CVPR 2021 Accepted Papers

The full list of 1,659 papers accepted at CVPR 2021 (IEEE/CVF Conference on Computer Vision and Pattern Recognition). Click any title for details, similar papers, and links to the original source. You can also search these papers by meaning, not just keywords.

1. Coordinate Attention for Efficient Mobile Network DesignPoster5,358 citations
2. Exploring Simple Siamese Representation LearningPoster5,117 citations
3. Rethinking Semantic Segmentation From a Sequence-to-Sequence Perspective With TransformersPoster4,009 citations
4. Taming Transformers for High-Resolution Image SynthesisPoster3,220 citations
5. RepVGG: Making VGG-Style ConvNets Great AgainPoster2,490 citations
6. Pre-Trained Image Processing TransformerPoster2,279 citations
7. Center-Based 3D Object Detection and TrackingPoster2,110 citations
8. Multi-Stage Progressive Image RestorationPoster2,028 citations
9. Scaled-YOLOv4: Scaling Cross Stage Partial NetworkPoster1,960 citations
10. pixelNeRF: Neural Radiance Fields From One or Few ImagesPoster1,894 citations
11. Natural Adversarial ExamplesPoster1,777 citations
12. NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo CollectionsPoster1,742 citations
13. D-NeRF: Neural Radiance Fields for Dynamic ScenesPoster1,585 citations
14. LoFTR: Detector-Free Local Feature Matching With TransformersPoster1,526 citations
15. Sparse R-CNN: End-to-End Object Detection With Learnable ProposalsPoster1,491 citations
16. Model-Contrastive Federated LearningPoster1,470 citations
17. Bottleneck Transformers for Visual RecognitionPoster1,453 citations
18. Transformer TrackingPoster1,430 citations
19. Encoding in Style: A StyleGAN Encoder for Image-to-Image TranslationPoster1,395 citations
20. Simple Copy-Paste Is a Strong Data Augmentation Method for Instance SegmentationPoster1,267 citations
21. Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual ConceptsPoster1,186 citations
22. Semi-Supervised Semantic Segmentation With Cross Pseudo SupervisionPoster1,158 citations
23. VinVL: Revisiting Visual Representations in Vision-Language ModelsPoster1,156 citations
24. DetectoRS: Detecting Objects With Recursive Feature Pyramid and Switchable Atrous ConvolutionPoster1,121 citations
25. AdaBins: Depth Estimation Using Adaptive BinsPoster1,113 citations
26. CutPaste: Self-Supervised Learning for Anomaly Detection and LocalizationPoster1,095 citations
27. VarifocalNet: An IoU-Aware Dense Object DetectorPoster1,075 citations
28. GIRAFFE: Representing Scenes As Compositional Generative Neural Feature FieldsPoster1,063 citations
29. Pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image SynthesisPoster1,038 citations
30. Transformer Interpretability Beyond Attention VisualizationPoster957 citations
31. IBRNet: Learning Multi-View Image-Based RenderingPoster956 citations
32. Meta Pseudo LabelsPoster928 citations
33. Understanding the Behaviour of Contrastive LossPoster892 citations
34. Multi-Attentional Deepfake DetectionPoster885 citations
35. Retinex-Inspired Unrolling With Cooperative Prior Architecture Search for Low-Light Image EnhancementPoster884 citations
36. Contrastive Learning for Compact Single Image DehazingPoster876 citations
37. Dynamic Head: Unifying Object Detection Heads With AttentionsPoster870 citations
38. Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual TrackingPoster865 citations
39. Neural Body: Implicit Neural Representations With Structured Latent Codes for Novel View Synthesis of Dynamic HumansPoster862 citations
40. Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic ScenesPoster862 citations
41. Dense Contrastive Learning for Self-Supervised Visual Pre-TrainingPoster856 citations
42. End-to-End Video Instance Segmentation With TransformersPoster854 citations
43. DER: Dynamically Expandable Representation for Class Incremental LearningPoster834 citations
44. Diffusion Probabilistic Models for 3D Point Cloud GenerationPoster828 citations
45. Learning Continuous Image Representation With Local Implicit Image FunctionPoster828 citations
46. You Only Look One-Level FeaturePoster820 citations
47. Rethinking BiSeNet for Real-Time Semantic SegmentationPoster814 citations
48. End-to-End Human Pose and Mesh Reconstruction with TransformersPoster812 citations
49. Dual-Stream Multiple Instance Learning Network for Whole Slide Image Classification With Self-Supervised Contrastive LearningPoster811 citations
50. Less Is More: ClipBERT for Video-and-Language Learning via Sparse SamplingPoster771 citations
51. ReDet: A Rotation-Equivariant Detector for Aerial Object DetectionPoster751 citations
52. MagFace: A Universal Representation for Face Recognition and Quality AssessmentPoster690 citations
53. Closed-Form Factorization of Latent Semantics in GANsPoster688 citations
54. Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR SegmentationPoster675 citations
55. NeRV: Neural Reflectance and Visibility Fields for Relighting and View SynthesisPoster653 citations
56. MaX-DeepLab: End-to-End Panoptic Segmentation With Mask TransformersPoster651 citations
57. Multi-Modal Fusion Transformer for End-to-End Autonomous DrivingPoster649 citations
58. Predator: Registration of 3D Point Clouds With Low OverlapPoster646 citations
59. UP-DETR: Unsupervised Pre-Training for Object Detection With TransformersPoster643 citations
60. Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar ReconstructionPoster638 citations
61. Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic SegmentationPoster631 citations
62. Towards Open World Object DetectionPoster630 citations
63. Categorical Depth Distribution Network for Monocular 3D Object DetectionPoster621 citations
64. Image Super-Resolution With Non-Local Sparse AttentionPoster614 citations
65. Spatiotemporal Contrastive Video Representation LearningPoster614 citations
66. BasicVSR: The Search for Essential Components in Video Super-Resolution and BeyondPoster598 citations
67. Multiresolution Knowledge Distillation for Anomaly DetectionPoster589 citations
68. See Through Gradients: Image Batch Recovery via GradInversionPoster588 citations
69. Towards Real-World Blind Face Restoration With Generative Facial PriorPoster588 citations
70. FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency SpacePoster586 citations
71. Distilling Knowledge via Knowledge ReviewPoster580 citations
72. OTA: Optimal Transport Assignment for Object DetectionPoster579 citations
73. A Fourier-Based Framework for Domain GeneralizationPoster563 citations
74. PAConv: Position Adaptive Convolution With Dynamic Kernel Assembling on Point CloudsPoster555 citations
75. TDN: Temporal Difference Networks for Efficient Action RecognitionPoster545 citations
76. Neural Geometric Level of Detail: Real-Time Rendering With Implicit 3D ShapesPoster543 citations
77. StyleSpace Analysis: Disentangled Controls for StyleGAN Image GenerationPoster537 citations
78. FSCE: Few-Shot Object Detection via Contrastive Proposal EncodingPoster531 citations
79. Scaling Local Self-Attention for Parameter Efficient Visual BackbonesPoster528 citations
