf.com/content_ECCV_2018/html/Ananya_Harsh_Jha_Disentangling_Factors_of_ECCV_2018_paper.html) | ECCV | [code](https://github.com/ananyahjha93/cycle-consistent-vae) | 19 |
| [CTAP: Complementary Temporal Action Proposal Generation](http://openaccess.thecvf.com/content_ECCV_2018/html/Jiyang_Gao_CTAP_Complementary_Temporal_ECCV_2018_paper.html) | ECCV | [code](https://github.com/jiyanggao/CTAP) | 18 |
| [DVAE#: Discrete Variational Autoencoders with Relaxed Boltzmann Priors](http://arxiv.org/abs/1805.07445v3) | NIPS | [code](https://github.com/dojoteef/dvae) | 18 |
| [Conditional Image-Text Embedding Networks](http://openaccess.thecvf.com/content_ECCV_2018/html/Bryan_Plummer_Conditional_Image-Text_Embedding_ECCV_2018_paper.html) | ECCV | [code](https://github.com/BryanPlummer/cite) | 18 |
| [EPINET: A Fully-Convolutional Neural Network Using Epipolar Geometry for Depth From Light Field Images](http://openaccess.thecvf.com/content_cvpr_2018/papers/Shin_EPINET_A_Fully-Convolutional_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/chshin10/epinet) | 18 |
| [Glimpse Clouds: Human Activity Recognition From Unstructured Feature Points](http://openaccess.thecvf.com/content_cvpr_2018/papers/Baradel_Glimpse_Clouds_Human_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/fabienbaradel/glimpse_clouds) | 18 |
| [Bayesian Optimization of Combinatorial Structures](http://proceedings.mlr.press/v80/baptista18a.html) | ICML | [code](https://github.com/baptistar/BOCS) | 18 |
| [FeaStNet: Feature-Steered Graph Convolutions for 3D Shape Analysis](http://openaccess.thecvf.com/content_cvpr_2018/papers/Verma_FeaStNet_Feature-Steered_Graph_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/nitika-verma/FeaStNet) | 18 |
| [Learning Type-Aware Embeddings for Fashion Compatibility](http://openaccess.thecvf.com/content_ECCV_2018/html/Mariya_Vasileva_Learning_Type-Aware_Embeddings_ECCV_2018_paper.html) | ECCV | [code](https://github.com/mvasil/fashion-compatibility) | 17 |
| [Sliced Wasserstein Distance for Learning Gaussian Mixture Models](http://openaccess.thecvf.com/content_cvpr_2018/papers/Kolouri_Sliced_Wasserstein_Distance_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/skolouri/swgmm) | 17 |
| [Revisiting Deep Intrinsic Image Decompositions](http://openaccess.thecvf.com/content_cvpr_2018/papers/Fan_Revisiting_Deep_Intrinsic_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/fqnchina/IntrinsicImage) | 17 |
| [A Spectral Approach to Gradient Estimation for Implicit Distributions](http://proceedings.mlr.press/v80/shi18a.html) | ICML | [code](https://github.com/thjashin/spectral-stein-grad) | 17 |
| [Hierarchical Novelty Detection for Visual Object Recognition](http://openaccess.thecvf.com/content_cvpr_2018/papers/Lee_Hierarchical_Novelty_Detection_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/kibok90/cvpr2018-hnd) | 17 |
| [Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies](http://openaccess.thecvf.com/content_cvpr_2018/papers/Joo_Total_Capture_A_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/Myzhencai/Total-Capture) | 17 |
| [Learning Generative ConvNets via Multi-Grid Modeling and Sampling](http://openaccess.thecvf.com/content_cvpr_2018/papers/Gao_Learning_Generative_ConvNets_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/ruiqigao/Multigrid_learning) | 17 |
| [Learning 3D Shape Completion From Laser Scan Data With Weak Supervision](http://openaccess.thecvf.com/content_cvpr_2018/papers/Stutz_Learning_3D_Shape_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/davidstutz/cvpr2018-shape-completion) | 17 |
| [Triplet Loss in Siamese Network for Object Tracking](http://openaccess.thecvf.com/content_ECCV_2018/html/Xingping_Dong_Triplet_Loss_with_ECCV_2018_paper.html) | ECCV | [code](https://github.com/shenjianbing/TripletTracking) | 17 |
| [Adversarial Attack on Graph Structured Data](http://proceedings.mlr.press/v80/dai18b.html) | ICML | [code](https://github.com/Hanjun-Dai/graph_adversarial_attack) | 17 |
| [Arbitrary Style Transfer With Deep Feature Reshuffle](http://openaccess.thecvf.com/content_cvpr_2018/papers/Gu_Arbitrary_Style_Transfer_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/msracver/Style-Feature-Reshuffle) | 17 |
| [Visual Question Reasoning on General Dependency Tree](http://openaccess.thecvf.com/content_cvpr_2018/papers/Cao_Visual_Question_Reasoning_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/bezorro/ACMN-Pytorch) | 17 |
| [Predicting Gaze in Egocentric Video by Learning Task-dependent Attention Transition](http://openaccess.thecvf.com/content_ECCV_2018/html/Huang_Predicting_Gaze_in_ECCV_2018_paper.html) | ECCV | [code](https://github.com/hyf015/egocentric-gaze-prediction) | 16 |
| [Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networks](https://arxiv.org/abs/1802.04034) | NIPS | [code](https://github.com/ytsmiling/lmt) | 16 |
| [Coded Sparse Matrix Multiplication](http://proceedings.mlr.press/v80/wang18e.html) | ICML | [code](https://github.com/ksopyla/CudaDotProd) | 16 |
| [Weakly-Supervised Action Segmentation With Iterative Soft Boundary Assignment](http://openaccess.thecvf.com/content_cvpr_2018/papers/Ding_Weakly-Supervised_Action_Segmentation_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/Zephyr-D/TCFPN-ISBA) | 16 |
| [Recovering 3D Planes from a Single Image via Convolutional Neural Networks](http://openaccess.thecvf.com/content_ECCV_2018/html/Fengting_Yang_Recovering_3D_Planes_ECCV_2018_paper.html) | ECCV | [code](https://github.com/fuy34/planerecover) | 16 |
| [SegStereo: Exploiting Semantic Information for Disparity Estimation](http://openaccess.thecvf.com/content_ECCV_2018/html/Guorun_Yang_SegStereo_Exploiting_Semantic_ECCV_2018_paper.html) | ECCV | [code](https://github.com/yangguorun/SegStereo) | 16 |
| [Functional Gradient Boosting based on Residual Network Perception](http://proceedings.mlr.press/v80/nitanda18a.html) | ICML | [code](https://github.com/anitan0925/ResFGB) | 16 |
| [NAG: Network for Adversary Generation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Mopuri_NAG_Network_for_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/val-iisc/nag) | 16 |
| [Generative Probabilistic Novelty Detection with Adversarial Autoencoders](http://arxiv.org/abs/1807.02588v1) | NIPS | [code](https://github.com/podgorskiy/GPND) | 16 |
| [Hashing as Tie-Aware Learning to Rank](http://openaccess.thecvf.com/content_cvpr_2018/papers/He_Hashing_as_Tie-Aware_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/kunhe/TALR) | 15 |
| [Pose Proposal Networks](http://openaccess.thecvf.com/content_ECCV_2018/html/Sekii_Pose_Proposal_Networks_ECCV_2018_paper.html) | ECCV | [code](https://github.com/salihkaragoz/MultiPerson-pose-estimation) | 15 |
| [Convolutional Sequence to Sequence Model for Human Dynamics](http://openaccess.thecvf.com/content_cvpr_2018/papers/Li_Convolutional_Sequence_to_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/chaneyddtt/Convolutional-Sequence-to-Sequence-Model-for-Human-Dynamics) | 15 |
| [Joint Pose and Expression Modeling for Facial Expression Recognition](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_Joint_Pose_and_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/FFZhang1231/Facial-expression-recognition) | 15 |
| [Grounding Referring Expressions in Images by Variational Context](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_Grounding_Referring_Expressions_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/yuleiniu/vc) | 15 |
| [Rethinking the Form of Latent States in Image Captioning](http://openaccess.thecvf.com/content_ECCV_2018/html/Bo_Dai_Rethinking_the_Form_ECCV_2018_paper.html) | ECCV | [code](https://github.com/doubledaibo/2dcaption_eccv2018) | 15 |
| [Open Set Domain Adaptation by Backpropagation](http://openaccess.thecvf.com/content_ECCV_2018/html/Kuniaki_Saito_Adversarial_Open_Set_ECCV_2018_paper.html) | ECCV | [code](https://github.com/YU1ut/openset-DA) | 15 |
| [Neural Sign Language Translation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Camgoz_Neural_Sign_Language_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/neccam/nslt) | 15 |
| [SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters](http://openaccess.thecvf.com/content_ECCV_2018/html/Yifan_Xu_SpiderCNN_Deep_Learning_ECCV_2018_paper.html) | ECCV | [code](https://github.com/xyf513/SpiderCNN) | 15 |
| [Efficient Neural Audio Synthesis](http://proceedings.mlr.press/v80/kalchbrenner18a.html) | ICML | [code](https://github.com/fedden/TensorFlow-Efficient-Neural-Audio-Synthesis) | 15 |
| [Deep Learning Under Privileged Information Using Heteroscedastic Dropout](http://openaccess.thecvf.com/content_cvpr_2018/papers/Lambert_Deep_Learning_Under_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/johnwlambert/dlupi-heteroscedastic-dropout) | 14 |
| [Image Transformer](http://proceedings.mlr.press/v80/parmar18a.html) | ICML | [code](https://github.com/ssingal05/ImageTransformer) | 14 |
| [Learning to Understand Image Blur](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_Learning_to_Understand_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/Lotuslisa/Understand_Image_Blur) | 14 |
| [Learning and Using the Arrow of Time](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wei_Learning_and_Using_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/donglaiw/AoT_TCAM) | 14 |
| [Action Sets: Weakly Supervised Action Segmentation Without Ordering Constraints](http://openaccess.thecvf.com/content_cvpr_2018/papers/Richard_Action_Sets_Weakly_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/alexanderrichard/action-sets) | 14 |
| [Learning to Forecast and Refine Residual Motion for Image-to-Video Generation](http://openaccess.thecvf.com/content_ECCV_2018/html/Long_Zhao_Learning_to_Forecast_ECCV_2018_paper.html) | ECCV | [code](https://github.com/garyzhao/FRGAN) | 14 |
| [Multi-Scale Weighted Nuclear Norm Image Restoration](http://openaccess.thecvf.com/content_cvpr_2018/papers/Yair_Multi-Scale_Weighted_Nuclear_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/noamyairTC/MSWNNM) | 14 |
| [Synthesizing Robust Adversarial Examples](http://proceedings.mlr.press/v80/athalye18b.html) | ICML | [code](https://github.com/prabhant/synthesizing-robust-adversarial-examples) | 13 |
| [Fine-Grained Visual Categorization using Meta-Learning Optimization with Sample Selection of Auxiliary Data](http://openaccess.thecvf.com/content_ECCV_2018/html/Yabin_Zhang_Fine-Grained_Visual_Categorization_ECCV_2018_paper.html) | ECCV | [code](https://github.com/YabinZhang1994/MetaFGNet) | 13 |
| [Assessing Generative Models via Precision and Recall](http://arxiv.org/abs/1806.00035v1) | NIPS | [code](https://github.com/msmsajjadi/precision-recall-distributions) | 13 |
| [Deep Diffeomorphic Transformer Networks](http://openaccess.thecvf.com/content_cvpr_2018/papers/Detlefsen_Deep_Diffeomorphic_Transformer_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/SkafteNicki/ddtn) | 13 |
| [Learning by Asking Questions](http://openaccess.thecvf.com/content_cvpr_2018/papers/Misra_Learning_by_Asking_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/yanghoonkim/question_generation) | 13 |
| [Towards Human-Machine Cooperation: Self-Supervised Sample Mining for Object Detection](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_Towards_Human-Machine_Cooperation_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/yanxp/SSM) | 13 |
| [Variational Autoencoders for Deforming 3D Mesh Models](http://openaccess.thecvf.com/content_cvpr_2018/papers/Tan_Variational_Autoencoders_for_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/aldehydecho/Mesh-VAE) | 13 |
| [Min-Entropy Latent Model for Weakly Supervised Object Detection](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wan_Min-Entropy_Latent_Model_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/Winfrand/MELM) | 13 |
| [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](http://openaccess.thecvf.com/content_cvpr_2018/papers/Anderson_Bottom-Up_and_Top-Down_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/Wentong-DST/up-down-captioner) | 13 |
