Home

Awesome

<div align="left"> <h1> <img alt="HEADER" src="src/asset/header.jpg" width="900" height="300"></img> </h1>
20182017201620152014201320122011201020092008TweetSuggestions

This work is in continuous progress and update. We are adding new PWC everyday! Tweet me @fvzaur
Use this thread to request us your favorite conference to be added to our watchlist and to PWC list.

Latest update: NIPS 2018 added!

感谢支持

2018

TitleConfCodeStars
Video-to-Video SynthesisNIPScode4749
Deep Image PriorCVPRcode3451
StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image TranslationCVPRcode3104
Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression NetworkECCVcode2109
Learning to See in the DarkCVPRcode2033
Glow: Generative Flow with Invertible 1x1 ConvolutionsNIPScode1862
Squeeze-and-Excitation NetworksCVPRcode1263
Efficient Neural Architecture Search via Parameters SharingICMLcode1189
Multimodal Unsupervised Image-to-image TranslationECCVcode1183
Non-Local Neural NetworksCVPRcode859
Image Generation From Scene GraphsCVPRcode772
Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?CVPRcode690
Single-Shot Refinement Neural Network for Object DetectionCVPRcode668
GANimation: Anatomically-aware Facial Animation from a Single ImageECCVcode628
Detect-and-Track: Efficient Pose Estimation in VideosCVPRcode549
Relation Networks for Object DetectionCVPRcode532
PointCNNNIPScode506
Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial ExamplesICMLcode491
Simple Baselines for Human Pose Estimation and TrackingECCVcode488
Taskonomy: Disentangling Task Transfer LearningCVPRcode453
Which Training Methods for GANs do actually Converge?ICMLcode453
Cascaded Pyramid Network for Multi-Person Pose EstimationCVPRcode447
Pelee: A Real-Time Object Detection System on Mobile DevicesNIPScode441
Generative Image Inpainting With Contextual AttentionCVPRcode441
Neural 3D Mesh RendererCVPRcode436
Look at Boundary: A Boundary-Aware Face Alignment AlgorithmCVPRcode416
Zero-Shot Recognition via Semantic Embeddings and Knowledge GraphsCVPRcode412
End-to-End Recovery of Human Shape and PoseCVPRcode388
In-Place Activated BatchNorm for Memory-Optimized Training of DNNsCVPRcode388
ICNet for Real-Time Semantic Segmentation on High-Resolution ImagesECCVcode372
The Unreasonable Effectiveness of Deep Features as a Perceptual MetricCVPRcode360
Distractor-aware Siamese Networks for Visual Object TrackingECCVcode350
Frustum PointNets for 3D Object Detection From RGB-D DataCVPRcode346
Efficient Interactive Annotation of Segmentation Datasets With Polygon-RNN++CVPRcode339
Gibson Env: Real-World Perception for Embodied AgentsCVPRcode332
Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual ReasoningCVPRcode309
Soccer on Your TabletopCVPRcode308
Noise2Noise: Learning Image Restoration without Clean DataICMLcode304
GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera PoseCVPRcode301
GeoNet: Geometric Neural Network for Joint Depth and Surface Normal EstimationCVPRcode301
Neural Baby TalkCVPRcode292
Acquisition of Localization Confidence for Accurate Object DetectionECCVcode285
The Lovász-Softmax Loss: A Tractable Surrogate for the Optimization of the Intersection-Over-Union Measure in Neural NetworksCVPRcode283
PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost VolumeCVPRcode283
Fast End-to-End Trainable Guided FilterCVPRcode274
Adversarially Regularized AutoencodersICMLcode261
License Plate Detection and Recognition in Unconstrained ScenariosECCVcode258
Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark DetectorsCVPRcode257
Supervising Unsupervised LearningNIPScode255
Pyramid Stereo Matching NetworkCVPRcode250
Convolutional Neural Networks With Alternately Updated CliqueCVPRcode250
Deep Photo Enhancer: Unpaired Learning for Image Enhancement From Photographs With GANsCVPRcode241
Neural Relational Inference for Interacting SystemsICMLcode240
