ICCV 2021 Accepted Papers

The full list of 1,612 papers accepted at ICCV 2021 (IEEE/CVF International Conference on Computer Vision). 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. Swin Transformer: Hierarchical Vision Transformer Using Shifted WindowsPoster29,925 citations
2. Emerging Properties in Self-Supervised Vision TransformersPoster6,990 citations
3. Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction Without ConvolutionsPoster5,090 citations
4. ViViT: A Video Vision TransformerPoster2,888 citations
5. Point TransformerPoster2,633 citations
6. CvT: Introducing Convolutions to Vision TransformersPoster2,598 citations
7. Tokens-to-Token ViT: Training Vision Transformers From Scratch on ImageNetPoster2,573 citations
8. Segmenter: Transformer for Semantic SegmentationPoster2,259 citations
9. Vision Transformers for Dense PredictionPoster2,233 citations
10. Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance FieldsPoster2,219 citations
11. An Empirical Study of Training Self-Supervised Vision TransformersPoster2,178 citations
12. CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image ClassificationPoster2,006 citations
13. The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution GeneralizationPoster2,004 citations
14. Multiscale Vision TransformersPoster1,664 citations
15. Nerfies: Deformable Neural Radiance FieldsPoster1,543 citations
16. StyleCLIP: Text-Driven Manipulation of StyleGAN ImageryPoster1,379 citations
17. Going Deeper With Image TransformersPoster1,328 citations
18. Frozen in Time: A Joint Video and Image Encoder for End-to-End RetrievalPoster1,303 citations
19. PlenOctrees for Real-Time Rendering of Neural Radiance FieldsPoster1,173 citations
20. TransReID: Transformer-Based Object Re-IdentificationPoster1,156 citations
21. FcaNet: Frequency Channel Attention NetworksPoster1,130 citations
22. TOOD: Task-Aligned One-Stage Object DetectionPoster1,116 citations
23. Learning Spatio-Temporal Transformer for Visual TrackingPoster1,080 citations
24. Oriented R-CNN for Object DetectionPoster1,021 citations
25. MDETR - Modulated Detection for End-to-End Multi-Modal UnderstandingPoster980 citations
26. MVSNeRF: Fast Generalizable Radiance Field Reconstruction From Multi-View StereoPoster907 citations
27. Conformer: Local Features Coupling Global Representations for Visual RecognitionPoster890 citations
28. Channel-Wise Topology Refinement Graph Convolution for Skeleton-Based Action RecognitionPoster872 citations
29. UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View ReconstructionPoster862 citations
30. KiloNeRF: Speeding Up Neural Radiance Fields With Thousands of Tiny MLPsPoster855 citations
31. Conditional DETR for Fast Training ConvergencePoster829 citations
32. DRAEM - A Discriminatively Trained Reconstruction Embedding for Surface Anomaly DetectionPoster820 citations
33. LeViT: A Vision Transformer in ConvNet's Clothing for Faster InferencePoster815 citations
34. BARF: Bundle-Adjusting Neural Radiance FieldsPoster810 citations
35. ILVR: Conditioning Method for Denoising Diffusion Probabilistic ModelsPoster805 citations
36. Designing a Practical Degradation Model for Deep Blind Image Super-ResolutionPoster793 citations
37. MUSIQ: Multi-Scale Image Quality TransformerPoster780 citations
38. Rethinking Coarse-To-Fine Approach in Single Image DeblurringPoster770 citations
39. Rethinking Spatial Dimensions of Vision TransformersPoster761 citations
40. Incorporating Learnable Membrane Time Constant To Enhance Learning of Spiking Neural NetworksPoster729 citations
41. FastNeRF: High-Fidelity Neural Rendering at 200FPSPoster697 citations
42. Big Self-Supervised Models Advance Medical Image ClassificationPoster695 citations
43. iMAP: Implicit Mapping and Positioning in Real-TimePoster689 citations
44. Incorporating Convolution Designs Into Visual TransformersPoster659 citations
45. 3D Human Pose Estimation With Spatial and Temporal TransformersPoster649 citations
46. Exploring Cross-Image Pixel Contrast for Semantic SegmentationPoster624 citations
47. Large Scale Interactive Motion Forecasting for Autonomous Driving: The Waymo Open Motion DatasetPoster624 citations
48. End-to-End Semi-Supervised Object Detection With Soft TeacherPoster620 citations
49. PoinTr: Diverse Point Cloud Completion With Geometry-Aware TransformersPoster608 citations
50. Baking Neural Radiance Fields for Real-Time View SynthesisPoster604 citations
51. Invisible Backdoor Attack With Sample-Specific TriggersPoster603 citations
52. AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent ForecastingPoster594 citations
53. AI Choreographer: Music Conditioned 3D Dance Generation With AIST++Poster576 citations
54. 3D Shape Generation and Completion Through Point-Voxel DiffusionPoster574 citations
55. An End-to-End Transformer Model for 3D Object DetectionPoster573 citations
56. Action-Conditioned 3D Human Motion Synthesis With Transformer VAEPoster567 citations
57. With a Little Help From My Friends: Nearest-Neighbor Contrastive Learning of Visual RepresentationsPoster561 citations
58. Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene From Monocular VideoPoster557 citations
59. Visual Saliency TransformerPoster552 citations
60. Asymmetric Loss for Multi-Label ClassificationPoster547 citations
61. NeRD: Neural Reflectance Decomposition From Image CollectionsPoster547 citations
62. Putting NeRF on a Diet: Semantically Consistent Few-Shot View SynthesisPoster541 citations
63. Voxel Transformer for 3D Object DetectionPoster532 citations
64. DenseTNT: End-to-End Trajectory Prediction From Dense Goal SetsPoster528 citations
65. In-Place Scene Labelling and Understanding With Implicit Scene RepresentationPoster527 citations
66. ACDC: The Adverse Conditions Dataset With Correspondences for Semantic Driving Scene UnderstandingPoster525 citations
67. Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot LearningPoster520 citations
68. Animatable Neural Radiance Fields for Modeling Dynamic Human BodiesPoster514 citations
69. Understanding Robustness of Transformers for Image ClassificationPoster503 citations
70. Common Objects in 3D: Large-Scale Learning and Evaluation of Real-Life 3D Category ReconstructionPoster491 citations
71. PARE: Part Attention Regressor for 3D Human Body EstimationPoster480 citations
72. Weakly-Supervised Video Anomaly Detection With Robust Temporal Feature Magnitude LearningPoster462 citations
73. Co-Scale Conv-Attentional Image TransformersPoster461 citations
74. AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head SynthesisPoster452 citations
75. Pixel Difference Networks for Efficient Edge DetectionPoster452 citations
76. Dynamic View Synthesis From Dynamic Monocular VideoPoster441 citations
77. FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture SearchPoster432 citations
78. Rethinking and Improving Relative Position Encoding for Vision TransformerPoster430 citations
79. Co2L: Contrastive Continual LearningPoster428 citations
80. Rethinking Transformer-Based Set Prediction for Object DetectionPoster425 citations
81. Hypercorrelation Squeeze for Few-Shot SegmentationPoster420 citations
82. Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image EncodingPoster419 citations
83. UniT: Multimodal Multitask Learning With a Unified TransformerPoster417 citations
84. AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style TransferPoster413 citations
85. Dynamic DETR: End-to-End Object Detection With Dynamic AttentionPoster409 citations
86. DetCo: Unsupervised Contrastive Learning for Object DetectionPoster408 citations
87. Learning To Estimate Hidden Motions With Global Motion AggregationPoster408 citations
88. Mesh GraphormerPoster408 citations
89. TransPose: Keypoint Localization via TransformerPoster408 citations
90. TransVG: End-to-End Visual Grounding With TransformersPoster408 citations
91. AutoFormer: Searching Transformers for Visual RecognitionPoster407 citations
92. GLoRIA: A Multimodal Global-Local Representation Learning Framework for Label-Efficient Medical Image RecognitionPoster404 citations
93. TAM: Temporal Adaptive Module for Video RecognitionPoster403 citations
94. Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene UnderstandingPoster395 citations
95. ReStyle: A Residual-Based StyleGAN Encoder via Iterative RefinementPoster393 citations
96. Generic Attention-Model Explainability for Interpreting Bi-Modal and Encoder-Decoder TransformersPoster392 citations
97. Is Pseudo-Lidar Needed for Monocular 3D Object Detection?Poster388 citations
98. PyMAF: 3D Human Pose and Shape Regression With Pyramidal Mesh Alignment Feedback LoopPoster386 citations
99. TokenPose: Learning Keypoint Tokens for Human Pose EstimationPoster386 citations
100. Fast Convergence of DETR With Spatially Modulated Co-AttentionPoster379 citations
101. Parametric Contrastive LearningPoster377 citations
102. TrivialAugment: Tuning-Free Yet State-of-the-Art Data AugmentationPoster371 citations
103. Walk in the Cloud: Learning Curves for Point Clouds Shape AnalysisPoster367 citations
104. Channel-Wise Knowledge Distillation for Dense PredictionPoster366 citations
105. Instances As QueriesPoster365 citations
106. Learning Self-Consistency for Deepfake DetectionPoster365 citations
107. Rethinking Counting and Localization in Crowds: A Purely Point-Based FrameworkPoster365 citations
108. Learning Target Candidate Association To Keep Track of What Not To TrackPoster364 citations
109. Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-IdentificationPoster361 citations
110. Focal Frequency Loss for Image Reconstruction and SynthesisPoster361 citations
111. SelfReg: Self-Supervised Contrastive Regularization for Domain GeneralizationPoster360 citations
112. Group-Free 3D Object Detection via TransformersPoster357 citations
113. Learning Object-Compositional Neural Radiance Field for Editable Scene RenderingPoster356 citations
114. HuMoR: 3D Human Motion Model for Robust Pose EstimationPoster354 citations
115. CoMatch: Semi-Supervised Learning With Contrastive Graph RegularizationPoster353 citations
116. DeFRCN: Decoupled Faster R-CNN for Few-Shot Object DetectionPoster347 citations
117. Vector Neurons: A General Framework for SO(3)-Equivariant NetworksPoster345 citations
118. From Goals, Waypoints & Paths to Long Term Human Trajectory ForecastingPoster343 citations
119. DocFormer: End-to-End Transformer for Document UnderstandingPoster342 citations
120. Fake It Till You Make It: Face Analysis in the Wild Using Synthetic Data AlonePoster339 citations
121. Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective With TransformersPoster338 citations
122. Just Ask: Learning To Answer Questions From Millions of Narrated VideosPoster337 citations
123. Seasonal Contrast: Unsupervised Pre-Training From Uncurated Remote Sensing DataPoster336 citations
124. RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud SegmentationPoster333 citations
125. FIERY: Future Instance Prediction in Bird's-Eye View From Surround Monocular CamerasPoster330 citations
126. Monocular, One-Stage, Regression of Multiple 3D PeoplePoster327 citations
127. SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution With Skip-TransformerPoster326 citations
128. Generalized Source-Free Domain AdaptationPoster324 citations
129. COTR: Correspondence Transformer for Matching Across ImagesPoster320 citations
130. Self-Supervised Pretraining of 3D Features on Any Point-CloudPoster316 citations
131. CondLaneNet: A Top-To-Down Lane Detection Framework Based on Conditional ConvolutionPoster315 citations
132. Image Inpainting via Conditional Texture and Structure Dual GenerationPoster314 citations