| [Gradient-Based Meta-Learning with Learned Layerwise Metric and Subspace](http://proceedings.mlr.press/v80/lee18a.html) | ICML | [code](https://github.com/yoonholee/MT-net) | 13 |
| [Learning a Discriminative Filter Bank Within a CNN for Fine-Grained Recognition](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_Learning_a_Discriminative_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/hubeihubei/DFL-CNN-pytorch) | 13 |
| [Finding Influential Training Samples for Gradient Boosted Decision Trees](http://proceedings.mlr.press/v80/sharchilev18a.html) | ICML | [code](https://github.com/bsharchilev/influence_boosting) | 13 |
| [Gesture Recognition: Focus on the Hands](http://openaccess.thecvf.com/content_cvpr_2018/papers/Narayana_Gesture_Recognition_Focus_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/beckabec/HandDetection) | 12 |
| [Cross-View Image Synthesis Using Conditional GANs](http://openaccess.thecvf.com/content_cvpr_2018/papers/Regmi_Cross-View_Image_Synthesis_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/kregmi/cross-view-image-synthesis) | 12 |
| [Joint Optimization Framework for Learning With Noisy Labels](http://openaccess.thecvf.com/content_cvpr_2018/papers/Tanaka_Joint_Optimization_Framework_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/DaikiTanaka-UT/JointOptimization) | 12 |
| [Future Person Localization in First-Person Videos](http://openaccess.thecvf.com/content_cvpr_2018/papers/Yagi_Future_Person_Localization_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/takumayagi/fpl) | 12 |
| [AutoLoc: Weakly-supervised Temporal Action Localization in Untrimmed Videos](http://openaccess.thecvf.com/content_ECCV_2018/html/Zheng_Shou_AutoLoc_Weakly-supervised_Temporal_ECCV_2018_paper.html) | ECCV | [code](https://github.com/zhengshou/AutoLoc) | 12 |
| [Learning Transferable Architectures for Scalable Image Recognition](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zoph_Learning_Transferable_Architectures_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/aussetg/nasnet.pytorch) | 12 |
| [Clipped Action Policy Gradient](http://proceedings.mlr.press/v80/fujita18a.html) | ICML | [code](https://github.com/pfnet-research/capg) | 12 |
| [Mix and Match Networks: Encoder-Decoder Alignment for Zero-Pair Image Translation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_Mix_and_Match_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/yaxingwang/Mix-and-match-networks) | 12 |
| [Decouple Learning for Parameterized Image Operators](http://openaccess.thecvf.com/content_ECCV_2018/html/Qingnan_Fan_Learning_to_Learn_ECCV_2018_paper.html) | ECCV | [code](https://github.com/fqnchina/DecoupleLearning) | 12 |
| [Generalized Earley Parser: Bridging Symbolic Grammars and Sequence Data for Future Prediction](http://proceedings.mlr.press/v80/qi18a.html) | ICML | [code](https://github.com/SiyuanQi/generalized-earley-parser) | 12 |
| [Adaptive Skip Intervals: Temporal Abstraction for Recurrent Dynamical Models](https://arxiv.org/abs/1808.04768) | NIPS | [code](https://github.com/neitzal/adaptive-skip-intervals) | 12 |
| [AMNet: Memorability Estimation With Attention](http://openaccess.thecvf.com/content_cvpr_2018/papers/Fajtl_AMNet_Memorability_Estimation_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/ok1zjf/AMNet) | 12 |
| [Adversarial Time-to-Event Modeling](http://proceedings.mlr.press/v80/chapfuwa18a.html) | ICML | [code](https://github.com/paidamoyo/adversarial_time_to_event) | 12 |
| [Reversible Recurrent Neural Networks](nan) | NIPS | [code](https://github.com/gan3sh500/revrnn) | 12 |
| [Human Pose Estimation With Parsing Induced Learner](http://openaccess.thecvf.com/content_cvpr_2018/papers/Nie_Human_Pose_Estimation_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/NieXC/pytorch-pil) | 11 |
| [ShapeStacks: Learning Vision-Based Physical Intuition for Generalised Object Stacking](http://openaccess.thecvf.com/content_ECCV_2018/html/Oliver_Groth_ShapeStacks_Learning_Vision-Based_ECCV_2018_paper.html) | ECCV | [code](https://github.com/ogroth/shapestacks) | 11 |
| [A Joint Sequence Fusion Model for Video Question Answering and Retrieval](http://openaccess.thecvf.com/content_ECCV_2018/html/Youngjae_Yu_A_Joint_Sequence_ECCV_2018_paper.html) | ECCV | [code](https://github.com/yj-yu/lsmdc) | 11 |
| [Learning Face Age Progression: A Pyramid Architecture of GANs](http://openaccess.thecvf.com/content_cvpr_2018/papers/Yang_Learning_Face_Age_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/ajithvallabai/Pyramid-Architecture-of-GANs) | 11 |
| [Robust Physical-World Attacks on Deep Learning Visual Classification](http://openaccess.thecvf.com/content_cvpr_2018/papers/Eykholt_Robust_Physical-World_Attacks_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/evtimovi/robust_physical_perturbations) | 11 |
| [High-Quality Prediction Intervals for Deep Learning: A Distribution-Free, Ensembled Approach](http://proceedings.mlr.press/v80/pearce18a.html) | ICML | [code](https://github.com/TeaPearce/Deep_Learning_Prediction_Intervals) | 11 |
| [Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes Theory](http://proceedings.mlr.press/v80/amit18a.html) | ICML | [code](https://github.com/ron-amit/meta-learning-adjusting-priors) | 11 |
| [Multimodal Explanations: Justifying Decisions and Pointing to the Evidence](http://openaccess.thecvf.com/content_cvpr_2018/papers/Park_Multimodal_Explanations_Justifying_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/Seth-Park/MultimodalExplanations) | 11 |
| [Accelerating Natural Gradient with Higher-Order Invariance](http://proceedings.mlr.press/v80/song18a.html) | ICML | [code](https://github.com/ermongroup/higher_order_invariance) | 11 |
| [Hierarchical Multi-Label Classification Networks](http://proceedings.mlr.press/v80/wehrmann18a.html) | ICML | [code](https://github.com/omoju/receiptdID) | 11 |
| [Convolutional Image Captioning](http://openaccess.thecvf.com/content_cvpr_2018/papers/Aneja_Convolutional_Image_Captioning_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/eladhoffer/captionGeneration.torch) | 11 |
| [Boosting Domain Adaptation by Discovering Latent Domains](http://openaccess.thecvf.com/content_cvpr_2018/papers/Mancini_Boosting_Domain_Adaptation_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/mancinimassimiliano/latent_domains_DA) | 11 |
| [Logo Synthesis and Manipulation With Clustered Generative Adversarial Networks](http://openaccess.thecvf.com/content_cvpr_2018/papers/Sage_Logo_Synthesis_and_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/alex-sage/logo-gen) | 10 |
| [PacGAN: The power of two samples in generative adversarial networks](http://arxiv.org/abs/1712.04086v2) | NIPS | [code](https://github.com/fjxmlzn/PacGAN) | 10 |
| [Attention Clusters: Purely Attention Based Local Feature Integration for Video Classification](http://openaccess.thecvf.com/content_cvpr_2018/papers/Long_Attention_Clusters_Purely_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/pomonam/AttentionCluster) | 10 |
| [End-to-End Incremental Learning](http://openaccess.thecvf.com/content_ECCV_2018/html/Francisco_M._Castro_End-to-End_Incremental_Learning_ECCV_2018_paper.html) | ECCV | [code](https://github.com/fmcp/EndToEndIncrementalLearning) | 10 |
| [Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Lyu_Multi-Oriented_Scene_Text_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/JK-Rao/Corner_Segmentation_TextDetection) | 10 |
| [On GANs and GMMs](http://arxiv.org/abs/1805.12462v1) | NIPS | [code](https://github.com/eitanrich/gans-n-gmms) | 10 |
| [Salient Object Detection Driven by Fixation Prediction](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_Salient_Object_Detection_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/wenguanwang/ASNet) | 9 |
| [Semantic Video Segmentation by Gated Recurrent Flow Propagation](http://openaccess.thecvf.com/content_cvpr_2018/papers/Nilsson_Semantic_Video_Segmentation_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/D-Nilsson/GRFP) | 9 |
| [Constraint-Aware Deep Neural Network Compression](http://openaccess.thecvf.com/content_ECCV_2018/html/Changan_Chen_Constraints_Matter_in_ECCV_2018_paper.html) | ECCV | [code](https://github.com/ChanganVR/ConstraintAwareCompression) | 9 |
| [Statistically-motivated Second-order Pooling](http://openaccess.thecvf.com/content_ECCV_2018/html/Kaicheng_Yu_Statistically-motivated_Second-order_Pooling_ECCV_2018_paper.html) | ECCV | [code](https://github.com/kcyu2014/smsop) | 9 |
| [Excitation Backprop for RNNs](http://openaccess.thecvf.com/content_cvpr_2018/papers/Bargal_Excitation_Backprop_for_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/sbargal/Caffe-ExcitationBP-RNNs) | 9 |
| [Analyzing Uncertainty in Neural Machine Translation](http://proceedings.mlr.press/v80/ott18a.html) | ICML | [code](https://github.com/facebookresearch/analyzing-uncertainty-nmt) | 9 |
| [Learning Dynamics of Linear Denoising Autoencoders](http://proceedings.mlr.press/v80/pretorius18a.html) | ICML | [code](https://github.com/arnupretorius/lindaedynamics_icml2018) | 9 |
| [Saliency Detection in 360° Videos](http://openaccess.thecvf.com/content_ECCV_2018/html/Ziheng_Zhang_Saliency_Detection_in_ECCV_2018_paper.html) | ECCV | [code](https://github.com/xuyanyu-shh/Saliency-detection-in-360-video) | 9 |
| [Density Adaptive Point Set Registration](http://openaccess.thecvf.com/content_cvpr_2018/papers/Lawin_Density_Adaptive_Point_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/felja633/DARE) | 9 |
| [Decoupled Parallel Backpropagation with Convergence Guarantee](http://proceedings.mlr.press/v80/huo18a.html) | ICML | [code](https://github.com/slowbull/DDG) | 9 |
| [Classification from Pairwise Similarity and Unlabeled Data](http://proceedings.mlr.press/v80/bao18a.html) | ICML | [code](https://github.com/levelfour/SU_Classification) | 9 |
| [oi-VAE: Output Interpretable VAEs for Nonlinear Group Factor Analysis](http://proceedings.mlr.press/v80/ainsworth18a.html) | ICML | [code](https://github.com/samuela/oi-vae) | 9 |
| [Modeling Sparse Deviations for Compressed Sensing using Generative Models](http://proceedings.mlr.press/v80/dhar18a.html) | ICML | [code](https://github.com/ermongroup/sparse_gen) | 9 |
| [Pixels, Voxels, and Views: A Study of Shape Representations for Single View 3D Object Shape Prediction](http://openaccess.thecvf.com/content_cvpr_2018/papers/Shin_Pixels_Voxels_and_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/daeyun/object-shapes-cvpr18) | 9 |
| [Towards Open-Set Identity Preserving Face Synthesis](http://openaccess.thecvf.com/content_cvpr_2018/papers/Bao_Towards_Open-Set_Identity_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/chloeguoqing/Towards-Open-Set-Identity-Preserving-Face-Synthesis) | 9 |
| [Five-Point Fundamental Matrix Estimation for Uncalibrated Cameras](http://openaccess.thecvf.com/content_cvpr_2018/papers/Barath_Five-Point_Fundamental_Matrix_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/danini/five-point-fundamental) | 8 |
| [BourGAN: Generative Networks with Metric Embeddings](https://arxiv.org/abs/1805.07674) | NIPS | [code](https://github.com/a554b554/BourGAN) | 8 |
| [Fast Information-theoretic Bayesian Optimisation](http://proceedings.mlr.press/v80/ru18a.html) | ICML | [code](https://github.com/rubinxin/FITBO) | 8 |
| [Deep Variational Reinforcement Learning for POMDPs](http://proceedings.mlr.press/v80/igl18a.html) | ICML | [code](https://github.com/oxwhirl/Deep-Variational-Reinforcement-Learning) | 8 |
| [Specular-to-Diffuse Translation for Multi-View Reconstruction](http://openaccess.thecvf.com/content_ECCV_2018/html/Shihao_Wu_Specular-to-Diffuse_Translation_for_ECCV_2018_paper.html) | ECCV | [code](https://github.com/wsh312/S2Dnet) | 8 |
| [Dynamic Conditional Networks for Few-Shot Learning](http://openaccess.thecvf.com/content_ECCV_2018/html/Fang_Zhao_Dynamic_Conditional_Networks_ECCV_2018_paper.html) | ECCV | [code](https://github.com/ZhaoJ9014/Dynamic-Conditional-Networks-for-Few-Shot-Learning.pytorch) | 8 |
