[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-9614":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":10,"languages":10,"totalLinesOfCode":10,"stars":11,"forks":12,"watchers":13,"openIssues":14,"contributorsCount":15,"subscribersCount":15,"size":15,"stars1d":15,"stars7d":15,"stars30d":16,"stars90d":15,"forks30d":15,"starsTrendScore":15,"compositeScore":17,"rankGlobal":10,"rankLanguage":10,"license":10,"archived":18,"fork":18,"defaultBranch":19,"hasWiki":20,"hasPages":20,"topics":21,"createdAt":10,"pushedAt":10,"updatedAt":30,"readmeContent":31,"aiSummary":32,"trendingCount":15,"starSnapshotCount":15,"syncStatus":16,"lastSyncTime":33,"discoverSource":34},9614,"pwc","zziz\u002Fpwc","zziz","This repository is no longer maintained.","",null,15328,2432,1153,19,0,2,67.2,false,"master",true,[22,23,24,25,26,27,28,29],"code","cvpr","eccv","iccv","icml","machine-learning","nips","paper","2026-06-12 04:00:46","\u003Cdiv align=\"left\">\n\u003Ch1>\n    \u003Cimg alt=\"HEADER\" src=\"src\u002Fasset\u002Fheader.jpg\" width=\"900\" height=\"300\">\u003C\u002Fimg>\n\u003C\u002Fh1>\n\n| [2018](#2018) | [2017](#2017) | [2016](#2016) | [2015](#2015) | [2014](#2014) | [2013](#2013) | 2012 | 2011 | 2010 | 2009 | 2008 | [![Tweet](https:\u002F\u002Fimg.shields.io\u002Ftwitter\u002Furl\u002Fhttp\u002Fshields.io.svg?style=social)](https:\u002F\u002Ftwitter.com\u002Fintent\u002Ftweet?text=Papers%20with%20code.%20Sorted%20by%20stars.%20Updated%20weekly.%20&url=https:\u002F\u002Fgithub.com\u002Fzziz\u002Fpwc&via=fvzaur&hashtags=machinelearning,paper,code,github) | [Suggestions](https:\u002F\u002Fgithub.com\u002Fzziz\u002Fpwc\u002Fissues\u002F1) |    \n|:-------:|:-------:|:-------:|:-------:|:-------:|:-------:|:-------:|:-------:|:-------:|:-------:|:-------:|:-------:|:-------:|\n\nThis work is in continuous progress and update. We are adding new PWC everyday! Tweet me [@fvzaur](https:\u002F\u002Ftwitter.com\u002Ffvzaur)   \nUse [this](https:\u002F\u002Fgithub.com\u002Fzziz\u002Fpwc\u002Fissues\u002F11) thread to request us your favorite conference to be added to our watchlist and to PWC list.   \n#### Weekly updated pushed! \n\n## 2018\n| Title | Conf | Code | Stars |\n|:--------|:--------:|:--------:|:--------:|\n| [Video-to-Video Synthesis](https:\u002F\u002Farxiv.org\u002Fabs\u002F1808.06601) | NIPS | [code](https:\u002F\u002Fgithub.com\u002FNVIDIA\u002Fvid2vid) | 5578 | \n| [Deep Image Prior](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FUlyanov_Deep_Image_Prior_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002FDmitryUlyanov\u002Fdeep-image-prior) | 3736 | \n| [StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FChoi_StarGAN_Unified_Generative_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fyunjey\u002FStarGAN) | 3405 | \n| [Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FYao_Feng_Joint_3D_Face_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002FYadiraF\u002FPRNet) | 2434 | \n| [Learning to See in the Dark](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FChen_Learning_to_See_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fcchen156\u002FLearning-to-See-in-the-Dark) | 2326 | \n| [Glow: Generative Flow with Invertible 1x1 Convolutions](http:\u002F\u002Farxiv.org\u002Fabs\u002F1807.03039v2) | NIPS | [code](https:\u002F\u002Fgithub.com\u002Fopenai\u002Fglow) | 2088 | \n| [Squeeze-and-Excitation Networks](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FHu_Squeeze-and-Excitation_Networks_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fhujie-frank\u002FSENet) | 1477 | \n| [Efficient Neural Architecture Search via Parameters Sharing](http:\u002F\u002Fproceedings.mlr.press\u002Fv80\u002Fpham18a.html) | ICML | [code](https:\u002F\u002Fgithub.com\u002Fcarpedm20\u002FENAS-pytorch) | 1382 | \n| [Multimodal Unsupervised Image-to-image Translation](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FXun_Huang_Multimodal_Unsupervised_Image-to-image_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002FNVlabs\u002FMUNIT) | 1296 | \n| [Non-Local Neural Networks](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FWang_Non-Local_Neural_Networks_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Fvideo-nonlocal-net) | 992 | \n| [Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FHara_Can_Spatiotemporal_3D_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fkenshohara\u002F3D-ResNets-PyTorch) | 924 | \n| [Single-Shot Refinement Neural Network for Object Detection](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FZhang_Single-Shot_Refinement_Neural_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fsfzhang15\u002FRefineDet) | 875 | \n| [Image Generation From Scene Graphs](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FJohnson_Image_Generation_From_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fsg2im) | 851 | \n| [GANimation: Anatomically-aware Facial Animation from a Single Image](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FAlbert_Pumarola_Anatomically_Coherent_Facial_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Falbertpumarola\u002FGANimation) | 772 | \n| [Simple Baselines for Human Pose Estimation and Tracking](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FBin_Xiao_Simple_Baselines_for_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002FMicrosoft\u002Fhuman-pose-estimation.pytorch) | 752 | \n| [Visualizing the Loss Landscape of Neural Nets](http:\u002F\u002Farxiv.org\u002Fabs\u002F1712.09913v2) | NIPS | [code](https:\u002F\u002Fgithub.com\u002Ftomgoldstein\u002Floss-landscape) | 724 | \n| [Detect-and-Track: Efficient Pose Estimation in Videos](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FGirdhar_Detect-and-Track_Efficient_Pose_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002FDetectAndTrack) | 650 | \n| [Relation Networks for Object Detection](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FHu_Relation_Networks_for_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fmsracver\u002FRelation-Networks-for-Object-Detection) | 635 | \n| [Generative Image Inpainting With Contextual Attention](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FYu_Generative_Image_Inpainting_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002FJiahuiYu\u002Fgenerative_inpainting) | 609 | \n| [PointCNN](http:\u002F\u002Farxiv.org\u002Fabs\u002F1801.07791v3) | NIPS | [code](https:\u002F\u002Fgithub.com\u002Fyangyanli\u002FPointCNN) | 607 | \n| [Look at Boundary: A Boundary-Aware Face Alignment Algorithm](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FWu_Look_at_Boundary_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fwywu\u002FLAB) | 575 | \n| [Pelee: A Real-Time Object Detection System on Mobile Devices](nan) | NIPS | [code](https:\u002F\u002Fgithub.com\u002FRobert-JunWang\u002FPelee) | 548 | \n| [Distractor-aware Siamese Networks for Visual Object Tracking](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FZheng_Zhu_Distractor-aware_Siamese_Networks_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Ffoolwood\u002FDaSiamRPN) | 545 | \n| [Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples](http:\u002F\u002Fproceedings.mlr.press\u002Fv80\u002Fathalye18a.html) | ICML | [code](https:\u002F\u002Fgithub.com\u002Fanishathalye\u002Fobfuscated-gradients) | 535 | \n| [Which Training Methods for GANs do actually Converge?](http:\u002F\u002Fproceedings.mlr.press\u002Fv80\u002Fmescheder18a.html) | ICML | [code](https:\u002F\u002Fgithub.com\u002FLMescheder\u002FGAN_stability) | 520 | \n| [End-to-End Recovery of Human Shape and Pose](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FKanazawa_End-to-End_Recovery_of_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fakanazawa\u002Fhmr) | 502 | \n| [Taskonomy: Disentangling Task Transfer Learning](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FZamir_Taskonomy_Disentangling_Task_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002FStanfordVL\u002Ftaskonomy) | 502 | \n| [Cascaded Pyramid Network for Multi-Person Pose Estimation](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FChen_Cascaded_Pyramid_Network_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fchenyilun95\u002Ftf-cpn) | 497 | \n| [Neural 3D Mesh Renderer](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FKato_Neural_3D_Mesh_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fhiroharu-kato\u002Fneural_renderer) | 489 | \n| [Zero-Shot Recognition via Semantic Embeddings and Knowledge Graphs](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FWang_Zero-Shot_Recognition_via_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002FJudyYe\u002Fzero-shot-gcn) | 489 | \n| [In-Place Activated BatchNorm for Memory-Optimized Training of DNNs](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FBulo_In-Place_Activated_BatchNorm_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fmapillary\u002Finplace_abn) | 485 | \n| [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FZhang_The_Unreasonable_Effectiveness_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Frichzhang\u002FPerceptualSimilarity) | 447 | \n| [Frustum PointNets for 3D Object Detection From RGB-D Data](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FQi_Frustum_PointNets_for_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fcharlesq34\u002Ffrustum-pointnets) | 434 | \n| [The Lovász-Softmax Loss: A Tractable Surrogate for the Optimization of the Intersection-Over-Union Measure in Neural Networks](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FBerman_The_LovaSz-Softmax_Loss_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fbermanmaxim\u002FLovaszSoftmax) | 416 | \n| [ICNet for Real-Time Semantic Segmentation on High-Resolution Images](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FHengshuang_Zhao_ICNet_for_Real-Time_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Fhszhao\u002FICNet) | 415 | \n| [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FSun_PWC-Net_CNNs_for_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002FNVlabs\u002FPWC-Net) | 398 | \n| [Efficient Interactive Annotation of Segmentation Datasets With Polygon-RNN++](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FAcuna_Efficient_Interactive_Annotation_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Ffidler-lab\u002Fpolyrnn-pp-pytorch) | 397 | \n| [Gibson Env: Real-World Perception for Embodied Agents](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FXia_Gibson_Env_Real-World_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002FStanfordVL\u002FGibsonEnv) | 385 | \n| [Acquisition of Localization Confidence for Accurate Object Detection](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FBorui_Jiang_Acquisition_of_Localization_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Fvacancy\u002FPreciseRoIPooling) | 384 | \n| [Noise2Noise: Learning Image Restoration without Clean Data](http:\u002F\u002Fproceedings.mlr.press\u002Fv80\u002Flehtinen18a.html) | ICML | [code](https:\u002F\u002Fgithub.com\u002Fyu4u\u002Fnoise2noise) | 370 | \n| [GeoNet: Geometric Neural Network for Joint Depth and Surface Normal Estimation](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FQi_GeoNet_Geometric_Neural_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fyzcjtr\u002FGeoNet) | 359 | \n| [GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FYin_GeoNet_Unsupervised_Learning_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fyzcjtr\u002FGeoNet) | 359 | \n| [A Style-Aware Content Loss for Real-time HD Style Transfer](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FArtsiom_Sanakoyeu_A_Style-aware_Content_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002FCompVis\u002Fadaptive-style-transfer) | 349 | \n| [Soccer on Your Tabletop](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FRematas_Soccer_on_Your_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fkrematas\u002Fsoccerontable) | 338 | \n| [Pyramid Stereo Matching Network](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FChang_Pyramid_Stereo_Matching_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002FJiaRenChang\u002FPSMNet) | 335 | \n| [Neural Baby Talk](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FLu_Neural_Baby_Talk_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fjiasenlu\u002FNeuralBabyTalk) | 332 | \n| [License Plate Detection and Recognition in Unconstrained Scenarios](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FSergio_Silva_License_Plate_Detection_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Fsergiomsilva\u002Falpr-unconstrained) | 326 | \n| [Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FDong_Supervision-by-Registration_An_Unsupervised_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Fsupervision-by-registration) | 326 | \n| [Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FNanyang_Wang_Pixel2Mesh_Generating_3D_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Fnywang16\u002FPixel2Mesh) | 323 | \n| [Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FMascharka_Transparency_by_Design_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fdavidmascharka\u002Ftbd-nets) | 317 | \n| [Fast End-to-End Trainable Guided Filter](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FWu_Fast_End-to-End_Trainable_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fwuhuikai\u002FDeepGuidedFilter) | 312 | \n| [Deep Clustering for Unsupervised Learning of Visual Features](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FMathilde_Caron_Deep_Clustering_for_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Fdeepcluster) | 302 | \n| [Deep Photo Enhancer: Unpaired Learning for Image Enhancement From Photographs With GANs](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FChen_Deep_Photo_Enhancer_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fnothinglo\u002FDeep-Photo-Enhancer) | 294 | \n| [Neural Relational Inference for Interacting Systems](http:\u002F\u002Fproceedings.mlr.press\u002Fv80\u002Fkipf18a.html) | ICML | [code](https:\u002F\u002Fgithub.com\u002Fethanfetaya\u002FNRI) | 289 | \n| [Adversarially Regularized Autoencoders](http:\u002F\u002Fproceedings.mlr.press\u002Fv80\u002Fzhao18b.html) | ICML | [code](https:\u002F\u002Fgithub.com\u002Fjakezhaojb\u002FARAE) | 282 | \n| [Learning to Adapt Structured Output Space for Semantic Segmentation](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FTsai_Learning_to_Adapt_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fwasidennis\u002FAdaptSegNet) | 280 | \n| [Convolutional Neural Networks With Alternately Updated Clique](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FYang_Convolutional_Neural_Networks_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fiboing\u002FCliqueNet) | 272 | \n| [Learning to Segment Every Thing](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FHu_Learning_to_Segment_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fronghanghu\u002Fseg_every_thing) | 269 | \n| [Supervising Unsupervised Learning](http:\u002F\u002Farxiv.org\u002Fabs\u002F1709.05262v2) | NIPS | [code](https:\u002F\u002Fgithub.com\u002Fquinnliu\u002FmachineLearning) | 262 | \n| [LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FHui_LiteFlowNet_A_Lightweight_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Ftwhui\u002FLiteFlowNet) | 261 | \n| [Bilinear Attention Networks](http:\u002F\u002Farxiv.org\u002Fabs\u002F1805.07932v1) | NIPS | [code](https:\u002F\u002Fgithub.com\u002Fjnhwkim\u002Fban-vqa) | 258 | \n| [ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FSachin_Mehta_ESPNet_Efficient_Spatial_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Fsacmehta\u002FESPNet) | 254 | \n| [An intriguing failing of convolutional neural networks and the CoordConv solution](https:\u002F\u002Farxiv.org\u002Fabs\u002F1807.03247) | NIPS | [code](https:\u002F\u002Fgithub.com\u002Fmkocabas\u002FCoordConv-pytorch) | 249 | \n| [End-to-End Learning of Motion Representation for Video Understanding](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FFan_End-to-End_Learning_of_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002FLijieFan\u002Ftvnet) | 238 | \n| [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FYulun_Zhang_Image_Super-Resolution_Using_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Fyulunzhang\u002FRCAN) | 234 | \n| [Iterative Visual Reasoning Beyond Convolutions](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FChen_Iterative_Visual_Reasoning_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fendernewton\u002Fiter-reason) | 228 | \n| [Semi-Parametric Image Synthesis](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FQi_Semi-Parametric_Image_Synthesis_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fxjqicuhk\u002FSIMS) | 226 | \n| [Compressed Video Action