Learning to Adapt Structured Output Space for Semantic SegmentationCVPRcode239
An intriguing failing of convolutional neural networks and the CoordConv solutionNIPScode230
Learning to Segment Every ThingCVPRcode227
LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow EstimationCVPRcode223
End-to-End Learning of Motion Representation for Video UnderstandingCVPRcode222
Pixel2Mesh: Generating 3D Mesh Models from Single RGB ImagesECCVcode219
Bilinear Attention NetworksNIPScode216
Iterative Visual Reasoning Beyond ConvolutionsCVPRcode213
Semi-Parametric Image SynthesisCVPRcode213
A Style-Aware Content Loss for Real-time HD Style TransferECCVcode201
Style Aggregated Network for Facial Landmark DetectionCVPRcode192
Pose-Robust Face Recognition via Deep Residual Equivariant MappingCVPRcode189
GraphRNN: Generating Realistic Graphs with Deep Auto-regressive ModelsICMLcode186
Referring RelationshipsCVPRcode185
MoCoGAN: Decomposing Motion and Content for Video GenerationCVPRcode184
Compressed Video Action RecognitionCVPRcode180
LayoutNet: Reconstructing the 3D Room Layout From a Single RGB ImageCVPRcode178
ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic SegmentationECCVcode176
Latent Alignment and Variational AttentionNIPScode172
Multi-Content GAN for Few-Shot Font Style TransferCVPRcode170
SPLATNet: Sparse Lattice Networks for Point Cloud ProcessingCVPRcode166
Attentive Generative Adversarial Network for Raindrop Removal From a Single ImageCVPRcode158
Single View Stereo MatchingCVPRcode158
Unsupervised Feature Learning via Non-Parametric Instance DiscriminationCVPRcode156
An End-to-End TextSpotter With Explicit Alignment and AttentionCVPRcode156
Social GAN: Socially Acceptable Trajectories With Generative Adversarial NetworksCVPRcode154
ST-GAN: Spatial Transformer Generative Adversarial Networks for Image CompositingCVPRcode153
Evolved Policy GradientsNIPScode151
Optimizing Video Object Detection via a Scale-Time LatticeCVPRcode150
Large-Scale Point Cloud Semantic Segmentation With Superpoint GraphsCVPRcode150
Learning Category-Specific Mesh Reconstruction from Image CollectionsECCVcode146
Group NormalizationECCVcode145
DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial NetworksCVPRcode142
MegaDepth: Learning Single-View Depth Prediction From Internet PhotosCVPRcode142
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile DevicesCVPRcode142
Deep Clustering for Unsupervised Learning of Visual FeaturesECCVcode139
BSN: Boundary Sensitive Network for Temporal Action Proposal GenerationECCVcode139
Learning a Single Convolutional Super-Resolution Network for Multiple DegradationsCVPRcode139
Facelet-Bank for Fast Portrait ManipulationCVPRcode138
Image Super-Resolution Using Very Deep Residual Channel Attention NetworksECCVcode137
ECO: Efficient Convolutional Network for Online Video UnderstandingECCVcode137
PlaneNet: Piece-Wise Planar Reconstruction From a Single RGB ImageCVPRcode137
Self-Imitation LearningICMLcode136
Residual Dense Network for Image Super-ResolutionCVPRcode134
Embodied Question AnsweringCVPRcode132
Unsupervised Cross-Dataset Person Re-Identification by Transfer Learning of Spatial-Temporal PatternsCVPRcode131
Two-Stream Convolutional Networks for Dynamic Texture SynthesisCVPRcode131
Densely Connected Pyramid Dehazing NetworkCVPRcode130
Camera Style Adaptation for Person Re-IdentificationCVPRcode128
Neural Motifs: Scene Graph Parsing With Global ContextCVPRcode127
Weakly and Semi Supervised Human Body Part Parsing via Pose-Guided Knowledge TransferCVPRcode125
Relational recurrent neural networksNIPScode124
LSTM Pose MachinesCVPRcode124
SO-Net: Self-Organizing Network for Point Cloud AnalysisCVPRcode123
Image-Image Domain Adaptation With Preserved Self-Similarity and Domain-Dissimilarity for Person Re-IdentificationCVPRcode121
Context Embedding NetworksCVPRcode120