| [Learning Facial Action Units From Web Images With Scalable Weakly Supervised Clustering](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhao_Learning_Facial_Action_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/zkl20061823/WSC) | 8 |
| [High-Resolution Image Synthesis and Semantic Manipulation With Conditional GANs](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_High-Resolution_Image_Synthesis_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/chenxli/High-Resolution-Image-Synthesis-and-Semantic-Manipulation-with-Conditional-GANsl-) | 8 |
| [Deep Defense: Training DNNs with Improved Adversarial Robustness](http://arxiv.org/abs/1803.00404v2) | NIPS | [code](https://github.com/ZiangYan/deepdefense.pytorch) | 8 |
| [Learning K-way D-dimensional Discrete Codes for Compact Embedding Representations](http://proceedings.mlr.press/v80/chen18g.html) | ICML | [code](https://github.com/chentingpc/kdcode-lm) | 8 |
| [Light Structure from Pin Motion: Simple and Accurate Point Light Calibration for Physics-based Modeling](http://openaccess.thecvf.com/content_ECCV_2018/html/Hiroaki_Santo_Light_Structure_from_ECCV_2018_paper.html) | ECCV | [code](https://github.com/hiroaki-santo/light-structure-from-pin-motion) | 7 |
| [Non-metric Similarity Graphs for Maximum Inner Product Search](nan) | NIPS | [code](https://github.com/stanis-morozov/ip-nsw) | 7 |
| [Towards Realistic Predictors](http://openaccess.thecvf.com/content_ECCV_2018/html/Pei_Wang_Towards_Realistic_Predictors_ECCV_2018_paper.html) | ECCV | [code](https://github.com/peiwang062/towards-realistic-predictors) | 7 |
| [Deep Non-Blind Deconvolution via Generalized Low-Rank Approximation](nan) | NIPS | [code](https://github.com/rwenqi/NBD-GLRA) | 7 |
| [Don’t Just Assume Look and Answer: Overcoming Priors for Visual Question Answering](http://openaccess.thecvf.com/content_cvpr_2018/papers/Agrawal_Dont_Just_Assume_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/AishwaryaAgrawal/GVQA) | 7 |
| [Learning Dual Convolutional Neural Networks for Low-Level Vision](http://openaccess.thecvf.com/content_cvpr_2018/papers/Pan_Learning_Dual_Convolutional_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/galad-loth/DualCNN-TF) | 7 |
| [The Mirage of Action-Dependent Baselines in Reinforcement Learning](http://proceedings.mlr.press/v80/tucker18a.html) | ICML | [code](https://github.com/brain-research/mirage-rl) | 7 |
| [DVQA: Understanding Data Visualizations via Question Answering](http://openaccess.thecvf.com/content_cvpr_2018/papers/Kafle_DVQA_Understanding_Data_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/kushalkafle/DVQA_dataset) | 7 |
| [A Two-Step Disentanglement Method](http://openaccess.thecvf.com/content_cvpr_2018/papers/Hadad_A_Two-Step_Disentanglement_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/naamahadad/A-Two-Step-Disentanglement-Method) | 7 |
| [Detecting and Correcting for Label Shift with Black Box Predictors](http://proceedings.mlr.press/v80/lipton18a.html) | ICML | [code](https://github.com/zackchase/label-shift) | 7 |
| [Conditional Prior Networks for Optical Flow](http://openaccess.thecvf.com/content_ECCV_2018/html/Yanchao_Yang_Conditional_Prior_Networks_ECCV_2018_paper.html) | ECCV | [code](https://github.com/YanchaoYang/Conditional-Prior-Networks) | 7 |
| [Generative Adversarial Learning Towards Fast Weakly Supervised Detection](http://openaccess.thecvf.com/content_cvpr_2018/papers/Shen_Generative_Adversarial_Learning_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/shenyunhang/GAL-fWSD) | 7 |
| [Adversarial Learning with Local Coordinate Coding](http://proceedings.mlr.press/v80/cao18a.html) | ICML | [code](https://github.com/guoyongcs/LCCGAN) | 7 |
| [Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks](http://openaccess.thecvf.com/content_cvpr_2018/papers/Kuen_Stochastic_Downsampling_for_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/xternalz/SDPoint) | 7 |
| [AttnGAN: Fine-Grained Text to Image Generation With Attentional Generative Adversarial Networks](http://openaccess.thecvf.com/content_cvpr_2018/papers/Xu_AttnGAN_Fine-Grained_Text_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/Wentong-DST/attn-gan) | 7 |
| [Learning to Explain: An Information-Theoretic Perspective on Model Interpretation](http://proceedings.mlr.press/v80/chen18j.html) | ICML | [code](https://github.com/nickvosk/acl2015-dataset-learning-to-explain-entity-relationships) | 7 |
| [Banach Wasserstein GAN](http://arxiv.org/abs/1806.06621v1) | NIPS | [code](https://github.com/adler-j/bwgan) | 7 |
| [Gradually Updated Neural Networks for Large-Scale Image Recognition](http://proceedings.mlr.press/v80/qiao18b.html) | ICML | [code](https://github.com/joe-siyuan-qiao/GUNN) | 7 |
| [Learning Steady-States of Iterative Algorithms over Graphs](http://proceedings.mlr.press/v80/dai18a.html) | ICML | [code](https://github.com/Hanjun-Dai/steady_state_embedding) | 7 |
| [Progressive Attention Guided Recurrent Network for Salient Object Detection](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_Progressive_Attention_Guided_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/zhangxiaoning666/PAGR) | 7 |
| [Zoom and Learn: Generalizing Deep Stereo Matching to Novel Domains](http://openaccess.thecvf.com/content_cvpr_2018/papers/Pang_Zoom_and_Learn_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/Artifineuro/zole) | 6 |
| [Unsupervised holistic image generation from key local patches](http://openaccess.thecvf.com/content_ECCV_2018/html/Donghoon_Lee_Unsupervised_holistic_image_ECCV_2018_paper.html) | ECCV | [code](https://github.com/hellbell/KeyPatchGan) | 6 |
| [Inner Space Preserving Generative Pose Machine](http://openaccess.thecvf.com/content_ECCV_2018/html/Shuangjun_Liu_Inner_Space_Preserving_ECCV_2018_paper.html) | ECCV | [code](https://github.com/ostadabbas/isp-gpm) | 6 |
| [Bilevel Programming for Hyperparameter Optimization and Meta-Learning](http://proceedings.mlr.press/v80/franceschi18a.html) | ICML | [code](https://github.com/prolearner/hyper-representation) | 6 |
| [Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition](http://openaccess.thecvf.com/content_cvpr_2018/papers/Sun_Optical_Flow_Guided_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/kitsune999/Optical-Flow-Guided-Feature) | 6 |
| [Breaking the Activation Function Bottleneck through Adaptive Parameterization](https://arxiv.org/abs/1805.08574) | NIPS | [code](https://github.com/flennerhag/alstm) | 6 |
| [Ultra Large-Scale Feature Selection using Count-Sketches](http://proceedings.mlr.press/v80/aghazadeh18a.html) | ICML | [code](https://github.com/rdspring1/MISSION) | 6 |
| [Dynamic Scene Deblurring Using Spatially Variant Recurrent Neural Networks](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_Dynamic_Scene_Deblurring_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/zhjwustc/cvpr18_rnn_deblur_matcaffe) | 6 |
| [Orthogonally Decoupled Variational Gaussian Processes](http://arxiv.org/abs/1809.08820v1) | NIPS | [code](https://github.com/hughsalimbeni/orth_decoupled_var_gps) | 6 |
| [Batch Bayesian Optimization via Multi-objective Acquisition Ensemble for Automated Analog Circuit Design](http://proceedings.mlr.press/v80/lyu18a.html) | ICML | [code](https://github.com/Alaya-in-Matrix/MACE) | 6 |
| [A Modulation Module for Multi-task Learning with Applications in Image Retrieval](http://openaccess.thecvf.com/content_ECCV_2018/html/Xiangyun_Zhao_A_Modulation_Module_ECCV_2018_paper.html) | ECCV | [code](https://github.com/Zhaoxiangyun/Multi-Task-Modulation-Module) | 6 |
| [A Memory Network Approach for Story-Based Temporal Summarization of 360° Videos](http://openaccess.thecvf.com/content_cvpr_2018/papers/Lee_A_Memory_Network_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/sangho-vision/PFMN) | 6 |
| [Towards Effective Low-Bitwidth Convolutional Neural Networks](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhuang_Towards_Effective_Low-Bitwidth_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/nowgood/QuantizeCNNModel) | 5 |
| [Disentangling Factors of Variation by Mixing Them](http://openaccess.thecvf.com/content_cvpr_2018/papers/Hu_Disentangling_Factors_of_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/HuQyang/Disentangling-Factors-of-Variation-by-Mixing-Them) | 5 |
| [Weakly-supervised Video Summarization using Variational Encoder-Decoder and Web Prior](http://openaccess.thecvf.com/content_ECCV_2018/html/Sijia_Cai_Weakly-supervised_Video_Summarization_ECCV_2018_paper.html) | ECCV | [code](https://github.com/cssjcai/vesd) | 5 |
| [Learning Longer-term Dependencies in RNNs with Auxiliary Losses](http://proceedings.mlr.press/v80/trinh18a.html) | ICML | [code](https://github.com/belepi93/rnn-auxiliary-loss) | 5 |
| [Contour Knowledge Transfer for Salient Object Detection](http://openaccess.thecvf.com/content_ECCV_2018/html/Xin_Li_Contour_Knowledge_Transfer_ECCV_2018_paper.html) | ECCV | [code](https://github.com/lixin666/C2SNet) | 5 |
| [HybridNet: Classification and Reconstruction Cooperation for Semi-Supervised Learning](http://openaccess.thecvf.com/content_ECCV_2018/html/Thomas_Robert_HybridNet_Classification_and_ECCV_2018_paper.html) | ECCV | [code](https://github.com/dakshitagrawal97/HybridNet) | 5 |
| [Sidekick Policy Learning for Active Visual Exploration](http://openaccess.thecvf.com/content_ECCV_2018/html/Santhosh_Kumar_Ramakrishnan_Sidekick_Policy_Learning_ECCV_2018_paper.html) | ECCV | [code](https://github.com/srama2512/sidekicks) | 5 |
| [Learning to Localize Sound Source in Visual Scenes](http://openaccess.thecvf.com/content_cvpr_2018/papers/Senocak_Learning_to_Localize_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/ardasnck/learning_to_localize_sound) | 5 |
| [Neural Architecture Optimization](http://arxiv.org/abs/1808.07233v3) | NIPS | [code](https://github.com/dicarlolab/archconvnets) | 5 |
| [COLA: Decentralized Linear Learning](nan) | NIPS | [code](https://github.com/epfml/cola) | 5 |
| [Diverse and Coherent Paragraph Generation from Images](http://openaccess.thecvf.com/content_ECCV_2018/html/Moitreya_Chatterjee_Diverse_and_Coherent_ECCV_2018_paper.html) | ECCV | [code](https://github.com/metro-smiles/CapG_RevG_Code) | 5 |
| [DRACO: Byzantine-resilient Distributed Training via Redundant Gradients](http://proceedings.mlr.press/v80/chen18l.html) | ICML | [code](https://github.com/hwang595/Draco) | 5 |
| [Inter and Intra Topic Structure Learning with Word Embeddings](http://proceedings.mlr.press/v80/zhao18a.html) | ICML | [code](https://github.com/ethanhezhao/WEDTM) | 5 |
| [Estimating the Success of Unsupervised Image to Image Translation](http://openaccess.thecvf.com/content_ECCV_2018/html/Lior_Wolf_Estimating_the_Success_ECCV_2018_paper.html) | ECCV | [code](https://github.com/sagiebenaim/gan_bound) | 5 |
| [Dynamic-Structured Semantic Propagation Network](http://openaccess.thecvf.com/content_cvpr_2018/papers/Liang_Dynamic-Structured_Semantic_Propagation_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/limberc/DSSPN) | 5 |
| [The Description Length of Deep Learning models](https://arxiv.org/abs/1802.07044) | NIPS | [code](https://github.com/leonardblier/descriptionlengthdeeplearning) | 5 |
| [Stereo Vision-based Semantic 3D Object and Ego-motion Tracking for Autonomous Driving](http://openaccess.thecvf.com/content_ECCV_2018/html/Peiliang_LI_Stereo_Vision-based_Semantic_ECCV_2018_paper.html) | ECCV | [code](https://github.com/zhanghanduo/stereo_semantic_mapping) | 5 |
| [Blind Justice: Fairness with Encrypted Sensitive Attributes](http://proceedings.mlr.press/v80/kilbertus18a.html) | ICML | [code](https://github.com/nikikilbertus/blind-justice) | 5 |
| [Transfer Learning via Learning to Transfer](http://proceedings.mlr.press/v80/wei18a.html) | ICML | [code](https://github.com/QuebecAI/webcam-transfer-learning-v1) | 5 |
| [Deepcode: Feedback Codes via Deep Learning](http://arxiv.org/abs/1807.00801v1) | NIPS | [code](https://github.com/hyejikim1/Deepcode) | 4 |