Recognition](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FWu_Compressed_Video_Action_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fchaoyuaw\u002Fpytorch-coviar) | 225 | \n| [Style Aggregated Network for Facial Landmark Detection](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FDong_Style_Aggregated_Network_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002FD-X-Y\u002FSAN) | 223 | \n| [Pose-Robust Face Recognition via Deep Residual Equivariant Mapping](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FCao_Pose-Robust_Face_Recognition_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fpenincillin\u002FDREAM) | 220 | \n| [Multi-Content GAN for Few-Shot Font Style Transfer](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FAzadi_Multi-Content_GAN_for_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fazadis\u002FMC-GAN) | 218 | \n| [GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models](http:\u002F\u002Fproceedings.mlr.press\u002Fv80\u002Fyou18a.html) | ICML | [code](https:\u002F\u002Fgithub.com\u002FJiaxuanYou\u002Fgraph-generation) | 214 | \n| [Referring Relationships](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FKrishna_Referring_Relationships_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002FStanfordVL\u002FReferringRelationships) | 210 | \n| [MoCoGAN: Decomposing Motion and Content for Video Generation](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FTulyakov_MoCoGAN_Decomposing_Motion_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fsergeytulyakov\u002Fmocogan) | 205 | \n| [Latent Alignment and Variational Attention](http:\u002F\u002Farxiv.org\u002Fabs\u002F1807.03756v1) | NIPS | [code](https:\u002F\u002Fgithub.com\u002Fharvardnlp\u002Fvar-attn) | 204 | \n| [LayoutNet: Reconstructing the 3D Room Layout From a Single RGB Image](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FZou_LayoutNet_Reconstructing_the_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fzouchuhang\u002FLayoutNet) | 202 | \n| [Large-Scale Point Cloud Semantic Segmentation With Superpoint Graphs](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FLandrieu_Large-Scale_Point_Cloud_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Floicland\u002Fsuperpoint_graph) | 197 | \n| [An End-to-End TextSpotter With Explicit Alignment and Attention](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FHe_An_End-to-End_TextSpotter_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Ftonghe90\u002Ftextspotter) | 195 | \n| [DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FKupyn_DeblurGAN_Blind_Motion_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002FRaphaelMeudec\u002Fdeblur-gan) | 189 | \n| [SPLATNet: Sparse Lattice Networks for Point Cloud Processing](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FSu_SPLATNet_Sparse_Lattice_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002FNVlabs\u002Fsplatnet) | 188 | \n| [Attentive Generative Adversarial Network for Raindrop Removal From a Single Image](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FQian_Attentive_Generative_Adversarial_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Frui1996\u002FDeRaindrop) | 186 | \n| [Single View Stereo Matching](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FLuo_Single_View_Stereo_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Flawy623\u002FSVS) | 182 | \n| [MegaDepth: Learning Single-View Depth Prediction From Internet Photos](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FLi_MegaDepth_Learning_Single-View_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Flixx2938\u002FMegaDepth) | 181 | \n| [ECO: Efficient Convolutional Network for Online Video Understanding](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FMohammadreza_Zolfaghari_ECO_Efficient_Convolutional_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Fmzolfaghari\u002FECO-efficient-video-understanding) | 180 | \n| [Unsupervised Feature Learning via Non-Parametric Instance Discrimination](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FWu_Unsupervised_Feature_Learning_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fzhirongw\u002Flemniscate.pytorch) | 180 | \n| [ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositing](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FLin_ST-GAN_Spatial_Transformer_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fchenhsuanlin\u002Fspatial-transformer-GAN) | 179 | \n| [Video Based Reconstruction of 3D People Models](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FAlldieck_Video_Based_Reconstruction_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fthmoa\u002Fvideoavatars) | 179 | \n| [Social GAN: Socially Acceptable Trajectories With Generative Adversarial Networks](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FGupta_Social_GAN_Socially_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fagrimgupta92\u002Fsgan) | 178 | \n| [Learning Category-Specific Mesh Reconstruction from Image Collections](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FAngjoo_Kanazawa_Learning_Category-Specific_Mesh_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Fakanazawa\u002Fcmr) | 176 | \n| [Realistic Evaluation of Deep Semi-Supervised Learning Algorithms](http:\u002F\u002Farxiv.org\u002Fabs\u002F1804.09170v2) | NIPS | [code](https:\u002F\u002Fgithub.com\u002Fbrain-research\u002Frealistic-ssl-evaluation) | 175 | \n| [BSN: Boundary Sensitive Network for Temporal Action Proposal Generation](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FTianwei_Lin_BSN_Boundary_Sensitive_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Fwzmsltw\u002FBSN-boundary-sensitive-network) | 175 | \n| [Group Normalization](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FYuxin_Wu_Group_Normalization_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Fshaohua0116\u002FGroup-Normalization-Tensorflow) | 175 | \n| [Real-Time Seamless Single Shot 6D Object Pose Prediction](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FTekin_Real-Time_Seamless_Single_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002FMicrosoft\u002Fsingleshotpose) | 174 | \n| [MVSNet: Depth Inference for Unstructured Multi-view Stereo](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FYao_Yao_MVSNet_Depth_Inference_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002FYoYo000\u002FMVSNet) | 174 | \n| [Neural Motifs: Scene Graph Parsing With Global Context](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FZellers_Neural_Motifs_Scene_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Frowanz\u002Fneural-motifs) | 171 | \n| [Learning a Single Convolutional Super-Resolution Network for Multiple Degradations](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FZhang_Learning_a_Single_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fcszn\u002FSRMD) | 169 | \n| [Optimizing Video Object Detection via a Scale-Time Lattice](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FChen_Optimizing_Video_Object_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fhellock\u002Fscale-time-lattice) | 168 | \n| [MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FMuhammed_Kocabas_MultiPoseNet_Fast_Multi-Person_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Fsalihkaragoz\u002Fpose-residual-network-pytorch) | 167 | \n| [Unsupervised Cross-Dataset Person Re-Identification by Transfer Learning of Spatial-Temporal Patterns](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FLv_Unsupervised_Cross-Dataset_Person_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fahangchen\u002FTFusion) | 166 | \n| [Weakly Supervised Instance Segmentation Using Class Peak Response](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FZhou_Weakly_Supervised_Instance_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002FZhouYanzhao\u002FPRM) | 166 | \n| [PlaneNet: Piece-Wise Planar Reconstruction From a Single RGB Image](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FLiu_PlaneNet_Piece-Wise_Planar_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fart-programmer\u002FPlaneNet) | 164 | \n| [Residual Dense Network for Image Super-Resolution](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FZhang_Residual_Dense_Network_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fyulunzhang\u002FRDN) | 163 | \n| [Embodied Question Answering](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FDas_Embodied_Question_Answering_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002FEmbodiedQA) | 