80. Spatial-Phase Shallow Learning: Rethinking Face Forgery Detection in Frequency DomainPoster517 citations
81. Lips Don't Lie: A Generalisable and Robust Approach To Face Forgery DetectionPoster515 citations
82. Enhancing the Transferability of Adversarial Attacks Through Variance TuningPoster511 citations
83. Graph Attention TrackingPoster511 citations
84. VirTex: Learning Visual Representations From Textual AnnotationsPoster505 citations
85. One-Shot Free-View Neural Talking-Head Synthesis for Video ConferencingPoster504 citations
86. Lite-HRNet: A Lightweight High-Resolution NetworkPoster503 citations
87. Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation LearningPoster498 citations
88. Camouflaged Object Segmentation With Distraction MiningPoster495 citations
89. Quasi-Dense Similarity Learning for Multiple Object TrackingPoster492 citations
90. Counterfactual VQA: A Cause-Effect Look at Language BiasPoster491 citations
91. 3D Object Detection With PointformerPoster488 citations
92. Prototype Augmentation and Self-Supervision for Incremental LearningPoster486 citations
93. Space-Time Neural Irradiance Fields for Free-Viewpoint VideoPoster485 citations
94. Open-Vocabulary Object Detection Using CaptionsPoster484 citations
95. Keep Your Eyes on the Lane: Real-Time Attention-Guided Lane DetectionPoster482 citations
96. Multimodal Motion Prediction With Stacked TransformersPoster481 citations
97. Generalizing Face Forgery Detection With High-Frequency FeaturesPoster478 citations
98. Adaptive Prototype Learning and Allocation for Few-Shot SegmentationPoster473 citations
99. Simultaneously Localize, Segment and Rank the Camouflaged ObjectsPoster472 citations
100. TediGAN: Text-Guided Diverse Face Image Generation and ManipulationPoster472 citations
101. HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape EstimationPoster469 citations
102. Involution: Inverting the Inherence of Convolution for Visual RecognitionPoster468 citations
103. Reducing Domain Gap by Reducing Style BiasPoster464 citations
104. NExT-QA: Next Phase of Question-Answering to Explaining Temporal ActionsPoster463 citations
105. Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place RecognitionPoster463 citations
106. PointAugmenting: Cross-Modal Augmentation for 3D Object DetectionPoster463 citations
107. GDR-Net: Geometry-Guided Direct Regression Network for Monocular 6D Object Pose EstimationPoster462 citations
108. Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text RecognitionPoster461 citations
109. Diverse Branch Block: Building a Convolution as an Inception-Like UnitPoster460 citations
110. SE-SSD: Self-Ensembling Single-Stage Object Detector From Point CloudPoster460 citations
111. Track To Detect and Segment: An Online Multi-Object TrackerPoster452 citations
112. Neighbor2Neighbor: Self-Supervised Denoising From Single Noisy ImagesPoster451 citations
113. Rainbow Memory: Continual Learning With a Memory of Diverse SamplesPoster451 citations
114. Cross-Modal Contrastive Learning for Text-to-Image GenerationPoster434 citations
115. Diverse Part Discovery: Occluded Person Re-Identification With Part-Aware TransformerPoster433 citations
116. Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual RepresentationPoster433 citations
117. Unsupervised Degradation Representation Learning for Blind Super-ResolutionPoster429 citations
118. COMPLETER: Incomplete Multi-View Clustering via Contrastive PredictionPoster424 citations
119. Boundary IoU: Improving Object-Centric Image Segmentation EvaluationPoster405 citations
120. Bottom-Up Human Pose Estimation via Disentangled Keypoint RegressionPoster401 citations
121. Improving Calibration for Long-Tailed RecognitionPoster398 citations
122. Few-Shot Incremental Learning With Continually Evolved ClassifiersPoster395 citations
123. DatasetGAN: Efficient Labeled Data Factory With Minimal Human EffortPoster393 citations
124. Exploring and Distilling Posterior and Prior Knowledge for Radiology Report GenerationPoster393 citations
125. PatchmatchNet: Learned Multi-View Patchmatch StereoPoster391 citations
126. General Multi-Label Image Classification With TransformersPoster387 citations
127. Anomaly Detection in Video via Self-Supervised and Multi-Task LearningPoster383 citations
128. SpinNet: Learning a General Surface Descriptor for 3D Point Cloud RegistrationPoster380 citations
129. CoCosNet v2: Full-Resolution Correspondence Learning for Image TranslationPoster371 citations
130. Unbiased Mean Teacher for Cross-Domain Object DetectionPoster371 citations
131. Flow-Guided One-Shot Talking Face Generation With a High-Resolution Audio-Visual DatasetPoster368 citations
132. Distribution Alignment: A Unified Framework for Long-Tail Visual RecognitionPoster365 citations
133. PhySG: Inverse Rendering With Spherical Gaussians for Physics-Based Material Editing and RelightingPoster365 citations
134. FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose EstimationPoster364 citations
135. STMTrack: Template-Free Visual Tracking With Space-Time Memory NetworksPoster364 citations
136. Function4D: Real-Time Human Volumetric Capture From Very Sparse Consumer RGBD SensorsPoster361 citations
137. NeuralRecon: Real-Time Coherent 3D Reconstruction From Monocular VideoPoster358 citations
138. Few-Shot Classification With Feature Map Reconstruction NetworksPoster357 citations
139. PointDSC: Robust Point Cloud Registration Using Deep Spatial ConsistencyPoster355 citations
140. Dense Label Encoding for Boundary Discontinuity Free Rotation DetectionPoster350 citations
141. CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised LearningPoster349 citations
142. Deep Stable Learning for Out-of-Distribution GeneralizationPoster347 citations
143. GAN Prior Embedded Network for Blind Face Restoration in the WildPoster347 citations
144. CFNet: Cascade and Fused Cost Volume for Robust Stereo MatchingPoster346 citations
145. Contrastive Learning Based Hybrid Networks for Long-Tailed Image ClassificationPoster346 citations
146. The Temporal Opportunist: Self-Supervised Multi-Frame Monocular DepthPoster346 citations
147. RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective WhiteningPoster343 citations
148. MIST: Multiple Instance Self-Training Framework for Video Anomaly DetectionPoster342 citations
149. Learning Salient Boundary Feature for Anchor-free Temporal Action LocalizationPoster341 citations
150. HOTR: End-to-End Human-Object Interaction Detection With TransformersPoster339 citations
151. Mutual Graph Learning for Camouflaged Object DetectionPoster338 citations
152. CausalVAE: Disentangled Representation Learning via Neural Structural Causal ModelsPoster337 citations
153. How Well Do Self-Supervised Models Transfer?Poster336 citations
154. PANDA: Adapting Pretrained Features for Anomaly Detection and SegmentationPoster336 citations
155. Checkerboard Context Model for Efficient Learned Image CompressionPoster334 citations
156. Exploring Data-Efficient 3D Scene Understanding With Contrastive Scene ContextsPoster334 citations