| [Configurable Markov Decision Processes](http://proceedings.mlr.press/v80/metelli18a.html) | ICML | [code](https://github.com/albertometelli/Configurable-Markov-Decision-Processes-ICML-2018) | 4 |
| [A Framework for Evaluating 6-DOF Object Trackers](http://openaccess.thecvf.com/content_ECCV_2018/html/Mathieu_Garon_A_Framework_for_ECCV_2018_paper.html) | ECCV | [code](https://github.com/lvsn/6DOF_tracking_evaluation) | 4 |
| [Differentially Private Database Release via Kernel Mean Embeddings](http://proceedings.mlr.press/v80/balog18a.html) | ICML | [code](https://github.com/matejbalog/RKHS-private-database) | 4 |
| [Recognizing Human Actions as the Evolution of Pose Estimation Maps](http://openaccess.thecvf.com/content_cvpr_2018/papers/Liu_Recognizing_Human_Actions_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/nkliuyifang/Skeleton-based-Human-Action-Recognition) | 4 |
| [Connecting Pixels to Privacy and Utility: Automatic Redaction of Private Information in Images](http://openaccess.thecvf.com/content_cvpr_2018/papers/Orekondy_Connecting_Pixels_to_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/tribhuvanesh/visual_redactions) | 4 |
| [DeLS-3D: Deep Localization and Segmentation With a 3D Semantic Map](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_DeLS-3D_Deep_Localization_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/pengwangucla/DeLS-3D) | 4 |
| [Geolocation Estimation of Photos using a Hierarchical Model and Scene Classification](http://openaccess.thecvf.com/content_ECCV_2018/html/Eric_Muller-Budack_Geolocation_Estimation_of_ECCV_2018_paper.html) | ECCV | [code](https://github.com/TIBHannover/GeoEstimation) | 4 |
| [Tracking Emerges by Colorizing Videos](http://openaccess.thecvf.com/content_ECCV_2018/html/Carl_Vondrick_Self-supervised_Tracking_by_ECCV_2018_paper.html) | ECCV | [code](https://github.com/Oh-Yoojin/Tracking-Emerges-by-Colorizing-Videos) | 4 |
| [Diverse Conditional Image Generation by Stochastic Regression with Latent Drop-Out Codes](http://openaccess.thecvf.com/content_ECCV_2018/html/Yang_He_Diverse_Conditional_Image_ECCV_2018_paper.html) | ECCV | [code](https://github.com/SSAW14/Image_Generation_with_Latent_Code) | 4 |
| [Inference Suboptimality in Variational Autoencoders](http://proceedings.mlr.press/v80/cremer18a.html) | ICML | [code](https://github.com/lxuechen/inference-suboptimality) | 4 |
| [Black Box FDR](http://proceedings.mlr.press/v80/tansey18a.html) | ICML | [code](https://github.com/tansey/bb-fdr) | 4 |
| [Feedback-Prop: Convolutional Neural Network Inference Under Partial Evidence](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_Feedback-Prop_Convolutional_Neural_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/uvavision/feedbackprop) | 4 |
| [Quadrature-based features for kernel approximation](http://arxiv.org/abs/1802.03832v3) | NIPS | [code](https://github.com/quffka/quffka) | 4 |
| [Joint Representation and Truncated Inference Learning for Correlation Filter based Tracking](http://openaccess.thecvf.com/content_ECCV_2018/html/Yingjie_Yao_Joint_Representation_and_ECCV_2018_paper.html) | ECCV | [code](https://github.com/tourmaline612/RTINet) | 4 |
| [Transferable Adversarial Perturbations](http://openaccess.thecvf.com/content_ECCV_2018/html/Bruce_Hou_Transferable_Adversarial_Perturbations_ECCV_2018_paper.html) | ECCV | [code](https://github.com/vinayprabhu/Gainsboro-box-attacks-) | 4 |
| [Single Image Water Hazard Detection using FCN with Reflection Attention Units](http://openaccess.thecvf.com/content_ECCV_2018/html/Xiaofeng_Han_Single_Image_Water_ECCV_2018_paper.html) | ECCV | [code](https://github.com/Cow911/SingleImageWaterHazardDetectionWithRAU) | 4 |
| [Multimodal Generative Models for Scalable Weakly-Supervised Learning](http://arxiv.org/abs/1802.05335v2) | NIPS | [code](https://github.com/mhw32/multimodal-vae-public) | 4 |
| [Importance Weighted Transfer of Samples in Reinforcement Learning](http://proceedings.mlr.press/v80/tirinzoni18a.html) | ICML | [code](https://github.com/AndreaTirinzoni/iw-transfer-rl) | 3 |
| [Feature Generating Networks for Zero-Shot Learning](http://openaccess.thecvf.com/content_cvpr_2018/papers/Xian_Feature_Generating_Networks_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/akku1506/Feature-Generating-Networks-for-ZSL) | 3 |
| [DICOD: Distributed Convolutional Coordinate Descent for Convolutional Sparse Coding](http://proceedings.mlr.press/v80/moreau18a.html) | ICML | [code](https://github.com/tomMoral/Dicod) | 3 |
| [CapProNet: Deep Feature Learning via Orthogonal Projections onto Capsule Subspaces](nan) | NIPS | [code](https://github.com/maple-research-lab/CapProNet) | 3 |
| [Bidirectional Retrieval Made Simple](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wehrmann_Bidirectional_Retrieval_Made_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/jwehrmann/chain-vse) | 3 |
| [Multilingual Anchoring: Interactive Topic Modeling and Alignment Across Languages](nan) | NIPS | [code](https://github.com/forest-snow/mtanchor_demo) | 3 |
| [A Hybrid l1-l0 Layer Decomposition Model for Tone Mapping](http://openaccess.thecvf.com/content_cvpr_2018/papers/Liang_A_Hybrid_l1-l0_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/csjunxu/L1L0_TM-CVPR2018) | 3 |
| [Spatially-Adaptive Filter Units for Deep Neural Networks](http://openaccess.thecvf.com/content_cvpr_2018/papers/Tabernik_Spatially-Adaptive_Filter_Units_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/skokec/DAU-ConvNet) | 3 |
| [Learning to Branch](http://proceedings.mlr.press/v80/balcan18a.html) | ICML | [code](https://github.com/StoneyJackson/github-workflow-activity) | 3 |
| [Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives](nan) | NIPS | [code](https://github.com/IBM/Contrastive-Explanation-Method) | 3 |
| [Lifelong Learning via Progressive Distillation and Retrospection](http://openaccess.thecvf.com/content_ECCV_2018/html/Saihui_Hou_Progressive_Lifelong_Learning_ECCV_2018_paper.html) | ECCV | [code](https://github.com/hshustc/ECCV18_Lifelong_Learning) | 3 |
| [CLEAR: Cumulative LEARning for One-Shot One-Class Image Recognition](http://openaccess.thecvf.com/content_cvpr_2018/papers/Kozerawski_CLEAR_Cumulative_LEARning_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/JKozerawski/CLEAR-osoc) | 3 |
| [Not to Cry Wolf: Distantly Supervised Multitask Learning in Critical Care](http://proceedings.mlr.press/v80/schwab18a.html) | ICML | [code](https://github.com/d909b/DSMT-Nets) | 3 |
| [Learning Answer Embeddings for Visual Question Answering](http://openaccess.thecvf.com/content_cvpr_2018/papers/Hu_Learning_Answer_Embeddings_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/hexiang-hu/answer_embedding) | 3 |
| [Information Constraints on Auto-Encoding Variational Bayes](http://arxiv.org/abs/1805.08672v2) | NIPS | [code](https://github.com/romain-lopez/HCV) | 3 |
| [Parallel Bayesian Network Structure Learning](http://proceedings.mlr.press/v80/gao18b.html) | ICML | [code](https://github.com/bign8/PyStruct) | 3 |
| [Ring Loss: Convex Feature Normalization for Face Recognition](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zheng_Ring_Loss_Convex_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/vsatyakumar/Ring-Loss-Keras) | 3 |
| [Teaching Categories to Human Learners With Visual Explanations](http://openaccess.thecvf.com/content_cvpr_2018/papers/Aodha_Teaching_Categories_to_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/macaodha/explain_teach) | 3 |
| [Stabilizing Gradients for Deep Neural Networks via Efficient SVD Parameterization](http://proceedings.mlr.press/v80/zhang18g.html) | ICML | [code](https://github.com/zhangjiong724/spectral-RNN) | 3 |
| [Deep Burst Denoising](http://openaccess.thecvf.com/content_ECCV_2018/html/Clement_Godard_Deep_Burst_Denoising_ECCV_2018_paper.html) | ECCV | [code](https://github.com/mrharicot/deep_burst_denoising) | 3 |
| [Convergent Tree Backup and Retrace with Function Approximation](http://proceedings.mlr.press/v80/touati18a.html) | ICML | [code](https://github.com/ahmed-touati/convergent-off-policy) | 3 |
| [Gaze Prediction in Dynamic 360° Immersive Videos](http://openaccess.thecvf.com/content_cvpr_2018/papers/Xu_Gaze_Prediction_in_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/xuyanyu-shh/VR-EyeTracking) | 3 |
| [Statistical Recurrent Models on Manifold valued Data](http://arxiv.org/abs/1805.11204v1) | NIPS | [code](https://github.com/zhenxingjian/SPD-SRU) | 3 |
| [End-to-End Flow Correlation Tracking With Spatial-Temporal Attention](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhu_End-to-End_Flow_Correlation_CVPR_2018_paper.pdf) | CVPR | [code](https://github.com/zhengzhugithub/FlowTrack) | 3 |
<div align="right">
<b><a href="#----">↥ back to top</a></b>
</div>
## 2017
| Title | Conf | Code | Stars |
|:--------|:--------:|:--------:|:--------:|
| [Bridging the Gap Between Value and Policy Based Reinforcement Learning](http://papers.nips.cc/paper/6870-bridging-the-gap-between-value-and-policy-based-reinforcement-learning.pdf) | NIPS | [code](https://github.com/tensorflow/models) | 46593 |
| [REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models](http://papers.nips.cc/paper/6856-rebar-low-variance-unbiased-gradient-estimates-for-discrete-latent-variable-models.pdf) | NIPS | [code](https://github.com/tensorflow/models) | 46593 |
| [Focal Loss for Dense Object Detection](http://openaccess.thecvf.com/content_iccv_2017/html/Lin_Focal_Loss_for_ICCV_2017_paper.html) | ICCV | [code](https://github.com/facebookresearch/Detectron) | 18356 |
| [Mask R-CNN](http://openaccess.thecvf.com/content_iccv_2017/html/He_Mask_R-CNN_ICCV_2017_paper.html) | ICCV | [code](https://github.com/matterport/Mask_RCNN) | 9493 |
| [Deep Photo Style Transfer](http://openaccess.thecvf.com/content_cvpr_2017/html/Luan_Deep_Photo_Style_CVPR_2017_paper.html) | CVPR | [code](https://github.com/luanfujun/deep-photo-styletransfer) | 8655 |
| [LightGBM: A Highly Efficient Gradient Boosting Decision Tree](http://papers.nips.cc/paper/6907-lightgbm-a-highly-efficient-gradient-boosting-decision-tree.pdf) | NIPS | [code](https://github.com/Microsoft/LightGBM) | 7536 |
| [Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation](http://papers.nips.cc/paper/7112-scalable-trust-region-method-for-deep-reinforcement-learning-using-kronecker-factored-approximation.pdf) | NIPS | [code](https://github.com/openai/baselines) | 6449 |
| [Attention is All you Need](http://papers.nips.cc/paper/7181-attention-is-all-you-need.pdf) | NIPS | [code](https://github.com/tensorflow/tensor2tensor) | 6288 |
| [Large Pose 3D Face Reconstruction From a Single Image via Direct Volumetric CNN Regression](http://openaccess.thecvf.com/content_iccv_2017/html/Jackson_Large_Pose_3D_ICCV_2017_paper.html) | ICCV | [code](https://github.com/AaronJackson/vrn) | 3354 |
| [Densely Connected Convolutional Networks](http://openaccess.thecvf.com/content_cvpr_2017/html/Huang_Densely_Connected_Convolutional_CVPR_2017_paper.html) | CVPR | [code](https://github.com/liuzhuang13/DenseNet) | 3130 |
| [A Unified Approach to Interpreting Model Predictions](http://papers.nips.cc/paper/7062-a-unified-approach-to-interpreting-model-predictions.pdf) | NIPS | [code](https://github.com/slundberg/shap) | 3122 |
| [Deformable Convolutional Networks](http://openaccess.thecvf.com/content_iccv_2017/html/Dai_Deformable_Convolutional_Networks_ICCV_2017_paper.html) | ICCV | [code](https://github.com/msracver/Deformable-ConvNets) | 2165 |
| [ELF: An Extensive, Lightweight and Flexible Research Platform for Real-time Strategy Games](http://papers.nips.cc/paper/6859-elf-an-extensive-lightweight-and-flexible-research-platform-for-real-time-strategy-games.pdf) | NIPS | [code](https://github.com/facebookresearch/ELF) | 1823 |
| [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](http://openaccess.thecvf.com/content_cvpr_2017/html/Qi_PointNet_Deep_Learning_CVPR_2017_paper.html) | CVPR | [code](https://github.com/charlesq34/pointnet) | 1523 |