162 | \n| [Evolved Policy Gradients](http:\u002F\u002Farxiv.org\u002Fabs\u002F1802.04821v2) | NIPS | [code](https:\u002F\u002Fgithub.com\u002Fopenai\u002FEPG) | 160 | \n| [Camera Style Adaptation for Person Re-Identification](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FZhong_Camera_Style_Adaptation_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fzhunzhong07\u002FCamStyle) | 159 | \n| [Weakly and Semi Supervised Human Body Part Parsing via Pose-Guided Knowledge Transfer](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FFang_Weakly_and_Semi_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002FMVIG-SJTU\u002FWSHP) | 159 | \n| [Scale-Recurrent Network for Deep Image Deblurring](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FTao_Scale-Recurrent_Network_for_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fjiangsutx\u002FSRN-Deblur) | 159 | \n| [Unsupervised Learning of Monocular Depth Estimation and Visual Odometry With Deep Feature Reconstruction](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FZhan_Unsupervised_Learning_of_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002FHuangying-Zhan\u002FDepth-VO-Feat) | 158 | \n| [Relational recurrent neural networks](https:\u002F\u002Farxiv.org\u002Fabs\u002F1806.01822) | NIPS | [code](https:\u002F\u002Fgithub.com\u002FL0SG\u002Frelational-rnn-pytorch) | 157 | \n| [Densely Connected Pyramid Dehazing Network](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FZhang_Densely_Connected_Pyramid_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fhezhangsprinter\u002FDCPDN) | 155 | \n| [Image Inpainting for Irregular Holes Using Partial Convolutions](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FGuilin_Liu_Image_Inpainting_for_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Fnaoto0804\u002Fpytorch-inpainting-with-partial-conv) | 153 | \n| [SO-Net: Self-Organizing Network for Point Cloud Analysis](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FLi_SO-Net_Self-Organizing_Network_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Flijx10\u002FSO-Net) | 152 | \n| [Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FSun_Pix3D_Dataset_and_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fxingyuansun\u002Fpix3d) | 152 | \n| [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FZhang_ShuffleNet_An_Extremely_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fcamel007\u002FCaffe-ShuffleNet) | 152 | \n| [DenseASPP for Semantic Segmentation in Street Scenes](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FYang_DenseASPP_for_Semantic_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002FDeepMotionAIResearch\u002FDenseASPP) | 151 | \n| [Facelet-Bank for Fast Portrait Manipulation](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FChen_Facelet-Bank_for_Fast_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fyingcong\u002FFacelet_Bank) | 150 | \n| [Self-Imitation Learning](http:\u002F\u002Fproceedings.mlr.press\u002Fv80\u002Foh18b.html) | ICML | [code](https:\u002F\u002Fgithub.com\u002Fjunhyukoh\u002Fself-imitation-learning) | 145 | \n| [Graph R-CNN for Scene Graph Generation](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FJianwei_Yang_Graph_R-CNN_for_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Fjwyang\u002Fgraph-rcnn.pytorch) | 144 | \n| [A Closer Look at Spatiotemporal Convolutions for Action Recognition](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FTran_A_Closer_Look_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Firhumshafkat\u002FR2Plus1D-PyTorch) | 143 | \n| [Cross-Domain Weakly-Supervised Object Detection Through Progressive Domain Adaptation](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FInoue_Cross-Domain_Weakly-Supervised_Object_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fnaoto0804\u002Fcross-domain-detection) | 143 | \n| [Quantized Densely Connected U-Nets for Efficient Landmark Localization](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FZhiqiang_Tang_Quantized_Densely_Connected_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Fzhiqiangdon\u002FCU-Net) | 143 | \n| [Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Deraining](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FXia_Li_Recurrent_Squeeze-and-Excitation_Context_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002FXiaLiPKU\u002FRESCAN) | 142 | \n| [Two-Stream Convolutional Networks for Dynamic Texture Synthesis](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FTesfaldet_Two-Stream_Convolutional_Networks_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fryersonvisionlab\u002Ftwo-stream-dyntex-synth) | 141 | \n| [Integral Human Pose Regression](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FXiao_Sun_Integral_Human_Pose_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002FJimmySuen\u002Fintegral-human-pose) | 141 | \n| [Adaptive Affinity Fields for Semantic Segmentation](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FJyh-Jing_Hwang_Adaptive_Affinity_Field_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Ftwke18\u002FAdaptive_Affinity_Fields) | 141 | \n| [LSTM Pose Machines](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FLuo_LSTM_Pose_Machines_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Flawy623\u002FLSTM_Pose_Machines) | 141 | \n| [Structure Inference Net: Object Detection Using Scene-Level Context and Instance-Level Relationships](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FLiu_Structure_Inference_Net_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fchoasup\u002FSIN) | 140 | \n| [Recovering Realistic Texture in Image Super-Resolution by Deep Spatial Feature Transform](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FWang_Recovering_Realistic_Texture_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fxinntao\u002FCVPR18-SFTGAN) | 139 | \n| [Image-Image Domain Adaptation With Preserved Self-Similarity and Domain-Dissimilarity for Person Re-Identification](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FDeng_Image-Image_Domain_Adaptation_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002FSimon4Yan\u002FLearning-via-Translation) | 137 | \n| [Learning to Compare: Relation Network for Few-Shot Learning](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FSung_Learning_to_Compare_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Flzrobots\u002FLearningToCompare_ZSL) | 135 | \n| [CosFace: Large Margin Cosine Loss for Deep Face Recognition](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FWang_CosFace_Large_Margin_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fyule-li\u002FCosFace) | 135 | \n| [Deep Depth Completion of a Single RGB-D Image](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FZhang_Deep_Depth_Completion_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fyindaz\u002FDeepCompletionRelease) | 134 | \n| [Deep Back-Projection Networks for Super-Resolution](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FHaris_Deep_Back-Projection_Networks_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Falterzero\u002FDBPN-Pytorch) | 132 | \n| [Context Embedding Networks](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FKim_Context_Embedding_Networks_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fthunlp\u002FCANE) | 131 | \n| [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FKendall_Multi-Task_Learning_Using_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Falexgkendall\u002Fmultitaskvision) | 131 | \n| [Perturbative Neural Networks](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FJuefei-Xu_Perturbative_Neural_Networks_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fjuefeix\u002Fpnn.pytorch) | 130 | \n| [Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis](http:\u002F\u002Fproceedings.mlr.press\u002Fv80\u002Fwang18h.html) | ICML | [code](https:\u002F\u002Fgithub.com\u002Fsyang1993\u002Fgst-tacotron) | 129 | \n| [Fast and Accurate Online Video Object Segmentation via Tracking Parts](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FCheng_Fast_and_Accurate_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002FJingchunCheng\u002FFAVOS) | 129 | \n| [Nonlinear 3D Face Morphable Model](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FTran_Nonlinear_3D_Face_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Ftranluan\u002FNonlinear_Face_3DMM) | 