157. PSD: Principled Synthetic-to-Real Dehazing Guided by Physical PriorsPoster334 citations
158. Frequency-Aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery DetectionPoster333 citations
159. Learned Initializations for Optimizing Coordinate-Based Neural RepresentationsPoster331 citations
160. Audio-Visual Instance Discrimination with Cross-Modal AgreementPoster329 citations
161. Neural Prototype Trees for Interpretable Fine-Grained Image RecognitionPoster327 citations
162. Objects Are Different: Flexible Monocular 3D Object DetectionPoster327 citations
163. SGCN: Sparse Graph Convolution Network for Pedestrian Trajectory PredictionPoster327 citations
164. clDice - A Novel Topology-Preserving Loss Function for Tubular Structure SegmentationPoster327 citations
165. HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo MatchingPoster326 citations
166. Seesaw Loss for Long-Tailed Instance SegmentationPoster326 citations
167. A Large-Scale Study on Unsupervised Spatiotemporal Representation LearningPoster324 citations
168. Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object DetectionPoster324 citations
169. MoViNets: Mobile Video Networks for Efficient Video RecognitionPoster324 citations
170. BoxInst: High-Performance Instance Segmentation With Box AnnotationsPoster323 citations
171. Source-Free Domain Adaptation for Semantic SegmentationPoster322 citations
172. NeX: Real-Time View Synthesis With Neural Basis ExpansionPoster320 citations
173. VLN BERT: A Recurrent Vision-and-Language BERT for NavigationPoster319 citations
174. GLEAN: Generative Latent Bank for Large-Factor Image Super-ResolutionPoster315 citations
175. Motion Representations for Articulated AnimationPoster315 citations
176. DexYCB: A Benchmark for Capturing Hand Grasping of ObjectsPoster314 citations
177. Contrastive Embedding for Generalized Zero-Shot LearningPoster313 citations
178. WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face RecognitionPoster313 citations
179. Adaptive Aggregation Networks for Class-Incremental LearningPoster312 citations
180. Disentangling Label Distribution for Long-Tailed Visual RecognitionPoster312 citations
181. Neural Scene Graphs for Dynamic ScenesPoster312 citations
182. Exploring Sparsity in Image Super-Resolution for Efficient InferencePoster311 citations
183. Interpreting Super-Resolution Networks With Local Attribution MapsPoster311 citations
184. Railroad Is Not a Train: Saliency As Pseudo-Pixel Supervision for Weakly Supervised Semantic SegmentationPoster309 citations
185. FSDR: Frequency Space Domain Randomization for Domain GeneralizationPoster308 citations
186. Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic SegmentationPoster307 citations
187. Pose Recognition With Cascade TransformersPoster307 citations
188. Uncertainty-Aware Joint Salient Object and Camouflaged Object DetectionPoster307 citations
189. PLOP: Learning Without Forgetting for Continual Semantic SegmentationPoster305 citations
190. Seeing Out of the Box: End-to-End Pre-Training for Vision-Language Representation LearningPoster305 citations
191. Robust Point Cloud Registration Framework Based on Deep Graph MatchingPoster303 citations
192. SCF-Net: Learning Spatial Contextual Features for Large-Scale Point Cloud SegmentationPoster303 citations
193. Self-Supervised Augmentation Consistency for Adapting Semantic SegmentationPoster302 citations
194. VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware NormalizationPoster302 citations
195. Back to the Feature: Learning Robust Camera Localization From Pixels To PosePoster301 citations
196. Graph Stacked Hourglass Networks for 3D Human Pose EstimationPoster301 citations
197. (AF)2-S3Net: Attentive Feature Fusion With Adaptive Feature Selection for Sparse Semantic Segmentation NetworkPoster300 citations
198. Fourier Contour Embedding for Arbitrary-Shaped Text DetectionPoster298 citations
199. Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language FeedbackPoster297 citations
200. Learning the Best Pooling Strategy for Visual Semantic EmbeddingPoster296 citations
201. FVC: A New Framework Towards Deep Video Compression in Feature SpacePoster295 citations
202. VideoMoCo: Contrastive Video Representation Learning With Temporally Adversarial ExamplesPoster295 citations
203. Few-Shot Image Generation via Cross-Domain CorrespondencePoster294 citations
204. Calibrated RGB-D Salient Object DetectionPoster293 citations
205. Dive Into Ambiguity: Latent Distribution Mining and Pairwise Uncertainty Estimation for Facial Expression RecognitionPoster291 citations
206. Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive FusionPoster291 citations
207. FixBi: Bridging Domain Spaces for Unsupervised Domain AdaptationPoster290 citations
208. Distilling Object Detectors via Decoupled FeaturesPoster288 citations
209. MOS: Towards Scaling Out-of-Distribution Detection for Large Semantic SpacePoster288 citations
210. PD-GAN: Probabilistic Diverse GAN for Image InpaintingPoster287 citations
211. Discover Cross-Modality Nuances for Visible-Infrared Person Re-IdentificationPoster286 citations
212. RSTNet: Captioning With Adaptive Attention on Visual and Non-Visual WordsPoster286 citations
213. Learning To Recover 3D Scene Shape From a Single ImagePoster284 citations
214. Learning Placeholders for Open-Set RecognitionPoster283 citations
215. Real-Time High-Resolution Background MattingPoster282 citations
216. AutoInt: Automatic Integration for Fast Neural Volume RenderingPoster281 citations
217. Bipartite Graph Network With Adaptive Message Passing for Unbiased Scene Graph GenerationPoster281 citations
218. LiDAR R-CNN: An Efficient and Universal 3D Object DetectorPoster281 citations
219. HyperSeg: Patch-Wise Hypernetwork for Real-Time Semantic SegmentationPoster280 citations
220. NBNet: Noise Basis Learning for Image Denoising With Subspace ProjectionPoster280 citations
221. Semi-Supervised Semantic Segmentation With Directional Context-Aware ConsistencyPoster277 citations
222. Probabilistic Embeddings for Cross-Modal RetrievalPoster275 citations
223. Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAEPoster274 citations
224. MP3: A Unified Model To Map, Perceive, Predict and PlanPoster274 citations
225. Delving Into Localization Errors for Monocular 3D Object DetectionPoster272 citations
226. PU-GCN: Point Cloud Upsampling Using Graph Convolutional NetworksPoster271 citations
227. Representative Forgery Mining for Fake Face DetectionPoster271 citations
228. End-to-End Object Detection With Fully Convolutional NetworkPoster269 citations
229. General Instance Distillation for Object DetectionPoster269 citations
230. Alpha-Refine: Boosting Tracking Performance by Precise Bounding Box EstimationPoster268 citations
231. UAV-Human: A Large Benchmark for Human Behavior Understanding With Unmanned Aerial VehiclesPoster268 citations
232. ACTION-Net: Multipath Excitation for Action RecognitionPoster266 citations
233. End-to-End Human Object Interaction Detection With HOI TransformerPoster266 citations
234. Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-IdentificationPoster266 citations
235. TrafficSim: Learning To Simulate Realistic Multi-Agent BehaviorsPoster266 citations
236. QPIC: Query-Based Pairwise Human-Object Interaction Detection With Image-Wide Contextual InformationPoster265 citations
237. SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar NetworksPoster264 citations
238. Stereo Radiance Fields (SRF): Learning View Synthesis for Sparse Views of Novel ScenesPoster261 citations
239. Convolutional Neural Network Pruning With Structural Redundancy ReductionPoster260 citations
240. ArtFlow: Unbiased Image Style Transfer via Reversible Neural FlowsPoster258 citations
241. Beyond Static Features for Temporally Consistent 3D Human Pose and Shape From a VideoPoster257 citations
242. Distilling Causal Effect of Data in Class-Incremental LearningPoster257 citations
243. How2Sign: A Large-Scale Multimodal Dataset for Continuous American Sign LanguagePoster257 citations
244. Large-Capacity Image Steganography Based on Invertible Neural NetworksPoster257 citations
245. Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware FusionPoster256 citations
246. Dual Attention Suppression Attack: Generate Adversarial Camouflage in Physical WorldPoster255 citations
247. Instant-Teaching: An End-to-End Semi-Supervised Object Detection FrameworkPoster254 citations
248. Audio-Driven Emotional Video PortraitsPoster253 citations
249. Variational Relational Point Completion NetworkPoster253 citations
250. Counterfactual Zero-Shot and Open-Set Visual RecognitionPoster251 citations
251. Neural Feature Search for RGB-Infrared Person Re-IdentificationPoster251 citations
252. Improving Sign Language Translation With Monolingual Data by Sign Back-TranslationPoster249 citations
253. ST3D: Self-Training for Unsupervised Domain Adaptation on 3D Object DetectionPoster249 citations
254. Backdoor Attacks Against Deep Learning Systems in the Physical WorldPoster248 citations
255. DeRF: Decomposed Radiance FieldsPoster248 citations
256. Non-Salient Region Object Mining for Weakly Supervised Semantic SegmentationPoster248 citations
257. Ultra-High-Definition Image Dehazing via Multi-Guided Bilateral LearningPoster248 citations
258. Data-Free Model ExtractionPoster247 citations
259. KRISP: Integrating Implicit and Symbolic Knowledge for Open-Domain Knowledge-Based VQAPoster247 citations
260. Semantic Relation Reasoning for Shot-Stable Few-Shot Object DetectionPoster247 citations
261. AGORA: Avatars in Geography Optimized for Regression AnalysisPoster245 citations
262. Patch2Pix: Epipolar-Guided Pixel-Level CorrespondencesPoster244 citations
263. A Generalized Loss Function for Crowd Counting and LocalizationPoster243 citations
264. Multiple Object Tracking With Correlation LearningPoster243 citations
265. Recorrupted-to-Recorrupted: Unsupervised Deep Learning for Image DenoisingPoster242 citations
266. Intra-Inter Camera Similarity for Unsupervised Person Re-IdentificationPoster241 citations
267. Learning Multi-Scale Photo Exposure CorrectionPoster241 citations
268. LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture SearchPoster241 citations
269. Parser-Free Virtual Try-On via Distilling Appearance FlowsPoster241 citations
270. SG-Net: Spatial Granularity Network for One-Stage Video Instance SegmentationPoster241 citations
271. Semantic Segmentation With Generative Models: Semi-Supervised Learning and Strong Out-of-Domain GeneralizationPoster241 citations
272. Semantic-Aware Knowledge Distillation for Few-Shot Class-Incremental LearningPoster241 citations
273. 3D Human Action Representation Learning via Cross-View Consistency PursuitPoster240 citations
274. Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?Poster240 citations
275. MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object DetectionPoster240 citations
276. PiCIE: Unsupervised Semantic Segmentation Using Invariance and Equivariance in ClusteringPoster238 citations
277. Domain Adaptation With Auxiliary Target Domain-Oriented ClassifierPoster237 citations
278. BABEL: Bodies, Action and Behavior With English LabelsPoster236 citations
279. Towards Semantic Segmentation of Urban-Scale 3D Point Clouds: A Dataset, Benchmarks and ChallengesPoster236 citations
280. PMP-Net: Point Cloud Completion by Learning Multi-Step Point Moving PathsPoster235 citations
281. Unbalanced Feature Transport for Exemplar-Based Image TranslationPoster235 citations
282. Localizing Visual Sounds the Hard WayPoster234 citations
283. Time Lens: Event-Based Video Frame InterpolationPoster234 citations
284. Deep Occlusion-Aware Instance Segmentation With Overlapping BiLayersPoster233 citations
285. BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance SegmentationPoster232 citations
286. Dense Relation Distillation With Context-Aware Aggregation for Few-Shot Object DetectionPoster232 citations
287. Reconsidering Representation Alignment for Multi-View ClusteringPoster232 citations
288. Group-aware Label Transfer for Domain Adaptive Person Re-identificationPoster231 citations
289. Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild With Pose AnnotationsPoster231 citations
290. Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution MergingPoster230 citations
291. Offboard 3D Object Detection From Point Cloud SequencesPoster226 citations
292. Unsupervised Pre-Training for Person Re-IdentificationPoster226 citations
293. Self-Guided and Cross-Guided Learning for Few-Shot SegmentationPoster225 citations
294. Fully Convolutional Networks for Panoptic SegmentationPoster223 citations
295. Stable View SynthesisPoster223 citations
296. Beyond Bounding-Box: Convex-Hull Feature Adaptation for Oriented and Densely Packed Object DetectionPoster222 citations
297. Humble Teachers Teach Better Students for Semi-Supervised Object DetectionPoster221 citations
298. T2VLAD: Global-Local Sequence Alignment for Text-Video RetrievalPoster221 citations
299. Joint Generative and Contrastive Learning for Unsupervised Person Re-IdentificationPoster220 citations
300. Towards More Flexible and Accurate Object Tracking With Natural Language: Algorithms and BenchmarkPoster220 citations
301. Adaptive Consistency Prior Based Deep Network for Image DenoisingPoster219 citations
302. Generalized Few-Shot Object Detection Without ForgettingPoster219 citations
303. Learning Normal Dynamics in Videos With Meta Prototype NetworkPoster219 citations
304. Rethinking the Heatmap Regression for Bottom-Up Human Pose EstimationPoster219 citations
305. SMPLicit: Topology-Aware Generative Model for Clothed PeoplePoster219 citations
306. Feature Decomposition and Reconstruction Learning for Effective Facial Expression RecognitionPoster218 citations
307. ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data CharacteristicPoster217 citations
308. SSTVOS: Sparse Spatiotemporal Transformers for Video Object SegmentationPoster217 citations
309. SwiftNet: Real-Time Video Object SegmentationPoster216 citations