| [Improved Training of Wasserstein GANs](http://papers.nips.cc/paper/7159-improved-training-of-wasserstein-gans.pdf) | NIPS | [code](https://github.com/igul222/improved_wgan_training) | 1405 |
| [Fully Convolutional Instance-Aware Semantic Segmentation](http://openaccess.thecvf.com/content_cvpr_2017/html/Li_Fully_Convolutional_Instance-Aware_CVPR_2017_paper.html) | CVPR | [code](https://github.com/msracver/FCIS) | 1395 |
| [Aggregated Residual Transformations for Deep Neural Networks](http://openaccess.thecvf.com/content_cvpr_2017/html/Xie_Aggregated_Residual_Transformations_CVPR_2017_paper.html) | CVPR | [code](https://github.com/facebookresearch/ResNeXt) | 1361 |
| [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](http://openaccess.thecvf.com/content_cvpr_2017/html/Ledig_Photo-Realistic_Single_Image_CVPR_2017_paper.html) | CVPR | [code](https://github.com/tensorlayer/srgan) | 1301 |
| [Unsupervised Image-to-Image Translation Networks](http://papers.nips.cc/paper/6672-unsupervised-image-to-image-translation-networks.pdf) | NIPS | [code](https://github.com/mingyuliutw/unit) | 1205 |
| [Photographic Image Synthesis With Cascaded Refinement Networks](http://openaccess.thecvf.com/content_iccv_2017/html/Chen_Photographic_Image_Synthesis_ICCV_2017_paper.html) | ICCV | [code](https://github.com/CQFIO/PhotographicImageSynthesis) | 1142 |
| [High-Resolution Image Inpainting Using Multi-Scale Neural Patch Synthesis](http://openaccess.thecvf.com/content_cvpr_2017/html/Yang_High-Resolution_Image_Inpainting_CVPR_2017_paper.html) | CVPR | [code](https://github.com/leehomyc/Faster-High-Res-Neural-Inpainting) | 1072 |
| [SphereFace: Deep Hypersphere Embedding for Face Recognition](http://openaccess.thecvf.com/content_cvpr_2017/html/Liu_SphereFace_Deep_Hypersphere_CVPR_2017_paper.html) | CVPR | [code](https://github.com/wy1iu/sphereface) | 1048 |
| [Deep Feature Flow for Video Recognition](http://openaccess.thecvf.com/content_cvpr_2017/html/Zhu_Deep_Feature_Flow_CVPR_2017_paper.html) | CVPR | [code](https://github.com/msracver/Deep-Feature-Flow) | 966 |
| [Bayesian GAN](http://papers.nips.cc/paper/6953-bayesian-gan.pdf) | NIPS | [code](https://github.com/andrewgordonwilson/bayesgan) | 942 |
| [Pyramid Scene Parsing Network](http://openaccess.thecvf.com/content_cvpr_2017/html/Zhao_Pyramid_Scene_Parsing_CVPR_2017_paper.html) | CVPR | [code](https://github.com/hszhao/PSPNet) | 934 |
| [Efficient Modeling of Latent Information in Supervised Learning using Gaussian Processes](http://papers.nips.cc/paper/7098-efficient-modeling-of-latent-information-in-supervised-learning-using-gaussian-processes.pdf) | NIPS | [code](https://github.com/SheffieldML/GPy) | 906 |
| [Finding Tiny Faces](http://openaccess.thecvf.com/content_cvpr_2017/html/Hu_Finding_Tiny_Faces_CVPR_2017_paper.html) | CVPR | [code](https://github.com/peiyunh/tiny) | 856 |
| [Toward Multimodal Image-to-Image Translation](http://papers.nips.cc/paper/6650-toward-multimodal-image-to-image-translation.pdf) | NIPS | [code](https://github.com/junyanz/BiCycleGAN) | 794 |
| [Learning to Discover Cross-Domain Relations with Generative Adversarial Networks](http://proceedings.mlr.press/v70/kim17a.html) | ICML | [code](https://github.com/carpedm20/DiscoGAN-pytorch) | 784 |
| [YOLO9000: Better, Faster, Stronger](http://openaccess.thecvf.com/content_cvpr_2017/html/Redmon_YOLO9000_Better_Faster_CVPR_2017_paper.html) | CVPR | [code](https://github.com/philipperemy/yolo-9000) | 773 |
| [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](http://papers.nips.cc/paper/7095-pointnet-deep-hierarchical-feature-learning-on-point-sets-in-a-metric-space.pdf) | NIPS | [code](https://github.com/charlesq34/pointnet2) | 772 |
| [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](http://proceedings.mlr.press/v70/finn17a.html) | ICML | [code](https://github.com/cbfinn/maml) | 729 |
| [FlowNet 2.0: Evolution of Optical Flow Estimation With Deep Networks](http://openaccess.thecvf.com/content_cvpr_2017/html/Ilg_FlowNet_2.0_Evolution_CVPR_2017_paper.html) | CVPR | [code](https://github.com/lmb-freiburg/flownet2) | 720 |
| [Channel Pruning for Accelerating Very Deep Neural Networks](http://openaccess.thecvf.com/content_iccv_2017/html/He_Channel_Pruning_for_ICCV_2017_paper.html) | ICCV | [code](https://github.com/yihui-he/channel-pruning) | 649 |
| [Dilated Residual Networks](http://openaccess.thecvf.com/content_cvpr_2017/html/Yu_Dilated_Residual_Networks_CVPR_2017_paper.html) | CVPR | [code](https://github.com/fyu/drn) | 640 |
| [Inferring and Executing Programs for Visual Reasoning](http://openaccess.thecvf.com/content_iccv_2017/html/Johnson_Inferring_and_Executing_ICCV_2017_paper.html) | ICCV | [code](https://github.com/facebookresearch/clevr-iep) | 636 |
| [DSOD: Learning Deeply Supervised Object Detectors From Scratch](http://openaccess.thecvf.com/content_iccv_2017/html/Shen_DSOD_Learning_Deeply_ICCV_2017_paper.html) | ICCV | [code](https://github.com/szq0214/DSOD) | 582 |
| [Arbitrary Style Transfer in Real-Time With Adaptive Instance Normalization](http://openaccess.thecvf.com/content_iccv_2017/html/Huang_Arbitrary_Style_Transfer_ICCV_2017_paper.html) | ICCV | [code](https://github.com/xunhuang1995/AdaIN-style) | 572 |
| [Accelerating Eulerian Fluid Simulation With Convolutional Networks](http://proceedings.mlr.press/v70/tompson17a.html) | ICML | [code](https://github.com/google/FluidNet) | 570 |
| [Learning Disentangled Representations with Semi-Supervised Deep Generative Models](http://papers.nips.cc/paper/7174-learning-disentangled-representations-with-semi-supervised-deep-generative-models.pdf) | NIPS | [code](https://github.com/probtorch/probtorch) | 556 |
| [Inductive Representation Learning on Large Graphs](http://papers.nips.cc/paper/6703-inductive-representation-learning-on-large-graphs.pdf) | NIPS | [code](https://github.com/williamleif/GraphSAGE) | 552 |
| [Regressing Robust and Discriminative 3D Morphable Models With a Very Deep Neural Network](http://openaccess.thecvf.com/content_cvpr_2017/html/Tran_Regressing_Robust_and_CVPR_2017_paper.html) | CVPR | [code](https://github.com/anhttran/3dmm_cnn) | 537 |
| [How Far Are We From Solving the 2D & 3D Face Alignment Problem? (And a Dataset of 230,000 3D Facial Landmarks)](http://openaccess.thecvf.com/content_iccv_2017/html/Bulat_How_Far_Are_ICCV_2017_paper.html) | ICCV | [code](https://github.com/1adrianb/2D-and-3D-face-alignment) | 526 |
| [SSH: Single Stage Headless Face Detector](http://openaccess.thecvf.com/content_iccv_2017/html/Najibi_SSH_Single_Stage_ICCV_2017_paper.html) | ICCV | [code](https://github.com/mahyarnajibi/SSH) | 515 |
| [Learning From Simulated and Unsupervised Images Through Adversarial Training](http://openaccess.thecvf.com/content_cvpr_2017/html/Shrivastava_Learning_From_Simulated_CVPR_2017_paper.html) | CVPR | [code](https://github.com/carpedm20/simulated-unsupervised-tensorflow) | 492 |
| [Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space](http://openaccess.thecvf.com/content_cvpr_2017/html/Nguyen_Plug__Play_CVPR_2017_paper.html) | CVPR | [code](https://github.com/Evolving-AI-Lab/ppgn) | 487 |
| [Video Frame Interpolation via Adaptive Convolution](http://openaccess.thecvf.com/content_cvpr_2017/html/Niklaus_Video_Frame_Interpolation_CVPR_2017_paper.html) | CVPR | [code](https://github.com/sniklaus/pytorch-sepconv) | 482 |
| [Video Frame Interpolation via Adaptive Separable Convolution](http://openaccess.thecvf.com/content_iccv_2017/html/Niklaus_Video_Frame_Interpolation_ICCV_2017_paper.html) | ICCV | [code](https://github.com/sniklaus/pytorch-sepconv) | 482 |
| [GMS: Grid-based Motion Statistics for Fast, Ultra-Robust Feature Correspondence](http://openaccess.thecvf.com/content_cvpr_2017/html/Bian_GMS_Grid-based_Motion_CVPR_2017_paper.html) | CVPR | [code](https://github.com/JiawangBian/GMS-Feature-Matcher) | 460 |
| [Joint Detection and Identification Feature Learning for Person Search](http://openaccess.thecvf.com/content_cvpr_2017/html/Xiao_Joint_Detection_and_CVPR_2017_paper.html) | CVPR | [code](https://github.com/ShuangLI59/person_search) | 459 |
| [Dual Path Networks](http://papers.nips.cc/paper/7033-dual-path-networks.pdf) | NIPS | [code](https://github.com/cypw/DPNs) | 451 |
| [Flow-Guided Feature Aggregation for Video Object Detection](http://openaccess.thecvf.com/content_iccv_2017/html/Zhu_Flow-Guided_Feature_Aggregation_ICCV_2017_paper.html) | ICCV | [code](https://github.com/msracver/Flow-Guided-Feature-Aggregation) | 436 |
| [Deep Image Matting](http://openaccess.thecvf.com/content_cvpr_2017/html/Xu_Deep_Image_Matting_CVPR_2017_paper.html) | CVPR | [code](https://github.com/Joker316701882/Deep-Image-Matting) | 434 |
| [Richer Convolutional Features for Edge Detection](http://openaccess.thecvf.com/content_cvpr_2017/html/Liu_Richer_Convolutional_Features_CVPR_2017_paper.html) | CVPR | [code](https://github.com/yun-liu/rcf) | 399 |
| [Annotating Object Instances With a Polygon-RNN](http://openaccess.thecvf.com/content_cvpr_2017/html/Castrejon_Annotating_Object_Instances_CVPR_2017_paper.html) | CVPR | [code](https://github.com/fidler-lab/polyrnn-pp-pytorch) | 397 |
| [Recurrent Highway Networks](http://proceedings.mlr.press/v70/zilly17a.html) | ICML | [code](https://github.com/julian121266/RecurrentHighwayNetworks) | 397 |
| [Detect to Track and Track to Detect](http://openaccess.thecvf.com/content_iccv_2017/html/Feichtenhofer_Detect_to_Track_ICCV_2017_paper.html) | ICCV | [code](https://github.com/feichtenhofer/Detect-Track) | 387 |
| [RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation](http://openaccess.thecvf.com/content_cvpr_2017/html/Lin_RefineNet_Multi-Path_Refinement_CVPR_2017_paper.html) | CVPR | [code](https://github.com/guosheng/refinenet) | 379 |
| [Detecting Oriented Text in Natural Images by Linking Segments](http://openaccess.thecvf.com/content_cvpr_2017/html/Shi_Detecting_Oriented_Text_CVPR_2017_paper.html) | CVPR | [code](https://github.com/dengdan/seglink) | 364 |
| [Deep Lattice Networks and Partial Monotonic Functions](http://papers.nips.cc/paper/6891-deep-lattice-networks-and-partial-monotonic-functions.pdf) | NIPS | [code](https://github.com/tensorflow/lattice) | 349 |
| [Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results](http://papers.nips.cc/paper/6719-mean-teachers-are-better-role-models-weight-averaged-consistency-targets-improve-semi-supervised-deep-learning-results.pdf) | NIPS | [code](https://github.com/CuriousAI/mean-teacher/) | 347 |
| [RON: Reverse Connection With Objectness Prior Networks for Object Detection](http://openaccess.thecvf.com/content_cvpr_2017/html/Kong_RON_Reverse_Connection_CVPR_2017_paper.html) | CVPR | [code](https://github.com/taokong/RON) | 345 |
| [Universal Style Transfer via Feature Transforms](http://papers.nips.cc/paper/6642-universal-style-transfer-via-feature-transforms.pdf) | NIPS | [code](https://github.com/Yijunmaverick/UniversalStyleTransfer) | 344 |
| [Residual Attention Network for Image Classification](http://openaccess.thecvf.com/content_cvpr_2017/html/Wang_Residual_Attention_Network_CVPR_2017_paper.html) | CVPR | [code](https://github.com/fwang91/residual-attention-network) | 329 |
| [One-Shot Video Object Segmentation](http://openaccess.thecvf.com/content_cvpr_2017/html/Caelles_One-Shot_Video_Object_CVPR_2017_paper.html) | CVPR | [code](https://github.com/scaelles/OSVOS-TensorFlow) | 316 |
| [Accurate Single Stage Detector Using Recurrent Rolling Convolution](http://openaccess.thecvf.com/content_cvpr_2017/html/Ren_Accurate_Single_Stage_CVPR_2017_paper.html) | CVPR | [code](https://github.com/xiaohaoChen/rrc_detection) | 314 |
| [Feature Pyramid Networks for Object Detection](http://openaccess.thecvf.com/content_cvpr_2017/html/Lin_Feature_Pyramid_Networks_CVPR_2017_paper.html) | CVPR | [code](https://github.com/unsky/FPN) | 310 |
| [Efficient softmax approximation for GPUs](http://proceedings.mlr.press/v70/grave17a.html) | ICML | [code](https://github.com/facebookresearch/adaptive-softmax) | 304 |