133. LIRA: Learnable, Imperceptible and Robust Backdoor AttacksPoster310 citations
134. Learning To Diversify for Single Domain GeneralizationPoster307 citations
135. Unsupervised Semantic Segmentation by Contrasting Object Mask ProposalsPoster307 citations
136. Neural Radiance Flow for 4D View Synthesis and Video ProcessingPoster305 citations
137. Editing Conditional Radiance FieldsPoster304 citations
138. NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-View StereoPoster302 citations
139. Multimodal Co-Attention Transformer for Survival Prediction in Gigapixel Whole Slide ImagesPoster301 citations
140. RangeDet: In Defense of Range View for LiDAR-Based 3D Object DetectionPoster300 citations
141. Unsupervised Point Cloud Pre-Training via Occlusion CompletionPoster300 citations
142. Exploring Temporal Coherence for More General Video Face Forgery DetectionPoster299 citations
143. Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets From 3D ScansPoster299 citations
144. Refining Activation Downsampling With SoftPoolPoster299 citations
145. Improving 3D Object Detection With Channel-Wise TransformerPoster298 citations
146. HiFT: Hierarchical Feature Transformer for Aerial TrackingPoster297 citations
147. High-Fidelity Pluralistic Image Completion With TransformersPoster297 citations
148. Vision-Language Transformer and Query Generation for Referring SegmentationPoster297 citations
149. Channel Augmented Joint Learning for Visible-Infrared RecognitionPoster296 citations
150. Uncertainty-Guided Transformer Reasoning for Camouflaged Object DetectionPoster296 citations
151. 3D-FRONT: 3D Furnished Rooms With layOuts and semaNTicsPoster295 citations
152. Gait Recognition via Effective Global-Local Feature Representation and Local Temporal AggregationPoster294 citations
153. Geography-Aware Self-Supervised LearningPoster291 citations
154. Admix: Enhancing the Transferability of Adversarial AttacksPoster290 citations
155. GRF: Learning a General Radiance Field for 3D Representation and RenderingPoster290 citations
156. Feature Importance-Aware Transferable Adversarial AttacksPoster288 citations
157. Semi-Supervised Semantic Segmentation With Pixel-Level Contrastive Learning From a Class-Wise Memory BankPoster288 citations
158. Continual Prototype Evolution: Learning Online From Non-Stationary Data StreamsPoster285 citations
159. Rethinking the Backdoor Attacks' Triggers: A Frequency PerspectivePoster281 citations
160. On the Robustness of Vision Transformers to Adversarial ExamplesPoster280 citations
161. A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame PredictionPoster278 citations
162. TransFER: Learning Relation-Aware Facial Expression Representations With TransformersPoster278 citations
163. Human Pose Regression With Residual Log-Likelihood EstimationPoster277 citations
164. OpenGAN: Open-Set Recognition via Open Data GenerationPoster276 citations
165. Adaptive Adversarial Network for Source-Free Domain AdaptationPoster274 citations
166. Relational Embedding for Few-Shot ClassificationPoster274 citations
167. Visformer: The Vision-Friendly TransformerPoster274 citations
168. Anticipative Video TransformerPoster273 citations
169. MVTN: Multi-View Transformation Network for 3D Shape RecognitionPoster269 citations
170. Self-Calibrating Neural Radiance FieldsPoster268 citations
171. ICE: Inter-Instance Contrastive Encoding for Unsupervised Person Re-IdentificationPoster266 citations
172. Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training DataPoster263 citations
173. Geometry Uncertainty Projection Network for Monocular 3D Object DetectionPoster263 citations
174. NEAT: Neural Attention Fields for End-to-End Autonomous DrivingPoster263 citations
175. MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion PredictionPoster262 citations
176. Self-Knowledge Distillation With Progressive Refinement of TargetsPoster262 citations
177. Learning To Track With Object PermanencePoster258 citations
178. SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit ShapesPoster258 citations
179. Specificity-Preserving RGB-D Saliency DetectionPoster256 citations
180. TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object LocalizationPoster254 citations
181. VidTr: Video Transformer Without ConvolutionsPoster253 citations
182. HiNet: Deep Image Hiding by Invertible NetworkPoster252 citations
183. PIRenderer: Controllable Portrait Image Generation via Semantic Neural RenderingPoster252 citations
184. SS-IL: Separated Softmax for Incremental LearningPoster251 citations
185. FaPN: Feature-Aligned Pyramid Network for Dense Image PredictionPoster250 citations
186. Spatio-Temporal Self-Supervised Representation Learning for 3D Point CloudsPoster248 citations
187. A Simple Feature Augmentation for Domain GeneralizationPoster246 citations
188. Learning by Aligning: Visible-Infrared Person Re-Identification Using Cross-Modal CorrespondencesPoster246 citations
189. FREE: Feature Refinement for Generalized Zero-Shot LearningPoster244 citations
190. MeshTalk: 3D Face Animation From Speech Using Cross-Modality DisentanglementPoster241 citations
191. Learn To Match: Automatic Matching Network Design for Visual TrackingPoster239 citations
192. Transformer-Based Attention Networks for Continuous Pixel-Wise PredictionPoster239 citations
193. End-to-End Dense Video Captioning With Parallel DecodingPoster238 citations
194. CodeNeRF: Disentangled Neural Radiance Fields for Object CategoriesPoster236 citations
195. On Feature Decorrelation in Self-Supervised LearningPoster236 citations
196. A Unified Objective for Novel Class DiscoveryPoster235 citations
197. Image Retrieval on Real-Life Images With Pre-Trained Vision-and-Language ModelsPoster235 citations
198. ResRep: Lossless CNN Pruning via Decoupling Remembering and ForgettingPoster235 citations
199. Relaxed Transformer Decoders for Direct Action Proposal GenerationPoster234 citations
200. ALL Snow Removed: Single Image Desnowing Algorithm Using Hierarchical Dual-Tree Complex Wavelet Representation and Contradict Channel LossPoster232 citations
201. End-to-End Urban Driving by Imitating a Reinforcement Learning CoachPoster232 citations
202. Image Manipulation Detection by Multi-View Multi-Scale SupervisionPoster231 citations
203. Neural Articulated Radiance FieldPoster231 citations
204. Simpler Is Better: Few-Shot Semantic Segmentation With Classifier Weight TransformerPoster229 citations
205. Pixel Contrastive-Consistent Semi-Supervised Semantic SegmentationPoster226 citations
206. Temporal-Wise Attention Spiking Neural Networks for Event Streams ClassificationPoster224 citations
207. GNeRF: GAN-Based Neural Radiance Field Without Posed CameraPoster223 citations
208. Perception-Aware Multi-Sensor Fusion for 3D LiDAR Semantic SegmentationPoster223 citations
209. ARCH++: Animation-Ready Clothed Human Reconstruction RevisitedPoster222 citations
210. Always Be Dreaming: A New Approach for Data-Free Class-Incremental LearningPoster219 citations
211. ID-Reveal: Identity-Aware DeepFake Video DetectionPoster219 citations
212. Episodic Transformer for Vision-and-Language NavigationPoster214 citations
213. Cross-Modality Person Re-Identification via Modality Confusion and Center AggregationPoster213 citations
214. Score-Based Point Cloud DenoisingPoster211 citations
215. XVFI: eXtreme Video Frame InterpolationPoster210 citations
216. Contrastive Learning for Label Efficient Semantic SegmentationPoster209 citations
217. Pixel-Perfect Structure-From-Motion With Featuremetric RefinementPoster209 citations
218. Joint Audio-Visual Deepfake DetectionPoster207 citations
219. OMNet: Learning Overlapping Mask for Partial-to-Partial Point Cloud RegistrationPoster207 citations
220. H2O: Two Hands Manipulating Objects for First Person Interaction RecognitionPoster205 citations
221. Panoptic Segmentation of Satellite Image Time Series With Convolutional Temporal Attention NetworksPoster204 citations
222. Synthesis of Compositional Animations From Textual DescriptionsPoster202 citations
223. Where2Act: From Pixels to Actions for Articulated 3D ObjectsPoster202 citations
224. Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object DetectionPoster201 citations
225. TF-Blender: Temporal Feature Blender for Video Object DetectionPoster200 citations
226. Influence-Balanced Loss for Imbalanced Visual ClassificationPoster199 citations
227. ShapeConv: Shape-Aware Convolutional Layer for Indoor RGB-D Semantic SegmentationPoster199 citations
228. SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point GenerationPoster198 citations
229. Space-Time-Separable Graph Convolutional Network for Pose ForecastingPoster197 citations
230. Residual Attention: A Simple but Effective Method for Multi-Label RecognitionPoster196 citations
231. AA-RMVSNet: Adaptive Aggregation Recurrent Multi-View Stereo NetworkPoster195 citations
232. Divide-and-Assemble: Learning Block-Wise Memory for Unsupervised Anomaly DetectionPoster193 citations
233. Hierarchical Aggregation for 3D Instance SegmentationPoster193 citations
234. OVANet: One-vs-All Network for Universal Domain AdaptationPoster193 citations
235. Naturalistic Physical Adversarial Patch for Object DetectorsPoster192 citations
236. HiT: Hierarchical Transformer With Momentum Contrast for Video-Text RetrievalPoster191 citations
237. Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments With Support SamplesPoster191 citations
238. Evidential Deep Learning for Open Set Action RecognitionPoster190 citations
239. Leveraging Auxiliary Tasks With Affinity Learning for Weakly Supervised Semantic SegmentationPoster190 citations
240. Stochastic Scene-Aware Motion PredictionPoster190 citations
241. Adaptive Graph Convolution for Point Cloud AnalysisPoster189 citations
242. Hand-Object Contact Consistency Reasoning for Human Grasps GenerationPoster189 citations
243. Visual Alignment Constraint for Continuous Sign Language RecognitionPoster189 citations
244. Probabilistic Modeling for Human Mesh RecoveryPoster188 citations
245. Efficient Visual Pretraining With Contrastive DetectionPoster187 citations
246. Scalable Vision Transformers With Hierarchical PoolingPoster186 citations
247. ACE: Ally Complementary Experts for Solving Long-Tailed Recognition in One-ShotPoster185 citations
248. Fog Simulation on Real LiDAR Point Clouds for 3D Object Detection in Adverse WeatherPoster185 citations
249. Self-Supervised Video Object Segmentation by Motion GroupingPoster185 citations
250. Asymmetric Bilateral Motion Estimation for Video Frame InterpolationPoster184 citations
251. From Two to One: A New Scene Text Recognizer With Visual Language Modeling NetworkPoster184 citations
252. LayoutTransformer: Layout Generation and Completion With Self-AttentionPoster184 citations
253. Video Self-Stitching Graph Network for Temporal Action LocalizationPoster184 citations
254. Zen-NAS: A Zero-Shot NAS for High-Performance Image RecognitionPoster184 citations
255. Gait Recognition in the Wild: A BenchmarkPoster182 citations
256. Large-Scale Robust Deep AUC Maximization: A New Surrogate Loss and Empirical Studies on Medical Image ClassificationPoster181 citations
257. 3DVG-Transformer: Relation Modeling for Visual Grounding on Point CloudsPoster180 citations
258. Full-Duplex Strategy for Video Object SegmentationPoster180 citations
259. CrackFormer: Transformer Network for Fine-Grained Crack DetectionPoster179 citations
260. FuseFormer: Fusing Fine-Grained Information in Transformers for Video InpaintingPoster179 citations
261. Modulated Graph Convolutional Network for 3D Human Pose EstimationPoster179 citations