310. Beyond Max-Margin: Class Margin Equilibrium for Few-Shot Object DetectionPoster215 citations
311. Multimodal Contrastive Training for Visual Representation LearningPoster215 citations
312. Temporal-Relational CrossTransformers for Few-Shot Action RecognitionPoster215 citations
313. Deep RGB-D Saliency Detection With Depth-Sensitive Attention and Automatic Multi-Modal FusionPoster214 citations
314. Dynamic Weighted Learning for Unsupervised Domain AdaptationPoster214 citations
315. Point 4D Transformer Networks for Spatio-Temporal Modeling in Point Cloud VideosPoster214 citations
316. Cross-Domain Gradient Discrepancy Minimization for Unsupervised Domain AdaptationPoster212 citations
317. House-GAN++: Generative Adversarial Layout Refinement Network towards Intelligent Computational Agent for Professional ArchitectsPoster212 citations
318. Equalization Loss v2: A New Gradient Balance Approach for Long-Tailed Object DetectionPoster211 citations
319. TextOCR: Towards Large-Scale End-to-End Reasoning for Arbitrary-Shaped Scene TextPoster211 citations
320. VisualVoice: Audio-Visual Speech Separation With Cross-Modal ConsistencyPoster211 citations
321. Activate or Not: Learning Customized ActivationPoster208 citations
322. DoDNet: Learning To Segment Multi-Organ and Tumors From Multiple Partially Labeled DatasetsPoster208 citations
323. PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose EstimationPoster207 citations
324. SimPLE: Similar Pseudo Label Exploitation for Semi-Supervised ClassificationPoster207 citations
325. Fine-Grained Shape-Appearance Mutual Learning for Cloth-Changing Person Re-IdentificationPoster206 citations
326. Patch-VQ: 'Patching Up' the Video Quality ProblemPoster206 citations
327. Prototypical Cross-Domain Self-Supervised Learning for Few-Shot Unsupervised Domain AdaptationPoster206 citations
328. Actor-Context-Actor Relation Network for Spatio-Temporal Action LocalizationPoster204 citations
329. DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic SegmentationPoster204 citations
330. RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object DetectionPoster204 citations
331. Soteria: Provable Defense Against Privacy Leakage in Federated Learning From Representation PerspectivePoster204 citations
332. MAZE: Data-Free Model Stealing Attack Using Zeroth-Order Gradient EstimationPoster203 citations
333. Self-Promoted Prototype Refinement for Few-Shot Class-Incremental LearningPoster203 citations
334. Open Domain Generalization with Domain-Augmented Meta-LearningPoster202 citations
335. ArtEmis: Affective Language for Visual ArtPoster201 citations
336. MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual RecognitionPoster201 citations
337. On Feature Normalization and Data AugmentationPoster201 citations
338. VIGOR: Cross-View Image Geo-Localization Beyond One-to-One RetrievalPoster201 citations
339. Invertible Denoising Network: A Light Solution for Real Noise RemovalPoster200 citations
340. Unsupervised Multi-Source Domain Adaptation Without Access to Source DataPoster200 citations
341. Fair Attribute Classification Through Latent Space De-BiasingPoster199 citations
342. Learning Graph Embeddings for Compositional Zero-Shot LearningPoster199 citations
343. Adversarial Generation of Continuous ImagesPoster198 citations
344. Pulsar: Efficient Sphere-Based Neural RenderingPoster198 citations
345. Causal Attention for Vision-Language TasksPoster197 citations
346. FS-Net: Fast Shape-Based Network for Category-Level 6D Object Pose Estimation With Decoupled Rotation MechanismPoster197 citations
347. MotionRNN: A Flexible Model for Video Prediction With Spacetime-Varying MotionsPoster197 citations
348. One Shot Face Swapping on MegapixelsPoster197 citations
349. Encoder Fusion Network With Co-Attention Embedding for Referring Image SegmentationPoster196 citations
350. Energy-Based Learning for Scene Graph GenerationPoster196 citations
351. Scale-Aware Graph Neural Network for Few-Shot Semantic SegmentationPoster196 citations
352. Progressive Semantic-Aware Style Transformation for Blind Face RestorationPoster195 citations
353. Semi-Supervised 3D Hand-Object Poses Estimation With Interactions in TimePoster195 citations
354. AdvSim: Generating Safety-Critical Scenarios for Self-Driving VehiclesPoster194 citations
355. Deep Gradient Projection Networks for Pan-sharpeningPoster194 citations
356. Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent RepresentationsPoster193 citations
357. Progressive Domain Expansion Network for Single Domain GeneralizationPoster193 citations
358. Robust Multimodal Vehicle Detection in Foggy Weather Using Complementary Lidar and Radar SignalsPoster193 citations
359. Exploiting Spatial Dimensions of Latent in GAN for Real-Time Image EditingPoster192 citations
360. Multi-Institutional Collaborations for Improving Deep Learning-Based Magnetic Resonance Image Reconstruction Using Federated LearningPoster192 citations
361. TAP: Text-Aware Pre-Training for Text-VQA and Text-CaptionPoster192 citations
362. Benchmarking Representation Learning for Natural World Image CollectionsPoster191 citations
363. Dynamic Slimmable NetworkPoster191 citations
364. Mixed-Privacy Forgetting in Deep NetworksPoster191 citations
365. Jo-SRC: A Contrastive Approach for Combating Noisy LabelsPoster190 citations
366. Neighborhood Contrastive Learning for Novel Class DiscoveryPoster190 citations
367. Refine Myself by Teaching Myself: Feature Refinement via Self-Knowledge DistillationPoster190 citations
368. SiamMOT: Siamese Multi-Object TrackingPoster190 citations
369. Fast End-to-End Learning on Protein SurfacesPoster189 citations
370. MobileDets: Searching for Object Detection Architectures for Mobile AcceleratorsPoster189 citations
371. SOE-Net: A Self-Attention and Orientation Encoding Network for Point Cloud Based Place RecognitionPoster189 citations
372. SelfDoc: Self-Supervised Document Representation LearningPoster189 citations
373. Task-Aware Variational Adversarial Active LearningPoster189 citations
374. Dual-GAN: Joint BVP and Noise Modeling for Remote Physiological MeasurementPoster188 citations
375. Efficient Regional Memory Network for Video Object SegmentationPoster188 citations
376. Learning Calibrated Medical Image Segmentation via Multi-Rater Agreement ModelingPoster188 citations
377. Image Generators With Conditionally-Independent Pixel SynthesisPoster187 citations
378. Robust Consistent Video Depth EstimationPoster187 citations
379. VoxelContext-Net: An Octree Based Framework for Point Cloud CompressionPoster187 citations
380. SceneGraphFusion: Incremental 3D Scene Graph Prediction From RGB-D SequencesPoster186 citations
381. Deep Gaussian Scale Mixture Prior for Spectral Compressive ImagingPoster185 citations
382. Meta Batch-Instance Normalization for Generalizable Person Re-IdentificationPoster185 citations
383. CoLA: Weakly-Supervised Temporal Action Localization With Snippet Contrastive LearningPoster184 citations
384. Re-Labeling ImageNet: From Single to Multi-Labels, From Global to Localized LabelsPoster183 citations