128 | \n| [BodyNet: Volumetric Inference of 3D Human Body Shapes](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FGul_Varol_BodyNet_Volumetric_Inference_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Fgulvarol\u002Fbodynet) | 126 | \n| [3D-CODED: 3D Correspondences by Deep Deformation](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FThibault_Groueix_Shape_correspondences_from_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002FThibaultGROUEIX\u002F3D-CODED) | 125 | \n| [DeepMVS: Learning Multi-View Stereopsis](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FHuang_DeepMVS_Learning_Multi-View_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fphuang17\u002FDeepMVS) | 125 | \n| [Hierarchical Imitation and Reinforcement Learning](http:\u002F\u002Fproceedings.mlr.press\u002Fv80\u002Fle18a.html) | ICML | [code](https:\u002F\u002Fgithub.com\u002Fhoangminhle\u002Fhierarchical_IL_RL) | 124 | \n| [Domain Adaptive Faster R-CNN for Object Detection in the Wild](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FChen_Domain_Adaptive_Faster_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fyuhuayc\u002Fda-faster-rcnn) | 123 | \n| [L4: Practical loss-based stepsize adaptation for deep learning](http:\u002F\u002Farxiv.org\u002Fabs\u002F1802.05074v4) | NIPS | [code](https:\u002F\u002Fgithub.com\u002Fmartius-lab\u002Fl4-optimizer) | 123 | \n| [A Generative Adversarial Approach for Zero-Shot Learning From Noisy Texts](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FZhu_A_Generative_Adversarial_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002FEthanZhu90\u002FZSL_GAN_CVPR18) | 122 | \n| [Recurrent Relational Networks](http:\u002F\u002Farxiv.org\u002Fabs\u002F1711.08028v2) | NIPS | [code](https:\u002F\u002Fgithub.com\u002Frasmusbergpalm\u002Frecurrent-relational-networks) | 121 | \n| [Gated Path Planning Networks](http:\u002F\u002Fproceedings.mlr.press\u002Fv80\u002Flee18c.html) | ICML | [code](https:\u002F\u002Fgithub.com\u002Flileee\u002Fgated-path-planning-networks) | 121 | \n| [PSANet: Point-wise Spatial Attention Network for Scene Parsing](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FHengshuang_Zhao_PSANet_Point-wise_Spatial_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Fhszhao\u002FPSANet) | 121 | \n| [Rethinking Feature Distribution for Loss Functions in Image Classification](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FWan_Rethinking_Feature_Distribution_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002FWeitaoVan\u002FL-GM-loss) | 120 | \n| [Density-Aware Single Image De-Raining Using a Multi-Stream Dense Network](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FZhang_Density-Aware_Single_Image_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fhezhangsprinter\u002FDID-MDN) | 118 | \n| [FOTS: Fast Oriented Text Spotting With a Unified Network](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FLiu_FOTS_Fast_Oriented_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fjiangxiluning\u002FFOTS.PyTorch) | 118 | \n| [ELEGANT: Exchanging Latent Encodings with GAN for Transferring Multiple Face Attributes](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FTaihong_Xiao_ELEGANT_Exchanging_Latent_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002FPrinsphield\u002FELEGANT) | 117 | \n| [PU-Net: Point Cloud Upsampling Network](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FYu_PU-Net_Point_Cloud_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fyulequan\u002FPU-Net) | 117 | \n| [PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FMallya_PackNet_Adding_Multiple_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Farunmallya\u002Fpacknet) | 117 | \n| [Long-term Tracking in the Wild: a Benchmark](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FEfstratios_Gavves_Long-term_Tracking_in_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Foxuva\u002Flong-term-tracking-benchmark) | 116 | \n| [Factoring Shape, Pose, and Layout From the 2D Image of a 3D Scene](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FTulsiani_Factoring_Shape_Pose_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fshubhtuls\u002Ffactored3d) | 114 | \n| [Repulsion Loss: Detecting Pedestrians in a Crowd](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FWang_Repulsion_Loss_Detecting_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fbailvwangzi\u002Frepulsion_loss_ssd) | 113 | \n| [Unsupervised Attention-guided Image-to-Image Translation](https:\u002F\u002Farxiv.org\u002Fabs\u002F1806.02311) | NIPS | [code](https:\u002F\u002Fgithub.com\u002FAlamiMejjati\u002FUnsupervised-Attention-guided-Image-to-Image-Translation) | 110 | \n| [Attention-based Deep Multiple Instance Learning](http:\u002F\u002Fproceedings.mlr.press\u002Fv80\u002Filse18a.html) | ICML | [code](https:\u002F\u002Fgithub.com\u002FAMLab-Amsterdam\u002FAttentionDeepMIL) | 109 | \n| [Learning Blind Video Temporal Consistency](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FWei-Sheng_Lai_Real-Time_Blind_Video_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Fphoenix104104\u002Ffast_blind_video_consistency) | 109 | \n| [Noisy Natural Gradient as Variational Inference](http:\u002F\u002Fproceedings.mlr.press\u002Fv80\u002Fzhang18l.html) | ICML | [code](https:\u002F\u002Fgithub.com\u002Fwlwkgus\u002FNoisyNaturalGradient) | 108 | \n| [End-to-End Weakly-Supervised Semantic Alignment](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FRocco_End-to-End_Weakly-Supervised_Semantic_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fignacio-rocco\u002Fweakalign) | 106 | \n| [Decoupled Networks](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FLiu_Decoupled_Networks_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fwy1iu\u002FDCNets) | 105 | \n| [LiDAR-Video Driving Dataset: Learning Driving Policies Effectively](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FChen_LiDAR-Video_Driving_Dataset_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fdriving-behavior\u002FDBNet) | 104 | \n| [MAttNet: Modular Attention Network for Referring Expression Comprehension](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FYu_MAttNet_Modular_Attention_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Flichengunc\u002FMAttNet) | 104 | \n| [LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FDongqing_Zhang_Optimized_Quantization_for_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002FMicrosoft\u002FLQ-Nets) | 103 | \n| [FSRNet: End-to-End Learning Face Super-Resolution With Facial Priors](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FChen_FSRNet_End-to-End_Learning_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Ftyshiwo\u002FFSRNet) | 100 | \n| [Deep Mutual Learning](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FZhang_Deep_Mutual_Learning_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002FYingZhangDUT\u002FDeep-Mutual-Learning) | 100 | \n| [Macro-Micro Adversarial Network for Human Parsing](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FYawei_Luo_Macro-Micro_Adversarial_Network_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002FRoyalVane\u002FMMAN) | 98 | \n| [ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FDai_ScanComplete_Large-Scale_Scene_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fangeladai\u002FScanComplete) | 97 | \n| [Learning Depth From Monocular Videos Using Direct Methods](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FWang_Learning_Depth_From_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002FMightyChaos\u002FLKVOLearner) | 97 | \n| [VITON: An Image-Based Virtual Try-On Network](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FHan_VITON_An_Image-Based_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fxthan\u002FVITON) | 95 | \n| [Cascade R-CNN: Delving Into High Quality Object Detection](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FCai_Cascade_R-CNN_Delving_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fguoruoqian\u002Fcascade-rcnn_Pytorch) | 93 | \n| [Learning Human-Object Interactions by Graph Parsing Neural Networks](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FSiyuan_Qi_Learning_Human-Object_Interactions_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002FSiyuanQi\u002Fgpnn) | 93 | \n| [Future Frame Prediction for Anomaly Detection – A New