262. DeepCAD: A Deep Generative Network for Computer-Aided Design ModelsPoster178 citations
263. Explaining in Style: Training a GAN To Explain a Classifier in StyleSpacePoster178 citations
264. Syncretic Modality Collaborative Learning for Visible Infrared Person Re-IdentificationPoster178 citations
265. Learnable Boundary Guided Adversarial TrainingPoster177 citations
266. Better Aggregation in Test-Time AugmentationPoster176 citations
267. Spatial-Temporal Transformer for Dynamic Scene Graph GenerationPoster175 citations
268. Active Domain Adaptation via Clustering Uncertainty-Weighted EmbeddingsPoster173 citations
269. GAN-Control: Explicitly Controllable GANsPoster173 citations
270. Complementary Patch for Weakly Supervised Semantic SegmentationPoster172 citations
271. CrossCLR: Cross-Modal Contrastive Learning for Multi-Modal Video RepresentationsPoster172 citations
272. MINE: Towards Continuous Depth MPI With NeRF for Novel View SynthesisPoster171 citations
273. Entropy Maximization and Meta Classification for Out-of-Distribution Detection in Semantic SegmentationPoster170 citations
274. Learning To Resize Images for Computer Vision TasksPoster170 citations
275. SENTRY: Selective Entropy Optimization via Committee Consistency for Unsupervised Domain AdaptationPoster170 citations
276. Semantically Coherent Out-of-Distribution DetectionPoster170 citations
277. Airbert: In-Domain Pretraining for Vision-and-Language NavigationPoster169 citations
278. Context-Sensitive Temporal Feature Learning for Gait RecognitionPoster169 citations
279. Domain Adaptive Semantic Segmentation With Self-Supervised Depth EstimationPoster169 citations
280. Infinite Nature: Perpetual View Generation of Natural Scenes From a Single ImagePoster169 citations
281. Geometry-Based Distance Decomposition for Monocular 3D Object DetectionPoster168 citations
282. DOLG: Single-Stage Image Retrieval With Deep Orthogonal Fusion of Local and Global FeaturesPoster167 citations
283. Graph Contrastive ClusteringPoster167 citations
284. Reconstructing Hand-Object Interactions in the WildPoster167 citations
285. TeachText: CrossModal Generalized Distillation for Text-Video RetrievalPoster167 citations
286. AutoShape: Real-Time Shape-Aware Monocular 3D Object DetectionPoster165 citations
287. Meta-Learning With Task-Adaptive Loss Function for Few-Shot LearningPoster165 citations
288. IDM: An Intermediate Domain Module for Domain Adaptive Person Re-IDPoster164 citations
289. Predicting With Confidence on Unseen DistributionsPoster164 citations
290. Learning Skeletal Graph Neural Networks for Hard 3D Pose EstimationPoster163 citations
291. Mining Latent Classes for Few-Shot SegmentationPoster162 citations
292. Modulated Periodic Activations for Generalizable Local Functional RepresentationsPoster162 citations
293. Perturbed Self-Distillation: Weakly Supervised Large-Scale Point Cloud Semantic SegmentationPoster162 citations
294. Re-Distributing Biased Pseudo Labels for Semi-Supervised Semantic Segmentation: A Baseline InvestigationPoster162 citations
295. Active Learning for Deep Object Detection via Probabilistic ModelingPoster161 citations
296. FACIAL: Synthesizing Dynamic Talking Face With Implicit Attribute LearningPoster161 citations
297. Unlocking the Potential of Ordinary Classifier: Class-Specific Adversarial Erasing Framework for Weakly Supervised Semantic SegmentationPoster161 citations
298. Guided Point Contrastive Learning for Semi-Supervised Point Cloud Semantic SegmentationPoster160 citations
299. Multi-VAE: Learning Disentangled View-Common and View-Peculiar Visual Representations for Multi-View ClusteringPoster160 citations
300. SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose EstimationPoster160 citations
301. SPEC: Seeing People in the Wild With an Estimated CameraPoster160 citations
302. Unconstrained Scene Generation With Locally Conditioned Radiance FieldsPoster160 citations
303. CM-NAS: Cross-Modality Neural Architecture Search for Visible-Infrared Person Re-IdentificationPoster159 citations
304. CR-Fill: Generative Image Inpainting With Auxiliary Contextual ReconstructionPoster159 citations
305. MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?Poster159 citations
306. TACo: Token-Aware Cascade Contrastive Learning for Video-Text AlignmentPoster159 citations
307. RECALL: Replay-Based Continual Learning in Semantic SegmentationPoster158 citations
308. GroupFormer: Group Activity Recognition With Clustered Spatial-Temporal TransformerPoster157 citations
309. SGPA: Structure-Guided Prior Adaptation for Category-Level 6D Object Pose EstimationPoster156 citations
310. DualPoseNet: Category-Level 6D Object Pose and Size Estimation Using Dual Pose Network With Refined Learning of Pose ConsistencyPoster155 citations
311. Single-Shot Hyperspectral-Depth Imaging With Learned Diffractive OpticsPoster155 citations
312. Spatially-Adaptive Image Restoration Using Distortion-Guided NetworksPoster155 citations
313. Multitask AET With Orthogonal Tangent Regularity for Dark Object DetectionPoster154 citations
314. OadTR: Online Action Detection With TransformersPoster154 citations
315. SynFace: Face Recognition With Synthetic DataPoster154 citations
316. Fourier Space Losses for Efficient Perceptual Image Super-ResolutionPoster153 citations
317. Context Decoupling Augmentation for Weakly Supervised Semantic SegmentationPoster152 citations
318. DC-ShadowNet: Single-Image Hard and Soft Shadow Removal Using Unsupervised Domain-Classifier Guided NetworkPoster152 citations
319. Understanding and Evaluating Racial Biases in Image CaptioningPoster152 citations
320. Weakly Supervised Contrastive LearningPoster152 citations
321. Broaden Your Views for Self-Supervised Video LearningPoster151 citations
322. Recurrent Mask Refinement for Few-Shot Medical Image SegmentationPoster151 citations
323. A Simple Baseline for Semi-Supervised Semantic Segmentation With Strong Data AugmentationPoster150 citations
324. Hierarchical Memory Matching Network for Video Object SegmentationPoster149 citations
325. Learning Meta-Class Memory for Few-Shot Semantic SegmentationPoster149 citations
326. Query Adaptive Few-Shot Object Detection With Heterogeneous Graph Convolutional NetworksPoster149 citations
327. Unidentified Video Objects: A Benchmark for Dense, Open-World SegmentationPoster149 citations
328. Enriching Local and Global Contexts for Temporal Action LocalizationPoster148 citations
329. Ensemble Attention Distillation for Privacy-Preserving Federated LearningPoster148 citations
330. FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance SegmentationPoster148 citations
331. InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds Through Instance Multi-Level Contextual ReferringPoster147 citations
332. KoDF: A Large-Scale Korean DeepFake Detection DatasetPoster147 citations
333. Spatially Conditioned Graphs for Detecting Human-Object InteractionsPoster147 citations
334. Z-Score Normalization, Hubness, and Few-Shot LearningPoster147 citations
335. DAE-GAN: Dynamic Aspect-Aware GAN for Text-to-Image SynthesisPoster146 citations
336. Densely Guided Knowledge Distillation Using Multiple Teacher AssistantsPoster146 citations
337. Universal-Prototype Enhancing for Few-Shot Object DetectionPoster146 citations
338. Learning a Single Network for Scale-Arbitrary Super-ResolutionPoster145 citations
339. Probabilistic Monocular 3D Human Pose Estimation With Normalizing FlowsPoster145 citations
340. R-MSFM: Recurrent Multi-Scale Feature Modulation for Monocular Depth EstimatingPoster145 citations
341. Learning Multi-Scene Absolute Pose Regression With TransformersPoster144 citations
342. LookOut: Diverse Multi-Future Prediction and Planning for Self-DrivingPoster144 citations
343. Structure-Preserving Deraining With Residue Channel Prior GuidancePoster144 citations
344. Instance Segmentation in 3D Scenes Using Semantic Superpoint Tree NetworksPoster143 citations
345. MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory PredictionPoster143 citations
346. Region-Aware Contrastive Learning for Semantic SegmentationPoster143 citations
347. Black-Box Detection of Backdoor Attacks With Limited Information and DataPoster142 citations
348. BossNAS: Exploring Hybrid CNN-Transformers With Block-Wisely Self-Supervised Neural Architecture SearchPoster142 citations
349. Generalize Then Adapt: Source-Free Domain Adaptive Semantic SegmentationPoster142 citations
350. Interpretable Image Recognition by Constructing Transparent Embedding SpacePoster142 citations
351. Learning To Match Features With Seeded Graph Matching NetworkPoster142 citations
352. Pyramid Point Cloud Transformer for Large-Scale Place RecognitionPoster142 citations
353. CPF: Learning a Contact Potential Field To Model the Hand-Object InteractionPoster141 citations
354. High-Performance Discriminative Tracking With TransformersPoster141 citations
355. Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-ResolutionPoster141 citations
356. Talk-To-Edit: Fine-Grained Facial Editing via DialogPoster141 citations
357. Occlude Them All: Occlusion-Aware Attention Network for Occluded Person Re-IDPoster140 citations
358. RGB-D Saliency Detection via Cascaded Mutual Information MinimizationPoster139 citations
359. Region Similarity Representation LearningPoster139 citations
360. Social NCE: Contrastive Learning of Socially-Aware Motion RepresentationsPoster139 citations
361. RFNet: Region-Aware Fusion Network for Incomplete Multi-Modal Brain Tumor SegmentationPoster138 citations
362. Semantics Disentangling for Generalized Zero-Shot LearningPoster138 citations
363. Change Is Everywhere: Single-Temporal Supervised Object Change Detection in Remote Sensing ImageryPoster137 citations
364. Crossover Learning for Fast Online Video Instance SegmentationPoster137 citations
365. ECS-Net: Improving Weakly Supervised Semantic Segmentation by Using Connections Between Class Activation MapsPoster137 citations
366. EPP-MVSNet: Epipolar-Assembling Based Depth Prediction for Multi-View StereoPoster137 citations
367. Learning To Drive From a World on RailsPoster137 citations
368. Deep Hough Voting for Robust Global RegistrationPoster136 citations
369. Distributional Robustness Loss for Long-Tail LearningPoster136 citations
370. GraphFPN: Graph Feature Pyramid Network for Object DetectionPoster136 citations
371. Rethinking the Truly Unsupervised Image-to-Image TranslationPoster136 citations
372. SAT: 2D Semantics Assisted Training for 3D Visual GroundingPoster136 citations
373. Structured Bird's-Eye-View Traffic Scene Understanding From Onboard ImagesPoster136 citations
374. Towards Real-World X-Ray Security Inspection: A High-Quality Benchmark and Lateral Inhibition Module for Prohibited Items DetectionPoster136 citations
375. Vector-Decomposed Disentanglement for Domain-Invariant Object DetectionPoster136 citations
376. HeadGAN: One-Shot Neural Head Synthesis and EditingPoster135 citations
377. Self-Mutual Distillation Learning for Continuous Sign Language RecognitionPoster135 citations
378. 3D Local Convolutional Neural Networks for Gait RecognitionPoster134 citations
379. Separable Flow: Learning Motion Cost Volumes for Optical Flow EstimationPoster134 citations
380. Fine-Grained Semantics-Aware Representation Enhancement for Self-Supervised Monocular Depth EstimationPoster133 citations
381. HRegNet: A Hierarchical Network for Large-Scale Outdoor LiDAR Point Cloud RegistrationPoster133 citations
382. Online Knowledge Distillation for Efficient Pose EstimationPoster133 citations
383. The Way to My Heart Is Through Contrastive Learning: Remote Photoplethysmography From Unlabelled VideoPoster133 citations
