CVPR 2020 Accepted Papers

The full list of 1,466 papers accepted at CVPR 2020 (IEEE/CVF Conference on Computer Vision and Pattern Recognition). Click any title for details, similar papers, and links to the original source. You can also search these papers by meaning, not just keywords.

1. Momentum Contrast for Unsupervised Visual Representation LearningOral15,734 citations
2. EfficientDet: Scalable and Efficient Object DetectionPoster8,837 citations
3. ECA-Net: Efficient Channel Attention for Deep Convolutional Neural NetworksPoster7,872 citations
4. Analyzing and Improving the Image Quality of StyleGANPoster7,789 citations
5. nuScenes: A Multimodal Dataset for Autonomous DrivingPoster7,379 citations
6. GhostNet: More Features From Cheap OperationsPoster4,614 citations
7. Scalability in Perception for Autonomous Driving: Waymo Open DatasetPoster3,735 citations
8. Self-Training With Noisy Student Improves ImageNet ClassificationPoster3,136 citations
9. SuperGlue: Learning Feature Matching With Graph Neural NetworksOral2,892 citations
10. BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask LearningOral2,855 citations
11. PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object DetectionPoster2,428 citations
12. Bridging the Gap Between Anchor-Based and Anchor-Free Detection via Adaptive Training Sample SelectionOral2,298 citations
13. Designing Network Design SpacesPoster2,278 citations
14. StarGAN v2: Diverse Image Synthesis for Multiple DomainsPoster2,173 citations
15. RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point CloudsOral2,143 citations
16. Zero-Reference Deep Curve Estimation for Low-Light Image EnhancementPoster2,093 citations
17. Self-Supervised Learning of Pretext-Invariant RepresentationsPoster1,843 citations
18. Celeb-DF: A Large-Scale Challenging Dataset for DeepFake ForensicsPoster1,723 citations
19. RetinaFace: Single-Shot Multi-Level Face Localisation in the WildPoster1,569 citations
20. MaskGAN: Towards Diverse and Interactive Facial Image ManipulationPoster1,388 citations
21. X3D: Expanding Architectures for Efficient Video RecognitionOral1,365 citations
22. Dynamic Convolution: Attention Over Convolution KernelsOral1,342 citations
23. Interpreting the Latent Space of GANs for Semantic Face EditingPoster1,327 citations
24. Disentangling and Unifying Graph Convolutions for Skeleton-Based Action RecognitionOral1,312 citations
25. Meshed-Memory Transformer for Image CaptioningPoster1,303 citations
26. PointRend: Image Segmentation As RenderingOral1,268 citations
27. 3DSSD: Point-Based 3D Single Stage Object DetectorOral1,242 citations
28. CNN-Generated Images Are Surprisingly Easy to Spot... for NowOral1,237 citations
29. VIBE: Video Inference for Human Body Pose and Shape EstimationPoster1,216 citations
30. PointPainting: Sequential Fusion for 3D Object DetectionPoster1,183 citations
31. Learned Image Compression With Discretized Gaussian Mixture Likelihoods and Attention ModulesPoster1,181 citations
32. Circle Loss: A Unified Perspective of Pair Similarity OptimizationOral1,174 citations
33. FDA: Fourier Domain Adaptation for Semantic SegmentationPoster1,143 citations
34. Exploring Self-Attention for Image RecognitionPoster1,130 citations
35. Face X-Ray for More General Face Forgery DetectionOral1,126 citations
36. Learning Texture Transformer Network for Image Super-ResolutionPoster1,107 citations
37. Point-GNN: Graph Neural Network for 3D Object Detection in a Point CloudPoster1,095 citations
38. HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose EstimationPoster1,075 citations
39. Differentiable Volumetric Rendering: Learning Implicit 3D Representations Without 3D SupervisionPoster1,069 citations
40. BBN: Bilateral-Branch Network With Cumulative Learning for Long-Tailed Visual RecognitionOral1,043 citations
41. HRank: Filter Pruning Using High-Rank Feature MapOral1,040 citations
42. Multi-Scale Boosted Dehazing Network With Dense Feature FusionPoster1,034 citations
43. Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory PredictionPoster1,032 citations
44. Siamese Box Adaptive Network for Visual TrackingPoster1,031 citations
45. Semi-Supervised Semantic Segmentation With Cross-Consistency TrainingPoster1,026 citations
46. VectorNet: Encoding HD Maps and Agent Dynamics From Vectorized RepresentationPoster1,022 citations
47. Skeleton-Based Action Recognition With Shift Graph Convolutional NetworkOral1,008 citations
48. DeepEMD: Few-Shot Image Classification With Differentiable Earth Mover's Distance and Structured ClassifiersOral1,005 citations
49. SiamCAR: Siamese Fully Convolutional Classification and Regression for Visual TrackingOral980 citations
50. Learning Memory-Guided Normality for Anomaly DetectionPoster964 citations
51. PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human DigitizationOral955 citations
52. Few-Shot Learning via Embedding Adaptation With Set-to-Set FunctionsPoster940 citations
53. Uninformed Students: Student-Teacher Anomaly Detection With Discriminative Latent EmbeddingsPoster926 citations
54. ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday TasksPoster922 citations
55. Multi-Scale Interactive Network for Salient Object DetectionPoster917 citations
56. Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo MatchingOral897 citations
57. 3D Packing for Self-Supervised Monocular Depth EstimationOral881 citations
58. Self-Supervised Equivariant Attention Mechanism for Weakly Supervised Semantic SegmentationOral881 citations
59. Unbiased Scene Graph Generation From Biased TrainingOral870 citations
60. End-to-End Learning of Visual Representations From Uncurated Instructional VideosOral867 citations
61. Multi-Scale Progressive Fusion Network for Single Image DerainingPoster844 citations
62. Siam R-CNN: Visual Tracking by Re-DetectionPoster825 citations
63. Camouflaged Object DetectionOral806 citations
64. Rethinking Classification and Localization for Object DetectionPoster792 citations
65. Blindly Assess Image Quality in the Wild Guided by a Self-Adaptive Hyper NetworkPoster788 citations
66. Strip Pooling: Rethinking Spatial Pooling for Scene ParsingPoster788 citations
67. CenterMask: Real-Time Anchor-Free Instance SegmentationPoster783 citations
68. Probabilistic Regression for Visual TrackingPoster783 citations
69. Suppressing Uncertainties for Large-Scale Facial Expression RecognitionPoster783 citations
70. Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic SegmentationPoster776 citations
71. PointASNL: Robust Point Clouds Processing Using Nonlocal Neural Networks With Adaptive SamplingPoster764 citations
72. PolarMask: Single Shot Instance Segmentation With Polar RepresentationOral764 citations
73. Few-Shot Object Detection With Attention-RPN and Multi-Relation DetectorPoster758 citations
74. Deep Unfolding Network for Image Super-ResolutionPoster756 citations
75. X-Linear Attention Networks for Image CaptioningPoster746 citations
76. SEAN: Image Synthesis With Semantic Region-Adaptive NormalizationOral731 citations
77. Sign Language Transformers: Joint End-to-End Sign Language Recognition and TranslationOral726 citations
78. TDAN: Temporally-Deformable Alignment Network for Video Super-ResolutionPoster726 citations
79. Generalized ODIN: Detecting Out-of-Distribution Image Without Learning From Out-of-Distribution DataPoster725 citations
80. Structure Aware Single-Stage 3D Object Detection From Point CloudPoster720 citations
81. Revisiting Knowledge Distillation via Label Smoothing RegularizationOral719 citations
82. On the Detection of Digital Face ManipulationPoster715 citations
83. Relation-Aware Global Attention for Person Re-IdentificationPoster713 citations
84. Combating Noisy Labels by Agreement: A Joint Training Method with Co-RegularizationPoster706 citations
85. High-Frequency Component Helps Explain the Generalization of Convolutional Neural NetworksOral700 citations
86. Adversarial Examples Improve Image RecognitionPoster699 citations
87. Dreaming to Distill: Data-Free Knowledge Transfer via DeepInversionOral699 citations
88. BlendMask: Top-Down Meets Bottom-Up for Instance SegmentationOral697 citations
89. CurricularFace: Adaptive Curriculum Learning Loss for Deep Face RecognitionPoster686 citations
90. PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative ModelsPoster679 citations
91. Local Implicit Grid Representations for 3D ScenesPoster659 citations
92. From Fidelity to Perceptual Quality: A Semi-Supervised Approach for Low-Light Image EnhancementPoster657 citations
93. Image2StyleGAN++: How to Edit the Embedded Images?Poster654 citations
94. GraspNet-1Billion: A Large-Scale Benchmark for General Object GraspingPoster650 citations
95. Residual Feature Aggregation Network for Image Super-ResolutionPoster645 citations
96. TEA: Temporal Excitation and Aggregation for Action RecognitionPoster638 citations
97. Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action RecognitionPoster635 citations
98. PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic SegmentationPoster630 citations
99. Distribution-Aware Coordinate Representation for Human Pose EstimationPoster627 citations
100. Deep Global RegistrationOral621 citations
101. AANet: Adaptive Aggregation Network for Efficient Stereo MatchingPoster620 citations
102. Searching Central Difference Convolutional Networks for Face Anti-SpoofingPoster620 citations
103. Maintaining Discrimination and Fairness in Class Incremental LearningPoster614 citations
104. The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural NetworksOral614 citations
105. PVN3D: A Deep Point-Wise 3D Keypoints Voting Network for 6DoF Pose EstimationPoster613 citations
106. Equalization Loss for Long-Tailed Object RecognitionPoster612 citations
107. G-TAD: Sub-Graph Localization for Temporal Action DetectionPoster604 citations
108. RPM-Net: Robust Point Matching Using Learned FeaturesPoster597 citations
109. Few-Shot Class-Incremental LearningOral590 citations
110. AugFPN: Improving Multi-Scale Feature Learning for Object DetectionPoster589 citations
111. DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery DetectionPoster586 citations
112. SAL: Sign Agnostic Learning of Shapes From Raw DataOral586 citations
113. Learning a Neural Solver for Multiple Object TrackingOral579 citations
114. Implicit Functions in Feature Space for 3D Shape Reconstruction and CompletionPoster578 citations
115. Seeing Through Fog Without Seeing Fog: Deep Multimodal Sensor Fusion in Unseen Adverse WeatherPoster577 citations
116. 12-in-1: Multi-Task Vision and Language Representation LearningPoster575 citations
117. Learning to Learn Single Domain GeneralizationPoster572 citations
118. SAPIEN: A SimulAted Part-Based Interactive ENvironmentOral560 citations
119. Learning in the Frequency DomainPoster557 citations
120. Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep NetworksPoster556 citations
121. High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-IdentificationPoster555 citations
122. Improving Convolutional Networks With Self-Calibrated ConvolutionsPoster542 citations
123. Adaptive Subspaces for Few-Shot LearningPoster539 citations
124. PF-Net: Point Fractal Network for 3D Point Cloud CompletionPoster536 citations
125. Recurrent Feature Reasoning for Image InpaintingPoster535 citations
126. BlendedMVS: A Large-Scale Dataset for Generalized Multi-View Stereo NetworksPoster534 citations
127. Revisiting the Sibling Head in Object DetectorPoster532 citations