Fast and Accurate Online Video Object Segmentation via Tracking PartsCVPRcode119
Cross-Domain Weakly-Supervised Object Detection Through Progressive Domain AdaptationCVPRcode119
Learning to Compare: Relation Network for Few-Shot LearningCVPRcode118
Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image DerainingECCVcode116
Structure Inference Net: Object Detection Using Scene-Level Context and Instance-Level RelationshipsCVPRcode116
MVSNet: Depth Inference for Unstructured Multi-view StereoECCVcode116
Weakly Supervised Instance Segmentation Using Class Peak ResponseCVPRcode116
L4: Practical loss-based stepsize adaptation for deep learningNIPScode116
A Closer Look at Spatiotemporal Convolutions for Action RecognitionCVPRcode115
Unsupervised Learning of Monocular Depth Estimation and Visual Odometry With Deep Feature ReconstructionCVPRcode114
Pix3D: Dataset and Methods for Single-Image 3D Shape ModelingCVPRcode114
MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual NetworkECCVcode113
Gated Path Planning NetworksICMLcode113
PackNet: Adding Multiple Tasks to a Single Network by Iterative PruningCVPRcode110
Decoupled NetworksCVPRcode109
Video Based Reconstruction of 3D People ModelsCVPRcode109
CosFace: Large Margin Cosine Loss for Deep Face RecognitionCVPRcode109
DeepMVS: Learning Multi-View StereopsisCVPRcode108
Hierarchical Imitation and Reinforcement LearningICMLcode107
Real-Time Seamless Single Shot 6D Object Pose PredictionCVPRcode107
Adaptive Affinity Fields for Semantic SegmentationECCVcode107
Long-term Tracking in the Wild: a BenchmarkECCVcode106
Realistic Evaluation of Deep Semi-Supervised Learning AlgorithmsNIPScode106
Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and SemanticsCVPRcode104
Deep Back-Projection Networks for Super-ResolutionCVPRcode104
3D-CODED: 3D Correspondences by Deep DeformationECCVcode102
Recovering Realistic Texture in Image Super-Resolution by Deep Spatial Feature TransformCVPRcode102
Scale-Recurrent Network for Deep Image DeblurringCVPRcode101
PU-Net: Point Cloud Upsampling NetworkCVPRcode101
Noisy Natural Gradient as Variational InferenceICMLcode100
Domain Adaptive Faster R-CNN for Object Detection in the WildCVPRcode99
Rethinking Feature Distribution for Loss Functions in Image ClassificationCVPRcode97
DenseASPP for Semantic Segmentation in Street ScenesCVPRcode97
Quantized Densely Connected U-Nets for Efficient Landmark LocalizationECCVcode97
Graph R-CNN for Scene Graph GenerationECCVcode96
Factoring Shape, Pose, and Layout From the 2D Image of a 3D SceneCVPRcode94
Density-Aware Single Image De-Raining Using a Multi-Stream Dense NetworkCVPRcode93
Deep Depth Completion of a Single RGB-D ImageCVPRcode93
MAttNet: Modular Attention Network for Referring Expression ComprehensionCVPRcode92
Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech SynthesisICMLcode91
ELEGANT: Exchanging Latent Encodings with GAN for Transferring Multiple Face AttributesECCVcode89
Neural Arithmetic Logic UnitsNIPScode87
Perturbative Neural NetworksCVPRcode86
Knowledge Aided Consistency for Weakly Supervised Phrase GroundingCVPRcode86
Repulsion Loss: Detecting Pedestrians in a CrowdCVPRcode86
End-to-End Weakly-Supervised Semantic AlignmentCVPRcode86
Learning Blind Video Temporal ConsistencyECCVcode84
PSANet: Point-wise Spatial Attention Network for Scene ParsingECCVcode84
Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask WeightsECCVcode83
Nonlinear 3D Face Morphable ModelCVPRcode81
Deep Mutual LearningCVPRcode80
Image Inpainting for Irregular Holes Using Partial ConvolutionsECCVcode79
BodyNet: Volumetric Inference of 3D Human Body ShapesECCVcode78
Integral Human Pose RegressionECCVcode77
FSRNet: End-to-End Learning Face Super-Resolution With Facial PriorsCVPRcode77
Attention-based Deep Multiple Instance LearningICMLcode77
LiDAR-Video Driving Dataset: Learning Driving Policies EffectivelyCVPRcode77