385. Combined Depth Space Based Architecture Search for Person Re-IdentificationPoster182 citations
386. Reformulating HOI Detection As Adaptive Set PredictionPoster182 citations
387. TPCN: Temporal Point Cloud Networks for Motion ForecastingPoster179 citations
388. VIP-DeepLab: Learning Visual Perception With Depth-Aware Video Panoptic SegmentationPoster179 citations
389. ABMDRNet: Adaptive-Weighted Bi-Directional Modality Difference Reduction Network for RGB-T Semantic SegmentationPoster178 citations
390. AdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations From Self-Trained Negative AdversariesPoster178 citations
391. Embedded Discriminative Attention Mechanism for Weakly Supervised Semantic SegmentationPoster178 citations
392. ForgeryNet: A Versatile Benchmark for Comprehensive Forgery AnalysisPoster178 citations
393. MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-ResolutionPoster178 citations
394. Learning Statistical Texture for Semantic SegmentationPoster177 citations
395. Removing Raindrops and Rain Streaks in One GoPoster177 citations
396. Complete & Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point CloudsPoster176 citations
397. Context-Aware Biaffine Localizing Network for Temporal Sentence GroundingPoster176 citations
398. Flow-Based Kernel Prior With Application to Blind Super-ResolutionPoster176 citations
399. HoHoNet: 360 Indoor Holistic Understanding With Latent Horizontal FeaturesPoster176 citations
400. Learning To Count EverythingPoster176 citations
401. Regularizing Generative Adversarial Networks Under Limited DataPoster176 citations
402. Deformed Implicit Field: Modeling 3D Shapes With Learned Dense CorrespondencePoster175 citations
403. KeepAugment: A Simple Information-Preserving Data Augmentation ApproachPoster175 citations
404. Auto-Exposure Fusion for Single-Image Shadow RemovalPoster174 citations
405. Interventional Video Grounding With Dual Contrastive LearningPoster174 citations
406. Towards Long-Form Video UnderstandingPoster174 citations
407. Training Networks in Null Space of Feature Covariance for Continual LearningPoster174 citations
408. Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a BlinkPoster173 citations
409. Coming Down to Earth: Satellite-to-Street View Synthesis for Geo-LocalizationPoster173 citations
410. Improving the Efficiency and Robustness of Deepfakes Detection Through Precise Geometric FeaturesPoster173 citations
411. Pixel-Wise Anomaly Detection in Complex Driving ScenesPoster173 citations
412. Goal-Oriented Gaze Estimation for Zero-Shot LearningPoster172 citations
413. STaR: Self-Supervised Tracking and Reconstruction of Rigid Objects in Motion With Neural RenderingPoster172 citations
414. Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-Localization in Large Scenes From Body-Mounted SensorsPoster171 citations
415. One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic SegmentationPoster171 citations
416. img2pose: Face Alignment and Detection via 6DoF, Face Pose EstimationPoster171 citations
417. Instance Localization for Self-Supervised Detection PretrainingPoster170 citations
418. Interactive Self-Training With Mean Teachers for Semi-Supervised Object DetectionPoster170 citations
419. Partially View-Aligned Representation Learning With Noise-Robust Contrastive LossPoster170 citations
420. Point Cloud Upsampling via Disentangled RefinementPoster170 citations
421. Uncertainty Reduction for Model Adaptation in Semantic SegmentationPoster170 citations
422. Unsupervised Real-World Image Super Resolution via Domain-Distance Aware TrainingPoster170 citations
423. HVPR: Hybrid Voxel-Point Representation for Single-Stage 3D Object DetectionPoster169 citations
424. Domain Consensus Clustering for Universal Domain AdaptationPoster168 citations
425. Dynamic Region-Aware ConvolutionPoster168 citations
426. Focus on Local: Detecting Lane Marker From Bottom Up via Key PointPoster168 citations
427. Multiple Instance Active Learning for Object DetectionPoster168 citations
428. Open World Compositional Zero-Shot LearningPoster168 citations
429. RAFT-3D: Scene Flow Using Rigid-Motion EmbeddingsPoster168 citations
430. Populating 3D Scenes by Learning Human-Scene InteractionPoster167 citations
431. Progressive Modality Reinforcement for Human Multimodal Emotion Recognition From Unaligned Multimodal SequencesPoster167 citations
432. Refining Pseudo Labels With Clustering Consensus Over Generations for Unsupervised Object Re-IdentificationPoster167 citations
433. Deep Dual Consecutive Network for Human Pose EstimationPoster166 citations
434. Scan2Cap: Context-Aware Dense Captioning in RGB-D ScansPoster166 citations
435. Temporal Context Aggregation Network for Temporal Action Proposal RefinementPoster166 citations
436. Visual Room RearrangementPoster166 citations
437. We Are More Than Our Joints: Predicting How 3D Bodies MovePoster166 citations
438. Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd CountingPoster165 citations
439. Farewell to Mutual Information: Variational Distillation for Cross-Modal Person Re-IdentificationPoster165 citations
440. Learning Temporal Consistency for Low Light Video Enhancement From Single ImagesPoster165 citations
441. Network Pruning via Performance MaximizationPoster165 citations
442. On Robustness and Transferability of Convolutional Neural NetworksPoster165 citations
443. Transferable Semantic Augmentation for Domain AdaptationPoster165 citations
444. Unsupervised 3D Shape Completion Through GAN InversionPoster164 citations
445. Iterative Filter Adaptive Network for Single Image Defocus DeblurringPoster163 citations
446. SimPoE: Simulated Character Control for 3D Human Pose EstimationPoster163 citations
447. Asymmetric Gained Deep Image Compression With Continuous Rate AdaptationPoster162 citations
448. Locate Then Segment: A Strong Pipeline for Referring Image SegmentationPoster162 citations
449. Sequence-to-Sequence Contrastive Learning for Text RecognitionPoster162 citations
450. Adversarially Adaptive Normalization for Single Domain GeneralizationPoster161 citations
451. On Learning the Geodesic Path for Incremental LearningPoster161 citations
452. Prototype Completion With Primitive Knowledge for Few-Shot LearningPoster161 citations
453. An Alternative Probabilistic Interpretation of the Huber LossPoster160 citations
454. Facial Action Unit Detection With TransformersPoster160 citations
455. Generalizable Person Re-Identification With Relevance-Aware Mixture of ExpertsPoster160 citations
456. PixMatch: Unsupervised Domain Adaptation via Pixelwise Consistency TrainingPoster160 citations
457. Thinking Fast and Slow: Efficient Text-to-Visual Retrieval With TransformersPoster160 citations
458. Are Labels Always Necessary for Classifier Accuracy Evaluation?Poster159 citations
459. Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot LearningPoster159 citations
460. Image-to-Image Translation via Hierarchical Style DisentanglementPoster159 citations
461. Multi-Objective Interpolation Training for Robustness To Label NoisePoster159 citations