128. GaitPart: Temporal Part-Based Model for Gait RecognitionPoster529 citations
129. D3Feat: Joint Learning of Dense Detection and Description of 3D Local FeaturesOral528 citations
130. CoverNet: Multimodal Behavior Prediction Using Trajectory SetsPoster527 citations
131. ActBERT: Learning Global-Local Video-Text RepresentationsOral523 citations
132. Temporal Pyramid Network for Action RecognitionPoster521 citations
133. D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual OdometryOral519 citations
134. PointGroup: Dual-Set Point Grouping for 3D Instance SegmentationOral519 citations
135. Cross-Domain Correspondence Learning for Exemplar-Based Image TranslationOral515 citations
136. Deformable Siamese Attention Networks for Visual Object TrackingPoster513 citations
137. ZeroQ: A Novel Zero Shot Quantization FrameworkPoster513 citations
138. StegaStamp: Invisible Hyperlinks in Physical PhotographsPoster512 citations
139. Unsupervised Person Re-Identification via Multi-Label ClassificationOral512 citations
140. SynSin: End-to-End View Synthesis From a Single ImageOral510 citations
141. Local Deep Implicit Functions for 3D ShapeOral503 citations
142. Deblurring by Realistic BlurringOral495 citations
143. Domain Adaptation for Image DehazingPoster489 citations
144. Towards Discriminability and Diversity: Batch Nuclear-Norm Maximization Under Label Insufficient SituationsOral489 citations
145. Proxy Anchor Loss for Deep Metric LearningPoster486 citations
146. Unsupervised Intra-Domain Adaptation for Semantic Segmentation Through Self-SupervisionOral480 citations
147. Image Super-Resolution With Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars MiningPoster478 citations
148. ABCNet: Real-Time Scene Text Spotting With Adaptive Bezier-Curve NetworkOral474 citations
149. StyleRig: Rigging StyleGAN for 3D Control Over Portrait ImagesOral473 citations
150. HOnnotate: A Method for 3D Annotation of Hand and Object PosesPoster470 citations
151. Multi-Modality Cross Attention Network for Image and Sentence MatchingPoster470 citations
152. AutoTrack: Towards High-Performance Visual Tracking for UAV With Automatic Spatio-Temporal RegularizationPoster462 citations
153. IMRAM: Iterative Matching With Recurrent Attention Memory for Cross-Modal Image-Text RetrievalPoster461 citations
154. A Model-Driven Deep Neural Network for Single Image Rain RemovalPoster457 citations
155. Softmax Splatting for Video Frame InterpolationPoster457 citations
156. Mnemonics Training: Multi-Class Incremental Learning Without ForgettingOral454 citations
157. What Makes Training Multi-Modal Classification Networks Hard?Poster453 citations
158. CycleISP: Real Image Restoration via Improved Data SynthesisOral450 citations
159. Style Normalization and Restitution for Generalizable Person Re-IdentificationPoster448 citations
160. Self2Self With Dropout: Learning Self-Supervised Denoising From Single ImagePoster447 citations
161. Structure-Preserving Super Resolution With Gradient GuidancePoster446 citations
162. In Defense of Grid Features for Visual Question AnsweringPoster444 citations
163. Interactive Two-Stream Decoder for Accurate and Fast Saliency DetectionPoster444 citations
164. Contextual Residual Aggregation for Ultra High-Resolution Image InpaintingOral443 citations
165. Learning to Restore Low-Light Images via Decomposition-and-EnhancementPoster443 citations
166. MetaIQA: Deep Meta-Learning for No-Reference Image Quality AssessmentPoster443 citations
167. Towards Fairness in Visual Recognition: Effective Strategies for Bias MitigationPoster441 citations
168. Google Landmarks Dataset v2 - A Large-Scale Benchmark for Instance-Level Recognition and RetrievalOral438 citations
169. Learning to Dress 3D People in Generative ClothingPoster435 citations
170. Cross-Modality Person Re-Identification With Shared-Specific Feature TransferPoster434 citations
171. Forward and Backward Information Retention for Accurate Binary Neural NetworksPoster431 citations
172. RMP-SNN: Residual Membrane Potential Neuron for Enabling Deeper High-Accuracy and Low-Latency Spiking Neural NetworkPoster430 citations
173. Action Genome: Actions As Compositions of Spatio-Temporal Scene GraphsPoster426 citations
174. Closed-Loop Matters: Dual Regression Networks for Single Image Super-ResolutionPoster425 citations
175. Towards Accurate Scene Text Recognition With Semantic Reasoning NetworksPoster424 citations
176. What's Hidden in a Randomly Weighted Neural Network?Poster424 citations
177. GHUM & GHUML: Generative 3D Human Shape and Articulated Pose ModelsOral423 citations
178. Watch Your Up-Convolution: CNN Based Generative Deep Neural Networks Are Failing to Reproduce Spectral DistributionsPoster422 citations
179. A U-Net Based Discriminator for Generative Adversarial NetworksPoster421 citations
180. UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational AutoencodersOral420 citations
181. Deep Snake for Real-Time Instance SegmentationOral415 citations
182. Semantic Drift Compensation for Class-Incremental LearningPoster413 citations
183. FineGym: A Hierarchical Video Dataset for Fine-Grained Action UnderstandingOral412 citations
184. Hi-CMD: Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-IdentificationPoster412 citations
185. Perceptual Quality Assessment of Smartphone PhotographyPoster412 citations
186. Dynamic Refinement Network for Oriented and Densely Packed Object DetectionOral411 citations
187. Dynamic Multiscale Graph Neural Networks for 3D Skeleton Based Human Motion PredictionOral410 citations
188. Universal Source-Free Domain AdaptationPoster410 citations
189. Single-View View Synthesis With Multiplane ImagesPoster408 citations
190. Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive LearningOral404 citations
191. Disentangling Physical Dynamics From Unknown Factors for Unsupervised Video PredictionPoster404 citations
192. Fine-Grained Video-Text Retrieval With Hierarchical Graph ReasoningPoster402 citations
193. Counterfactual Samples Synthesizing for Robust Visual Question AnsweringPoster401 citations
194. Central Similarity Quantization for Efficient Image and Video RetrievalPoster400 citations
195. From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture QualityPoster397 citations
196. MMTM: Multimodal Transfer Module for CNN FusionPoster397 citations
197. Cost Volume Pyramid Based Depth Inference for Multi-View StereoOral395 citations
198. Online Knowledge Distillation via Collaborative LearningOral395 citations
199. Global Texture Enhancement for Fake Face Detection in the WildPoster394 citations
200. Image Processing Using Multi-Code GAN PriorPoster394 citations
201. Memory Enhanced Global-Local Aggregation for Video Object DetectionPoster392 citations
202. Label Decoupling Framework for Salient Object DetectionPoster390 citations
203. JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object DetectionPoster389 citations
204. Object Relational Graph With Teacher-Recommended Learning for Video CaptioningPoster387 citations
205. Understanding Human Hands in Contact at Internet ScaleOral386 citations
206. Learning Depth-Guided Convolutions for Monocular 3D Object DetectionPoster384 citations
207. AD-Cluster: Augmented Discriminative Clustering for Domain Adaptive Person Re-IdentificationPoster383 citations
208. Deep Stereo Using Adaptive Thin Volume Representation With Uncertainty AwarenessOral383 citations
209. FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel DimensionsPoster383 citations
210. Reference-Based Sketch Image Colorization Using Augmented-Self Reference and Dense Semantic CorrespondencePoster382 citations
211. Scale-Space Flow for End-to-End Optimized Video CompressionPoster382 citations
212. Unsupervised Domain Adaptation via Structurally Regularized Deep ClusteringOral381 citations
213. ASLFeat: Learning Local Features of Accurate Shape and LocalizationPoster379 citations
214. Regularizing Class-Wise Predictions via Self-Knowledge DistillationPoster379 citations
215. ARCH: Animatable Reconstruction of Clothed HumansPoster378 citations
216. Exploring Categorical Regularization for Domain Adaptive Object DetectionPoster378 citations
217. Modeling the Background for Incremental Learning in Semantic SegmentationPoster378 citations
218. View-GCN: View-Based Graph Convolutional Network for 3D Shape AnalysisPoster378 citations
219. Adversarial Feature Hallucination Networks for Few-Shot LearningPoster375 citations
220. REVERIE: Remote Embodied Visual Referring Expression in Real Indoor EnvironmentsOral374 citations
221. Weakly-Supervised Semantic Segmentation via Sub-Category ExplorationPoster373 citations
222. Hyperbolic Image EmbeddingsOral372 citations
223. Hierarchical Clustering With Hard-Batch Triplet Loss for Person Re-IdentificationPoster368 citations
224. Unsupervised Learning of Probably Symmetric Deformable 3D Objects From Images in the WildOral367 citations
225. Squeeze-and-Attention Networks for Semantic SegmentationPoster365 citations
226. Neural Blind Deconvolution Using Deep PriorsPoster363 citations
227. D3S - A Discriminative Single Shot Segmentation TrackerPoster361 citations
228. FaceScape: A Large-Scale High Quality 3D Face Dataset and Detailed Riggable 3D Face PredictionPoster361 citations
229. Harmonizing Transferability and Discriminability for Adapting Object DetectorsPoster361 citations
230. Meta-Transfer Learning for Zero-Shot Super-ResolutionPoster361 citations
231. Learning Selective Self-Mutual Attention for RGB-D Saliency DetectionPoster359 citations
232. Attention Scaling for Crowd CountingPoster358 citations
233. Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition From a Domain Adaptation PerspectiveOral355 citations
234. Benchmarking Adversarial Robustness on Image ClassificationOral354 citations
235. Spatio-Temporal Graph for Video Captioning With Knowledge DistillationPoster354 citations
236. BSP-Net: Generating Compact Meshes via Binary Space PartitioningOral353 citations
237. ManiGAN: Text-Guided Image ManipulationPoster353 citations
238. Gradually Vanishing Bridge for Adversarial Domain AdaptationPoster352 citations
239. Overcoming Classifier Imbalance for Long-Tail Object Detection With Balanced Group SoftmaxOral351 citations
240. All in One Bad Weather Removal Using Architectural SearchPoster350 citations
241. DIST: Rendering Deep Implicit Signed Distance Function With Differentiable Sphere TracingPoster350 citations
242. 3D Photography Using Context-Aware Layered Depth InpaintingPoster349 citations
243. Neural Topological SLAM for Visual NavigationPoster349 citations
244. ImVoteNet: Boosting 3D Object Detection in Point Clouds With Image VotesPoster348 citations
245. Multi-Task Collaborative Network for Joint Referring Expression Comprehension and SegmentationOral348 citations
246. A Self-supervised Approach for Adversarial RobustnessOral346 citations
247. Clean-Label Backdoor Attacks on Video Recognition ModelsPoster346 citations
248. Unsupervised Person Re-Identification via Softened Similarity LearningPoster346 citations
249. HybridPose: 6D Object Pose Estimation Under Hybrid RepresentationsPoster345 citations
250. Spatially-Attentive Patch-Hierarchical Network for Adaptive Motion DeblurringPoster345 citations
251. TailorNet: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment StyleOral344 citations
252. TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training ModelOral344 citations