Baseline](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FLiu_Future_Frame_Prediction_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002FStevenLiuWen\u002Fano_pred_cvpr2018) | 92 | \n| [Multi-view to Novel view: Synthesizing novel views with Self-Learned Confidence](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FShao-Hua_Sun_Multi-view_to_Novel_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Fshaohua0116\u002FMultiview2Novelview) | 92 | \n| [Tell Me Where to Look: Guided Attention Inference Network](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FLi_Tell_Me_Where_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Falokwhitewolf\u002FGuided-Attention-Inference-Network) | 91 | \n| [Neural Kinematic Networks for Unsupervised Motion Retargetting](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FVillegas_Neural_Kinematic_Networks_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Frubenvillegas\u002Fcvpr2018nkn) | 90 | \n| [Learning SO(3) Equivariant Representations with Spherical CNNs](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FCarlos_Esteves_Learning_SO3_Equivariant_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Fdaniilidis-group\u002Fspherical-cnn) | 89 | \n| [One-Shot Unsupervised Cross Domain Translation](http:\u002F\u002Farxiv.org\u002Fabs\u002F1806.06029v1) | NIPS | [code](https:\u002F\u002Fgithub.com\u002Fsagiebenaim\u002FOneShotTranslation) | 89 | \n| [Synthesizing Images of Humans in Unseen Poses](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FBalakrishnan_Synthesizing_Images_of_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fbalakg\u002Fposewarp-cvpr2018) | 88 | \n| [Depth-aware CNN for RGB-D Segmentation](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FWeiyue_Wang_Depth-aware_CNN_for_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Flaughtervv\u002FDepthAwareCNN) | 88 | \n| [Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weights](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FArun_Mallya_Piggyback_Adapting_a_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Farunmallya\u002Fpiggyback) | 88 | \n| [Knowledge Aided Consistency for Weakly Supervised Phrase Grounding](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FChen_Knowledge_Aided_Consistency_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fkanchen-usc\u002FKAC-Net) | 87 | \n| [CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FLi_CSRNet_Dilated_Convolutional_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fleeyeehoo\u002FCSRNet-pytorch) | 87 | \n| [Neural Arithmetic Logic Units](http:\u002F\u002Farxiv.org\u002Fabs\u002F1808.00508v1) | NIPS | [code](https:\u002F\u002Fgithub.com\u002FllSourcell\u002FNeural_Arithmetic_Logic_Units) | 87 | \n| [A PID Controller Approach for Stochastic Optimization of Deep Networks](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FAn_A_PID_Controller_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Ftensorboy\u002FPIDOptimizer) | 87 | \n| [VITAL: VIsual Tracking via Adversarial Learning](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FSong_VITAL_VIsual_Tracking_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fybsong00\u002FVital_release) | 86 | \n| [Learning Spatial-Temporal Regularized Correlation Filters for Visual Tracking](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FLi_Learning_Spatial-Temporal_Regularized_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Flifeng9472\u002FSTRCF) | 86 | \n| [Recurrent Pixel Embedding for Instance Grouping](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FKong_Recurrent_Pixel_Embedding_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Faimerykong\u002FRecurrent-Pixel-Embedding-for-Instance-Grouping) | 85 | \n| [SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FWang_SGPN_Similarity_Group_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Flaughtervv\u002FSGPN) | 84 | \n| [Multi-Scale Location-Aware Kernel Representation for Object Detection](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FWang_Multi-Scale_Location-Aware_Kernel_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002FHwang64\u002FMLKP) | 84 | \n| [Repeatability Is Not Enough: Learning Affine Regions via Discriminability](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FDmytro_Mishkin_Repeatability_Is_Not_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Fducha-aiki\u002Faffnet) | 84 | \n| [“Zero-Shot” Super-Resolution Using Deep Internal Learning](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FShocher_Zero-Shot_Super-Resolution_Using_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fassafshocher\u002FZSSR) | 84 | \n| [DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistency](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FYuliang_Zou_DF-Net_Unsupervised_Joint_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Fvt-vl-lab\u002FDF-Net) | 82 | \n| [Multi-View Consistency as Supervisory Signal for Learning Shape and Pose Prediction](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FTulsiani_Multi-View_Consistency_as_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fshubhtuls\u002FmvcSnP) | 80 | \n| [Factorizable Net: An Efficient Subgraph-based Framework for Scene Graph Generation](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FYikang_LI_Factorizable_Net_An_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Fyikang-li\u002FFactorizableNet) | 78 | \n| [Generalizing A Person Retrieval Model Hetero- and Homogeneously](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FZhun_Zhong_Generalizing_A_Person_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Fzhunzhong07\u002FHHL) | 78 | \n| [Crafting a Toolchain for Image Restoration by Deep Reinforcement Learning](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FYu_Crafting_a_Toolchain_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fyuke93\u002FRL-Restore) | 77 | \n| [Pairwise Confusion for Fine-Grained Visual Classification](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FAbhimanyu_Dubey_Improving_Fine-Grained_Visual_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Fabhimanyudubey\u002Fconfusion) | 77 | \n| [Learning to Reweight Examples for Robust Deep Learning](http:\u002F\u002Fproceedings.mlr.press\u002Fv80\u002Fren18a.html) | ICML | [code](https:\u002F\u002Fgithub.com\u002Fdanieltan07\u002Flearning-to-reweight-examples) | 76 | \n| [Improving Generalization via  Scalable Neighborhood Component Analysis](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FZhirong_Wu_Improving_Embedding_Generalization_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002FMicrosoft\u002Fsnca.pytorch) | 76 | \n| [SparseMAP: Differentiable Sparse Structured Inference](http:\u002F\u002Fproceedings.mlr.press\u002Fv80\u002Fniculae18a.html) | ICML | [code](https:\u002F\u002Fgithub.com\u002Fvene\u002Fsparsemap) | 75 | \n| [PDE-Net: Learning PDEs from Data](http:\u002F\u002Fproceedings.mlr.press\u002Fv80\u002Flong18a.html) | ICML | [code](https:\u002F\u002Fgithub.com\u002FZichaoLong\u002FPDE-Net) | 75 | \n| [Pose-Normalized Image Generation for Person Re-identification](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FXuelin_Qian_Pose-Normalized_Image_Generation_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Fnaiq\u002FPN_GAN) | 75 | \n| [Disentangled Person Image Generation](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FMa_Disentangled_Person_Image_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fcharliememory\u002FDisentangled-Person-Image-Generation) | 75 | \n| [Learning to Navigate for Fine-grained Classification](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FZe_Yang_Learning_to_Navigate_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Fyangze0930\u002FNTS-Net) | 74 | \n| [Superpixel Sampling Networks](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FVarun_Jampani_Superpixel_Sampling_Networks_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002FNVlabs\u002Fssn_superpixels) | 74 | \n| [Shift-Net: Image Inpainting via Deep Feature Rearrangement](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FZhaoyi_Yan_Shift-Net_Image_Inpainting_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002FZhaoyi-Yan\u002FShift-Net_pytorch) | 74 | \n| [3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FAngela_Dai_3DMV_Joint_3D-Multi-View_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Fangeladai\u002F3DMV) | 