384. ELF-VC: Efficient Learned Flexible-Rate Video CodingPoster132 citations
385. Elaborative Rehearsal for Zero-Shot Action RecognitionPoster132 citations
386. Learning From Noisy Data With Robust Representation LearningPoster132 citations
387. WaveFill: A Wavelet-Based Generation Network for Image InpaintingPoster132 citations
388. GANcraft: Unsupervised 3D Neural Rendering of Minecraft WorldsPoster131 citations
389. GLiT: Neural Architecture Search for Global and Local Image TransformerPoster131 citations
390. Knowledge-Enriched Distributional Model Inversion AttacksPoster131 citations
391. Saliency-Associated Object TrackingPoster131 citations
392. Adaptive Unfolding Total Variation Network for Low-Light Image EnhancementPoster130 citations
393. Audio2Gestures: Generating Diverse Gestures From Speech Audio With Conditional Variational AutoencodersPoster130 citations
394. Clothing Status Awareness for Long-Term Person Re-IdentificationPoster130 citations
395. Distilling Virtual Examples for Long-Tailed RecognitionPoster130 citations
396. Fast Video Moment RetrievalPoster130 citations
397. SOTR: Segmenting Objects With TransformersPoster130 citations
398. LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-Based 3D DetectorPoster129 citations
399. Towards Flexible Blind JPEG Artifacts RemovalPoster129 citations
400. Causal Attention for Unbiased Visual RecognitionPoster128 citations
401. Dynamic Context-Sensitive Filtering Network for Video Salient Object DetectionPoster128 citations
402. Neural-GIF: Neural Generalized Implicit Functions for Animating People in ClothingPoster128 citations
403. Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency DomainPoster127 citations
404. Collaborative Unsupervised Visual Representation Learning From Decentralized DataPoster127 citations
405. Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal EstimationPoster127 citations
406. Multi-View 3D Reconstruction With TransformersPoster126 citations
407. Revisiting Adversarial Robustness Distillation: Robust Soft Labels Make Student BetterPoster126 citations
408. Self-Supervised Neural Networks for Spectral Snapshot Compressive ImagingPoster126 citations
409. Vision Transformer With Progressive SamplingPoster126 citations
410. AdvDrop: Adversarial Attack to DNNs by Dropping InformationPoster125 citations
411. Exploring Inter-Channel Correlation for Diversity-Preserved Knowledge DistillationPoster125 citations
412. Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image RescalingPoster125 citations
413. Self Supervision to Distillation for Long-Tailed Visual RecognitionPoster125 citations
414. Unshuffling Data for Improved Generalization in Visual Question AnsweringPoster125 citations
415. Exploring Classification Equilibrium in Long-Tailed Object DetectionPoster124 citations
416. MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports ActionsPoster124 citations
417. Group-Aware Contrastive Regression for Action Quality AssessmentPoster123 citations
418. Skeleton Cloud Colorization for Unsupervised 3D Action Representation LearningPoster123 citations
419. Spatial Uncertainty-Aware Semi-Supervised Crowd CountingPoster123 citations
420. StyleFormer: Real-Time Arbitrary Style Transfer via Parametric Style CompositionPoster123 citations
421. Video Instance Segmentation With a Propose-Reduce ParadigmPoster123 citations
422. Box-Aware Feature Enhancement for Single Object Tracking on Point CloudsPoster122 citations
423. Joint Inductive and Transductive Learning for Video Object SegmentationPoster122 citations
424. Adaptive Boundary Proposal Network for Arbitrary Shape Text DetectionPoster121 citations
425. Adaptive Focus for Efficient Video RecognitionPoster121 citations
426. Understanding and Mitigating Annotation Bias in Facial Expression RecognitionPoster121 citations
427. imGHUM: Implicit Generative Models of 3D Human Shape and Articulated PosePoster121 citations
428. A Broad Study on the Transferability of Visual Representations With Contrastive LearningPoster120 citations
429. Graspness Discovery in Clutters for Fast and Accurate Grasp DetectionPoster120 citations
430. STAR: A Structure-Aware Lightweight Transformer for Real-Time Image EnhancementPoster120 citations
431. TRAR: Routing the Attention Spans in Transformer for Visual Question AnsweringPoster120 citations
432. Towards Face Encryption by Generating Adversarial Identity MasksPoster120 citations
433. Transformer-Based Dual Relation Graph for Multi-Label Image RecognitionPoster120 citations
434. Uncertainty-Aware Pseudo Label Refinery for Domain Adaptive Semantic SegmentationPoster120 citations
435. Online Pseudo Label Generation by Hierarchical Cluster Dynamics for Adaptive Person Re-IdentificationPoster119 citations
436. Pseudo-Mask Matters in Weakly-Supervised Semantic SegmentationPoster119 citations
437. The Power of Points for Modeling Humans in ClothingPoster119 citations
438. Towards Vivid and Diverse Image Colorization With Generative Color PriorPoster119 citations
439. Universal Representation Learning From Multiple Domains for Few-Shot ClassificationPoster119 citations
440. Variable-Rate Deep Image Compression Through Spatially-Adaptive Feature TransformPoster119 citations
441. Deep Co-Training With Task Decomposition for Semi-Supervised Domain AdaptationPoster118 citations
442. NPMs: Neural Parametric Models for 3D Deformable ShapesPoster118 citations
443. Rehearsal Revealed: The Limits and Merits of Revisiting Samples in Continual LearningPoster118 citations
444. Single Image Defocus Deblurring Using Kernel-Sharing Parallel Atrous ConvolutionsPoster118 citations
445. 4DComplete: Non-Rigid Motion Estimation Beyond the Observable SurfacePoster117 citations
446. A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape RepresentationPoster117 citations
447. DRB-GAN: A Dynamic ResBlock Generative Adversarial Network for Artistic Style TransferPoster117 citations
448. Multi-Task Self-Training for Learning General RepresentationsPoster117 citations
449. Seeing Dynamic Scene in the Dark: A High-Quality Video Dataset With Mechatronic AlignmentPoster117 citations
450. Semantic Concentration for Domain AdaptationPoster117 citations
451. Student Customized Knowledge Distillation: Bridging the Gap Between Student and TeacherPoster117 citations
452. Conditional Diffusion for Interactive SegmentationPoster116 citations
453. Dressing in Order: Recurrent Person Image Generation for Pose Transfer, Virtual Try-On and Outfit EditingPoster116 citations
454. Learning Motion Priors for 4D Human Body Capture in 3D ScenesPoster116 citations
455. Preservational Learning Improves Self-Supervised Medical Image Models by Reconstructing Diverse ContextsPoster116 citations
456. Towards Real-World Prohibited Item Detection: A Large-Scale X-Ray BenchmarkPoster116 citations
457. Dynamic Attentive Graph Learning for Image RestorationPoster115 citations
458. Equivariant Imaging: Learning Beyond the Range SpacePoster115 citations
459. FloW: A Dataset and Benchmark for Floating Waste Detection in Inland WatersPoster115 citations
460. PnP-DETR: Towards Efficient Visual Analysis With TransformersPoster115 citations
461. CAPTRA: CAtegory-Level Pose Tracking for Rigid and Articulated Objects From Point CloudsPoster114 citations
462. ReCU: Reviving the Dead Weights in Binary Neural NetworksPoster114 citations
463. Rethinking Self-Supervised Correspondence Learning: A Video Frame-Level Similarity PerspectivePoster114 citations
464. Binocular Mutual Learning for Improving Few-Shot ClassificationPoster113 citations
465. LOKI: Long Term and Key Intentions for Trajectory PredictionPoster113 citations
466. Motion Deblurring With Real EventsPoster113 citations
467. One-Pass Multi-View Clustering for Large-Scale DataPoster113 citations
468. SLIM: Self-Supervised LiDAR Scene Flow and Motion SegmentationPoster113 citations
469. Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene SegmentationPoster113 citations
470. Exploiting Explanations for Model Inversion AttacksPoster112 citations
471. Learning Fast Sample Re-Weighting Without Reward DataPoster112 citations
472. Object Tracking by Jointly Exploiting Frame and Event DomainPoster112 citations
473. Sparse Needlets for Lighting Estimation With Spherical Transport LossPoster112 citations
474. Spatio-Temporal Dynamic Inference Network for Group Activity RecognitionPoster112 citations
475. CANet: A Context-Aware Network for Shadow RemovalPoster111 citations
476. E-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language TasksPoster111 citations
477. Event-Based Video Reconstruction Using TransformerPoster111 citations
478. Influence Selection for Active LearningPoster111 citations
479. Interacting Two-Hand 3D Pose and Shape Reconstruction From Single Color ImagePoster111 citations
480. Seeking Similarities Over Differences: Similarity-Based Domain Alignment for Adaptive Object DetectionPoster111 citations
481. DeepMultiCap: Performance Capture of Multiple Characters Using Sparse Multiview CamerasPoster110 citations
482. Graph-Based Asynchronous Event Processing for Rapid Object RecognitionPoster110 citations
483. Instance-Level Image Retrieval Using Reranking TransformersPoster110 citations
484. Learning of Visual Relations: The Devil Is in the TailsPoster110 citations
485. Location-Aware Single Image Reflection RemovalPoster110 citations
486. Mean Shift for Self-Supervised LearningPoster110 citations
487. Multimodal Clustering Networks for Self-Supervised Learning From Unlabeled VideosPoster110 citations
488. Physics-Based Human Motion Estimation and Synthesis From VideosPoster110 citations
489. A Hierarchical Transformation-Discriminating Generative Model for Few Shot Anomaly DetectionPoster109 citations
490. Auxiliary Tasks and Exploration Enable ObjectGoal NavigationPoster109 citations
491. Dynamic High-Pass Filtering and Multi-Spectral Attention for Image Super-ResolutionPoster109 citations
492. Excavating the Potential Capacity of Self-Supervised Monocular Depth EstimationPoster109 citations
493. Exploring Simple 3D Multi-Object Tracking for Autonomous DrivingPoster109 citations
494. C2N: Practical Generative Noise Modeling for Real-World DenoisingPoster108 citations
495. Unsupervised Depth Completion With Calibrated Backprojection LayersPoster108 citations
496. A Latent Transformer for Disentangled Face Editing in Images and VideosPoster107 citations
497. NGC: A Unified Framework for Learning With Open-World Noisy DataPoster107 citations
498. Pyramid Spatial-Temporal Aggregation for Video-Based Person Re-IdentificationPoster107 citations
499. Disentangled High Quality Salient Object DetectionPoster106 citations
500. Divide and Contrast: Self-Supervised Learning From Uncurated DataPoster106 citations
501. Enhanced Boundary Learning for Glass-Like Object SegmentationPoster106 citations
502. Frequency Domain Image Translation: More Photo-Realistic, Better Identity-PreservingPoster106 citations
503. Generative Layout Modeling Using Constraint GraphsPoster106 citations
504. IntraTomo: Self-Supervised Learning-Based Tomography via Sinogram Synthesis and PredictionPoster106 citations
505. Learning Signed Distance Field for Multi-View Surface ReconstructionPoster106 citations
506. Online Continual Learning With Natural Distribution Shifts: An Empirical Study With Visual DataPoster106 citations
507. Domain Generalization via Gradient SurgeryPoster105 citations
508. From General to Specific: Informative Scene Graph Generation via Balance AdjustmentPoster105 citations
509. Mining Contextual Information Beyond Image for Semantic SegmentationPoster105 citations