Multi-View Consistency as Supervisory Signal for Learning Shape and Pose PredictionCVPRcode76
Macro-Micro Adversarial Network for Human ParsingECCVcode76
Multi-view to Novel view: Synthesizing novel views with Self-Learned ConfidenceECCVcode75
LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural NetworksECCVcode75
Neural Kinematic Networks for Unsupervised Motion RetargettingCVPRcode75
Learning Spatial-Temporal Regularized Correlation Filters for Visual TrackingCVPRcode75
Synthesizing Images of Humans in Unseen PosesCVPRcode74
A PID Controller Approach for Stochastic Optimization of Deep NetworksCVPRcode74
Tell Me Where to Look: Guided Attention Inference NetworkCVPRcode74
Multi-Scale Location-Aware Kernel Representation for Object DetectionCVPRcode73
Recurrent Relational NetworksNIPScode73
VITON: An Image-Based Virtual Try-On NetworkCVPRcode73
VITAL: VIsual Tracking via Adversarial LearningCVPRcode73
Future Frame Prediction for Anomaly Detection – A New BaselineCVPRcode72
Recurrent Pixel Embedding for Instance GroupingCVPRcode71
Learning Human-Object Interactions by Graph Parsing Neural NetworksECCVcode69
Repeatability Is Not Enough: Learning Affine Regions via DiscriminabilityECCVcode67
Visual Feature Attribution Using Wasserstein GANsCVPRcode67
Avatar-Net: Multi-Scale Zero-Shot Style Transfer by Feature DecorationCVPRcode66
Learning SO(3) Equivariant Representations with Spherical CNNsECCVcode64
Factorizable Net: An Efficient Subgraph-based Framework for Scene Graph GenerationECCVcode64
SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance SegmentationCVPRcode64
ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D ScansCVPRcode64
One-Shot Unsupervised Cross Domain TranslationNIPScode62
Pairwise Confusion for Fine-Grained Visual ClassificationECCVcode62
Multi-Shot Pedestrian Re-Identification via Sequential Decision MakingCVPRcode62
Generalizing A Person Retrieval Model Hetero- and HomogeneouslyECCVcode61
Learning Depth From Monocular Videos Using Direct MethodsCVPRcode61
Optimizing the Latent Space of Generative NetworksICMLcode60
CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested ScenesCVPRcode59
“Zero-Shot” Super-Resolution Using Deep Internal LearningCVPRcode59
Learning Attentions: Residual Attentional Siamese Network for High Performance Online Visual TrackingCVPRcode59
PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place RecognitionCVPRcode58
Progressive Neural Architecture SearchECCVcode58
Generative Neural Machine TranslationNIPScode58
Learning to Reweight Examples for Robust Deep LearningICMLcode58
Object Level Visual Reasoning in VideosECCVcode57
Generate to Adapt: Aligning Domains Using Generative Adversarial NetworksCVPRcode57
Improving Generalization via Scalable Neighborhood Component AnalysisECCVcode57
Geometry-Aware Learning of Maps for Camera LocalizationCVPRcode57
Path-Level Network Transformation for Efficient Architecture SearchICMLcode57
Decorrelated Batch NormalizationCVPRcode57
Ordinal Depth Supervision for 3D Human Pose EstimationCVPRcode57
Disentangled Person Image GenerationCVPRcode57
Regularizing RNNs for Caption Generation by Reconstructing the Past With the PresentCVPRcode57
Diverse Image-to-Image Translation via Disentangled RepresentationsECCVcode56
Pointwise Convolutional Neural NetworksCVPRcode56
Neural Program Synthesis from Diverse Demonstration VideosICMLcode56
Learning Less Is More - 6D Camera Localization via 3D Surface RegressionCVPRcode55
Unsupervised Domain Adaptation for 3D Keypoint Estimation via View ConsistencyECCVcode55
Learning Latent Super-Events to Detect Multiple Activities in VideosCVPRcode55
Depth-aware CNN for RGB-D SegmentationECCVcode55
Crafting a Toolchain for Image Restoration by Deep Reinforcement LearningCVPRcode54
Unsupervised Discovery of Object Landmarks as Structural RepresentationsCVPRcode54
[