| [OctNet: Learning Deep 3D Representations at High Resolutions](http://openaccess.thecvf.com/content_cvpr_2017/html/Riegler_OctNet_Learning_Deep_CVPR_2017_paper.html) | CVPR | [code](https://github.com/griegler/octnet) | 302 |
| [Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution](http://openaccess.thecvf.com/content_cvpr_2017/html/Lai_Deep_Laplacian_Pyramid_CVPR_2017_paper.html) | CVPR | [code](https://github.com/phoenix104104/LapSRN) | 301 |
| [Pixel Recursive Super Resolution](http://openaccess.thecvf.com/content_iccv_2017/html/Dahl_Pixel_Recursive_Super_ICCV_2017_paper.html) | ICCV | [code](https://github.com/nilboy/pixel-recursive-super-resolution) | 301 |
| [Self-Critical Sequence Training for Image Captioning](http://openaccess.thecvf.com/content_cvpr_2017/html/Rennie_Self-Critical_Sequence_Training_CVPR_2017_paper.html) | CVPR | [code](https://github.com/ruotianluo/self-critical.pytorch) | 299 |
| [Age Progression/Regression by Conditional Adversarial Autoencoder](http://openaccess.thecvf.com/content_cvpr_2017/html/Zhang_Age_ProgressionRegression_by_CVPR_2017_paper.html) | CVPR | [code](https://github.com/ZZUTK/Face-Aging-CAAE) | 297 |
| [Style Transfer from Non-Parallel Text by Cross-Alignment](http://papers.nips.cc/paper/7259-style-transfer-from-non-parallel-text-by-cross-alignment.pdf) | NIPS | [code](https://github.com/shentianxiao/language-style-transfer) | 296 |
| [Dilated Recurrent Neural Networks](http://papers.nips.cc/paper/6613-dilated-recurrent-neural-networks.pdf) | NIPS | [code](https://github.com/code-terminator/DilatedRNN) | 285 |
| [Lifting From the Deep: Convolutional 3D Pose Estimation From a Single Image](http://openaccess.thecvf.com/content_cvpr_2017/html/Tome_Lifting_From_the_CVPR_2017_paper.html) | CVPR | [code](https://github.com/DenisTome/Lifting-from-the-Deep-release) | 280 |
| [DeepBach: a Steerable Model for Bach Chorales Generation](http://proceedings.mlr.press/v70/hadjeres17a.html) | ICML | [code](https://github.com/Ghadjeres/DeepBach) | 276 |
| [The Predictron: End-To-End Learning and Planning](http://proceedings.mlr.press/v70/silver17a.html) | ICML | [code](https://github.com/zhongwen/predictron) | 274 |
| [Convolutional Sequence to Sequence Learning](http://proceedings.mlr.press/v70/gehring17a.html) | ICML | [code](https://github.com/tobyyouup/conv_seq2seq) | 258 |
| [OptNet: Differentiable Optimization as a Layer in Neural Networks](http://proceedings.mlr.press/v70/amos17a.html) | ICML | [code](https://github.com/locuslab/optnet) | 245 |
| [Prototypical Networks for Few-shot Learning](http://papers.nips.cc/paper/6996-prototypical-networks-for-few-shot-learning.pdf) | NIPS | [code](https://github.com/jakesnell/prototypical-networks) | 244 |
| [Deep Voice: Real-time Neural Text-to-Speech](http://proceedings.mlr.press/v70/arik17a.html) | ICML | [code](https://github.com/israelg99/deepvoice) | 242 |
| [Reinforcement Learning with Deep Energy-Based Policies](http://proceedings.mlr.press/v70/haarnoja17a.html) | ICML | [code](https://github.com/haarnoja/softqlearning) | 233 |
| [Learning Deep CNN Denoiser Prior for Image Restoration](http://openaccess.thecvf.com/content_cvpr_2017/html/Zhang_Learning_Deep_CNN_CVPR_2017_paper.html) | CVPR | [code](https://github.com/cszn/IRCNN) | 231 |
| [GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium](http://papers.nips.cc/paper/7240-gans-trained-by-a-two-time-scale-update-rule-converge-to-a-local-nash-equilibrium.pdf) | NIPS | [code](https://github.com/bioinf-jku/TTUR) | 229 |
| [A Point Set Generation Network for 3D Object Reconstruction From a Single Image](http://openaccess.thecvf.com/content_cvpr_2017/html/Fan_A_Point_Set_CVPR_2017_paper.html) | CVPR | [code](https://github.com/fanhqme/PointSetGeneration) | 228 |
| [Deeply Supervised Salient Object Detection With Short Connections](http://openaccess.thecvf.com/content_cvpr_2017/html/Hou_Deeply_Supervised_Salient_CVPR_2017_paper.html) | CVPR | [code](https://github.com/Joker316701882/Salient-Object-Detection) | 228 |
| [BlitzNet: A Real-Time Deep Network for Scene Understanding](http://openaccess.thecvf.com/content_iccv_2017/html/Dvornik_BlitzNet_A_Real-Time_ICCV_2017_paper.html) | ICCV | [code](https://github.com/dvornikita/blitznet) | 227 |
| [Language Modeling with Gated Convolutional Networks](http://proceedings.mlr.press/v70/dauphin17a.html) | ICML | [code](https://github.com/anantzoid/Language-Modeling-GatedCNN) | 221 |
| [Unlabeled Samples Generated by GAN Improve the Person Re-Identification Baseline in Vitro](http://openaccess.thecvf.com/content_iccv_2017/html/Zheng_Unlabeled_Samples_Generated_ICCV_2017_paper.html) | ICCV | [code](https://github.com/layumi/Person-reID_GAN) | 215 |
| [Stacked Generative Adversarial Networks](http://openaccess.thecvf.com/content_cvpr_2017/html/Huang_Stacked_Generative_Adversarial_CVPR_2017_paper.html) | CVPR | [code](https://github.com/xunhuang1995/SGAN) | 215 |
| [RMPE: Regional Multi-Person Pose Estimation](http://openaccess.thecvf.com/content_iccv_2017/html/Fang_RMPE_Regional_Multi-Person_ICCV_2017_paper.html) | ICCV | [code](https://github.com/MVIG-SJTU/RMPE) | 215 |
| [Knowing When to Look: Adaptive Attention via a Visual Sentinel for Image Captioning](http://openaccess.thecvf.com/content_cvpr_2017/html/Lu_Knowing_When_to_CVPR_2017_paper.html) | CVPR | [code](https://github.com/jiasenlu/AdaptiveAttention) | 214 |
| [Generative Face Completion](http://openaccess.thecvf.com/content_cvpr_2017/html/Li_Generative_Face_Completion_CVPR_2017_paper.html) | CVPR | [code](https://github.com/Yijunmaverick/GenerativeFaceCompletion) | 212 |
| [VPGNet: Vanishing Point Guided Network for Lane and Road Marking Detection and Recognition](http://openaccess.thecvf.com/content_iccv_2017/html/Lee_VPGNet_Vanishing_Point_ICCV_2017_paper.html) | ICCV | [code](https://github.com/SeokjuLee/VPGNet) | 210 |
| [The Reversible Residual Network: Backpropagation Without Storing Activations](http://papers.nips.cc/paper/6816-the-reversible-residual-network-backpropagation-without-storing-activations.pdf) | NIPS | [code](https://github.com/renmengye/revnet-public) | 210 |
| [Recurrent Scale Approximation for Object Detection in CNN](http://openaccess.thecvf.com/content_iccv_2017/html/Liu_Recurrent_Scale_Approximation_ICCV_2017_paper.html) | ICCV | [code](https://github.com/sciencefans/RSA-for-object-detection) | 209 |
| [Learning From Synthetic Humans](http://openaccess.thecvf.com/content_cvpr_2017/html/Varol_Learning_From_Synthetic_CVPR_2017_paper.html) | CVPR | [code](https://github.com/gulvarol/surreal) | 207 |
| [Spatially Adaptive Computation Time for Residual Networks](http://openaccess.thecvf.com/content_cvpr_2017/html/Figurnov_Spatially_Adaptive_Computation_CVPR_2017_paper.html) | CVPR | [code](https://github.com/mfigurnov/sact) | 203 |
| [Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis](http://openaccess.thecvf.com/content_iccv_2017/html/Huang_Beyond_Face_Rotation_ICCV_2017_paper.html) | ICCV | [code](https://github.com/HRLTY/TP-GAN) | 202 |
| [3D Bounding Box Estimation Using Deep Learning and Geometry](http://openaccess.thecvf.com/content_cvpr_2017/html/Mousavian_3D_Bounding_Box_CVPR_2017_paper.html) | CVPR | [code](https://github.com/smallcorgi/3D-Deepbox) | 200 |
| [Multi-View 3D Object Detection Network for Autonomous Driving](http://openaccess.thecvf.com/content_cvpr_2017/html/Chen_Multi-View_3D_Object_CVPR_2017_paper.html) | CVPR | [code](https://github.com/bostondiditeam/MV3D) | 199 |
| [Visual Dialog](http://openaccess.thecvf.com/content_cvpr_2017/html/Das_Visual_Dialog_CVPR_2017_paper.html) | CVPR | [code](https://github.com/batra-mlp-lab/visdial) | 199 |
| [Interpretable Explanations of Black Boxes by Meaningful Perturbation](http://openaccess.thecvf.com/content_iccv_2017/html/Fong_Interpretable_Explanations_of_ICCV_2017_paper.html) | ICCV | [code](https://github.com/jacobgil/pytorch-explain-black-box) | 192 |
| [Inverse Compositional Spatial Transformer Networks](http://openaccess.thecvf.com/content_cvpr_2017/html/Lin_Inverse_Compositional_Spatial_CVPR_2017_paper.html) | CVPR | [code](https://github.com/chenhsuanlin/inverse-compositional-STN) | 189 |
| [FastMask: Segment Multi-Scale Object Candidates in One Shot](http://openaccess.thecvf.com/content_cvpr_2017/html/Hu_FastMask_Segment_Multi-Scale_CVPR_2017_paper.html) | CVPR | [code](https://github.com/voidrank/FastMask) | 189 |
| [OnACID: Online Analysis of Calcium Imaging Data in Real Time](http://papers.nips.cc/paper/6832-onacid-online-analysis-of-calcium-imaging-data-in-real-time.pdf) | NIPS | [code](https://github.com/simonsfoundation/caiman) | 189 |
| [Semantic Scene Completion From a Single Depth Image](http://openaccess.thecvf.com/content_cvpr_2017/html/Song_Semantic_Scene_Completion_CVPR_2017_paper.html) | CVPR | [code](https://github.com/shurans/sscnet) | 188 |
| [Learning Efficient Convolutional Networks Through Network Slimming](http://openaccess.thecvf.com/content_iccv_2017/html/Liu_Learning_Efficient_Convolutional_ICCV_2017_paper.html) | ICCV | [code](https://github.com/liuzhuang13/slimming) | 186 |
| [Learning Feature Pyramids for Human Pose Estimation](http://openaccess.thecvf.com/content_iccv_2017/html/Yang_Learning_Feature_Pyramids_ICCV_2017_paper.html) | ICCV | [code](https://github.com/bearpaw/PyraNet) | 185 |
| [Be Your Own Prada: Fashion Synthesis With Structural Coherence](http://openaccess.thecvf.com/content_iccv_2017/html/Zhu_Be_Your_Own_ICCV_2017_paper.html) | ICCV | [code](https://github.com/zhusz/ICCV17-fashionGAN) | 183 |
| [Scene Graph Generation by Iterative Message Passing](http://openaccess.thecvf.com/content_cvpr_2017/html/Xu_Scene_Graph_Generation_CVPR_2017_paper.html) | CVPR | [code](https://github.com/danfeiX/scene-graph-TF-release) | 182 |
| [Fast Image Processing With Fully-Convolutional Networks](http://openaccess.thecvf.com/content_iccv_2017/html/Chen_Fast_Image_Processing_ICCV_2017_paper.html) | ICCV | [code](https://github.com/CQFIO/FastImageProcessing) | 180 |
| [Learning Multiple Tasks with Multilinear Relationship Networks](http://papers.nips.cc/paper/6757-learning-multiple-tasks-with-multilinear-relationship-networks.pdf) | NIPS | [code](https://github.com/thuml/Xlearn) | 178 |
| [Learning to Reason: End-To-End Module Networks for Visual Question Answering](http://openaccess.thecvf.com/content_iccv_2017/html/Hu_Learning_to_Reason_ICCV_2017_paper.html) | ICCV | [code](https://github.com/ronghanghu/n2nmn) | 178 |
| [Single Shot Text Detector With Regional Attention](http://openaccess.thecvf.com/content_iccv_2017/html/He_Single_Shot_Text_ICCV_2017_paper.html) | ICCV | [code](https://github.com/BestSonny/SSTD) | 176 |
| [Binarized Convolutional Landmark Localizers for Human Pose Estimation and Face Alignment With Limited Resources](http://openaccess.thecvf.com/content_iccv_2017/html/Bulat_Binarized_Convolutional_Landmark_ICCV_2017_paper.html) | ICCV | [code](https://github.com/1adrianb/binary-human-pose-estimation) | 175 |
| [Deep Feature Interpolation for Image Content Changes](http://openaccess.thecvf.com/content_cvpr_2017/html/Upchurch_Deep_Feature_Interpolation_CVPR_2017_paper.html) | CVPR | [code](https://github.com/paulu/deepfeatinterp) | 170 |
| [On Human Motion Prediction Using Recurrent Neural Networks](http://openaccess.thecvf.com/content_cvpr_2017/html/Martinez_On_Human_Motion_CVPR_2017_paper.html) | CVPR | [code](https://github.com/una-dinosauria/human-motion-prediction) | 167 |
| [Image Super-Resolution via Deep Recursive Residual Network](http://openaccess.thecvf.com/content_cvpr_2017/html/Tai_Image_Super-Resolution_via_CVPR_2017_paper.html) | CVPR | [code](https://github.com/tyshiwo/DRRN_CVPR17) | 163 |
| [Learning Cross-Modal Embeddings for Cooking Recipes and Food Images](http://openaccess.thecvf.com/content_cvpr_2017/html/Salvador_Learning_Cross-Modal_Embeddings_CVPR_2017_paper.html) | CVPR | [code](https://github.com/torralba-lab/im2recipe) | 160 |
| [Input Convex Neural Networks](http://proceedings.mlr.press/v70/amos17b.html) | ICML | [code](https://github.com/locuslab/icnn) | 159 |