510. Mixture-Based Feature Space Learning for Few-Shot Image ClassificationPoster105 citations
511. N-ImageNet: Towards Robust, Fine-Grained Object Recognition With Event CamerasPoster105 citations
512. Encoder-Decoder With Multi-Level Attention for 3D Human Shape and Pose EstimationPoster104 citations
513. H3D-Net: Few-Shot High-Fidelity 3D Head ReconstructionPoster104 citations
514. Improving Contrastive Learning by Visualizing Feature TransformationPoster104 citations
515. Instance-Wise Hard Negative Example Generation for Contrastive Learning in Unpaired Image-to-Image TranslationPoster104 citations
516. SignBERT: Pre-Training of Hand-Model-Aware Representation for Sign Language RecognitionPoster104 citations
517. Towards Better Explanations of Class Activation MappingPoster104 citations
518. Generating Smooth Pose Sequences for Diverse Human Motion PredictionPoster103 citations
519. Representative Color Transform for Image EnhancementPoster103 citations
520. Video-Based Person Re-Identification With Spatial and Temporal Memory NetworksPoster103 citations
521. Beyond Question-Based Biases: Assessing Multimodal Shortcut Learning in Visual Question AnsweringPoster102 citations
522. BiaSwap: Removing Dataset Bias With Bias-Tailored Swapping AugmentationPoster102 citations
523. Geometry-Free View Synthesis: Transformers and No 3D PriorsPoster102 citations
524. Meta Gradient Adversarial AttackPoster102 citations
525. MicroNet: Improving Image Recognition With Extremely Low FLOPsPoster102 citations
526. BAPA-Net: Boundary Adaptation and Prototype Alignment for Cross-Domain Semantic SegmentationPoster101 citations
527. HIRE-SNN: Harnessing the Inherent Robustness of Energy-Efficient Deep Spiking Neural Networks by Training With Crafted Input NoisePoster101 citations
528. Compressing Visual-Linguistic Model via Knowledge DistillationPoster100 citations
529. Free-Form Description Guided 3D Visual Graph Network for Object Grounding in Point CloudPoster100 citations
530. Multiple Heads Are Better Than One: Few-Shot Font Generation With Multiple Localized ExpertsPoster100 citations
531. RePOSE: Fast 6D Object Pose Refinement via Deep Texture RenderingPoster100 citations
532. Deep Metric Learning for Open World Semantic SegmentationPoster99 citations
533. Labels4Free: Unsupervised Segmentation Using StyleGANPoster99 citations
534. Learning Action Completeness From Points for Weakly-Supervised Temporal Action LocalizationPoster99 citations
535. Multi-Instance Pose Networks: Rethinking Top-Down Pose EstimationPoster99 citations
536. OpenForensics: Large-Scale Challenging Dataset for Multi-Face Forgery Detection and Segmentation In-the-WildPoster99 citations
537. Pano-AVQA: Grounded Audio-Visual Question Answering on 360deg VideosPoster99 citations
538. Vision-Language Navigation With Random Environmental MixupPoster99 citations
539. C3-SemiSeg: Contrastive Semi-Supervised Segmentation via Cross-Set Learning and Dynamic Class-BalancingPoster98 citations
540. Context-Aware Scene Graph Generation With Seq2Seq TransformersPoster98 citations
541. High-Resolution Optical Flow From 1D Attention and CorrelationPoster98 citations
542. Real-Time Image Enhancer via Learnable Spatial-Aware 3D Lookup TablesPoster98 citations
543. Unsupervised Domain Adaptive 3D Detection With Multi-Level ConsistencyPoster98 citations
544. DeepGaze IIE: Calibrated Prediction in and Out-of-Domain for State-of-the-Art Saliency ModelingPoster97 citations
545. Exploring Relational Context for Multi-Task Dense PredictionPoster97 citations
546. Foreground-Action Consistency Network for Weakly Supervised Temporal Action LocalizationPoster97 citations
547. Omniscient Video Super-ResolutionPoster97 citations
548. ProFlip: Targeted Trojan Attack With Progressive Bit FlipsPoster97 citations
549. ReDAL: Region-Based and Diversity-Aware Active Learning for Point Cloud Semantic SegmentationPoster97 citations
550. Adversarial Unsupervised Domain Adaptation With Conditional and Label Shift: Infer, Align and IteratePoster96 citations
551. DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence From Box SupervisionPoster96 citations
552. Domain-Invariant Disentangled Network for Generalizable Object DetectionPoster96 citations
553. MonoIndoor: Towards Good Practice of Self-Supervised Monocular Depth Estimation for Indoor EnvironmentsPoster96 citations
554. SSH: A Self-Supervised Framework for Image HarmonizationPoster96 citations
555. Multi-View Radar Semantic SegmentationPoster95 citations
556. Orthogonal Projection LossPoster95 citations
557. A Backdoor Attack Against 3D Point Cloud ClassifiersPoster94 citations
558. Accelerating Atmospheric Turbulence Simulation via Learned Phase-to-Space TransformPoster94 citations
559. Federated Learning for Non-IID Data via Unified Feature Learning and Optimization Objective AlignmentPoster94 citations
560. Human Trajectory Prediction via Counterfactual AnalysisPoster94 citations
561. Learning Cross-Modal Contrastive Features for Video Domain AdaptationPoster94 citations
562. Partner-Assisted Learning for Few-Shot Image ClassificationPoster94 citations
563. Point-Set Distances for Learning Representations of 3D Point CloudsPoster94 citations
564. Waypoint Models for Instruction-Guided Navigation in Continuous EnvironmentsPoster94 citations
565. Do Image Classifiers Generalize Across Time?Poster93 citations
566. Paint Transformer: Feed Forward Neural Painting With Stroke PredictionPoster93 citations
567. Spatio-Temporal Representation Factorization for Video-Based Person Re-IdentificationPoster93 citations
568. Aligning Latent and Image Spaces To Connect the UnconnectablePoster92 citations
569. DepthTrack: Unveiling the Power of RGBD TrackingPoster92 citations
570. Exploiting a Joint Embedding Space for Generalized Zero-Shot Semantic SegmentationPoster92 citations
571. Gradient Normalization for Generative Adversarial NetworksPoster92 citations
572. On Generating Transferable Targeted PerturbationsPoster92 citations
573. Prototypical Matching and Open Set Rejection for Zero-Shot Semantic SegmentationPoster92 citations
574. Sketch Your Own GANPoster92 citations
575. Zero-Shot Day-Night Domain Adaptation With a Physics PriorPoster92 citations
576. Collaborative Optimization and Aggregation for Decentralized Domain Generalization and AdaptationPoster91 citations
577. ISNet: Integrate Image-Level and Semantic-Level Context for Semantic SegmentationPoster91 citations
578. Image Harmonization With TransformerPoster91 citations
579. MGSampler: An Explainable Sampling Strategy for Video Action RecognitionPoster91 citations
580. Progressive Correspondence Pruning by Consensus LearningPoster91 citations
581. Regularizing Nighttime Weirdness: Efficient Self-Supervised Monocular Depth Estimation in the DarkPoster91 citations
582. THDA: Treasure Hunt Data Augmentation for Semantic NavigationPoster91 citations
583. Learning To Stylize Novel ViewsPoster90 citations
584. Local Temperature Scaling for Probability CalibrationPoster90 citations
585. Context Reasoning Attention Network for Image Super-ResolutionPoster89 citations
586. Iterative Label Cleaning for Transductive and Semi-Supervised Few-Shot LearningPoster89 citations
587. LapsCore: Language-Guided Person Search via Color ReasoningPoster89 citations
588. Neural Image Compression via Attentional Multi-Scale Back Projection and Frequency DecompositionPoster89 citations
589. Self-Supervised Product Quantization for Deep Unsupervised Image RetrievalPoster89 citations
590. Three Steps to Multimodal Trajectory Prediction: Modality Clustering, Classification and SynthesisPoster89 citations
591. Dynamic CT Reconstruction From Limited Views With Implicit Neural Representations and Parametric Motion FieldsPoster88 citations
592. PixelSynth: Generating a 3D-Consistent Experience From a Single ImagePoster88 citations
593. Pri3D: Can 3D Priors Help 2D Representation Learning?Poster88 citations
594. Grafit: Learning Fine-Grained Image Representations With Coarse LabelsPoster87 citations
595. Joint Visual and Audio Learning for Video Highlight DetectionPoster87 citations
596. Learning To Generate Scene Graph From Natural Language SupervisionPoster87 citations
597. Learning Unsupervised Metaformer for Anomaly DetectionPoster87 citations
598. SA-ConvONet: Sign-Agnostic Optimization of Convolutional Occupancy NetworksPoster87 citations
599. Semi-Supervised Active Learning With Temporal Output DiscrepancyPoster87 citations
600. Sketch2Mesh: Reconstructing and Editing 3D Shapes From SketchesPoster87 citations
601. The Road To Know-Where: An Object-and-Room Informed Sequential BERT for Indoor Vision-Language NavigationPoster87 citations
602. Exploring Geometry-Aware Contrast and Clustering Harmonization for Self-Supervised 3D Object DetectionPoster86 citations
603. Few-Shot Semantic Segmentation With Cyclic Memory NetworkPoster86 citations
604. Learning To Know Where To See: A Visibility-Aware Approach for Occluded Person Re-IdentificationPoster86 citations
605. RDA: Robust Domain Adaptation via Fourier Adversarial AttackingPoster86 citations
606. Self-Supervised Monocular Depth Estimation for All Day Images Using Domain SeparationPoster86 citations
607. Synthesized Feature Based Few-Shot Class-Incremental Learning on a Mixture of SubspacesPoster86 citations
608. Towards Discriminative Representation Learning for Unsupervised Person Re-IdentificationPoster86 citations
609. 4D-Net for Learned Multi-Modal AlignmentPoster85 citations
610. CryoDRGN2: Ab Initio Neural Reconstruction of 3D Protein Structures From Real Cryo-EM ImagesPoster85 citations
611. Graph-to-3D: End-to-End Generation and Manipulation of 3D Scenes Using Scene GraphsPoster85 citations
612. Hierarchical Object-to-Zone Graph for Object NavigationPoster85 citations
613. Self-Supervised 3D Hand Pose Estimation From Monocular RGB via Contrastive LearningPoster85 citations
614. Shallow Bayesian Meta Learning for Real-World Few-Shot RecognitionPoster85 citations
615. Worldsheet: Wrapping the World in a 3D Sheet for View Synthesis From a Single ImagePoster85 citations
616. Bifold and Semantic Reasoning for Pedestrian Behavior PredictionPoster84 citations
617. Generic Event Boundary Detection: A Benchmark for Event SegmentationPoster84 citations
618. Learning Frequency-Aware Dynamic Network for Efficient Super-ResolutionPoster84 citations
619. Class Semantics-Based Attention for Action DetectionPoster83 citations
620. Contrastive Multimodal Fusion With TupleInfoNCEPoster83 citations
621. Estimating Egocentric 3D Human Pose in Global SpacePoster83 citations
622. Motion Guided Region Message Passing for Video CaptioningPoster83 citations
623. Point Cloud Augmentation With Weighted Local TransformationsPoster83 citations
624. THUNDR: Transformer-Based 3D Human Reconstruction With MarkersPoster83 citations
625. Towards Accurate Alignment in Real-Time 3D Hand-Mesh ReconstructionPoster83 citations
626. Cross-Sentence Temporal and Semantic Relations in Video Activity LocalisationPoster82 citations
627. Dual Path Learning for Domain Adaptation of Semantic SegmentationPoster82 citations
628. Geometry-Aware Self-Training for Unsupervised Domain Adaptation on Object Point CloudsPoster82 citations
629. Interactive Prototype Learning for Egocentric Action RecognitionPoster82 citations
630. MFNet: Multi-Filter Directive Network for Weakly Supervised Salient Object DetectionPoster82 citations
631. Pathdreamer: A World Model for Indoor NavigationPoster82 citations
632. Speech Drives Templates: Co-Speech Gesture Synthesis With Learned TemplatesPoster82 citations
633. Task-Aware Part Mining Network for Few-Shot LearningPoster82 citations