253. Feature-Metric Registration: A Fast Semi-Supervised Approach for Robust Point Cloud Registration Without CorrespondencesPoster343 citations
254. On Translation Invariance in CNNs: Convolutional Layers Can Exploit Absolute Spatial LocationPoster343 citations
255. MonoPair: Monocular 3D Object Detection Using Pairwise Spatial RelationshipsPoster342 citations
256. PPDM: Parallel Point Detection and Matching for Real-Time Human-Object Interaction DetectionPoster341 citations
257. Gated Channel Transformation for Visual RecognitionPoster340 citations
258. SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text RecognitionPoster340 citations
259. Learning Texture Invariant Representation for Domain Adaptation of Semantic SegmentationPoster339 citations
260. Visual Commonsense R-CNNPoster339 citations
261. Towards Photo-Realistic Virtual Try-On by Adaptively Generating-Preserving Image ContentPoster337 citations
262. Dense Regression Network for Video GroundingPoster336 citations
263. Weakly-Supervised Salient Object Detection via Scribble AnnotationsPoster335 citations
264. Hierarchical Conditional Relation Networks for Video Question AnsweringOral334 citations
265. Context Prior for Scene SegmentationPoster333 citations
266. Foreground-Aware Relation Network for Geospatial Object Segmentation in High Spatial Resolution Remote Sensing ImageryPoster333 citations
267. Adversarial Latent AutoencodersPoster332 citations
268. MAGSAC++, a Fast, Reliable and Accurate Robust EstimatorOral332 citations
269. FastDVDnet: Towards Real-Time Deep Video Denoising Without Flow EstimationOral330 citations
270. Single-Side Domain Generalization for Face Anti-SpoofingPoster330 citations
271. Conditional Gaussian Distribution Learning for Open Set RecognitionPoster329 citations
272. Data Uncertainty Learning in Face RecognitionPoster328 citations
273. FSS-1000: A 1000-Class Dataset for Few-Shot SegmentationPoster326 citations
274. Local-Global Video-Text Interactions for Temporal GroundingPoster325 citations
275. Point Cloud Completion by Skip-Attention Network With Hierarchical FoldingPoster325 citations
276. SpeedNet: Learning the Speediness in VideosOral322 citations
277. GPS-Net: Graph Property Sensing Network for Scene Graph GenerationOral321 citations
278. Improved Few-Shot Visual ClassificationPoster321 citations
279. Single-Stage Semantic Segmentation From Image LabelsPoster321 citations
280. Editing in Style: Uncovering the Local Semantics of GANsPoster320 citations
281. Listen to Look: Action Recognition by Previewing AudioPoster320 citations
282. Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-TrainingPoster320 citations
283. Few-Shot Video Classification via Temporal AlignmentPoster319 citations
284. High-Performance Long-Term Tracking With Meta-UpdaterOral319 citations
285. Cascaded Refinement Network for Point Cloud CompletionPoster318 citations
286. Self-Trained Deep Ordinal Regression for End-to-End Video Anomaly DetectionPoster318 citations
287. Incremental Few-Shot Object DetectionPoster316 citations
288. Grid-GCN for Fast and Scalable Point Cloud LearningPoster315 citations
289. MSG-GAN: Multi-Scale Gradients for Generative Adversarial NetworksPoster315 citations
290. Pose-Guided Visible Part Matching for Occluded Person ReIDPoster315 citations
291. Wavelet Integrated CNNs for Noise-Robust Image ClassificationPoster315 citations
292. Advancing High Fidelity Identity Swapping for Forgery DetectionOral314 citations
293. Distilling Knowledge From Graph Convolutional NetworksPoster314 citations
294. Mitigating Bias in Face Recognition Using Skewness-Aware Reinforcement LearningPoster314 citations
295. Context-Aware Attention Network for Image-Text RetrievalPoster313 citations
296. CARS: Continuous Evolution for Efficient Neural Architecture SearchPoster310 citations
297. Controllable Person Image Synthesis With Attribute-Decomposed GANOral309 citations
298. On the Uncertainty of Self-Supervised Monocular Depth EstimationPoster309 citations
299. Resolution Adaptive Networks for Efficient InferencePoster308 citations
300. Salience-Guided Cascaded Suppression Network for Person Re-IdentificationPoster307 citations
301. Single-Image HDR Reconstruction by Learning to Reverse the Camera PipelinePoster307 citations
302. Graph Structured Network for Image-Text MatchingPoster306 citations
303. Cross-Batch Memory for Embedding LearningOral304 citations
304. Predicting Semantic Map Representations From Images Using Pyramid Occupancy NetworksOral304 citations
305. Superpixel Segmentation With Fully Convolutional NetworksPoster304 citations
306. Cross-Domain Detection via Graph-Induced Prototype AlignmentOral302 citations
307. Learning Filter Pruning Criteria for Deep Convolutional Neural Networks AccelerationPoster301 citations
308. Old Is Gold: Redefining the Adversarially Learned One-Class Classifier Training ParadigmPoster301 citations
309. Towards Visually Explaining Variational AutoencodersOral301 citations
310. M2m: Imbalanced Classification via Major-to-Minor TranslationPoster300 citations
311. RoboTHOR: An Open Simulation-to-Real Embodied AI PlatformPoster300 citations
312. Fast Symmetric Diffeomorphic Image Registration with Convolutional Neural NetworksPoster299 citations
313. Fine-Grained Generalized Zero-Shot Learning via Dense Attribute-Based AttentionPoster299 citations
314. Learning Human-Object Interaction Detection Using Interaction PointsPoster297 citations
315. Noisier2Noise: Learning to Denoise From Unpaired Noisy DataPoster297 citations
316. AdaCoF: Adaptive Collaboration of Flows for Video Frame InterpolationPoster295 citations
317. EPOS: Estimating 6D Pose of Objects With SymmetriesPoster295 citations
318. Adversarial Robustness: From Self-Supervised Pre-Training to Fine-TuningPoster294 citations
319. GAN Compression: Efficient Architectures for Interactive Conditional GANsPoster294 citations
320. Inverse Rendering for Complex Indoor Scenes: Shape, Spatially-Varying Lighting and SVBRDF From a Single ImageOral294 citations
321. TBT: Targeted Neural Network Attack With Bit TrojanPoster293 citations
322. CvxNet: Learnable Convex DecompositionOral292 citations
323. OccuSeg: Occupancy-Aware 3D Instance SegmentationPoster292 citations
324. Self-Supervised Monocular Trained Depth Estimation Using Self-Attention and Discrete Disparity VolumePoster292 citations
325. CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local RefinementPoster289 citations
326. DeepLPF: Deep Local Parametric Filters for Image EnhancementPoster289 citations
327. Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic SegmentationPoster289 citations
328. Multi-Modal Domain Adaptation for Fine-Grained Action RecognitionOral288 citations
329. The Devil Is in the Details: Delving Into Unbiased Data Processing for Human Pose EstimationPoster288 citations
330. Deep Representation Learning on Long-Tailed Data: A Learnable Embedding Augmentation PerspectivePoster287 citations
331. Physically Realizable Adversarial Examples for LiDAR Object DetectionPoster287 citations
332. Say As You Wish: Fine-Grained Control of Image Caption Generation With Abstract Scene GraphsOral287 citations
333. Vision-Language Navigation With Self-Supervised Auxiliary Reasoning TasksOral287 citations
334. AdderNet: Do We Really Need Multiplications in Deep Learning?Oral286 citations
335. Group Sparsity: The Hinge Between Filter Pruning and Decomposition for Network CompressionPoster286 citations
336. Prime Sample Attention in Object DetectionPoster286 citations
337. DPGN: Distribution Propagation Graph Network for Few-Shot LearningPoster285 citations
338. Normalized and Geometry-Aware Self-Attention Network for Image CaptioningPoster284 citations
339. Adversarial Camouflage: Hiding Physical-World Attacks With Natural StylesPoster282 citations
340. Instance-Aware Image ColorizationPoster282 citations
341. A2dele: Adaptive and Attentive Depth Distiller for Efficient RGB-D Salient Object DetectionPoster281 citations
342. Deep Relational Reasoning Graph Network for Arbitrary Shape Text DetectionOral281 citations
343. NAS-FCOS: Fast Neural Architecture Search for Object DetectionPoster281 citations
344. Fast-MVSNet: Sparse-to-Dense Multi-View Stereo With Learned Propagation and Gauss-Newton RefinementPoster280 citations
345. Attention Mechanism Exploits Temporal Contexts: Real-Time 3D Human Pose ReconstructionOral279 citations
346. RetinaTrack: Online Single Stage Joint Detection and TrackingPoster279 citations
347. End-to-End Model-Free Reinforcement Learning for Urban Driving Using Implicit AffordancesPoster278 citations
348. Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes From a Single ImageOral278 citations
349. Convolution in the Cloud: Learning Deformable Kernels in 3D Graph Convolution Networks for Point Cloud AnalysisPoster277 citations
350. Effectively Unbiased FID and Inception Score and Where to Find ThemPoster277 citations
351. Universal Litmus Patterns: Revealing Backdoor Attacks in CNNsOral277 citations
352. Attention Convolutional Binary Neural Tree for Fine-Grained Visual CategorizationPoster276 citations
353. MaskFlownet: Asymmetric Feature Matching With Learnable Occlusion MaskOral276 citations
354. 3DRegNet: A Deep Neural Network for 3D Point RegistrationPoster275 citations
355. CRNet: Cross-Reference Networks for Few-Shot SegmentationPoster275 citations
356. A Physics-Based Noise Formation Model for Extreme Low-Light Raw DenoisingOral274 citations
357. How to Train Your Deep Multi-Object TrackerPoster274 citations
358. ContourNet: Taking a Further Step Toward Accurate Arbitrary-Shaped Scene Text DetectionPoster273 citations
359. VSGNet: Spatial Attention Network for Detecting Human Object Interactions Using Graph ConvolutionsPoster273 citations
360. Augment Your Batch: Improving Generalization Through Instance RepetitionPoster271 citations
361. Detection in Crowded Scenes: One Proposal, Multiple PredictionsOral271 citations
362. Orthogonal Convolutional Neural NetworksPoster271 citations
363. SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape OptimizationOral271 citations
364. Conditional Channel Gated Networks for Task-Aware Continual LearningOral270 citations
365. Cross-domain Object Detection through Coarse-to-Fine Feature AdaptationPoster270 citations
366. Learning for Video Compression With Hierarchical Quality and Recurrent EnhancementPoster270 citations
367. Video to Events: Recycling Video Datasets for Event CamerasPoster270 citations
368. PREDICT & CLUSTER: Unsupervised Skeleton Based Action RecognitionPoster268 citations
369. Bringing Old Photos Back to LifeOral267 citations
370. F-BRS: Rethinking Backpropagating Refinement for Interactive SegmentationOral267 citations
371. Multi-scale Domain-adversarial Multiple-instance CNN for Cancer Subtype Classification with Unannotated Histopathological ImagesOral267 citations
372. SGAS: Sequential Greedy Architecture SearchPoster267 citations
373. DeepCap: Monocular Human Performance Capture Using Weak SupervisionOral266 citations
374. Select, Supplement and Focus for RGB-D Saliency DetectionPoster266 citations
375. Spatial-Temporal Graph Convolutional Network for Video-Based Person Re-IdentificationPoster266 citations
376. LiDARsim: Realistic LiDAR Simulation by Leveraging the Real WorldOral265 citations
377. Actor-Transformers for Group Activity RecognitionPoster263 citations
378. HOPE-Net: A Graph-Based Model for Hand-Object Pose EstimationPoster263 citations
379. HVNet: Hybrid Voxel Network for LiDAR Based 3D Object DetectionPoster263 citations