| [Simple Does It: Weakly Supervised Instance and Semantic Segmentation](http://openaccess.thecvf.com/content_cvpr_2017/html/Khoreva_Simple_Does_It_CVPR_2017_paper.html) | CVPR | [code](https://github.com/philferriere/tfwss) | 159 |
| [Low-Shot Visual Recognition by Shrinking and Hallucinating Features](http://openaccess.thecvf.com/content_iccv_2017/html/Hariharan_Low-Shot_Visual_Recognition_ICCV_2017_paper.html) | ICCV | [code](https://github.com/facebookresearch/low-shot-shrink-hallucinate) | 158 |
| [Oriented Response Networks](http://openaccess.thecvf.com/content_cvpr_2017/html/Zhou_Oriented_Response_Networks_CVPR_2017_paper.html) | CVPR | [code](https://github.com/ZhouYanzhao/ORN) | 157 |
| [Soft Proposal Networks for Weakly Supervised Object Localization](http://openaccess.thecvf.com/content_iccv_2017/html/Zhu_Soft_Proposal_Networks_ICCV_2017_paper.html) | ICCV | [code](https://github.com/yeezhu/SPN.pytorch) | 154 |
| [Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks](http://proceedings.mlr.press/v70/mescheder17a.html) | ICML | [code](https://github.com/LMescheder/AdversarialVariationalBayes) | 147 |
| [Axiomatic Attribution for Deep Networks](http://proceedings.mlr.press/v70/sundararajan17a.html) | ICML | [code](https://github.com/hiranumn/IntegratedGradients) | 146 |
| [Gradient Episodic Memory for Continual Learning](http://papers.nips.cc/paper/7225-gradient-episodic-memory-for-continual-learning.pdf) | NIPS | [code](https://github.com/facebookresearch/GradientEpisodicMemory) | 146 |
| [DSAC - Differentiable RANSAC for Camera Localization](http://openaccess.thecvf.com/content_cvpr_2017/html/Brachmann_DSAC_-_Differentiable_CVPR_2017_paper.html) | CVPR | [code](https://github.com/cvlab-dresden/DSAC) | 144 |
| [Attend to You: Personalized Image Captioning With Context Sequence Memory Networks](http://openaccess.thecvf.com/content_cvpr_2017/html/Park_Attend_to_You_CVPR_2017_paper.html) | CVPR | [code](https://github.com/cesc-park/attend2u) | 143 |
| [Conditional Similarity Networks](http://openaccess.thecvf.com/content_cvpr_2017/html/Veit_Conditional_Similarity_Networks_CVPR_2017_paper.html) | CVPR | [code](https://github.com/andreasveit/conditional-similarity-networks) | 142 |
| [Language Modeling with Recurrent Highway Hypernetworks](http://papers.nips.cc/paper/6919-language-modeling-with-recurrent-highway-hypernetworks.pdf) | NIPS | [code](https://github.com/jsuarez5341/Recurrent-Highway-Hypernetworks-NIPS) | 141 |
| [Triple Generative Adversarial Nets](http://papers.nips.cc/paper/6997-triple-generative-adversarial-nets.pdf) | NIPS | [code](https://github.com/zhenxuan00/triple-gan) | 138 |
| [Interpolated Policy Gradient: Merging On-Policy and Off-Policy Gradient Estimation for Deep Reinforcement Learning](http://papers.nips.cc/paper/6974-interpolated-policy-gradient-merging-on-policy-and-off-policy-gradient-estimation-for-deep-reinforcement-learning.pdf) | NIPS | [code](https://github.com/shaneshixiang/rllabplusplus) | 138 |
| [One-Sided Unsupervised Domain Mapping](http://papers.nips.cc/paper/6677-one-sided-unsupervised-domain-mapping.pdf) | NIPS | [code](https://github.com/sagiebenaim/DistanceGAN) | 137 |
| [Detecting Visual Relationships With Deep Relational Networks](http://openaccess.thecvf.com/content_cvpr_2017/html/Dai_Detecting_Visual_Relationships_CVPR_2017_paper.html) | CVPR | [code](https://github.com/doubledaibo/drnet_cvpr2017) | 137 |
| [Attentive Recurrent Comparators](http://proceedings.mlr.press/v70/shyam17a.html) | ICML | [code](https://github.com/sanyam5/arc-pytorch) | 136 |
| [Towards 3D Human Pose Estimation in the Wild: A Weakly-Supervised Approach](http://openaccess.thecvf.com/content_iccv_2017/html/Zhou_Towards_3D_Human_ICCV_2017_paper.html) | ICCV | [code](https://github.com/xingyizhou/pose-hg-3d) | 136 |
| [Learning a Multi-View Stereo Machine](http://papers.nips.cc/paper/6640-learning-a-multi-view-stereo-machine.pdf) | NIPS | [code](https://github.com/akar43/lsm) | 135 |
| [Deep Learning for Precipitation Nowcasting: A Benchmark and A New Model](http://papers.nips.cc/paper/7145-deep-learning-for-precipitation-nowcasting-a-benchmark-and-a-new-model.pdf) | NIPS | [code](https://github.com/sxjscience/HKO-7) | 134 |
| [Multi-Context Attention for Human Pose Estimation](http://openaccess.thecvf.com/content_cvpr_2017/html/Chu_Multi-Context_Attention_for_CVPR_2017_paper.html) | CVPR | [code](https://github.com/bearpaw/pose-attention) | 131 |
| [Controlling Perceptual Factors in Neural Style Transfer](http://openaccess.thecvf.com/content_cvpr_2017/html/Gatys_Controlling_Perceptual_Factors_CVPR_2017_paper.html) | CVPR | [code](https://github.com/leongatys/NeuralImageSynthesis) | 130 |
| [Bayesian Compression for Deep Learning](http://papers.nips.cc/paper/6921-bayesian-compression-for-deep-learning.pdf) | NIPS | [code](https://github.com/KarenUllrich/Tutorial_BayesianCompressionForDL) | 130 |
| [Adversarial Discriminative Domain Adaptation](http://openaccess.thecvf.com/content_cvpr_2017/html/Tzeng_Adversarial_Discriminative_Domain_CVPR_2017_paper.html) | CVPR | [code](https://github.com/corenel/pytorch-adda) | 129 |
| [Working hard to know your neighbor's margins: Local descriptor learning loss](http://papers.nips.cc/paper/7068-working-hard-to-know-your-neighbors-margins-local-descriptor-learning-loss.pdf) | NIPS | [code](https://github.com/DagnyT/hardnet) | 128 |
| [Concrete Dropout](http://papers.nips.cc/paper/6949-concrete-dropout.pdf) | NIPS | [code](https://github.com/yaringal/ConcreteDropout) | 127 |
| [SegFlow: Joint Learning for Video Object Segmentation and Optical Flow](http://openaccess.thecvf.com/content_iccv_2017/html/Cheng_SegFlow_Joint_Learning_ICCV_2017_paper.html) | ICCV | [code](https://github.com/JingchunCheng/SegFlow) | 127 |
| [Segmentation-Aware Convolutional Networks Using Local Attention Masks](http://openaccess.thecvf.com/content_iccv_2017/html/Harley_Segmentation-Aware_Convolutional_Networks_ICCV_2017_paper.html) | ICCV | [code](https://github.com/aharley/segaware) | 126 |
| [Detail-Revealing Deep Video Super-Resolution](http://openaccess.thecvf.com/content_iccv_2017/html/Tao_Detail-Revealing_Deep_Video_ICCV_2017_paper.html) | ICCV | [code](https://github.com/jiangsutx/SPMC_VideoSR) | 126 |
| [CREST: Convolutional Residual Learning for Visual Tracking](http://openaccess.thecvf.com/content_iccv_2017/html/Song_CREST_Convolutional_Residual_ICCV_2017_paper.html) | ICCV | [code](https://github.com/ybsong00/CREST-Release) | 126 |
| [Discriminative Correlation Filter With Channel and Spatial Reliability](http://openaccess.thecvf.com/content_cvpr_2017/html/Lukezic_Discriminative_Correlation_Filter_CVPR_2017_paper.html) | CVPR | [code](https://github.com/alanlukezic/csr-dcf) | 124 |
| [SVDNet for Pedestrian Retrieval](http://openaccess.thecvf.com/content_iccv_2017/html/Sun_SVDNet_for_Pedestrian_ICCV_2017_paper.html) | ICCV | [code](https://github.com/syfafterzy/SVDNet-for-Pedestrian-Retrieval) | 121 |
| [Semantic Image Synthesis via Adversarial Learning](http://openaccess.thecvf.com/content_iccv_2017/html/Dong_Semantic_Image_Synthesis_ICCV_2017_paper.html) | ICCV | [code](https://github.com/woozzu/dong_iccv_2017) | 121 |
| [Spatiotemporal Multiplier Networks for Video Action Recognition](http://openaccess.thecvf.com/content_cvpr_2017/html/Feichtenhofer_Spatiotemporal_Multiplier_Networks_CVPR_2017_paper.html) | CVPR | [code](https://github.com/feichtenhofer/st-resnet) | 121 |
| [PoseTrack: Joint Multi-Person Pose Estimation and Tracking](http://openaccess.thecvf.com/content_cvpr_2017/html/Iqbal_PoseTrack_Joint_Multi-Person_CVPR_2017_paper.html) | CVPR | [code](https://github.com/iqbalu/PoseTrack-CVPR2017) | 121 |
| [Hierarchical Attentive Recurrent Tracking](http://papers.nips.cc/paper/6898-hierarchical-attentive-recurrent-tracking.pdf) | NIPS | [code](https://github.com/akosiorek/hart) | 121 |
| [Good Semi-supervised Learning That Requires a Bad GAN](http://papers.nips.cc/paper/7229-good-semi-supervised-learning-that-requires-a-bad-gan.pdf) | NIPS | [code](https://github.com/kimiyoung/ssl_bad_gan) | 120 |
| [Deep Watershed Transform for Instance Segmentation](http://openaccess.thecvf.com/content_cvpr_2017/html/Bai_Deep_Watershed_Transform_CVPR_2017_paper.html) | CVPR | [code](https://github.com/min2209/dwt) | 120 |
| [Associative Domain Adaptation](http://openaccess.thecvf.com/content_iccv_2017/html/Haeusser_Associative_Domain_Adaptation_ICCV_2017_paper.html) | ICCV | [code](https://github.com/haeusser/learning_by_association) | 119 |
| [Learning by Association -- A Versatile Semi-Supervised Training Method for Neural Networks](http://openaccess.thecvf.com/content_cvpr_2017/html/Haeusser_Learning_by_Association_CVPR_2017_paper.html) | CVPR | [code](https://github.com/haeusser/learning_by_association) | 119 |
| [Value Prediction Network](http://papers.nips.cc/paper/7192-value-prediction-network.pdf) | NIPS | [code](https://github.com/junhyukoh/value-prediction-network) | 119 |
| [Unrestricted Facial Geometry Reconstruction Using Image-To-Image Translation](http://openaccess.thecvf.com/content_iccv_2017/html/Sela_Unrestricted_Facial_Geometry_ICCV_2017_paper.html) | ICCV | [code](https://github.com/matansel/pix2vertex) | 119 |
| [MemNet: A Persistent Memory Network for Image Restoration](http://openaccess.thecvf.com/content_iccv_2017/html/Tai_MemNet_A_Persistent_ICCV_2017_paper.html) | ICCV | [code](https://github.com/tyshiwo/MemNet) | 119 |
| [Bayesian Optimization with Gradients](http://papers.nips.cc/paper/7111-bayesian-optimization-with-gradients.pdf) | NIPS | [code](https://github.com/wujian16/Cornell-MOE) | 117 |
| [TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning](http://papers.nips.cc/paper/6749-terngrad-ternary-gradients-to-reduce-communication-in-distributed-deep-learning.pdf) | NIPS | [code](https://github.com/wenwei202/terngrad) | 117 |
| [Compressed Sensing using Generative Models](http://proceedings.mlr.press/v70/bora17a.html) | ICML | [code](https://github.com/AshishBora/csgm) | 116 |
| [Switching Convolutional Neural Network for Crowd Counting](http://openaccess.thecvf.com/content_cvpr_2017/html/Sam_Switching_Convolutional_Neural_CVPR_2017_paper.html) | CVPR | [code](https://github.com/val-iisc/crowd-counting-scnn) | 116 |
| [WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification, Pointwise Localization and Segmentation](http://openaccess.thecvf.com/content_cvpr_2017/html/Durand_WILDCAT_Weakly_Supervised_CVPR_2017_paper.html) | CVPR | [code](https://github.com/durandtibo/wildcat.pytorch) | 116 |
| [Show, Adapt and Tell: Adversarial Training of Cross-Domain Image Captioner](http://openaccess.thecvf.com/content_iccv_2017/html/Chen_Show_Adapt_and_ICCV_2017_paper.html) | ICCV | [code](https://github.com/tsenghungchen/show-adapt-and-tell) | 115 |
| [Video Frame Synthesis Using Deep Voxel Flow](http://openaccess.thecvf.com/content_iccv_2017/html/Liu_Video_Frame_Synthesis_ICCV_2017_paper.html) | ICCV | [code](https://github.com/liuziwei7/voxel-flow) | 114 |
| [Multiple Instance Detection Network With Online Instance Classifier Refinement](http://openaccess.thecvf.com/content_cvpr_2017/html/Tang_Multiple_Instance_Detection_CVPR_2017_paper.html) | CVPR | [code](https://github.com/ppengtang/oicr) | 113 |
| [Deep Pyramidal Residual Networks](http://openaccess.thecvf.com/content_cvpr_2017/html/Han_Deep_Pyramidal_Residual_CVPR_2017_paper.html) | CVPR | [code](https://github.com/jhkim89/PyramidNet) | 112 |
| [Train longer, generalize better: closing the generalization gap in large batch training of neural networks](http://papers.nips.cc/paper/6770-train-longer-generalize-better-closing-the-generalization-gap-in-large-batch-training-of-neural-networks.pdf) | NIPS | [code](https://github.com/eladhoffer/bigBatch) | 112 |
| [Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction](http://openaccess.thecvf.com/content_cvpr_2017/html/Zhang_Split-Brain_Autoencoders_Unsupervised_CVPR_2017_paper.html) | CVPR | [code](https://github.com/richzhang/splitbrainauto) | 110 |