74 | \n| [Ordinal Depth Supervision for 3D Human Pose Estimation](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FPavlakos_Ordinal_Depth_Supervision_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fgeopavlakos\u002Fordinal-pose3d) | 74 | \n| [Path-Level Network Transformation for Efficient Architecture Search](http:\u002F\u002Fproceedings.mlr.press\u002Fv80\u002Fcai18a.html) | ICML | [code](https:\u002F\u002Fgithub.com\u002Fhan-cai\u002FPathLevel-EAS) | 73 | \n| [Diverse Image-to-Image Translation via Disentangled Representations](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FHsin-Ying_Lee_Diverse_Image-to-Image_Translation_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Ftaki0112\u002FDRIT-Tensorflow) | 72 | \n| [Visual Feature Attribution Using Wasserstein GANs](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FBaumgartner_Visual_Feature_Attribution_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Forobix\u002FVisual-Feature-Attribution-Using-Wasserstein-GANs-Pytorch) | 72 | \n| [Real-World Anomaly Detection in Surveillance Videos](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FSultani_Real-World_Anomaly_Detection_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002FWaqasSultani\u002FAnomalyDetectionCVPR2018) | 72 | \n| [Self-Supervised Adversarial Hashing Networks for Cross-Modal Retrieval](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FLi_Self-Supervised_Adversarial_Hashing_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Flelan-li\u002FSSAH) | 72 | \n| [Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FSiyuan_Huang_Monocular_Scene_Parsing_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Fthusiyuan\u002Fholistic_scene_parsing) | 72 | \n| [Learning to Find Good Correspondences](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FYi_Learning_to_Find_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fvcg-uvic\u002Flearned-correspondence-release) | 72 | \n| [Learning Less Is More - 6D Camera Localization via 3D Surface Regression](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FBrachmann_Learning_Less_Is_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fvislearn\u002FLessMore) | 72 | \n| [Object Level Visual Reasoning in Videos](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FFabien_Baradel_Object_Level_Visual_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Ffabienbaradel\u002Fobject_level_visual_reasoning) | 71 | \n| [Weakly-Supervised Semantic Segmentation Network With Deep Seeded Region Growing](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FHuang_Weakly-Supervised_Semantic_Segmentation_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fspeedinghzl\u002FDSRG) | 71 | \n| [Avatar-Net: Multi-Scale Zero-Shot Style Transfer by Feature Decoration](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FSheng_Avatar-Net_Multi-Scale_Zero-Shot_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002FLucasSheng\u002Favatar-net) | 71 | \n| [Fast and Accurate Single Image Super-Resolution via Information Distillation Network](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FHui_Fast_and_Accurate_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002FZheng222\u002FIDN-Caffe) | 71 | \n| [Regularizing RNNs for Caption Generation by Reconstructing the Past With the Present](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FChen_Regularizing_RNNs_for_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fchenxinpeng\u002FARNet) | 70 | \n| [Multi-Shot Pedestrian Re-Identification via Sequential Decision Making](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FZhang_Multi-Shot_Pedestrian_Re-Identification_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002FTuSimple\u002Frl-multishot-reid) | 70 | \n| [PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FUy_PointNetVLAD_Deep_Point_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fmikacuy\u002Fpointnetvlad) | 69 | \n| [Progressive Neural Architecture Search](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FChenxi_Liu_Progressive_Neural_Architecture_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Ftitu1994\u002Fprogressive-neural-architecture-search) | 68 | \n| [Generative Neural Machine Translation](http:\u002F\u002Farxiv.org\u002Fabs\u002F1806.05138v1) | NIPS | [code](https:\u002F\u002Fgithub.com\u002FZhenYangIACAS\u002FNMT_GAN) | 68 | \n| [Learning Latent Super-Events to Detect Multiple Activities in Videos](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FPiergiovanni_Learning_Latent_Super-Events_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fpiergiaj\u002Fsuper-events-cvpr18) | 67 | \n| [Generate to Adapt: Aligning Domains Using Generative Adversarial Networks](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FSankaranarayanan_Generate_to_Adapt_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fyogeshbalaji\u002FGenerate_To_Adapt) | 67 | \n| [Adversarial Feature Augmentation for Unsupervised Domain Adaptation](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FVolpi_Adversarial_Feature_Augmentation_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fricvolpi\u002Fadversarial-feature-augmentation) | 67 | \n| [Learning Attentions: Residual Attentional Siamese Network for High Performance Online Visual Tracking](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FWang_Learning_Attentions_Residual_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Ffoolwood\u002FRASNet) | 67 | \n| [Pointwise Convolutional Neural Networks](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FHua_Pointwise_Convolutional_Neural_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fscenenn\u002Fpointwise) | 67 | \n| [Optimizing the Latent Space of Generative Networks](http:\u002F\u002Fproceedings.mlr.press\u002Fv80\u002Fbojanowski18a.html) | ICML | [code](https:\u002F\u002Fgithub.com\u002Ftneumann\u002Fminimal_glo) | 66 | \n| [Part-Aligned Bilinear Representations for Person Re-Identification](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FYumin_Suh_Part-Aligned_Bilinear_Representations_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Fyuminsuh\u002Fpart_bilinear_reid) | 64 | \n| [Geometry-Aware Learning of Maps for Camera Localization](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FBrahmbhatt_Geometry-Aware_Learning_of_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fsamarth-robo\u002FMapNet) | 63 | \n| [Fighting Fake News: Image Splice Detection via Learned Self-Consistency](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FJacob_Huh_Fighting_Fake_News_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Fminyoungg\u002Fselfconsistency) | 62 | \n| [Isolating Sources of Disentanglement in Variational Autoencoders](http:\u002F\u002Farxiv.org\u002Fabs\u002F1802.04942v2) | NIPS | [code](https:\u002F\u002Fgithub.com\u002Frtqichen\u002Fbeta-tcvae) | 62 | \n| [Neural Program Synthesis from Diverse Demonstration Videos](http:\u002F\u002Fproceedings.mlr.press\u002Fv80\u002Fsun18a.html) | ICML | [code](https:\u002F\u002Fgithub.com\u002Fshaohua0116\u002Fdemo2program) | 62 | \n| [Learning Rigidity in Dynamic Scenes with a Moving Camera for 3D Motion Field Estimation](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FZhaoyang_Lv_Learning_Rigidity_in_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002FNVlabs\u002Flearningrigidity) | 61 | \n| [Rotation-Sensitive Regression for Oriented Scene Text Detection](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FLiao_Rotation-Sensitive_Regression_for_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002FMhLiao\u002FRRD) | 61 | \n| [Human Semantic Parsing for Person Re-Identification](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FKalayeh_Human_Semantic_Parsing_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Femrahbasaran\u002FSPReID) | 61 | \n| [Unsupervised Discovery of Object Landmarks as Structural Representations](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FZhang_Unsupervised_Discovery_of_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002FYutingZhang\u002Flmdis-rep) | 61 | \n| [IQA: Visual Question Answering in Interactive Environments](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FGordon_IQA_Visual_Question_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fdanielgordon10\u002Fthor-iqa-cvpr-2018) | 60 | \n| [Hierarchical Long-term Video Prediction without