380. Plug-and-Play Algorithms for Large-Scale Snapshot Compressive ImagingOral263 citations
381. End-to-End Pseudo-LiDAR for Image-Based 3D Object DetectionPoster262 citations
382. GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking With 2D-3D Multi-Feature LearningPoster262 citations
383. Learning 3D Semantic Scene Graphs From 3D Indoor ReconstructionsPoster262 citations
384. Instance-Aware, Context-Focused, and Memory-Efficient Weakly Supervised Object DetectionPoster261 citations
385. DoveNet: Deep Image Harmonization via Domain VerificationPoster260 citations
386. Weakly Supervised Semantic Point Cloud Segmentation: Towards 10x Fewer LabelsPoster260 citations
387. M-LVC: Multiple Frames Prediction for Learned Video CompressionPoster259 citations
388. Mapillary Street-Level Sequences: A Dataset for Lifelong Place RecognitionOral259 citations
389. Reusing Discriminators for Encoding: Towards Unsupervised Image-to-Image TranslationPoster259 citations
390. SpineNet: Learning Scale-Permuted Backbone for Recognition and LocalizationPoster259 citations
391. Transfer Learning From Synthetic to Real-Noise Denoising With Adaptive Instance NormalizationPoster259 citations
392. Enhanced Transport Distance for Unsupervised Domain AdaptationPoster257 citations
393. Monocular Real-Time Hand Shape and Motion Capture Using Multi-Modal DataPoster257 citations
394. CIAGAN: Conditional Identity Anonymization Generative Adversarial NetworksPoster255 citations
395. Online Deep Clustering for Unsupervised Representation LearningPoster255 citations
396. Parsing-Based View-Aware Embedding Network for Vehicle Re-IdentificationPoster255 citations
397. APQ: Joint Search for Network Architecture, Pruning and Quantization PolicyPoster253 citations
398. 3D-MPA: Multi-Proposal Aggregation for 3D Semantic Instance SegmentationPoster251 citations
399. Iterative Answer Prediction With Pointer-Augmented Multimodal Transformers for TextVQAOral251 citations
400. When2com: Multi-Agent Perception via Communication Graph GroupingPoster251 citations
401. DSGN: Deep Stereo Geometry Network for 3D Object DetectionPoster250 citations
402. TPNet: Trajectory Proposal Network for Motion PredictionPoster250 citations
403. Temporally Distributed Networks for Fast Video Semantic SegmentationPoster250 citations
404. UCTGAN: Diverse Image Inpainting Based on Unsupervised Cross-Space TranslationPoster250 citations
405. Deep Semantic Clustering by Partition Confidence MaximisationPoster248 citations
406. Learning Integral Objects With Intra-Class Discriminator for Weakly-Supervised Semantic SegmentationPoster248 citations
407. Single-Stage 6D Object Pose EstimationPoster247 citations
408. Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the WildOral247 citations
409. UniPose: Unified Human Pose Estimation in Single Images and VideosPoster246 citations
410. Boosting Few-Shot Learning With Adaptive Margin LossPoster245 citations
411. Category-Level Articulated Object Pose EstimationOral245 citations
412. Deep Spatial Gradient and Temporal Depth Learning for Face Anti-SpoofingOral245 citations
413. Block-Wisely Supervised Neural Architecture Search With Knowledge DistillationPoster244 citations
414. Label Distribution Learning on Auxiliary Label Space Graphs for Facial Expression RecognitionPoster244 citations
415. Cars Can't Fly Up in the Sky: Improving Urban-Scene Segmentation via Height-Driven Attention NetworksPoster242 citations
416. Background Matting: The World Is Your Green ScreenPoster241 citations
417. Dual Super-Resolution Learning for Semantic SegmentationOral241 citations
418. RL-CycleGAN: Reinforcement Learning Aware Simulation-to-RealOral241 citations
419. A Real-Time Cross-Modality Correlation Filtering Method for Referring Expression ComprehensionPoster240 citations
420. D2Det: Towards High Quality Object Detection and Instance SegmentationPoster240 citations
421. Generative-Discriminative Feature Representations for Open-Set RecognitionPoster240 citations
422. Graph Embedded Pose Clustering for Anomaly DetectionPoster238 citations
423. Agriculture-Vision: A Large Aerial Image Database for Agricultural Pattern AnalysisPoster237 citations
424. Evaluating Weakly Supervised Object Localization Methods RightPoster237 citations
425. MSeg: A Composite Dataset for Multi-Domain Semantic SegmentationPoster237 citations
426. Syn2Real Transfer Learning for Image Deraining Using Gaussian ProcessesOral236 citations
427. Tracking by Instance Detection: A Meta-Learning ApproachOral235 citations
428. Universal Physical Camouflage Attacks on Object DetectorsPoster235 citations
429. Cross-Domain Face Presentation Attack Detection via Multi-Domain Disentangled Representation LearningPoster234 citations
430. Deep Kinematics Analysis for Monocular 3D Human Pose EstimationPoster233 citations
431. Distortion Agnostic Deep WatermarkingPoster233 citations
432. SER-FIQ: Unsupervised Estimation of Face Image Quality Based on Stochastic Embedding RobustnessPoster232 citations
433. Towards Efficient Model Compression via Learned Global RankingOral232 citations
434. Deep Image Spatial Transformation for Person Image GenerationPoster231 citations
435. Music Gesture for Visual Sound SeparationPoster231 citations
436. PointAugment: An Auto-Augmentation Framework for Point Cloud ClassificationOral230 citations
437. BiFuse: Monocular 360 Depth Estimation via Bi-Projection FusionPoster229 citations
438. MLCVNet: Multi-Level Context VoteNet for 3D Object DetectionPoster229 citations
439. MineGAN: Effective Knowledge Transfer From GANs to Target Domains With Few ImagesPoster229 citations
440. GLU-Net: Global-Local Universal Network for Dense Flow and CorrespondencesOral228 citations
441. MAST: A Memory-Augmented Self-Supervised TrackerPoster227 citations
442. Satellite Image Time Series Classification With Pixel-Set Encoders and Temporal Self-AttentionOral227 citations
443. Spatial Pyramid Based Graph Reasoning for Semantic SegmentationPoster227 citations
444. Cascaded Deep Monocular 3D Human Pose Estimation With Evolutionary Training DataOral226 citations
445. Instance Credibility Inference for Few-Shot LearningPoster226 citations
446. SampleNet: Differentiable Point Cloud SamplingOral226 citations
447. Distilling Image Dehazing With Heterogeneous Task ImitationPoster225 citations
448. Referring Image Segmentation via Cross-Modal Progressive ComprehensionPoster225 citations
449. DMCP: Differentiable Markov Channel Pruning for Neural NetworksOral224 citations
450. xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic SegmentationPoster224 citations
451. Epipolar TransformersPoster223 citations
452. Rethinking Depthwise Separable Convolutions: How Intra-Kernel Correlations Lead to Improved MobileNetsPoster223 citations
453. PnPNet: End-to-End Perception and Prediction With Tracking in the LoopPoster221 citations
454. Syntax-Aware Action Targeting for Video CaptioningPoster221 citations
455. CentripetalNet: Pursuing High-Quality Keypoint Pairs for Object DetectionPoster220 citations
456. Deep Face Super-Resolution With Iterative Collaboration Between Attentive Recovery and Landmark EstimationPoster220 citations
457. Learning Multiview 3D Point Cloud RegistrationPoster220 citations
458. QEBA: Query-Efficient Boundary-Based Blackbox AttackPoster220 citations
459. Video Super-Resolution With Temporal Group AttentionPoster220 citations
460. Learning Dynamic Routing for Semantic SegmentationOral219 citations
461. Recursive Social Behavior Graph for Trajectory PredictionPoster219 citations
462. Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-ResolutionPoster219 citations
463. Learning Canonical Shape Space for Category-Level 6D Object Pose and Size EstimationPoster218 citations
464. PolyTransform: Deep Polygon Transformer for Instance SegmentationPoster218 citations
465. Something-Else: Compositional Action Recognition With Spatial-Temporal Interaction NetworksPoster218 citations
466. Towards Unified INT8 Training for Convolutional Neural NetworkPoster218 citations
467. Detail-recovery Image Deraining via Context Aggregation NetworksPoster217 citations
468. Leveraging Photometric Consistency Over Time for Sparsely Supervised Hand-Object ReconstructionPoster217 citations
469. Context Aware Graph Convolution for Skeleton-Based Action RecognitionPoster216 citations
470. Image Search With Text Feedback by Visiolinguistic Attention LearningPoster216 citations
471. OctSqueeze: Octree-Structured Entropy Model for LiDAR CompressionOral216 citations
472. Classifying, Segmenting, and Tracking Object Instances in Video with Mask PropagationOral215 citations
473. Predicting Lymph Node Metastasis Using Histopathological Images Based on Multiple Instance Learning With Deep Graph ConvolutionPoster215 citations
474. Towards Better Generalization: Joint Depth-Pose Learning Without PoseNetPoster215 citations
475. Train in Germany, Test in the USA: Making 3D Object Detectors GeneralizePoster215 citations
476. Structure-Guided Ranking Loss for Single Image Depth PredictionPoster214 citations
477. Attention-Guided Hierarchical Structure Aggregation for Image MattingPoster213 citations
478. Incremental Learning in Online ScenarioPoster213 citations
479. Learning by Analogy: Reliable Supervision From Transformations for Unsupervised Optical Flow EstimationPoster213 citations
480. Where Am I Looking At? Joint Location and Orientation Estimation by Cross-View MatchingPoster213 citations
481. Deep Optics for Single-Shot High-Dynamic-Range ImagingOral210 citations
482. Episode-Based Prototype Generating Network for Zero-Shot LearningPoster210 citations
483. Video Playback Rate Perception for Self-Supervised Spatio-Temporal Representation LearningPoster210 citations
484. When NAS Meets Robustness: In Search of Robust Architectures Against Adversarial AttacksPoster210 citations
485. Coherent Reconstruction of Multiple Humans From a Single ImagePoster208 citations
486. DaST: Data-Free Substitute Training for Adversarial AttacksOral208 citations
487. Adaptive Dilated Network With Self-Correction Supervision for CountingPoster207 citations
488. Gate-Shift Networks for Video Action RecognitionPoster207 citations
489. Video Panoptic SegmentationOral207 citations
490. Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New StrategyPoster206 citations
491. Stochastic Classifiers for Unsupervised Domain AdaptationPoster205 citations
492. iTAML: An Incremental Task-Agnostic Meta-learning ApproachPoster205 citations
493. MotionNet: Joint Perception and Motion Prediction for Autonomous Driving Based on Bird's Eye View MapsPoster204 citations
494. Object-Occluded Human Shape and Pose Estimation From a Single Color ImageOral204 citations
495. Deep Geometric Functional Maps: Robust Feature Learning for Shape CorrespondenceOral203 citations
496. NMS by Representative Region: Towards Crowded Pedestrian Detection by Proposal PairingPoster202 citations
497. Unpaired Image Super-Resolution Using Pseudo-SupervisionOral202 citations
498. AvatarMe: Realistically Renderable 3D Facial Reconstruction "In-the-Wild"Poster201 citations
499. Domain-Aware Visual Bias Eliminating for Generalized Zero-Shot LearningPoster201 citations
500. GanHand: Predicting Human Grasp Affordances in Multi-Object ScenesOral201 citations
501. Interactive Image Segmentation With First Click AttentionPoster201 citations
502. Meta-Learning of Neural Architectures for Few-Shot LearningOral201 citations