| [Unite the People: Closing the Loop Between 3D and 2D Human Representations](http://openaccess.thecvf.com/content_cvpr_2017/html/Lassner_Unite_the_People_CVPR_2017_paper.html) | CVPR | [code](https://github.com/classner/up) | 110 |
| [Learning Combinatorial Optimization Algorithms over Graphs](http://papers.nips.cc/paper/7214-learning-combinatorial-optimization-algorithms-over-graphs.pdf) | NIPS | [code](https://github.com/Hanjun-Dai/graph_comb_opt) | 109 |
| [FeUdal Networks for Hierarchical Reinforcement Learning](http://proceedings.mlr.press/v70/vezhnevets17a.html) | ICML | [code](https://github.com/dmakian/feudal_networks) | 107 |
| [ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression](http://openaccess.thecvf.com/content_iccv_2017/html/Luo_ThiNet_A_Filter_ICCV_2017_paper.html) | ICCV | [code](https://github.com/Roll920/ThiNet) | 105 |
| [Learning a Deep Embedding Model for Zero-Shot Learning](http://openaccess.thecvf.com/content_cvpr_2017/html/Zhang_Learning_a_Deep_CVPR_2017_paper.html) | CVPR | [code](https://github.com/lzrobots/DeepEmbeddingModel_ZSL) | 104 |
| [ECO: Efficient Convolution Operators for Tracking](http://openaccess.thecvf.com/content_cvpr_2017/html/Danelljan_ECO_Efficient_Convolution_CVPR_2017_paper.html) | CVPR | [code](https://github.com/nicewsyly/ECO) | 103 |
| [SCA-CNN: Spatial and Channel-Wise Attention in Convolutional Networks for Image Captioning](http://openaccess.thecvf.com/content_cvpr_2017/html/Chen_SCA-CNN_Spatial_and_CVPR_2017_paper.html) | CVPR | [code](https://github.com/zjuchenlong/sca-cnn.cvpr17) | 102 |
| [Multi-View Supervision for Single-View Reconstruction via Differentiable Ray Consistency](http://openaccess.thecvf.com/content_cvpr_2017/html/Tulsiani_Multi-View_Supervision_for_CVPR_2017_paper.html) | CVPR | [code](https://github.com/shubhtuls/drc) | 100 |
| [Task-based End-to-end Model Learning in Stochastic Optimization](http://papers.nips.cc/paper/7132-task-based-end-to-end-model-learning-in-stochastic-optimization.pdf) | NIPS | [code](https://github.com/locuslab/e2e-model-learning) | 100 |
| [Learning to Compose Domain-Specific Transformations for Data Augmentation](http://papers.nips.cc/paper/6916-learning-to-compose-domain-specific-transformations-for-data-augmentation.pdf) | NIPS | [code](https://github.com/HazyResearch/tanda) | 97 |
| [Genetic CNN](http://openaccess.thecvf.com/content_iccv_2017/html/Xie_Genetic_CNN_ICCV_2017_paper.html) | ICCV | [code](https://github.com/aqibsaeed/Genetic-CNN) | 97 |
| [HashNet: Deep Learning to Hash by Continuation](http://openaccess.thecvf.com/content_iccv_2017/html/Cao_HashNet_Deep_Learning_ICCV_2017_paper.html) | ICCV | [code](https://github.com/thuml/HashNet) | 97 |
| [Interleaved Group Convolutions](http://openaccess.thecvf.com/content_iccv_2017/html/Zhang_Interleaved_Group_Convolutions_ICCV_2017_paper.html) | ICCV | [code](https://github.com/hellozting/InterleavedGroupConvolutions) | 95 |
| [Deeply-Learned Part-Aligned Representations for Person Re-Identification](http://openaccess.thecvf.com/content_iccv_2017/html/Zhao_Deeply-Learned_Part-Aligned_Representations_ICCV_2017_paper.html) | ICCV | [code](https://github.com/zlmzju/part_reid) | 95 |
| [Best of Both Worlds: Transferring Knowledge from Discriminative Learning to a Generative Visual Dialog Model](http://papers.nips.cc/paper/6635-best-of-both-worlds-transferring-knowledge-from-discriminative-learning-to-a-generative-visual-dialog-model.pdf) | NIPS | [code](https://github.com/jiasenlu/visDial.pytorch) | 94 |
| [Multi-Scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimation](http://openaccess.thecvf.com/content_cvpr_2017/html/Xu_Multi-Scale_Continuous_CRFs_CVPR_2017_paper.html) | CVPR | [code](https://github.com/danxuhk/ContinuousCRF-CNN) | 93 |
| [Octree Generating Networks: Efficient Convolutional Architectures for High-Resolution 3D Outputs](http://openaccess.thecvf.com/content_iccv_2017/html/Tatarchenko_Octree_Generating_Networks_ICCV_2017_paper.html) | ICCV | [code](https://github.com/lmb-freiburg/ogn) | 92 |
| [Semantic Autoencoder for Zero-Shot Learning](http://openaccess.thecvf.com/content_cvpr_2017/html/Kodirov_Semantic_Autoencoder_for_CVPR_2017_paper.html) | CVPR | [code](https://github.com/Elyorcv/SAE) | 92 |
| [Deep Hyperspherical Learning](http://papers.nips.cc/paper/6984-deep-hyperspherical-learning.pdf) | NIPS | [code](https://github.com/wy1iu/SphereNet) | 92 |
| [Decoupled Neural Interfaces using Synthetic Gradients](http://proceedings.mlr.press/v70/jaderberg17a.html) | ICML | [code](https://github.com/andrewliao11/dni.pytorch) | 90 |
| [Geometric Matrix Completion with Recurrent Multi-Graph Neural Networks](http://papers.nips.cc/paper/6960-geometric-matrix-completion-with-recurrent-multi-graph-neural-networks.pdf) | NIPS | [code](https://github.com/fmonti/mgcnn) | 90 |
| [Practical Bayesian Optimization for Model Fitting with Bayesian Adaptive Direct Search](http://papers.nips.cc/paper/6780-practical-bayesian-optimization-for-model-fitting-with-bayesian-adaptive-direct-search.pdf) | NIPS | [code](https://github.com/lacerbi/bads) | 90 |
| [Optical Flow Estimation Using a Spatial Pyramid Network](http://openaccess.thecvf.com/content_cvpr_2017/html/Ranjan_Optical_Flow_Estimation_CVPR_2017_paper.html) | CVPR | [code](https://github.com/sniklaus/pytorch-spynet) | 90 |
| [AMC: Attention guided Multi-modal Correlation Learning for Image Search](http://openaccess.thecvf.com/content_cvpr_2017/html/Chen_AMC_Attention_guided_CVPR_2017_paper.html) | CVPR | [code](https://github.com/kanchen-usc/AMC_ATT) | 90 |
| [Deep Video Deblurring for Hand-Held Cameras](http://openaccess.thecvf.com/content_cvpr_2017/html/Su_Deep_Video_Deblurring_CVPR_2017_paper.html) | CVPR | [code](https://github.com/shuochsu/DeepVideoDeblurring) | 89 |
| [Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data](http://papers.nips.cc/paper/6784-unsupervised-learning-of-disentangled-and-interpretable-representations-from-sequential-data.pdf) | NIPS | [code](https://github.com/wnhsu/FactorizedHierarchicalVAE) | 88 |
| [Causal Effect Inference with Deep Latent-Variable Models](http://papers.nips.cc/paper/7223-causal-effect-inference-with-deep-latent-variable-models.pdf) | NIPS | [code](https://github.com/AMLab-Amsterdam/CEVAE) | 87 |
| [GANs for Biological Image Synthesis](http://openaccess.thecvf.com/content_iccv_2017/html/Osokin_GANs_for_Biological_ICCV_2017_paper.html) | ICCV | [code](https://github.com/aosokin/biogans) | 85 |
| [MMD GAN: Towards Deeper Understanding of Moment Matching Network](http://papers.nips.cc/paper/6815-mmd-gan-towards-deeper-understanding-of-moment-matching-network.pdf) | NIPS | [code](https://github.com/OctoberChang/MMD-GAN) | 84 |
| [Representation Learning by Learning to Count](http://openaccess.thecvf.com/content_iccv_2017/html/Noroozi_Representation_Learning_by_ICCV_2017_paper.html) | ICCV | [code](https://github.com/gitlimlab/Representation-Learning-by-Learning-to-Count) | 84 |
| [Optical Flow in Mostly Rigid Scenes](http://openaccess.thecvf.com/content_cvpr_2017/html/Wulff_Optical_Flow_in_CVPR_2017_paper.html) | CVPR | [code](https://github.com/jswulff/mrflow) | 83 |
| [Fast-Slow Recurrent Neural Networks](http://papers.nips.cc/paper/7173-fast-slow-recurrent-neural-networks.pdf) | NIPS | [code](https://github.com/amujika/Fast-Slow-LSTM) | 82 |
| [Unsupervised Video Summarization With Adversarial LSTM Networks](http://openaccess.thecvf.com/content_cvpr_2017/html/Mahasseni_Unsupervised_Video_Summarization_CVPR_2017_paper.html) | CVPR | [code](https://github.com/j-min/Adversarial_Video_Summary) | 82 |
| [Constrained Policy Optimization](http://proceedings.mlr.press/v70/achiam17a.html) | ICML | [code](https://github.com/jachiam/cpo) | 81 |
| [A-NICE-MC: Adversarial Training for MCMC](http://papers.nips.cc/paper/7099-a-nice-mc-adversarial-training-for-mcmc.pdf) | NIPS | [code](https://github.com/jiamings/a-nice-mc) | 80 |
| [Coarse-To-Fine Volumetric Prediction for Single-Image 3D Human Pose](http://openaccess.thecvf.com/content_cvpr_2017/html/Pavlakos_Coarse-To-Fine_Volumetric_Prediction_CVPR_2017_paper.html) | CVPR | [code](https://github.com/geopavlakos/c2f-vol-train) | 80 |
| [End-To-End Instance Segmentation With Recurrent Attention](http://openaccess.thecvf.com/content_cvpr_2017/html/Ren_End-To-End_Instance_Segmentation_CVPR_2017_paper.html) | CVPR | [code](https://github.com/renmengye/rec-attend-public) | 78 |
| [DeLiGAN : Generative Adversarial Networks for Diverse and Limited Data](http://openaccess.thecvf.com/content_cvpr_2017/html/Gurumurthy_DeLiGAN__Generative_CVPR_2017_paper.html) | CVPR | [code](https://github.com/val-iisc/deligan) | 78 |
| [Learning Shape Abstractions by Assembling Volumetric Primitives](http://openaccess.thecvf.com/content_cvpr_2017/html/Tulsiani_Learning_Shape_Abstractions_CVPR_2017_paper.html) | CVPR | [code](https://github.com/shubhtuls/volumetricPrimitives) | 77 |
| [Local Binary Convolutional Neural Networks](http://openaccess.thecvf.com/content_cvpr_2017/html/Juefei-Xu_Local_Binary_Convolutional_CVPR_2017_paper.html) | CVPR | [code](https://github.com/juefeix/lbcnn.torch) | 77 |
| [Raster-To-Vector: Revisiting Floorplan Transformation](http://openaccess.thecvf.com/content_iccv_2017/html/Liu_Raster-To-Vector_Revisiting_Floorplan_ICCV_2017_paper.html) | ICCV | [code](https://github.com/art-programmer/FloorplanTransformation) | 76 |
| [Positive-Unlabeled Learning with Non-Negative Risk Estimator](http://papers.nips.cc/paper/6765-positive-unlabeled-learning-with-non-negative-risk-estimator.pdf) | NIPS | [code](https://github.com/kiryor/nnPUlearning) | 76 |
| [Hard-Aware Deeply Cascaded Embedding](http://openaccess.thecvf.com/content_iccv_2017/html/Yuan_Hard-Aware_Deeply_Cascaded_ICCV_2017_paper.html) | ICCV | [code](https://github.com/PkuRainBow/Hard-Aware-Deeply-Cascaded-Embedding_release) | 75 |
| [Deep Image Harmonization](http://openaccess.thecvf.com/content_cvpr_2017/html/Tsai_Deep_Image_Harmonization_CVPR_2017_paper.html) | CVPR | [code](https://github.com/wasidennis/DeepHarmonization) | 73 |
| [Shape Completion Using 3D-Encoder-Predictor CNNs and Shape Synthesis](http://openaccess.thecvf.com/content_cvpr_2017/html/Dai_Shape_Completion_Using_CVPR_2017_paper.html) | CVPR | [code](https://github.com/angeladai/cnncomplete) | 73 |
| [Not All Pixels Are Equal: Difficulty-Aware Semantic Segmentation via Deep Layer Cascade](http://openaccess.thecvf.com/content_cvpr_2017/h
gitextract_pbxmyq_g/
├── CNAME
├── CONTRIBUTING.md
├── README.md
└── src/
├── README.md
└── pwc.csv
Condensed preview — 5 files, each showing path, character count, and a content snippet. Download the .json file or copy for the full structured content (769K chars).
[
{
"path": "CNAME",
"chars": 16,
"preview": "www.paperake.com"
},
{
"path": "CONTRIBUTING.md",
"chars": 669,
"preview": "### There are several ways that you can contribute \n\n#### 1. Inspect repositories for paper and verify their correctne"
},
{
"path": "README.md",
"chars": 353856,
"preview": "<div align=\"left\">\n<h1>\n <img alt=\"HEADER\" src=\"src/asset/header.jpg\" width=\"900\" height=\"300\"></img>\n</h1>\n\n| [2018]"
},
{
"path": "src/README.md",
"chars": 449,
"preview": "This folder contains all the raw data and code that is used to maintain this repository. \n\nAs this is a work in progress"
},
{
"path": "src/pwc.csv",
"chars": 409910,
"preview": "paper_title,paper_link,conference,year,repo_link,repo_star,last_update\nBridging the Gap Between Value and Policy Based R"
}
]
About this extraction
This page contains the full source code of the zziz/pwc GitHub repository, extracted and formatted as plain text for AI agents and large language models (LLMs). The extraction includes 5 files (747.0 KB), approximately 241.4k tokens. Use this with OpenClaw, Claude, ChatGPT, Cursor, Windsurf, or any other AI tool that accepts text input. You can copy the full output to your clipboard or download it as a .txt file.
Extracted by GitExtract — free GitHub repo to text converter for AI. Built by Nikandr Surkov.