634. Adversarial VQA: A New Benchmark for Evaluating the Robustness of VQA ModelsPoster81 citations
635. Learning Indoor Inverse Rendering With 3D Spatially-Varying LightingPoster81 citations
636. Rethinking Noise Synthesis and Modeling in Raw DenoisingPoster81 citations
637. Road Anomaly Detection by Partial Image Reconstruction With Segmentation CouplingPoster81 citations
638. Unsupervised Deep Video DenoisingPoster81 citations
639. Visual Graph Memory With Unsupervised Representation for Visual NavigationPoster81 citations
640. A Unified 3D Human Motion Synthesis Model via Conditional Variational Auto-EncoderPoster80 citations
641. Distilling Holistic Knowledge With Graph Neural NetworksPoster80 citations
642. Image Synthesis From Layout With Locality-Aware Mask AdaptionPoster80 citations
643. Joint Visual Semantic Reasoning: Multi-Stage Decoder for Text RecognitionPoster80 citations
644. Learning Inner-Group Relations on Point CloudsPoster80 citations
645. Learning With Noisy Labels via Sparse RegularizationPoster80 citations
646. Parallel Rectangle Flip Attack: A Query-Based Black-Box Attack Against Object DetectionPoster80 citations
647. Personalized and Invertible Face De-Identification by Disentangled Identity Information ManipulationPoster80 citations
648. Self-Supervised 3D Skeleton Action Representation Learning With Motion Consistency and ContinuityPoster80 citations
649. Target Adaptive Context Aggregation for Video Scene Graph GenerationPoster80 citations
650. Where Are You Heading? Dynamic Trajectory Prediction With Expert Goal ExamplesPoster80 citations
651. Boosting the Generalization Capability in Cross-Domain Few-Shot Learning via Noise-Enhanced Supervised AutoencoderPoster79 citations
652. How To Train Neural Networks for Flare RemovalPoster79 citations
653. Joint Representation Learning and Novel Category Discovery on Single- and Multi-Modal DataPoster79 citations
654. LoFGAN: Fusing Local Representations for Few-Shot Image GenerationPoster79 citations
655. Robust Small Object Detection on the Water Surface Through Fusion of Camera and Millimeter Wave RadarPoster79 citations
656. Solving Inefficiency of Self-Supervised Representation LearningPoster79 citations
657. Spatial and Semantic Consistency Regularizations for Pedestrian Attribute RecognitionPoster79 citations
658. Transporting Causal Mechanisms for Unsupervised Domain AdaptationPoster79 citations
659. Voxel-Based Network for Shape Completion by Leveraging Edge GenerationPoster79 citations
660. Data-Free Universal Adversarial Perturbation and Black-Box AttackPoster78 citations
661. Greedy Gradient Ensemble for Robust Visual Question AnsweringPoster78 citations
662. Learning Motion-Appearance Co-Attention for Zero-Shot Video Object SegmentationPoster78 citations
663. Mitigating Intensity Bias in Shadow Detection via Feature Decomposition and ReweightingPoster78 citations
664. MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep SubnetworksPoster78 citations
665. Online Refinement of Low-Level Feature Based Activation Map for Weakly Supervised Object LocalizationPoster78 citations
666. StructDepth: Leveraging the Structural Regularities for Self-Supervised Indoor Depth EstimationPoster78 citations
667. Watch Only Once: An End-to-End Video Action Detection FrameworkPoster78 citations
668. Contrast and Order Representations for Video Self-Supervised LearningPoster77 citations
669. GAN Inversion for Out-of-Range Images With Geometric TransformationsPoster77 citations
670. Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration Without ForgettingPoster77 citations
671. LatentCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable DirectionsPoster77 citations
672. M3D-VTON: A Monocular-to-3D Virtual Try-On NetworkPoster77 citations
673. STVGBert: A Visual-Linguistic Transformer Based Framework for Spatio-Temporal Video GroundingPoster77 citations
674. Towards Mixed-Precision Quantization of Neural Networks via Constrained OptimizationPoster77 citations
675. Track Without Appearance: Learn Box and Tracklet Embedding With Local and Global Motion Patterns for Vehicle TrackingPoster77 citations
676. ZFlow: Gated Appearance Flow-Based Virtual Try-On With 3D PriorsPoster77 citations
677. Boundary-Sensitive Pre-Training for Temporal Localization in VideosPoster76 citations
678. Class-Incremental Learning for Action Recognition in VideosPoster76 citations
679. D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised ActivationsPoster76 citations
680. Domain-Aware Universal Style TransferPoster76 citations
681. ECACL: A Holistic Framework for Semi-Supervised Domain AdaptationPoster76 citations
682. Hierarchical Kinematic Probability Distributions for 3D Human Shape and Pose Estimation From Images in the WildPoster76 citations
683. Trash To Treasure: Harvesting OOD Data With Cross-Modal Matching for Open-Set Semi-Supervised LearningPoster76 citations
684. Variational Feature Disentangling for Fine-Grained Few-Shot ClassificationPoster76 citations
685. 3DStyleNet: Creating 3D Shapes With Geometric and Texture Style VariationsPoster75 citations
686. On the Limits of Pseudo Ground Truth in Visual Camera Re-LocalisationPoster75 citations
687. Product1M: Towards Weakly Supervised Instance-Level Product Retrieval via Cross-Modal PretrainingPoster75 citations
688. Scene Context-Aware Salient Object DetectionPoster75 citations
689. Tune It the Right Way: Unsupervised Validation of Domain Adaptation via Soft Neighborhood DensityPoster75 citations
690. VMNet: Voxel-Mesh Network for Geodesic-Aware 3D Semantic SegmentationPoster75 citations
691. Webly Supervised Fine-Grained Recognition: Benchmark Datasets and an ApproachPoster75 citations
692. Adversarial Example Detection Using Latent Neighborhood GraphPoster74 citations
693. Attention Is Not Enough: Mitigating the Distribution Discrepancy in Asynchronous Multimodal Sequence FusionPoster74 citations
694. Deep Reparametrization of Multi-Frame Super-Resolution and DenoisingPoster74 citations
695. Dynamic Cross Feature Fusion for Remote Sensing PansharpeningPoster74 citations
696. Foreground Activation Maps for Weakly Supervised Object LocalizationPoster74 citations
697. HDR Video Reconstruction: A Coarse-To-Fine Network and a Real-World Benchmark DatasetPoster74 citations
698. Handwriting TransformersPoster74 citations
699. Bringing Events Into Video Deblurring With Non-Consecutively Blurry FramesPoster73 citations
700. CrossNorm and SelfNorm for Generalization Under Distribution ShiftsPoster73 citations
701. I2UV-HandNet: Image-to-UV Prediction Network for Accurate and High-Fidelity 3D Hand Mesh ModelingPoster73 citations
702. On Compositions of Transformations in Contrastive Self-Supervised LearningPoster73 citations
703. Patch Craft: Video Denoising by Deep Modeling and Patch MatchingPoster73 citations
704. Relating Adversarially Robust Generalization to Flat MinimaPoster73 citations
705. Adaptive Surface Normal Constraint for Depth EstimationPoster72 citations
706. Beyond Trivial Counterfactual Explanations With Diverse Valuable ExplanationsPoster72 citations
707. Dense Deep Unfolding Network With 3D-CNN Prior for Snapshot Compressive ImagingPoster72 citations
708. Image Synthesis via Semantic CompositionPoster72 citations
709. Minimal Adversarial Examples for Deep Learning on 3D Point CloudsPoster72 citations
710. Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image GenerationPoster72 citations
711. Summarize and Search: Learning Consensus-Aware Dynamic Convolution for Co-Saliency DetectionPoster72 citations
712. Tripartite Information Mining and Integration for Image MattingPoster72 citations
713. A General Recurrent Tracking Framework Without Real DataPoster71 citations
714. Adversarial Attacks on Multi-Agent CommunicationPoster71 citations
715. Curvature Generation in Curved Spaces for Few-Shot LearningPoster71 citations
716. Dual Contrastive Loss and Attention for GANsPoster71 citations
717. Generalizing Gaze Estimation With Outlier-Guided Collaborative AdaptationPoster71 citations
718. Gradient Distribution Alignment Certificates Better Adversarial Domain AdaptationPoster71 citations
719. PCAM: Product of Cross-Attention Matrices for Rigid Registration of Point CloudsPoster71 citations
720. Pseudo-Loss Confidence Metric for Semi-Supervised Few-Shot LearningPoster71 citations
721. Striking a Balance Between Stability and Plasticity for Class-Incremental LearningPoster71 citations
722. Time-Equivariant Contrastive Video Representation LearningPoster71 citations
723. Towards Discovery and Attribution of Open-World GAN Generated ImagesPoster71 citations
724. Deep Symmetric Network for Underexposed Image Enhancement With Recurrent Attentional LearningPoster70 citations
725. Digging Into Uncertainty in Self-Supervised Multi-View StereoPoster70 citations
726. Energy-Based Open-World Uncertainty Modeling for Confidence CalibrationPoster70 citations
727. Learning To Reduce Defocus Blur by Realistically Modeling Dual-Pixel DataPoster70 citations
728. Motion Basis Learning for Unsupervised Deep Homography Estimation With Subspace ProjectionPoster70 citations
729. Robust Watermarking for Deep Neural Networks via Bi-Level OptimizationPoster70 citations
730. ADNet: Leveraging Error-Bias Towards Normal Direction in Face AlignmentPoster69 citations
731. Full-Body Motion From a Single Head-Mounted Device: Generating SMPL Poses From Partial ObservationsPoster69 citations
732. Heterogeneous Relational Complement for Vehicle Re-IdentificationPoster69 citations
733. Knowledge Mining and Transferring for Domain Adaptive Object DetectionPoster69 citations
734. Learning a Sketch Tensor Space for Image Inpainting of Man-Made ScenesPoster69 citations
735. Mixed SIGNals: Sign Language Production via a Mixture of Motion PrimitivesPoster69 citations
736. Occluded Person Re-Identification With Single-Scale Global RepresentationsPoster69 citations
737. PX-NET: Simple and Efficient Pixel-Wise Training of Photometric Stereo NetworksPoster69 citations
738. Parsing Table Structures in the WildPoster69 citations
739. Refining Action Segmentation With Hierarchical Video RepresentationsPoster69 citations
740. TGRNet: A Table Graph Reconstruction Network for Table Structure RecognitionPoster69 citations
741. A New Journey From SDRTV to HDRTVPoster68 citations
742. Dual Bipartite Graph Learning: A General Approach for Domain Adaptive Object DetectionPoster68 citations
743. Learning Privacy-Preserving Optics for Human Pose EstimationPoster68 citations
744. VENet: Voting Enhancement Network for 3D Object DetectionPoster68 citations
745. Wanderlust: Online Continual Object Detection in the Real WorldPoster68 citations
746. AdaSGN: Adapting Joint Number and Model Size for Efficient Skeleton-Based Action RecognitionPoster67 citations
747. Deep Transport Network for Unsupervised Video Object SegmentationPoster67 citations
748. Dense Interaction Learning for Video-Based Person Re-IdentificationPoster67 citations
749. Stochastic Partial Swap: Enhanced Model Generalization and Interpretability for Fine-Grained RecognitionPoster67 citations
750. Conditional Variational Capsule Network for Open Set RecognitionPoster66 citations
751. Fooling LiDAR Perception via Adversarial Trajectory PerturbationPoster66 citations
752. GarmentNets: Category-Level Pose Estimation for Garments via Canonical Space Shape CompletionPoster66 citations
753. Graph-Based 3D Multi-Person Pose Estimation Using Multi-View ImagesPoster66 citations
754. ISD: Self-Supervised Learning by Iterative Similarity DistillationPoster66 citations
755. MLVSNet: Multi-Level Voting Siamese Network for 3D Visual TrackingPoster66 citations