503. Dynamic Convolutions: Exploiting Spatial Sparsity for Faster InferencePoster200 citations
504. The Garden of Forking Paths: Towards Multi-Future Trajectory PredictionPoster200 citations
505. Bi-Directional Relationship Inferring Network for Referring Image SegmentationPoster199 citations
506. P2B: Point-to-Box Network for 3D Object Tracking in Point CloudsOral199 citations
507. DuDoRNet: Learning a Dual-Domain Recurrent Network for Fast MRI Reconstruction With Deep T1 PriorPoster197 citations
508. Towards Universal Representation Learning for Deep Face RecognitionPoster197 citations
509. ViewAL: Active Learning With Viewpoint Entropy for Semantic SegmentationPoster197 citations
510. A Hierarchical Graph Network for 3D Object Detection on Point CloudsPoster196 citations
511. ACNe: Attentive Context Normalization for Robust Permutation-Equivariant LearningPoster196 citations
512. LUVLi Face Alignment: Estimating Landmarks' Location, Uncertainty, and Visibility LikelihoodPoster196 citations
513. Weakly-Supervised Action Localization by Generative Attention ModelingPoster196 citations
514. Spherical Space Domain Adaptation With Robust Pseudo-Label LossPoster195 citations
515. SCATTER: Selective Context Attentional Scene Text RecognizerPoster194 citations
516. Cascaded Deep Video Deblurring Using Temporal Sharpness PriorPoster193 citations
517. Low-Rank Compression of Neural Nets: Learning the Rank of Each LayerPoster193 citations
518. Learning Dynamic Relationships for 3D Human Motion PredictionPoster192 citations
519. Learning Video Object Segmentation From Unlabeled VideosPoster192 citations
520. Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene GenerationPoster192 citations
521. Context-Aware Human Motion PredictionPoster191 citations
522. A Multi-Task Mean Teacher for Semi-Supervised Shadow DetectionPoster190 citations
523. PQ-NET: A Generative Part Seq2Seq Network for 3D ShapesPoster190 citations
524. PaStaNet: Toward Human Activity Knowledge EnginePoster190 citations
525. Learning Meta Face Recognition in Unseen DomainsOral189 citations
526. Learning Multi-Granular Hypergraphs for Video-Based Person Re-IdentificationPoster189 citations
527. GreedyNAS: Towards Fast One-Shot NAS With Greedy SupernetPoster188 citations
528. Light Field Spatial Super-Resolution via Deep Combinatorial Geometry Embedding and Structural Consistency RegularizationPoster188 citations
529. PhysGAN: Generating Physical-World-Resilient Adversarial Examples for Autonomous DrivingPoster188 citations
530. FPConv: Learning Local Flattening for Point ConvolutionPoster187 citations
531. Robust Learning Through Cross-Task ConsistencyOral187 citations
532. Towards Causal VQA: Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic EditingPoster187 citations
533. Single Image Reflection Removal Through Cascaded RefinementPoster185 citations
534. DSNAS: Direct Neural Architecture Search Without Parameter RetrainingPoster184 citations
535. Learning Event-Based Motion DeblurringPoster184 citations
536. LiDAR-Based Online 3D Video Object Detection With Graph-Based Message Passing and Spatiotemporal Transformer AttentionPoster184 citations
537. Making Better Mistakes: Leveraging Class Hierarchies With Deep NetworksPoster184 citations
538. Towards Large Yet Imperceptible Adversarial Image Perturbations With Perceptual Color DistancePoster184 citations
539. Boosting the Transferability of Adversarial Samples via AttentionPoster182 citations
540. C2FNAS: Coarse-to-Fine Neural Architecture Search for 3D Medical Image SegmentationPoster182 citations
541. Interpretable and Accurate Fine-grained Recognition via Region GroupingOral182 citations
542. Just Go With the Flow: Self-Supervised Scene Flow EstimationOral182 citations
543. Rethinking Zero-Shot Video Classification: End-to-End Training for Realistic ApplicationsPoster182 citations
544. End-to-End Adversarial-Attention Network for Multi-Modal ClusteringPoster181 citations
545. PSGAN: Pose and Expression Robust Spatial-Aware GAN for Customizable Makeup TransferOral181 citations
546. Reliable Weighted Optimal Transport for Unsupervised Domain AdaptationPoster181 citations
547. Few Sample Knowledge Distillation for Efficient Network CompressionPoster180 citations
548. Towards Unsupervised Learning of Generative Models for 3D Controllable Image SynthesisPoster180 citations
549. Unsupervised Multi-Modal Image Registration via Geometry Preserving Image-to-Image TranslationPoster180 citations
550. Benchmarking the Robustness of Semantic Segmentation ModelsPoster179 citations
551. More Grounded Image Captioning by Distilling Image-Text Matching ModelPoster179 citations
552. ScrabbleGAN: Semi-Supervised Varying Length Handwritten Text GenerationPoster179 citations
553. Detecting Adversarial Samples Using Influence Functions and Nearest NeighborsPoster178 citations
554. Hyperbolic Visual Embedding Learning for Zero-Shot RecognitionPoster178 citations
555. Improving Action Segmentation via Graph-Based Temporal ReasoningPoster178 citations
556. Multi-Path Region Mining for Weakly Supervised 3D Semantic Segmentation on Point CloudsPoster178 citations
557. EmotiCon: Context-Aware Multimodal Emotion Recognition Using Frege's PrinciplePoster177 citations
558. Filter Response Normalization Layer: Eliminating Batch Dependence in the Training of Deep Neural NetworksOral177 citations
559. Heterogeneous Knowledge Distillation Using Information Flow ModelingPoster177 citations
560. Self-Supervised Scene De-OcclusionOral177 citations
561. Fast Sparse ConvNetsPoster176 citations
562. SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D ScansPoster176 citations
563. Detailed 2D-3D Joint Representation for Human-Object InteractionPoster175 citations
564. Video Modeling With Correlation NetworksPoster175 citations
565. Distilling Effective Supervision From Severe Label NoisePoster174 citations
566. What Can Be Transferred: Unsupervised Domain Adaptation for Endoscopic Lesions SegmentationPoster173 citations
567. Adaptive Hierarchical Down-Sampling for Point Cloud ClassificationPoster172 citations
568. Novel View Synthesis of Dynamic Scenes With Globally Coherent Depths From a Monocular CameraPoster172 citations
569. Two Causal Principles for Improving Visual DialogPoster172 citations
570. Generating 3D People in Scenes Without PeopleOral171 citations
571. Uncertainty-Aware Score Distribution Learning for Action Quality AssessmentOral171 citations
572. LatentFusion: End-to-End Differentiable Reconstruction and Rendering for Unseen Object Pose EstimationPoster170 citations
573. Can Weight Sharing Outperform Random Architecture Search? An Investigation With TuNASPoster169 citations
574. Deep Polarization Cues for Transparent Object SegmentationOral169 citations
575. Joint Semantic Segmentation and Boundary Detection Using Iterative Pyramid ContextsPoster169 citations
576. SESS: Self-Ensembling Semi-Supervised 3D Object DetectionOral169 citations
577. Structure Boundary Preserving Segmentation for Medical Image With Ambiguous BoundaryPoster169 citations
578. Generalized Zero-Shot Learning via Over-Complete DistributionPoster168 citations
579. Learning Fast and Robust Target Models for Video Object SegmentationOral168 citations
580. MiLeNAS: Efficient Neural Architecture Search via Mixed-Level ReformulationPoster168 citations
581. Reverse Perspective Network for Perspective-Aware Object CountingPoster168 citations
582. ClusterFit: Improving Generalization of Visual RepresentationsPoster167 citations
583. Evolving Losses for Unsupervised Video Representation LearningOral167 citations
584. Explaining Knowledge Distillation by Quantifying the KnowledgePoster166 citations
585. Neural Cages for Detail-Preserving 3D DeformationsOral166 citations
586. Neural Network Pruning With Residual-Connections and Limited-DataOral166 citations
587. Understanding Adversarial Examples From the Mutual Influence of Images and PerturbationsPoster166 citations
588. Deep Homography Estimation for Dynamic ScenesPoster165 citations
589. Densely Connected Search Space for More Flexible Neural Architecture SearchPoster165 citations
590. Don't Hit Me! Glass Detection in Real-World ScenesPoster165 citations
591. FocalMix: Semi-Supervised Learning for 3D Medical Image DetectionPoster165 citations
592. Context R-CNN: Long Term Temporal Context for Per-Camera Object DetectionPoster164 citations
593. Correlation-Guided Attention for Corner Detection Based Visual TrackingPoster164 citations
594. Transferring Cross-Domain Knowledge for Video Sign Language RecognitionOral164 citations
595. Unified Dynamic Convolutional Network for Super-Resolution With Variational DegradationsPoster164 citations
596. Auto-Encoding Twin-Bottleneck HashingPoster163 citations
597. DOA-GAN: Dual-Order Attentive Generative Adversarial Network for Image Copy-Move Forgery Detection and LocalizationPoster163 citations
598. Norm-Aware Embedding for Efficient Person SearchPoster163 citations
599. Robust Object Detection Under Occlusion With Context-Aware CompositionalNetsPoster163 citations
600. Seeing Around Street Corners: Non-Line-of-Sight Detection and Tracking In-the-Wild Using Doppler RadarPoster163 citations
601. Through Fog High-Resolution Imaging Using Millimeter Wave RadarPoster163 citations
602. Detecting Attended Visual Targets in VideoPoster161 citations
603. Dynamic Graph Message Passing NetworksOral161 citations
604. Sketchformer: Transformer-Based Representation for Sketched StructurePoster161 citations
605. Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point CloudsPoster160 citations
606. SDC-Depth: Semantic Divide-and-Conquer Network for Monocular Depth EstimationPoster160 citations
607. State-Relabeling Adversarial Active LearningOral160 citations
608. Counting Out Time: Class Agnostic Video Repetition Counting in the WildPoster159 citations
609. TransMatch: A Transfer-Learning Scheme for Semi-Supervised Few-Shot LearningPoster159 citations
610. AdaBits: Neural Network Quantization With Adaptive Bit-WidthsPoster158 citations
611. Interactive Object Segmentation With Inside-Outside GuidanceOral158 citations
612. ROAM: Recurrently Optimizing Tracking ModelPoster158 citations
613. Counterfactual Vision and Language LearningOral157 citations
614. Learning From Synthetic AnimalsOral157 citations
615. Neural Head Reenactment with Latent Pose DescriptorsPoster157 citations
616. Combining Detection and Tracking for Human Pose Estimation in VideosOral156 citations
617. Efficient Adversarial Training With Transferable Adversarial ExamplesPoster156 citations
618. Inter-Region Affinity Distillation for Road Marking SegmentationPoster156 citations
619. Phase Consistent Ecological Domain AdaptationPoster156 citations
620. Semantic Correspondence as an Optimal Transport ProblemPoster156 citations
621. Towards Inheritable Models for Open-Set Domain AdaptationOral156 citations
622. 3D Sketch-Aware Semantic Scene Completion via Semi-Supervised Structure PriorPoster155 citations
623. A Local-to-Global Approach to Multi-Modal Movie Scene SegmentationPoster155 citations
624. Anisotropic Convolutional Networks for 3D Semantic Scene CompletionPoster155 citations
625. Learning to Cartoonize Using White-Box Cartoon RepresentationsPoster155 citations
626. Deep White-Balance EditingOral154 citations
627. Stylization-Based Architecture for Fast Deep Exemplar ColorizationPoster154 citations
628. Towards Transferable Targeted AttackPoster154 citations
629. MANTRA: Memory Augmented Networks for Multiple Trajectory PredictionPoster153 citations