462. Variational Transformer Networks for Layout GenerationPoster159 citations
463. Back to Event Basics: Self-Supervised Learning of Image Reconstruction for Event Cameras via Photometric ConstancyPoster158 citations
464. Decoupled Dynamic Filter NetworksPoster158 citations
465. Deep Burst Super-ResolutionPoster158 citations
466. Cross-Domain Adaptive Clustering for Semi-Supervised Domain AdaptationPoster157 citations
467. Improving Multiple Pedestrian Tracking by Track Management and Occlusion HandlingPoster157 citations
468. Sequential Graph Convolutional Network for Active LearningPoster157 citations
469. A Second-Order Approach to Learning With Instance-Dependent Label NoisePoster156 citations
470. Depth-Conditioned Dynamic Message Propagation for Monocular 3D Object DetectionPoster156 citations
471. Learnable Graph Matching: Incorporating Graph Partitioning With Deep Feature Learning for Multiple Object TrackingPoster156 citations
472. MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty PropagationPoster156 citations
473. PISE: Person Image Synthesis and Editing With Decoupled GANPoster156 citations
474. 3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object DetectionPoster155 citations
475. Face Forensics in the WildPoster154 citations
476. Kaleido-BERT: Vision-Language Pre-Training on Fashion DomainPoster154 citations
477. RefineMask: Towards High-Quality Instance Segmentation With Fine-Grained FeaturesPoster154 citations
478. When Age-Invariant Face Recognition Meets Face Age Synthesis: A Multi-Task Learning FrameworkPoster154 citations
479. Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-IdentificationPoster153 citations
480. Mask Guided Matting via Progressive Refinement NetworkPoster153 citations
481. Pareto Self-Supervised Training for Few-Shot LearningPoster153 citations
482. Augmentation Strategies for Learning With Noisy LabelsPoster152 citations
483. CoSMo: Content-Style Modulation for Image Retrieval With Text FeedbackPoster152 citations
484. OpenMix: Reviving Known Knowledge for Discovering Novel Visual Categories in an Open WorldPoster152 citations
485. Scene Text Telescope: Text-Focused Scene Image Super-ResolutionPoster152 citations
486. HistoGAN: Controlling Colors of GAN-Generated and Real Images via Color HistogramsPoster151 citations
487. DG-Font: Deformable Generative Networks for Unsupervised Font GenerationPoster150 citations
488. Exponential Moving Average Normalization for Self-Supervised and Semi-Supervised LearningPoster150 citations
489. Learning Dynamic Alignment via Meta-Filter for Few-Shot LearningPoster150 citations
490. MOOD: Multi-Level Out-of-Distribution DetectionPoster150 citations
491. Cross-Iteration Batch NormalizationPoster149 citations
492. Learning Accurate Dense Correspondences and When To Trust ThemPoster149 citations
493. Panoptic-PolarNet: Proposal-Free LiDAR Point Cloud Panoptic SegmentationPoster149 citations
494. The Spatially-Correlative Loss for Various Image Translation TasksPoster149 citations
495. Black-Box Explanation of Object Detectors via Saliency MapsPoster148 citations
496. Hallucination Improves Few-Shot Object DetectionPoster148 citations
497. Improving Multiple Object Tracking With Single Object TrackingPoster148 citations
498. LaPred: Lane-Aware Prediction of Multi-Modal Future Trajectories of Dynamic AgentsPoster148 citations
499. Neural Lumigraph RenderingPoster148 citations
500. Bidirectional Projection Network for Cross Dimension Scene UnderstandingPoster147 citations
501. ContactOpt: Optimizing Contact To Improve GraspsPoster147 citations
502. Generalizable Pedestrian Detection: The Elephant in the RoomPoster147 citations
503. InverseForm: A Loss Function for Structured Boundary-Aware SegmentationPoster147 citations
504. Learning 3D Shape Feature for Texture-Insensitive Person Re-IdentificationPoster147 citations
505. ManipulaTHOR: A Framework for Visual Object ManipulationPoster147 citations
506. Pixel Codec AvatarsPoster147 citations
507. The Lottery Tickets Hypothesis for Supervised and Self-Supervised Pre-Training in Computer Vision ModelsPoster147 citations
508. High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation NetworkPoster146 citations
509. LEAP: Learning Articulated Occupancy of PeoplePoster146 citations
510. Learning To Filter: Siamese Relation Network for Robust TrackingPoster146 citations
511. Video Prediction Recalling Long-Term Motion Context via Memory Alignment LearningPoster146 citations
512. Synthesizing Long-Term 3D Human Motion and Interaction in 3D ScenesPoster145 citations
513. Your "Flamingo" is My "Bird": Fine-Grained, or NotPoster145 citations
514. Region-Aware Adaptive Instance Normalization for Image HarmonizationPoster144 citations
515. StyleMix: Separating Content and Style for Enhanced Data AugmentationPoster144 citations
516. XProtoNet: Diagnosis in Chest Radiography With Global and Local ExplanationsPoster144 citations
517. Anchor-Free Person SearchPoster143 citations
518. CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the WildPoster143 citations
519. EnD: Entangling and Disentangling Deep Representations for Bias CorrectionPoster143 citations
520. Network Quantization With Element-Wise Gradient ScalingPoster143 citations
521. From Shadow Generation To Shadow RemovalPoster142 citations
522. SuperMix: Supervising the Mixing Data AugmentationPoster142 citations
523. Fast and Accurate Model ScalingPoster141 citations
524. Learning High Fidelity Depths of Dressed Humans by Watching Social Media Dance VideosPoster141 citations
525. Progressive Contour Regression for Arbitrary-Shape Scene Text DetectionPoster141 citations
526. Learning a Proposal Classifier for Multiple Object TrackingPoster140 citations
527. Line Segment Detection Using Transformers Without EdgesPoster140 citations
528. SDD-FIQA: Unsupervised Face Image Quality Assessment With Similarity Distribution DistancePoster140 citations
529. Affordance Transfer Learning for Human-Object Interaction DetectionPoster139 citations
530. Deep Analysis of CNN-Based Spatio-Temporal Representations for Action RecognitionPoster139 citations
531. i3DMM: Deep Implicit 3D Morphable Model of Human HeadsPoster139 citations
532. Guided Integrated Gradients: An Adaptive Path Method for Removing NoisePoster137 citations
533. Lesion-Aware Transformers for Diabetic Retinopathy GradingPoster137 citations
534. MetaAlign: Coordinating Domain Alignment and Classification for Unsupervised Domain AdaptationPoster137 citations
535. 3D AffordanceNet: A Benchmark for Visual Object Affordance UnderstandingPoster136 citations
536. DCNAS: Densely Connected Neural Architecture Search for Semantic Image SegmentationPoster136 citations
537. Deep Implicit Templates for 3D Shape RepresentationPoster136 citations
538. Im2Vec: Synthesizing Vector Graphics Without Vector SupervisionPoster136 citations
539. Structured Scene Memory for Vision-Language NavigationPoster136 citations
540. VSPW: A Large-scale Dataset for Video Scene Parsing in the WildPoster136 citations