756. Sparse-to-Dense Feature Matching: Intra and Inter Domain Cross-Modal Learning in Domain Adaptation for 3D Semantic SegmentationPoster66 citations
757. Vi2CLR: Video and Image for Visual Contrastive Learning of RepresentationPoster66 citations
758. WarpedGANSpace: Finding Non-Linear RBF Paths in GAN Latent SpacePoster66 citations
759. AdaMML: Adaptive Multi-Modal Learning for Efficient Video RecognitionPoster65 citations
760. Dance With Self-Attention: A New Look of Conditional Random Fields on Anomaly Detection in VideosPoster65 citations
761. Describing and Localizing Multiple Changes With TransformersPoster65 citations
762. EigenGAN: Layer-Wise Eigen-Learning for GANsPoster65 citations
763. GDP: Stabilized Neural Network Pruning via Gates With Differentiable PolarizationPoster65 citations
764. Learning To Regress Bodies From Images Using Differentiable Semantic RenderingPoster65 citations
765. Learning To Track Objects From Unlabeled VideosPoster65 citations
766. MEDIRL: Predicting the Visual Attention of Drivers via Maximum Entropy Deep Inverse Reinforcement LearningPoster65 citations
767. MultiSiam: Self-Supervised Multi-Instance Siamese Representation Learning for Autonomous DrivingPoster65 citations
768. RINDNet: Edge Detection for Discontinuity in Reflectance, Illumination, Normal and DepthPoster65 citations
769. RandomRooms: Unsupervised Pre-Training From Synthetic Shapes and Randomized Layouts for 3D Object DetectionPoster65 citations
770. TransForensics: Image Forgery Localization With Dense Self-AttentionPoster65 citations
771. Unsupervised Layered Image Decomposition Into Object PrototypesPoster65 citations
772. DeePSD: Automatic Deep Skinning and Pose Space Deformation for 3D Garment AnimationPoster64 citations
773. GistNet: A Geometric Structure Transfer Network for Long-Tailed RecognitionPoster64 citations
774. Lightweight Multi-Person Total Motion Capture Using Sparse Multi-View CamerasPoster64 citations
775. MAAS: Multi-Modal Assignation for Active Speaker DetectionPoster64 citations
776. Motion Prediction Using Trajectory CuesPoster64 citations
777. PointBA: Towards Backdoor Attacks in 3D Point CloudPoster64 citations
778. SIGN: Spatial-Information Incorporated Generative Network for Generalized Zero-Shot Semantic SegmentationPoster64 citations
779. TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the WildPoster64 citations
780. Task Switching Network for Multi-Task LearningPoster64 citations
781. The Benefit of Distraction: Denoising Camera-Based Physiological Measurements Using Inverse AttentionPoster64 citations
782. When Do GANs Replicate? On the Choice of Dataset SizePoster64 citations
783. Achieving On-Mobile Real-Time Super-Resolution With Neural Architecture and Pruning SearchPoster63 citations
784. Attentional Pyramid Pooling of Salient Visual Residuals for Place RecognitionPoster63 citations
785. Contrasting Contrastive Self-Supervised Representation Learning PipelinesPoster63 citations
786. Deep Blind Video Super-ResolutionPoster63 citations
787. Diagonal Attention and Style-Based GAN for Content-Style Disentanglement in Image Generation and TranslationPoster63 citations
788. Dynamic Surface Function Networks for Clothed Human BodiesPoster63 citations
789. Efficient Video Compression via Content-Adaptive Super-ResolutionPoster63 citations
790. GP-S3Net: Graph-Based Panoptic Sparse Semantic Segmentation NetworkPoster63 citations
791. Hand Image Understanding via Deep Multi-Task LearningPoster63 citations
792. Multiview Pseudo-Labeling for Semi-Supervised Learning From VideoPoster63 citations
793. Personalized Trajectory Prediction via Distribution DiscriminationPoster63 citations
794. Rethinking Deep Image Prior for DenoisingPoster63 citations
795. Towards a Universal Model for Cross-Dataset Crowd CountingPoster63 citations
796. VIL-100: A New Dataset and a Baseline Model for Video Instance Lane DetectionPoster63 citations
797. VolumeFusion: Deep Depth Fusion for 3D Scene ReconstructionPoster63 citations
798. A Closer Look at Rotation-Invariant Deep Point Cloud AnalysisPoster62 citations
799. Building-GAN: Graph-Conditioned Architectural Volumetric Design GenerationPoster62 citations
800. Cross-Category Video Highlight Detection via Set-Based LearningPoster62 citations
801. EventHands: Real-Time Neural 3D Hand Pose Estimation From an Event StreamPoster62 citations
802. HAIR: Hierarchical Visual-Semantic Relational Reasoning for Video Question AnsweringPoster62 citations
803. How To Design a Three-Stage Architecture for Audio-Visual Active Speaker Detection in the WildPoster62 citations
804. Learning Conditional Knowledge Distillation for Degraded-Reference Image Quality AssessmentPoster62 citations
805. P2-Net: Joint Description and Detection of Local Features for Pixel and Point MatchingPoster62 citations
806. Rank & Sort Loss for Object Detection and Instance SegmentationPoster62 citations
807. Real-World Video Super-Resolution: A Benchmark Dataset and a Decomposition Based Learning SchemePoster62 citations
808. Toward Human-Like Grasp: Dexterous Grasping via Semantic Representation of Object-HandPoster62 citations
809. Zero-Shot Natural Language Video LocalizationPoster62 citations
810. CanvasVAE: Learning To Generate Vector Graphic DocumentsPoster61 citations
811. Image2Reverb: Cross-Modal Reverb Impulse Response SynthesisPoster61 citations
812. Self-Supervised Vessel Segmentation via Adversarial LearningPoster61 citations
813. SimROD: A Simple Adaptation Method for Robust Object DetectionPoster61 citations
814. Stochastic Transformer Networks With Linear Competing Units: Application To End-to-End SL TranslationPoster61 citations
815. Temporal Cue Guided Video Highlight Detection With Low-Rank Audio-Visual FusionPoster61 citations
816. Towards Interpretable Deep Metric Learning With Structural MatchingPoster61 citations
817. Unsupervised Real-World Super-Resolution: A Domain Adaptation PerspectivePoster61 citations
818. Boosting Weakly Supervised Object Detection via Learning Bounding Box AdjustersPoster60 citations
819. CDNet: Centripetal Direction Network for Nuclear Instance SegmentationPoster60 citations
820. Continual Learning on Noisy Data Streams via Self-Purified ReplayPoster60 citations
821. Cross-Camera Convolutional Color ConstancyPoster60 citations
822. HAA500: Human-Centric Atomic Action Dataset With Curated VideosPoster60 citations
823. Learning To Adversarially Blur Visual Object TrackingPoster60 citations
824. Manifold Alignment for Semantically Aligned Style TransferPoster60 citations
825. Meta Navigator: Search for a Good Adaptation Policy for Few-Shot LearningPoster60 citations
826. Multi-Anchor Active Domain Adaptation for Semantic SegmentationPoster60 citations
827. RobustNav: Towards Benchmarking Robustness in Embodied NavigationPoster60 citations
828. Self-Supervised Geometric Features Discovery via Interpretable Attention for Vehicle Re-Identification and BeyondPoster60 citations
829. Adversarial Attacks Are Reversible With Natural SupervisionPoster59 citations
830. DRIVE: Deep Reinforced Accident Anticipation With Visual ExplanationPoster59 citations
831. Deep Relational Metric LearningPoster59 citations
832. Discriminative Region-Based Multi-Label Zero-Shot LearningPoster59 citations
833. Extending Neural P-Frame Codecs for B-Frame CodingPoster59 citations
834. From Contexts to Locality: Ultra-High Resolution Image Segmentation via Locality-Aware Contextual CorrelationPoster59 citations
835. The Center of Attention: Center-Keypoint Grouping via Attention for Multi-Person Pose EstimationPoster59 citations
836. Unpaired Learning for Deep Image Deraining With Rain Direction RegularizerPoster59 citations
837. Collaborative and Adversarial Learning of Focused and Dispersive Representations for Semi-Supervised Polyp SegmentationPoster58 citations
838. DecentLaM: Decentralized Momentum SGD for Large-Batch Deep TrainingPoster58 citations
839. EventHPE: Event-Based 3D Human Pose and Shape EstimationPoster58 citations
840. Hybrid Neural Fusion for Full-Frame Video StabilizationPoster58 citations
841. Improving Neural Network Efficiency via Post-Training Quantization With Adaptive Floating-PointPoster58 citations
842. Learning Attribute-Driven Disentangled Representations for Interactive Fashion RetrievalPoster58 citations
843. Low Curvature Activations Reduce Overfitting in Adversarial TrainingPoster58 citations
844. SCOUTER: Slot Attention-Based Classifier for Explainable Image RecognitionPoster58 citations
845. STEM: An Approach to Multi-Source Domain Adaptation With GuaranteesPoster58 citations
846. Shape Self-Correction for Unsupervised Point Cloud UnderstandingPoster58 citations
847. The Devil Is in the Task: Exploiting Reciprocal Appearance-Localization Features for Monocular 3D Object DetectionPoster58 citations
848. Triggering Failures: Out-of-Distribution Detection by Learning From Local Adversarial Attacks in Semantic SegmentationPoster58 citations
849. Video Pose Distillation for Few-Shot, Fine-Grained Sports Action RecognitionPoster58 citations
850. Audio-Visual Floorplan ReconstructionPoster57 citations
851. CDS: Cross-Domain Self-Supervised Pre-TrainingPoster57 citations
852. Crowd Counting With Partial Annotations in an ImagePoster57 citations
853. Domain Adaptive Video Segmentation via Temporal Consistency RegularizationPoster57 citations
854. Explainable Person Re-Identification With Attribute-Guided Metric DistillationPoster57 citations
855. ORBIT: A Real-World Few-Shot Dataset for Teachable Object RecognitionPoster57 citations
856. On Exposing the Challenging Long Tail in Future Prediction of Traffic ActorsPoster57 citations
857. Shape-Aware Multi-Person Pose Estimation From Multi-View ImagesPoster57 citations
858. T-SVDNet: Exploring High-Order Prototypical Correlations for Multi-Source Domain AdaptationPoster57 citations
859. Transductive Few-Shot Classification on the Oblique ManifoldPoster57 citations
860. Variational Attention: Propagating Domain-Specific Knowledge for Multi-Domain Learning in Crowd CountingPoster57 citations
861. ASCNet: Self-Supervised Video Representation Learning With Appearance-Speed ConsistencyPoster56 citations
862. AdaFit: Rethinking Learning-Based Normal Estimation on Point CloudsPoster56 citations
863. Clustering by Maximizing Mutual Information Across ViewsPoster56 citations
864. Discover the Unknown Biased Attribute of an Image ClassifierPoster56 citations
865. Dynamic Network Quantization for Efficient Video InferencePoster56 citations
866. Else-Net: Elastic Semantic Network for Continual Action Recognition From Skeleton DataPoster56 citations
867. End-to-End Detection and Pose Estimation of Two Interacting HandsPoster56 citations
868. HPNet: Deep Primitive Segmentation Using Hybrid RepresentationsPoster56 citations
869. HandFoldingNet: A 3D Hand Pose Estimation Network Using Multiscale-Feature Guided Folding of a 2D Hand SkeletonPoster56 citations
870. Learning Generative Models of Textured 3D Meshes From Real-World ImagesPoster56 citations
871. Learning Self-Similarity in Space and Time As Generalized Motion for Video Action RecognitionPoster56 citations
872. NAS-OoD: Neural Architecture Search for Out-of-Distribution GeneralizationPoster56 citations
873. NeuSpike-Net: High Speed Video Reconstruction via Bio-Inspired Neuromorphic CamerasPoster56 citations
874. Online Multi-Granularity Distillation for GAN CompressionPoster56 citations
875. Stacked Homography Transformations for Multi-View Pedestrian DetectionPoster56 citations
876. Towards High Fidelity Monocular Face Reconstruction With Rich Reflectance Using Self-Supervised Learning and Ray TracingPoster56 citations