630. Rethinking Computer-Aided Tuberculosis DiagnosisOral153 citations
631. A Transductive Approach for Video Object SegmentationPoster152 citations
632. ColorFool: Semantic Adversarial ColorizationPoster152 citations
633. Ego-Topo: Environment Affordances From Egocentric VideoOral152 citations
634. Erasing Integrated Learning: A Simple Yet Effective Approach for Weakly Supervised Object LocalizationOral152 citations
635. GeoDA: A Geometric Framework for Black-Box Adversarial AttacksPoster152 citations
636. Hierarchical Scene Coordinate Classification and Regression for Visual LocalizationPoster152 citations
637. Towards High-Fidelity 3D Face Reconstruction From In-the-Wild Images Using Graph Convolutional NetworksPoster152 citations
638. Adversarial Vertex Mixup: Toward Better Adversarially Robust GeneralizationOral151 citations
639. Creating Something From Nothing: Unsupervised Knowledge Distillation for Cross-Modal HashingPoster151 citations
640. EcoNAS: Finding Proxies for Economical Neural Architecture SearchPoster151 citations
641. Guided Variational Autoencoder for Disentanglement LearningPoster151 citations
642. Rethinking Differentiable Search for Mixed-Precision Neural NetworksPoster151 citations
643. SketchyCOCO: Image Generation From Freehand Scene SketchesOral151 citations
644. Symmetry and Group in Attribute-Object CompositionsPoster151 citations
645. What You See is What You Get: Exploiting Visibility for 3D Object DetectionOral151 citations
646. How Useful Is Self-Supervised Pretraining for Visual Tasks?Poster150 citations
647. Multi-Modal Graph Neural Network for Joint Reasoning on Vision and Scene TextPoster150 citations
648. TITAN: Future Forecast Using Action PriorsOral150 citations
649. The Edge of Depth: Explicit Constraints Between Segmentation and DepthPoster150 citations
650. Weakly-Supervised 3D Human Pose Learning via Multi-View Images in the WildPoster150 citations
651. Action Segmentation With Joint Self-Supervised Temporal Domain AdaptationPoster149 citations
652. Cross-Modal Pattern-Propagation for RGB-T TrackingPoster149 citations
653. State-Aware Tracker for Real-Time Video Object SegmentationPoster149 citations
654. A Stochastic Conditioning Scheme for Diverse Human Motion PredictionPoster148 citations
655. Rotate-and-Render: Unsupervised Photorealistic Face Rotation From Single-View ImagesPoster148 citations
656. Scale-Equalizing Pyramid Convolution for Object DetectionPoster148 citations
657. There and Back Again: Revisiting Backpropagation Saliency MethodsPoster148 citations
658. Explainable Object-Induced Action Decision for Autonomous VehiclesPoster147 citations
659. Lightweight Multi-View 3D Pose Estimation Through Camera-Disentangled RepresentationPoster147 citations
660. Mask Encoding for Single Shot Instance SegmentationPoster147 citations
661. Open Compound Domain AdaptationOral147 citations
662. Uncertainty-Aware CNNs for Depth Completion: Uncertainty from Beginning to EndPoster147 citations
663. Semantic Image Manipulation Using Scene GraphsPoster146 citations
664. Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity EstimationPoster145 citations
665. RiFeGAN: Rich Feature Generation for Text-to-Image Synthesis From Prior KnowledgePoster145 citations
666. End-to-End Learning Local Multi-View Descriptors for 3D Point CloudsPoster144 citations
667. Supervised Raw Video Denoising With a Benchmark Dataset on Dynamic ScenesPoster142 citations
668. Cascaded Human-Object Interaction RecognitionPoster141 citations
669. Don't Judge an Object by Its Context: Learning to Overcome Contextual BiasOral141 citations
670. A Unified Object Motion and Affinity Model for Online Multi-Object TrackingPoster139 citations
671. Deep Distance Transform for Tubular Structure Segmentation in CT ScansOral139 citations
672. Defending Against Model Stealing Attacks With Adaptive MisinformationPoster139 citations
673. SegGCN: Efficient 3D Point Cloud Segmentation With Fuzzy Spherical KernelPoster139 citations
674. TCTS: A Task-Consistent Two-Stage Framework for Person SearchPoster139 citations
675. Learning Physics-Guided Face Relighting Under Directional LightOral138 citations
676. Learning to Simulate Dynamic Environments With GameGANPoster138 citations
677. Multi-Granularity Reference-Aided Attentive Feature Aggregation for Video-Based Person Re-IdentificationPoster138 citations
678. Multimodal Categorization of Crisis Events in Social MediaPoster138 citations
679. DNU: Deep Non-Local Unrolling for Computational Spectral ImagingPoster137 citations
680. KeyPose: Multi-View 3D Labeling and Keypoint Estimation for Transparent ObjectsPoster137 citations
681. An Efficient PointLSTM for Point Clouds Based Gesture RecognitionPoster136 citations
682. Gait Recognition via Semi-supervised Disentangled Representation Learning to Identity and Covariate FeaturesPoster136 citations
683. GrappaNet: Combining Parallel Imaging With Deep Learning for Multi-Coil MRI ReconstructionPoster136 citations
684. Hierarchical Human Parsing With Typed Part-Relation ReasoningPoster136 citations
685. Hit-Detector: Hierarchical Trinity Architecture Search for Object DetectionPoster136 citations
686. Holistically-Attracted Wireframe ParsingPoster136 citations
687. Joint Demosaicing and Denoising With Self GuidancePoster136 citations
688. Learning to Transfer Texture From Clothing Images to 3D HumansPoster136 citations
689. Predicting Goal-Directed Human Attention Using Inverse Reinforcement LearningOral136 citations
690. S3VAE: Self-Supervised Sequential VAE for Representation Disentanglement and Data GenerationPoster136 citations
691. Sketch Less for More: On-the-Fly Fine-Grained Sketch-Based Image RetrievalOral135 citations
692. Collaborative Distillation for Ultra-Resolution Universal Style TransferPoster134 citations
693. Exploring Spatial-Temporal Multi-Frequency Analysis for High-Fidelity and Temporal-Consistency Video PredictionPoster134 citations
694. FReeNet: Multi-Identity Face ReenactmentPoster134 citations
695. Where Does It Exist: Spatio-Temporal Video Grounding for Multi-Form SentencesPoster134 citations
696. Deep Residual Flow for Out of Distribution DetectionPoster133 citations
697. Few-Shot Open-Set Recognition Using Meta-LearningPoster133 citations
698. Flow Contrastive Estimation of Energy-Based ModelsOral133 citations
699. G2L-Net: Global to Local Network for Real-Time 6D Pose Estimation With Embedding Vector FeaturesPoster133 citations
700. Self-Supervised Monocular Scene Flow EstimationOral133 citations
701. Unsupervised Learning for Intrinsic Image Decomposition From a Single ImagePoster133 citations
702. Cascade EF-GAN: Progressive Facial Expression Editing With Local FocusesOral132 citations
703. Diverse Image Generation via Self-Conditioned GANsPoster132 citations
704. Joint 3D Instance Segmentation and Object Detection for Autonomous DrivingPoster132 citations
705. Learning Representations by Predicting Bags of Visual WordsPoster132 citations
706. Polarized Reflection Removal With Perfect Alignment in the WildPoster132 citations
707. Learning the Redundancy-Free Features for Generalized Zero-Shot Object RecognitionPoster131 citations
708. Orderless Recurrent Models for Multi-Label ClassificationPoster131 citations
709. Tangent Images for Mitigating Spherical DistortionPoster131 citations
710. Three-Dimensional Reconstruction of Human InteractionsPoster131 citations
711. DualSDF: Semantic Shape Manipulation Using a Two-Level RepresentationPoster130 citations
712. Iteratively-Refined Interactive 3D Medical Image Segmentation With Multi-Agent Reinforcement LearningPoster130 citations
713. LG-GAN: Label Guided Adversarial Network for Flexible Targeted Attack of Point Cloud Based Deep NetworksPoster130 citations
714. Learning Individual Speaking Styles for Accurate Lip to Speech SynthesisPoster130 citations
715. Learning Unsupervised Hierarchical Part Decomposition of 3D Objects From a Single RGB ImagePoster130 citations
716. PhraseCut: Language-Based Image Segmentation in the WildPoster130 citations
717. Unsupervised Adaptation Learning for Hyperspectral Imagery Super-ResolutionPoster130 citations
718. Enhanced Blind Face Restoration With Multi-Exemplar Images and Adaptive Spatial Feature FusionOral129 citations
719. GroupFace: Learning Latent Groups and Constructing Group-Based Representations for Face RecognitionPoster129 citations
720. SpSequenceNet: Semantic Segmentation Network on 4D Point CloudsPoster129 citations
721. Space-Time-Aware Multi-Resolution Video EnhancementPoster129 citations
722. End-to-End Learnable Geometric Vision by Backpropagating PnP OptimizationPoster128 citations
723. Total Deep Variation for Linear Inverse ProblemsOral128 citations
724. Adaptive Graph Convolutional Network With Attention Graph Clustering for Co-Saliency DetectionPoster127 citations
725. Diversified Arbitrary Style Transfer via Deep Feature PerturbationPoster127 citations
726. Learning Rank-1 Diffractive Optics for Single-Shot High Dynamic Range ImagingOral127 citations
727. Oops! Predicting Unintentional Action in VideoPoster127 citations
728. 3DV: 3D Dynamic Voxel for Action Recognition in Depth VideoPoster126 citations
729. Learning From Noisy Anchors for One-Stage Object DetectionPoster126 citations
730. On the General Value of Evidence, and Bilingual Scene-Text Visual Question AnsweringPoster126 citations
731. Unsupervised Representation Learning for Gaze EstimationPoster126 citations
732. A Shared Multi-Attention Framework for Multi-Label Zero-Shot LearningOral125 citations
733. Autolabeling 3D Objects With Differentiable Rendering of SDF Shape PriorsOral125 citations
734. Discriminative Multi-Modality Speech RecognitionPoster125 citations
735. Learning to Forget for Meta-LearningPoster125 citations
736. Multiple Anchor Learning for Visual Object DetectionPoster125 citations
737. SmallBigNet: Integrating Core and Contextual Views for Video ClassificationPoster125 citations
738. SurfelGAN: Synthesizing Realistic Sensor Data for Autonomous DrivingOral125 citations
739. 3D Human Mesh Regression With Dense CorrespondencePoster124 citations
740. EventCap: Monocular 3D Capture of High-Speed Human Motions Using an Event CameraOral124 citations
741. Learning Longterm Representations for Person Re-Identification Using Radio SignalsPoster124 citations
742. Prior Guided GAN Based Semantic InpaintingPoster124 citations
743. Transform and Tell: Entity-Aware News Image CaptioningPoster124 citations
744. A Multigrid Method for Efficiently Training Video ModelsOral123 citations
745. Attention-Aware Multi-View StereoPoster123 citations
746. ClusterVO: Clustering Moving Instances and Estimating Visual Odometry for Self and SurroundingsPoster123 citations
747. Compressed Volumetric Heatmaps for Multi-Person 3D Pose EstimationPoster123 citations
748. EventSR: From Asynchronous Events to Image Reconstruction, Restoration, and Super-Resolution via End-to-End Adversarial LearningPoster123 citations
749. Multi-View Neural Human RenderingPoster123 citations
750. Collaborative Motion Prediction via Neural Motion Message PassingOral122 citations
751. Image Demoireing with Learnable Bandpass FiltersPoster122 citations
752. Learning Formation of Physically-Based Face AttributesPoster122 citations
753. Multi-Path Learning for Object Pose Estimation Across DomainsPoster122 citations
754. Efficient Dynamic Scene Deblurring Using Spatially Variant Deconvolution Network With Optical Flow Guided TrainingPoster121 citations