Supervision](http:\u002F\u002Fproceedings.mlr.press\u002Fv80\u002Fwichers18a.html) | ICML | [code](https:\u002F\u002Fgithub.com\u002Fbrain-research\u002Flong-term-video-prediction-without-supervision) | 60 | \n| [Unsupervised Domain Adaptation for 3D Keypoint Estimation via View Consistency](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FXingyi_Zhou_Unsupervised_Domain_Adaptation_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Fxingyizhou\u002F3DKeypoints-DA) | 60 | \n| [Exploit the Unknown Gradually: One-Shot Video-Based Person Re-Identification by Stepwise Learning](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FWu_Exploit_the_Unknown_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002FYu-Wu\u002FExploit-Unknown-Gradually) | 59 | \n| [Neural Style Transfer via Meta Networks](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FShen_Neural_Style_Transfer_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002FFalongShen\u002Fstyletransfer) | 59 | \n| [Frame-Recurrent Video Super-Resolution](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FSajjadi_Frame-Recurrent_Video_Super-Resolution_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fmsmsajjadi\u002FFRVSR) | 58 | \n| [PlaneMatch: Patch Coplanarity Prediction for Robust RGB-D Reconstruction](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FYifei_Shi_PlaneMatch_Patch_Coplanarity_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Fyifeishi\u002FPlaneMatch) | 57 | \n| [CBAM: Convolutional Block Attention Module](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FSanghyun_Woo_Convolutional_Block_Attention_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002FYoungkl0726\u002FConvolutional-Block-Attention-Module) | 57 | \n| [Decorrelated Batch Normalization](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FHuang_Decorrelated_Batch_Normalization_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fumich-vl\u002FDecorrelatedBN) | 57 | \n| [Learning Conditioned Graph Structures for Interpretable Visual Question Answering](nan) | NIPS | [code](https:\u002F\u002Fgithub.com\u002Faimbrain\u002Fvqa-project) | 57 | \n| [Hierarchical Bilinear Pooling for Fine-Grained Visual Recognition](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FChaojian_Yu_Hierarchical_Bilinear_Pooling_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002FChaojianYu\u002FHierarchical-Bilinear-Pooling) | 57 | \n| [Leveraging Unlabeled Data for Crowd Counting by Learning to Rank](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FLiu_Leveraging_Unlabeled_Data_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fxialeiliu\u002FCrowdCountingCVPR18) | 56 | \n| [Deep Marching Cubes: Learning Explicit Surface Representations](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FLiao_Deep_Marching_Cubes_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fyiyiliao\u002Fdeep_marching_cubes) | 56 | \n| [Learning From Synthetic Data: Addressing Domain Shift for Semantic Segmentation](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FSankaranarayanan_Learning_From_Synthetic_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fswamiviv\u002FLSD-seg) | 56 | \n| [LF-Net: Learning Local Features from Images](https:\u002F\u002Farxiv.org\u002Fabs\u002F1805.09662) | NIPS | [code](https:\u002F\u002Fgithub.com\u002Fvcg-uvic\u002Flf-net-release) | 55 | \n| [Semi-supervised Adversarial Learning to Generate Photorealistic Face Images of New Identities from 3D Morphable Model](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FBaris_Gecer_Semi-supervised_Adversarial_Learning_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Fbarisgecer\u002Ffacegan) | 55 | \n| [Discriminability Objective for Training Descriptive Captions](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FLuo_Discriminability_Objective_for_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fruotianluo\u002FDiscCaptioning) | 54 | \n| [BlockDrop: Dynamic Inference Paths in Residual Networks](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FWu_BlockDrop_Dynamic_Inference_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002FTushar-N\u002Fblockdrop) | 54 | \n| [Conditional Probability Models for Deep Image Compression](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FMentzer_Conditional_Probability_Models_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Ffab-jul\u002Fimgcomp-cvpr) | 54 | \n| [Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FPeng_Jointly_Optimize_Data_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fzhiqiangdon\u002Fpose-adv-aug) | 54 | \n| [Learning towards Minimum Hyperspherical Energy](http:\u002F\u002Farxiv.org\u002Fabs\u002F1805.09298v4) | NIPS | [code](https:\u002F\u002Fgithub.com\u002Fwy1iu\u002FMHE) | 54 | \n| [DeepVS: A Deep Learning Based Video Saliency Prediction Approach](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FLai_Jiang_DeepVS_A_Deep_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Fremega\u002FOMCNN_2CLSTM) | 53 | \n| [Learning Efficient Single-stage Pedestrian Detectors by Asymptotic Localization Fitting](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FWei_Liu_Learning_Efficient_Single-stage_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Fliuwei16\u002FALFNet) | 52 | \n| [Learning Pixel-Level Semantic Affinity With Image-Level Supervision for Weakly Supervised Semantic Segmentation](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FAhn_Learning_Pixel-Level_Semantic_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fjiwoon-ahn\u002Fpsa) | 52 | \n| [Wasserstein Introspective Neural Networks](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FLee_Wasserstein_Introspective_Neural_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fkjunelee\u002FWINN) | 51 | \n| [SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FChen_SketchyGAN_Towards_Diverse_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fwchen342\u002FSketchyGAN) | 51 | \n| [Self-produced Guidance for Weakly-supervised Object Localization](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FXiaolin_Zhang_Self-produced_Guidance_for_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Fxiaomengyc\u002FSPG) | 51 | \n| [Measuring abstract reasoning in neural networks](http:\u002F\u002Fproceedings.mlr.press\u002Fv80\u002Fsantoro18a.html) | ICML | [code](https:\u002F\u002Fgithub.com\u002Fdeepmind\u002Fabstract-reasoning-matrices) | 51 | \n| [A Unified Feature Disentangler for Multi-Domain Image Translation and Manipulation](https:\u002F\u002Farxiv.org\u002Fabs\u002F1809.01361) | NIPS | [code](https:\u002F\u002Fgithub.com\u002FXenderLiu\u002FUFDN) | 51 | \n| [RayNet: Learning Volumetric 3D Reconstruction With Ray Potentials](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FPaschalidou_RayNet_Learning_Volumetric_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fpaschalidoud\u002Fraynet) | 51 | \n| [Coloring with Words: Guiding Image Colorization Through Text-based Palette Generation](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_ECCV_2018\u002Fhtml\u002FHyojin_Bahng_Coloring_with_Words_ECCV_2018_paper.html) | ECCV | [code](https:\u002F\u002Fgithub.com\u002Fawesome-davian\u002FText2Colors) | 50 | \n| [Efficient end-to-end learning for quantizable representations](http:\u002F\u002Fproceedings.mlr.press\u002Fv80\u002Fjeong18a.html) | ICML | [code](https:\u002F\u002Fgithub.com\u002Fmaestrojeong\u002FDeep-Hash-Table-ICML18) | 50 | \n| [Visual Question Generation as Dual Task of Visual Question Answering](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FLi_Visual_Question_Generation_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fyikang-li\u002FiQAN) | 50 | \n| [Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam](http:\u002F\u002Fproceedings.mlr.press\u002Fv80\u002Fkhan18a.html) | ICML | [code](https:\u002F\u002Fgithub.com\u002Femtiyaz\u002Fvadam) | 49 | \n| [Surface Networks](http:\u002F\u002Fopenaccess.thecvf.com\u002Fcontent_cvpr_2018\u002Fpapers\u002FKostrikov_Surface_Networks_CVPR_2018_paper.pdf) | CVPR | [code](https:\u002F\u002Fgithub.com\u002Fjiangzhongshi\u002FSurfaceNetworks) | 48 | \n| [Deep k-Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Con","该项目是一个已不再维护的代码仓库，旨在收集并整理近年来在各大顶级会议（如CVPR、ECCV、ICCV、ICML、NIPS等）上发表的重要论文及其开源实现。其核心功能是提供一个按年份和会议分类的论文列表，并附带每篇论文的GitHub代码链接以及项目星标数，方便研究者和开发者快速找到感兴趣的高质量资源。此项目特别适合于机器学习领域的研究人员、学生及从业者，在寻找最新研究成果或参考现有技术实现时使用。","2026-06-11 03:23:46","top_topic"]