877. ACAV100M: Automatic Curation of Large-Scale Datasets for Audio-Visual Video Representation LearningPoster55 citations
878. Distilling Optimal Neural Networks: Rapid Search in Diverse SpacesPoster55 citations
879. Evolving Search Space for Neural Architecture SearchPoster55 citations
880. LabOR: Labeling Only if Required for Domain Adaptive Semantic SegmentationPoster55 citations
881. Learning Anchored Unsigned Distance Functions With Gradient Direction Alignment for Single-View Garment ReconstructionPoster55 citations
882. Learning With Noisy Labels for Robust Point Cloud SegmentationPoster55 citations
883. Move2Hear: Active Audio-Visual Source SeparationPoster55 citations
884. Procedure Planning in Instructional Videos via Contextual Modeling and Model-Based Policy LearningPoster55 citations
885. Unified Graph Structured Models for Video UnderstandingPoster55 citations
886. Divide and Conquer for Single-Frame Temporal Action LocalizationPoster54 citations
887. Dual-Camera Super-Resolution With Aligned Attention ModulesPoster54 citations
888. EvIntSR-Net: Event Guided Multiple Latent Frames Reconstruction and Super-ResolutionPoster54 citations
889. Explain Me the Painting: Multi-Topic Knowledgeable Art Description GenerationPoster54 citations
890. Joint Topology-Preserving and Feature-Refinement Network for Curvilinear Structure SegmentationPoster54 citations
891. LocalTrans: A Multiscale Local Transformer Network for Cross-Resolution Homography EstimationPoster54 citations
892. A Style and Semantic Memory Mechanism for Domain GeneralizationPoster53 citations
893. AINet: Association Implantation for Superpixel SegmentationPoster53 citations
894. Augmented Lagrangian Adversarial AttacksPoster53 citations
895. Batch Normalization Increases Adversarial Vulnerability and Decreases Adversarial Transferability: A Non-Robust Feature PerspectivePoster53 citations
896. Deep Implicit Surface Point Prediction NetworksPoster53 citations
897. Generative Adversarial Registration for Improved Conditional Deformable TemplatesPoster53 citations
898. In Defense of Scene Graphs for Image CaptioningPoster53 citations
899. Learning Hierarchical Graph Neural Networks for Image ClusteringPoster53 citations
900. PARTS: Unsupervised Segmentation With Slots, Attention and Independence MaximizationPoster53 citations
901. SIGNET: Efficient Neural Representation for Light FieldsPoster53 citations
902. Support-Set Based Cross-Supervision for Video GroundingPoster53 citations
903. The Surprising Effectiveness of Visual Odometry Techniques for Embodied PointGoal NavigationPoster53 citations
904. VideoLT: Large-Scale Long-Tailed Video RecognitionPoster53 citations
905. AdvRush: Searching for Adversarially Robust Neural ArchitecturesPoster52 citations
906. Contextually Plausible and Diverse 3D Human Motion PredictionPoster52 citations
907. Learning RAW-to-sRGB Mappings With Inaccurately Aligned SupervisionPoster52 citations
908. Meta-Aggregator: Learning To Aggregate for 1-Bit Graph Neural NetworksPoster52 citations
909. Multi-Modality Associative Bridging Through Memory: Speech Sound Recollected From Face VideoPoster52 citations
910. Multi-Source Domain Adaptation for Object DetectionPoster52 citations
911. Multiresolution Deep Implicit Functions for 3D Shape RepresentationPoster52 citations
912. Robust Small-Scale Pedestrian Detection With Cued Recall via Memory LearningPoster52 citations
913. SLAMP: Stochastic Latent Appearance and Motion PredictionPoster52 citations
914. Self-Supervised Video Representation Learning With Meta-Contrastive NetworkPoster52 citations
915. Cloud Transformers: A Universal Approach to Point Cloud Processing TasksPoster51 citations
916. Fast Light-Field Disparity Estimation With Multi-Disparity-Scale Cost AggregationPoster51 citations
917. Kernel Methods in Hyperbolic SpacesPoster51 citations
918. MGNet: Monocular Geometric Scene Understanding for Autonomous DrivingPoster51 citations
919. Meta Pairwise Relationship Distillation for Unsupervised Person Re-IdentificationPoster51 citations
920. PlaneTR: Structure-Guided Transformers for 3D Plane RecoveryPoster51 citations
921. SLIDE: Single Image 3D Photography With Soft Layering and Depth-Aware InpaintingPoster51 citations
922. StarEnhancer: Learning Real-Time and Style-Aware Image EnhancementPoster51 citations
923. Visual Distant Supervision for Scene Graph GenerationPoster51 citations
924. Warp Consistency for Unsupervised Learning of Dense CorrespondencesPoster51 citations
925. Act the Part: Learning Interaction Strategies for Articulated Object Part DiscoveryPoster50 citations
926. Auto Graph Encoder-Decoder for Neural Network PruningPoster50 citations
927. CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape ParsingPoster50 citations
928. Concept Generalization in Visual Representation LearningPoster50 citations
929. DRINet: A Dual-Representation Iterative Learning Network for Point Cloud SegmentationPoster50 citations
930. Detection and Continual Learning of Novel Face Presentation AttacksPoster50 citations
931. Direct Differentiable Augmentation SearchPoster50 citations
932. FloorPlanCAD: A Large-Scale CAD Drawing Dataset for Panoptic Symbol SpottingPoster50 citations
933. Hyperspectral Image Denoising With Realistic DataPoster50 citations
934. Internal Video Inpainting by Implicit Long-Range PropagationPoster50 citations
935. Learning Bias-Invariant Representation by Cross-Sample Mutual Information MinimizationPoster50 citations
936. Localized Simple Multiple Kernel K-MeansPoster50 citations
937. MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object DetectionPoster50 citations
938. Multi-Scale Matching Networks for Semantic CorrespondencePoster50 citations
939. PASS: Protected Attribute Suppression System for Mitigating Bias in Face RecognitionPoster50 citations
940. von Mises-Fisher Loss: An Exploration of Embedding Geometries for Supervised LearningPoster50 citations
941. BuildingNet: Learning To Label 3D BuildingsPoster49 citations
942. CTRL-C: Camera Calibration TRansformer With Line-ClassificationPoster49 citations
943. Can Scale-Consistent Monocular Depth Be Learned in a Self-Supervised Scale-Invariant Manner?Poster49 citations
944. Differentiable Surface Rendering via Non-Differentiable SamplingPoster49 citations
945. Diverse Image Style Transfer via Invertible Cross-Space MappingPoster49 citations
946. Dynamic Divide-and-Conquer Adversarial Training for Robust Semantic SegmentationPoster49 citations
947. Learned Spatial Representations for Few-Shot Talking-Head SynthesisPoster49 citations
948. Learning an Augmented RGB Representation With Cross-Modal Knowledge Distillation for Action DetectionPoster49 citations
949. RAIN: Reinforced Hybrid Attention Inference Network for Motion ForecastingPoster49 citations
950. SUNet: Symmetric Undistortion Network for Rolling Shutter CorrectionPoster49 citations
951. Scribble-Supervised Semantic Segmentation InferencePoster49 citations
952. Self-Supervised Visual Representations Learning by Contrastive Mask PredictionPoster49 citations
953. StereOBJ-1M: Large-Scale Stereo Image Dataset for 6D Object Pose EstimationPoster49 citations
954. Towards Alleviating the Modeling Ambiguity of Unsupervised Monocular 3D Human Pose EstimationPoster49 citations
955. Uniformity in Heterogeneity: Diving Deep Into Count Interval Partition for Crowd CountingPoster49 citations
956. 3D Human Texture Estimation From a Single Image With TransformersPoster48 citations
957. Adaptive Curriculum LearningPoster48 citations
958. COMISR: Compression-Informed Video Super-ResolutionPoster48 citations
959. Geometric Unsupervised Domain Adaptation for Semantic SegmentationPoster48 citations
960. Improving Robustness Against Common Corruptions With Frequency Biased ModelsPoster48 citations
961. Learning Compatible EmbeddingsPoster48 citations
962. Light Field Saliency Detection With Dual Local Graph Learning and Reciprocative GuidancePoster48 citations
963. PR-GCN: A Deep Graph Convolutional Network With Point Refinement for 6D Pose EstimationPoster48 citations
964. PU-EVA: An Edge-Vector Based Approximation Solution for Flexible-Scale Point Cloud UpsamplingPoster48 citations
965. Pyramid Architecture Search for Real-Time Image DeblurringPoster48 citations
966. RFNet: Recurrent Forward Network for Dense Point Cloud CompletionPoster48 citations
967. Scribble-Supervised Semantic Segmentation by Uncertainty Reduction on Neural Representation and Self-Supervision on Neural EigenspacePoster48 citations
968. Visual Relationship Detection Using Part-and-Sum Transformers With Composite QueriesPoster48 citations
969. Hypergraph Neural Networks for Hypergraph MatchingPoster47 citations
970. Impact of Aliasing on Generalization in Deep Convolutional NetworksPoster47 citations
971. Improving Low-Precision Network Quantization via Bin RegularizationPoster47 citations
972. Motion-Focused Contrastive Learning of Video RepresentationsPoster47 citations
973. Neural Video Portrait Relighting in Real-Time via Consistency ModelingPoster47 citations
974. On the Importance of Distractors for Few-Shot ClassificationPoster47 citations
975. Once Quantization-Aware Training: High Performance Extremely Low-Bit Architecture SearchPoster47 citations
976. Towards Novel Target Discovery Through Open-Set Domain AdaptationPoster47 citations
977. Unsupervised Learning of Fine Structure Generation for 3D Point Clouds by 2D Projections MatchingPoster47 citations
978. Unsupervised Non-Rigid Image Distortion Removal via Grid DeformationPoster47 citations
979. Adversarial Robustness for Unsupervised Domain AdaptationPoster46 citations
980. An Asynchronous Kalman Filter for Hybrid Event CamerasPoster46 citations
981. Continual Neural Mapping: Learning an Implicit Scene Representation From Sequential ObservationsPoster46 citations
982. DCT-SNN: Using DCT To Distribute Spatial Information Over Time for Low-Latency Spiking Neural NetworksPoster46 citations
983. Distance-Aware QuantizationPoster46 citations
984. From Continuity to Editability: Inverting GANs With Consecutive ImagesPoster46 citations
985. Global Pooling, More Than Meets the Eye: Position Information Is Encoded Channel-Wise in CNNsPoster46 citations
986. Light Source Guided Single-Image Flare Removal From Unpaired DataPoster46 citations
987. SGMNet: Learning Rotation-Invariant Point Cloud Representations via Sorted Gram MatrixPoster46 citations
988. Self-Regulation for Semantic SegmentationPoster46 citations
989. Self-Supervised Representation Learning From Flow EquivariancePoster46 citations
990. Semantic Diversity Learning for Zero-Shot Multi-Label ClassificationPoster46 citations
991. Semi-Supervised Active Learning for Semi-Supervised Models: Exploit Adversarial Examples With Graph-Based Virtual LabelsPoster46 citations
992. The Right To Talk: An Audio-Visual Transformer ApproachPoster46 citations
993. YouRefIt: Embodied Reference Understanding With Language and GesturePoster46 citations
994. BN-NAS: Neural Architecture Search With Batch NormalizationPoster45 citations
995. COOKIE: Contrastive Cross-Modal Knowledge Sharing Pre-Training for Vision-Language RepresentationPoster45 citations
996. Defocus Map Estimation and Deblurring From a Single Dual-Pixel ImagePoster45 citations
997. Detecting Human-Object Relationships in VideosPoster45 citations
998. Detecting Invisible PeoplePoster45 citations
999. Exploring Robustness of Unsupervised Domain Adaptation in Semantic SegmentationPoster45 citations
1000. Few-Shot Image Classification: Just Use a Library of Pre-Trained Feature Extractors and a Simple ClassifierPoster45 citations

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