755. Optimizing Rank-Based Metrics With Blackbox DifferentiationOral121 citations
756. Unsupervised Domain Adaptation With Hierarchical Gradient SynchronizationPoster121 citations
757. Compositional Convolutional Neural Networks: A Deep Architecture With Innate Robustness to Partial OcclusionPoster120 citations
758. Graph-Guided Architecture Search for Real-Time Semantic SegmentationPoster120 citations
759. Hypergraph Attention Networks for Multimodal LearningPoster120 citations
760. Leveraging 2D Data to Learn Textured 3D Mesh GenerationOral120 citations
761. The Knowledge Within: Methods for Data-Free Model CompressionPoster120 citations
762. Instance Guided Proposal Network for Person SearchOral119 citations
763. Lighthouse: Predicting Lighting Volumes for Spatially-Coherent IlluminationPoster119 citations
764. MoreFusion: Multi-object Reasoning for 6D Pose Estimation from Volumetric FusionPoster119 citations
765. Rethinking the Route Towards Weakly Supervised Object LocalizationPoster119 citations
766. Semi-Supervised Semantic Image Segmentation With Self-Correcting NetworksPoster119 citations
767. Warping Residual Based Image Stitching for Large ParallaxPoster119 citations
768. OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfoldPoster118 citations
769. Attentive Weights Generation for Few Shot Learning via Information MaximizationPoster117 citations
770. Cross-Domain Semantic Segmentation via Domain-Invariant Interactive Relation TransferPoster117 citations
771. Future Video Synthesis With Object Motion PredictionPoster117 citations
772. Image Based Virtual Try-On Network From Unpaired DataOral117 citations
773. Progressive Relation Learning for Group Activity RecognitionPoster117 citations
774. VecRoad: Point-Based Iterative Graph Exploration for Road Graphs ExtractionPoster117 citations
775. Learn to Augment: Joint Data Augmentation and Network Optimization for Text RecognitionPoster116 citations
776. Learning to Cluster Faces via Confidence and Connectivity EstimationPoster116 citations
777. Associate-3Ddet: Perceptual-to-Conceptual Association for 3D Point Cloud Object DetectionPoster115 citations
778. Cross-View Tracking for Multi-Human 3D Pose Estimation at Over 100 FPSPoster115 citations
779. Robust Reference-Based Super-Resolution With Similarity-Aware Deformable ConvolutionPoster115 citations
780. Semantically Multi-Modal Image SynthesisPoster115 citations
781. Smooth Shells: Multi-Scale Shape Registration With Functional MapsOral115 citations
782. AdversarialNAS: Adversarial Neural Architecture Search for GANsPoster114 citations
783. High-Resolution Daytime Translation Without Domain LabelsOral114 citations
784. Adaptive Fractional Dilated Convolution Network for Image Aesthetics AssessmentPoster113 citations
785. Articulation-Aware Canonical Surface MappingPoster113 citations
786. Boosting Semantic Human Matting With Coarse AnnotationsOral113 citations
787. C-Flow: Conditional Generative Flow Models for Images and 3D Point CloudsPoster113 citations
788. Synthetic Learning: Learn From Distributed Asynchronized Discriminator GAN Without Sharing Medical Image DataPoster113 citations
789. Universal Weighting Metric Learning for Cross-Modal MatchingPoster113 citations
790. You2Me: Inferring Body Pose in Egocentric Video via First and Second Person InteractionsOral113 citations
791. A Novel Recurrent Encoder-Decoder Structure for Large-Scale Multi-View Stereo Reconstruction From an Open Aerial DatasetPoster112 citations
792. FALCON: A Fourier Transform Based Approach for Fast and Secure Convolutional Neural Network PredictionsOral112 citations
793. G3AN: Disentangling Appearance and Motion for Video GenerationPoster112 citations
794. Learning Invariant Representation for Unsupervised Image RestorationPoster112 citations
795. Learning to Segment the TailPoster112 citations
796. A Context-Aware Loss Function for Action Spotting in Soccer VideosPoster111 citations
797. Bi-Directional Interaction Network for Person SearchPoster111 citations
798. Fashion Outfit Complementary Item RetrievalPoster111 citations
799. HUMBI: A Large Multiview Dataset of Human Body ExpressionsPoster111 citations
800. Learning Better Lossless Compression Using Lossy CompressionPoster111 citations
801. Pattern-Structure Diffusion for Multi-Task LearningPoster111 citations
802. COCAS: A Large-Scale Clothes Changing Person Dataset for Re-IdentificationPoster110 citations
803. Joint Filtering of Intensity Images and Neuromorphic Events for High-Resolution Noise-Robust ImagingPoster110 citations
804. Neuromorphic Camera Guided High Dynamic Range ImagingPoster110 citations
805. PANDA: A Gigapixel-Level Human-Centric Video DatasetPoster110 citations
806. Factorized Higher-Order CNNs With an Application to Spatio-Temporal Emotion EstimationPoster109 citations
807. Graph-Structured Referring Expression Reasoning in the WildOral109 citations
808. L2-GCN: Layer-Wise and Learned Efficient Training of Graph Convolutional NetworksPoster109 citations
809. MTL-NAS: Task-Agnostic Neural Architecture Search Towards General-Purpose Multi-Task LearningPoster109 citations
810. Memory Aggregation Networks for Efficient Interactive Video Object SegmentationPoster109 citations
811. Normal Assisted Stereo Depth EstimationPoster109 citations
812. Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image SynthesisOral109 citations
813. CenterMask: Single Shot Instance Segmentation With Point RepresentationPoster108 citations
814. Defending and Harnessing the Bit-Flip Based Adversarial Weight AttackPoster108 citations
815. DR Loss: Improving Object Detection by Distributional RankingPoster107 citations
816. DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D MeshesOral107 citations
817. Solving Mixed-Modal Jigsaw Puzzle for Fine-Grained Sketch-Based Image RetrievalPoster107 citations
818. Two-Shot Spatially-Varying BRDF and Shape EstimationPoster107 citations
819. ARShadowGAN: Shadow Generative Adversarial Network for Augmented Reality in Single Light ScenesPoster106 citations
820. DeFeat-Net: General Monocular Depth via Simultaneous Unsupervised Representation LearningPoster106 citations
821. Don't Even Look Once: Synthesizing Features for Zero-Shot DetectionPoster106 citations
822. Private-kNN: Practical Differential Privacy for Computer VisionPoster106 citations
823. Transferable, Controllable, and Inconspicuous Adversarial Attacks on Person Re-identification With Deep Mis-RankingOral106 citations
824. Breaking the Cycle - Colleagues Are All You NeedPoster105 citations
825. Cooling-Shrinking Attack: Blinding the Tracker With Imperceptible NoisesPoster105 citations
826. DeepFLASH: An Efficient Network for Learning-Based Medical Image RegistrationPoster105 citations
827. 4D Association Graph for Realtime Multi-Person Motion Capture Using Multiple Video CamerasOral104 citations
828. Active Speakers in ContextPoster104 citations
829. Exploring Data Aggregation in Policy Learning for Vision-Based Urban Autonomous DrivingPoster104 citations
830. IntrA: 3D Intracranial Aneurysm Dataset for Deep LearningOral104 citations
831. Learning a Neural 3D Texture Space From 2D ExemplarsPoster104 citations
832. Neural Point Cloud Rendering via Multi-Plane ProjectionPoster104 citations
833. Weakly Supervised Fine-Grained Image Classification via Guassian Mixture Model Oriented Discriminative LearningOral104 citations
834. Bi3D: Stereo Depth Estimation via Binary ClassificationsPoster103 citations
835. Blurry Video Frame InterpolationOral103 citations
836. Channel Attention Based Iterative Residual Learning for Depth Map Super-ResolutionPoster103 citations
837. Efficient Derivative Computation for Cumulative B-Splines on Lie GroupsOral103 citations
838. Hierarchical Pyramid Diverse Attention Networks for Face RecognitionPoster103 citations
839. Overcoming Multi-Model Forgetting in One-Shot NAS With Diversity MaximizationPoster103 citations
840. SAM: The Sensitivity of Attribution Methods to HyperparametersOral103 citations
841. SCOUT: Self-Aware Discriminant Counterfactual ExplanationsPoster103 citations
842. DeepDeform: Learning Non-Rigid RGB-D Reconstruction With Semi-Supervised DataPoster102 citations
843. Enhancing Cross-Task Black-Box Transferability of Adversarial Examples With Dispersion ReductionPoster102 citations
844. Learning Instance Occlusion for Panoptic SegmentationPoster102 citations
845. Modality Shifting Attention Network for Multi-Modal Video Question AnsweringPoster102 citations
846. Multi-Dimensional Pruning: A Unified Framework for Model CompressionOral102 citations
847. MixNMatch: Multifactor Disentanglement and Encoding for Conditional Image GenerationPoster101 citations
848. Retina-Like Visual Image Reconstruction via Spiking Neural ModelOral101 citations
849. Towards Backward-Compatible Representation LearningOral101 citations
850. Weakly-Supervised Domain Adaptation via GAN and Mesh Model for Estimating 3D Hand Poses Interacting ObjectsOral101 citations
851. Discrete Model Compression With Resource Constraint for Deep Neural NetworksPoster100 citations
852. From Depth What Can You See? Depth Completion via Auxiliary Image ReconstructionPoster100 citations
853. Learning to Discriminate Information for Online Action DetectionPoster100 citations
854. One-Shot Adversarial Attacks on Visual Tracking With Dual AttentionPoster100 citations
855. Self-Supervised Learning of Interpretable Keypoints From Unlabelled VideosOral100 citations
856. Taking a Deeper Look at Co-Salient Object DetectionPoster100 citations
857. Attribution in Scale and SpacePoster99 citations
858. KFNet: Learning Temporal Camera Relocalization Using Kalman FilteringOral99 citations
859. Look-Into-Object: Self-Supervised Structure Modeling for Object RecognitionPoster99 citations
860. Progressive Mirror DetectionPoster99 citations
861. Robust Partial Matching for Person Search in the WildPoster99 citations
862. A Disentangling Invertible Interpretation Network for Explaining Latent RepresentationsPoster98 citations
863. Single Image Reflection Removal With Physically-Based Training ImagesOral98 citations
864. Training Noise-Robust Deep Neural Networks via Meta-LearningPoster98 citations
865. Unsupervised Instance Segmentation in Microscopy Images via Panoptic Domain Adaptation and Task Re-WeightingPoster98 citations
866. Correspondence Networks With Adaptive Neighbourhood ConsensusPoster97 citations
867. Deep 3D Capture: Geometry and Reflectance From Sparse Multi-View ImagesPoster97 citations
868. Instance Shadow DetectionPoster97 citations
869. Interactive Multi-Label CNN Learning With Partial LabelsPoster97 citations
870. Reinforced Feature Points: Optimizing Feature Detection and Description for a High-Level TaskOral97 citations
871. RoutedFusion: Learning Real-Time Depth Map FusionOral97 citations
872. Search to Distill: Pearls Are Everywhere but Not the EyesOral97 citations
873. Two-Stage Peer-Regularized Feature Recombination for Arbitrary Image Style TransferPoster97 citations
874. Upgrading Optical Flow to 3D Scene Flow Through Optical ExpansionOral97 citations
875. Correction Filter for Single Image Super-Resolution: Robustifying Off-the-Shelf Deep Super-ResolversOral96 citations
876. FeatureFlow: Robust Video Interpolation via Structure-to-Texture GenerationPoster96 citations
877. Inflated Episodic Memory With Region Self-Attention for Long-Tailed Visual RecognitionPoster96 citations
878. LT-Net: Label Transfer by Learning Reversible Voxel-Wise Correspondence for One-Shot Medical Image SegmentationPoster96 citations
879. Learning Multi-Object Tracking and Segmentation From Automatic AnnotationsPoster96 citations
880. STAViS: Spatio-Temporal AudioVisual Saliency NetworkPoster96 citations
881. Unity Style Transfer for Person Re-IdentificationPoster96 citations
882. Composed Query Image Retrieval Using Locally Bounded FeaturesPoster95 citations
883. CookGAN: Causality Based Text-to-Image SynthesisPoster95 citations
884. Event Probability Mask (EPM) and Event Denoising Convolutional Neural Network (EDnCNN) for Neuromorphic CamerasPoster95 citations
885. On Isometry Robustness of Deep 3D Point Cloud Models Under Adversarial AttacksPoster95 citations
886. P-nets: Deep Polynomial Neural NetworksPoster95 citations
887. SLV: Spatial Likelihood Voting for Weakly Supervised Object DetectionPoster95 citations
888. Training Quantized Neural Networks With a Full-Precision Auxiliary ModuleOral95 citations
889. 3FabRec: Fast Few-Shot Face Alignment by ReconstructionOral94 citations
890. DUNIT: Detection-Based Unsupervised Image-to-Image TranslationPoster94 citations
891. Decoupled Representation Learning for Skeleton-Based Gesture RecognitionPoster94 citations
892. Exploring Category-Agnostic Clusters for Open-Set Domain AdaptationPoster94 citations
893. Real-Time Panoptic Segmentation From Dense DetectionsOral94 citations
894. Domain Balancing: Face Recognition on Long-Tailed DomainsPoster93 citations
895. End-to-End Camera Calibration for Broadcast VideosPoster93 citations
896. GAMIN: Generative Adversarial Multiple Imputation Network for Highly Missing DataPoster93 citations
897. HandVoxNet: Deep Voxel-Based Network for 3D Hand Shape and Pose Estimation From a Single Depth MapPoster93 citations
898. Towards Verifying Robustness of Neural Networks Against A Family of Semantic PerturbationsOral93 citations
899. BANet: Bidirectional Aggregation Network With Occlusion Handling for Panoptic SegmentationOral92 citations
900. Beyond Short-Term Snippet: Video Relation Detection With Spatio-Temporal Global ContextPoster92 citations
901. Deep Fair Clustering for Visual LearningPoster92 citations
902. Fashion Editing With Adversarial Parsing LearningPoster92 citations
903. Knowledge As Priors: Cross-Modal Knowledge Generalization for Datasets Without Superior KnowledgePoster92 citations
904. Telling Left From Right: Learning Spatial Correspondence of Sight and SoundOral92 citations
905. Distilled Semantics for Comprehensive Scene Understanding from VideosPoster91 citations
906. Learning Situational DrivingPoster91 citations
907. STEFANN: Scene Text Editor Using Font Adaptive Neural NetworkPoster91 citations
908. End-to-End Optimization of Scene LayoutOral90 citations
909. Improving One-Shot NAS by Suppressing the Posterior FadingPoster90 citations
910. Learn2Perturb: An End-to-End Feature Perturbation Learning to Improve Adversarial RobustnessPoster90 citations
911. Optical Non-Line-of-Sight Physics-Based 3D Human Pose EstimationPoster90 citations
912. Self-Supervised Deep Visual Odometry With Online AdaptationOral90 citations
913. Stochastic Sparse Subspace ClusteringPoster90 citations
914. BiDet: An Efficient Binarized Object DetectorPoster89 citations
915. FGN: Fully Guided Network for Few-Shot Instance SegmentationPoster89 citations
916. Hierarchical Graph Attention Network for Visual Relationship DetectionPoster89 citations
917. KeypointNet: A Large-Scale 3D Keypoint Dataset Aggregated From Numerous Human AnnotationsPoster89 citations
918. Memory-Efficient Hierarchical Neural Architecture Search for Image DenoisingPoster89 citations
919. Real-World Person Re-Identification via Degradation Invariance LearningPoster89 citations
920. SwapText: Image Based Texts Transfer in ScenesPoster89 citations
921. Global-Local GCN: Large-Scale Label Noise Cleansing for Face RecognitionPoster88 citations
922. Learning Video Stabilization Using Optical FlowPoster88 citations
923. Learning When and Where to Zoom With Deep Reinforcement LearningOral88 citations
924. Towards Robust Image Classification Using Sequential Attention ModelsPoster88 citations
925. Unifying Training and Inference for Panoptic SegmentationPoster88 citations
926. A Semi-Supervised Assessor of Neural ArchitecturesPoster87 citations
927. Attention-Driven Cropping for Very High Resolution Facial Landmark DetectionPoster87 citations
928. Organ at Risk Segmentation for Head and Neck Cancer Using Stratified Learning and Neural Architecture SearchPoster87 citations
929. SCT: Set Constrained Temporal Transformer for Set Supervised Action SegmentationPoster87 citations
930. Unpaired Portrait Drawing Generation via Asymmetric Cycle MappingPoster87 citations
931. Basis Prediction Networks for Effective Burst Denoising With Large KernelsPoster86 citations
932. Deep Adversarial Decomposition: A Unified Framework for Separating Superimposed ImagesPoster86 citations
933. Geometric Structure Based and Regularized Depth Estimation From 360 Indoor ImageryPoster86 citations
934. PointGMM: A Neural GMM Network for Point CloudsPoster86 citations
935. Learning Visual Motion Segmentation Using Event SurfacesPoster85 citations
936. Learning to Evaluate Perception Models Using Planner-Centric MetricsPoster85 citations
937. PandaNet: Anchor-Based Single-Shot Multi-Person 3D Pose EstimationPoster85 citations
938. SQuINTing at VQA Models: Introspecting VQA Models With Sub-QuestionsOral85 citations
939. Smoothing Adversarial Domain Attack and P-Memory Reconsolidation for Cross-Domain Person Re-IdentificationPoster85 citations
940. Through the Looking Glass: Neural 3D Reconstruction of Transparent ShapesOral85 citations
941. Unsupervised Reinforcement Learning of Transferable Meta-Skills for Embodied NavigationPoster85 citations
942. Single Image Optical Flow Estimation With an Event CameraPoster84 citations
943. Your Local GAN: Designing Two Dimensional Local Attention Mechanisms for Generative ModelsPoster84 citations
944. 4D Visualization of Dynamic Events From Unconstrained Multi-View VideosPoster83 citations
945. Disentangled Image Generation Through Structured Noise InjectionOral83 citations
946. Non-Line-of-Sight Surface Reconstruction Using the Directional Light-Cone TransformOral83 citations
947. BidNet: Binocular Image Dehazing Without Explicit Disparity EstimationPoster82 citations
948. Computing the Testing Error Without a Testing SetOral82 citations
949. Correlating Edge, Pose With ParsingPoster82 citations
950. Fast Template Matching and Update for Video Object Tracking and SegmentationPoster82 citations
951. Intra- and Inter-Action Understanding via Temporal Action ParsingPoster82 citations
952. Progressive Adversarial Networks for Fine-Grained Domain AdaptationPoster82 citations
953. Self-Learning Video Rain Streak Removal: When Cyclic Consistency Meets Temporal CorrespondencePoster82 citations
954. IDA-3D: Instance-Depth-Aware 3D Object Detection From Stereo Vision for Autonomous DrivingPoster81 citations
955. Robust Superpixel-Guided Attentional Adversarial AttackPoster81 citations
956. STINet: Spatio-Temporal-Interactive Network for Pedestrian Detection and Trajectory PredictionPoster81 citations
957. BEDSR-Net: A Deep Shadow Removal Network From a Single Document ImagePoster80 citations
958. Fusing Wearable IMUs With Multi-View Images for Human Pose Estimation: A Geometric ApproachPoster80 citations
959. Hardware-in-the-Loop End-to-End Optimization of Camera Image Processing PipelinesOral80 citations
960. Selective Transfer With Reinforced Transfer Network for Partial Domain AdaptationPoster80 citations
961. Sketch-BERT: Learning Sketch Bidirectional Encoder Representation From Transformers by Self-Supervised Learning of Sketch GestaltPoster80 citations
962. An End-to-End Edge Aggregation Network for Moving Object SegmentationPoster79 citations
963. Bidirectional Graph Reasoning Network for Panoptic SegmentationPoster79 citations
964. Bodies at Rest: 3D Human Pose and Shape Estimation From a Pressure Image Using Synthetic DataOral79 citations
965. Focus on Defocus: Bridging the Synthetic to Real Domain Gap for Depth EstimationPoster79 citations
966. Learning Multi-View Camera Relocalization With Graph Neural NetworksPoster79 citations
967. Learning Temporal Co-Attention Models for Unsupervised Video Action LocalizationOral79 citations
968. Multiview-Consistent Semi-Supervised Learning for 3D Human Pose EstimationPoster79 citations
969. Video Instance Segmentation Tracking With a Modified VAE ArchitecturePoster79 citations
970. Conv-MPN: Convolutional Message Passing Neural Network for Structured Outdoor Architecture ReconstructionPoster78 citations
971. Deep Active Learning for Biased Datasets via Fisher Kernel Self-SupervisionPoster78 citations
972. Geometry-Aware Satellite-to-Ground Image Synthesis for Urban AreasPoster78 citations
973. Learning to Super Resolve Intensity Images From EventsOral78 citations
974. Self-Supervised Domain-Aware Generative Network for Generalized Zero-Shot LearningPoster78 citations
975. Single-Step Adversarial Training With Dropout SchedulingPoster78 citations
976. Speech2Action: Cross-Modal Supervision for Action RecognitionPoster78 citations
977. Uncertainty-Aware Mesh Decoder for High Fidelity 3D Face ReconstructionPoster78 citations
978. Unsupervised Learning From Video With Deep Neural EmbeddingsPoster78 citations
979. Learning to See Through ObstructionsPoster77 citations
980. SP-NAS: Serial-to-Parallel Backbone Search for Object DetectionPoster77 citations
981. Violin: A Large-Scale Dataset for Video-and-Language InferencePoster77 citations
982. Automatic Neural Network Compression by Sparsity-Quantization Joint Learning: A Constrained Optimization-Based ApproachPoster76 citations
983. Background Data Resampling for Outlier-Aware ClassificationPoster76 citations
984. FroDO: From Detections to 3D ObjectsPoster76 citations
985. Improving the Robustness of Capsule Networks to Image Affine TransformationsPoster76 citations
986. Learning Interactions and Relationships Between Movie CharactersOral76 citations
987. On Vocabulary Reliance in Scene Text RecognitionPoster76 citations
988. Show, Edit and Tell: A Framework for Editing Image CaptionsPoster76 citations
989. Cops-Ref: A New Dataset and Task on Compositional Referring Expression ComprehensionPoster75 citations
990. Deep Facial Non-Rigid Multi-View StereoPoster75 citations
991. Deep Non-Line-of-Sight ReconstructionPoster75 citations
992. Fusion-Aware Point Convolution for Online Semantic 3D Scene SegmentationPoster75 citations
993. Large-Scale Object Detection in the Wild From Imbalanced Multi-LabelsOral75 citations
994. MUXConv: Information Multiplexing in Convolutional Neural NetworksPoster75 citations
995. Self-Supervised Learning of Video-Induced Visual InvariancesPoster75 citations
996. Assessing Image Quality Issues for Real-World ProblemsPoster74 citations
997. Cross-Spectral Face Hallucination via Disentangling Independent FactorsPoster74 citations
998. Neural Networks Are More Productive Teachers Than Human Raters: Active Mixup for Data-Efficient Knowledge Distillation From a Blackbox ModelOral74 citations
999. CONSAC: Robust Multi-Model Fitting by Conditional Sample ConsensusPoster73 citations
1000. Fast Video Object Segmentation With Temporal Aggregation Network and Dynamic Template MatchingPoster73 citations

Looking for submission deadlines instead? See the conference deadline calendar.