541. AttentiveNAS: Improving Neural Architecture Search via Attentive SamplingPoster135 citations
542. Few-Shot 3D Point Cloud Semantic SegmentationPoster135 citations
543. Invertible Image Signal ProcessingPoster135 citations
544. TesseTrack: End-to-End Learnable Multi-Person Articulated 3D Pose TrackingPoster135 citations
545. Cycle4Completion: Unpaired Point Cloud Completion Using Cycle Transformation With Missing Region CodingPoster134 citations
546. Learning Position and Target Consistency for Memory-Based Video Object SegmentationPoster134 citations
547. Semi-Supervised Action Recognition With Temporal Contrastive LearningPoster134 citations
548. Detection, Tracking, and Counting Meets Drones in Crowds: A BenchmarkPoster133 citations
549. FBNetV3: Joint Architecture-Recipe Search Using Predictor PretrainingPoster133 citations
550. Fully Convolutional Scene Graph GenerationPoster133 citations
551. Multi-Label Learning From Single Positive LabelsPoster133 citations
552. PointFlow: Flowing Semantics Through Points for Aerial Image SegmentationPoster133 citations
553. AutoFlow: Learning a Better Training Set for Optical FlowPoster132 citations
554. Deep Implicit Moving Least-Squares Functions for 3D ReconstructionPoster132 citations
555. Disentangled Cycle Consistency for Highly-Realistic Virtual Try-OnPoster132 citations
556. Equivariant Point Network for 3D Point Cloud AnalysisPoster132 citations
557. Glance and Gaze: Inferring Action-Aware Points for One-Stage Human-Object Interaction DetectionPoster132 citations
558. Learning To Predict Visual Attributes in the WildPoster132 citations
559. Greedy Hierarchical Variational Autoencoders for Large-Scale Video PredictionPoster131 citations
560. Manifold Regularized Dynamic Network PruningPoster131 citations
561. Memory Oriented Transfer Learning for Semi-Supervised Image DerainingPoster131 citations
562. SOON: Scenario Oriented Object Navigation With Graph-Based ExplorationPoster131 citations
563. Robust Audio-Visual Instance DiscriminationPoster130 citations
564. AGQA: A Benchmark for Compositional Spatio-Temporal ReasoningPoster129 citations
565. Holistic 3D Scene Understanding From a Single Image With Implicit RepresentationPoster129 citations
566. LASR: Learning Articulated Shape Reconstruction From a Monocular VideoPoster129 citations
567. Leveraging Line-Point Consistence To Preserve Structures for Wide Parallax Image StitchingPoster129 citations
568. The Translucent Patch: A Physical and Universal Attack on Object DetectorsPoster129 citations
569. Topological Planning With Transformers for Vision-and-Language NavigationPoster129 citations
570. 3D-MAN: 3D Multi-Frame Attention Network for Object DetectionPoster128 citations
571. Adaptive Class Suppression Loss for Long-Tail Object DetectionPoster128 citations
572. Improving Transferability of Adversarial Patches on Face Recognition With Generative ModelsPoster128 citations
573. M3P: Learning Universal Representations via Multitask Multilingual Multimodal Pre-TrainingPoster128 citations
574. RSG: A Simple but Effective Module for Learning Imbalanced DatasetsPoster128 citations
575. SurFree: A Fast Surrogate-Free Black-Box AttackPoster128 citations
576. Wasserstein Contrastive Representation DistillationPoster128 citations
577. Deep Convolutional Dictionary Learning for Image DenoisingPoster127 citations
578. Information Bottleneck Disentanglement for Identity SwappingPoster127 citations
579. Nearest Neighbor Matching for Deep ClusteringPoster127 citations
580. Positive Sample Propagation Along the Audio-Visual Event LinePoster127 citations
581. Progressive Semantic SegmentationPoster127 citations
582. StyleMeUp: Towards Style-Agnostic Sketch-Based Image RetrievalPoster127 citations
583. Back-Tracing Representative Points for Voting-Based 3D Object Detection in Point CloudsPoster126 citations
584. BiCnet-TKS: Learning Efficient Spatial-Temporal Representation for Video Person Re-IdentificationPoster126 citations
585. Face Forgery Detection by 3D DecompositionPoster126 citations
586. FlowStep3D: Model Unrolling for Self-Supervised Scene Flow EstimationPoster126 citations
587. Exploring Heterogeneous Clues for Weakly-Supervised Audio-Visual Video ParsingPoster125 citations
588. Improving Unsupervised Image Clustering With Robust LearningPoster125 citations
589. OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised LearningPoster125 citations
590. Open-Book Video Captioning With Retrieve-Copy-Generate NetworkPoster125 citations
591. Rethinking Channel Dimensions for Efficient Model DesignPoster125 citations
592. Improving the Transferability of Adversarial Samples With Adversarial TransformationsPoster124 citations
593. Model-Based 3D Hand Reconstruction via Self-Supervised LearningPoster124 citations
594. What if We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer LabelsPoster124 citations
595. Adaptive Consistency Regularization for Semi-Supervised Transfer LearningPoster123 citations
596. Generative Hierarchical Features From Synthesizing ImagesPoster123 citations
597. Neural Parts: Learning Expressive 3D Shape Abstractions With Invertible Neural NetworksPoster123 citations
598. RPN Prototype Alignment for Domain Adaptive Object DetectorPoster123 citations
599. Semantic Audio-Visual NavigationPoster123 citations
600. A2-FPN: Attention Aggregation Based Feature Pyramid Network for Instance SegmentationPoster122 citations
601. Look Before You Leap: Learning Landmark Features for One-Stage Visual GroundingPoster122 citations
602. Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic SegmentationPoster121 citations
603. Deep Animation Video Interpolation in the WildPoster121 citations
604. Graph-Based High-Order Relation Discovery for Fine-Grained RecognitionPoster121 citations
605. Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting With Their ExplanationsPoster121 citations
606. Amalgamating Knowledge From Heterogeneous Graph Neural NetworksPoster120 citations
607. From Synthetic to Real: Unsupervised Domain Adaptation for Animal Pose EstimationPoster120 citations
608. Image Inpainting Guided by Coherence Priors of Semantics and TexturesPoster120 citations
609. LipSync3D: Data-Efficient Learning of Personalized 3D Talking Faces From Video Using Pose and Lighting NormalizationPoster120 citations
610. CDFI: Compression-Driven Network Design for Frame InterpolationPoster119 citations
611. Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style TransferPoster119 citations
612. DriveGAN: Towards a Controllable High-Quality Neural SimulationPoster119 citations
613. MetaCorrection: Domain-Aware Meta Loss Correction for Unsupervised Domain Adaptation in Semantic SegmentationPoster119 citations
614. Bridge To Answer: Structure-Aware Graph Interaction Network for Video Question AnsweringPoster118 citations
615. DeepVideoMVS: Multi-View Stereo on Video With Recurrent Spatio-Temporal FusionPoster118 citations
616. Depth Completion With Twin Surface Extrapolation at Occlusion BoundariesPoster118 citations
617. Detecting Human-Object Interaction via Fabricated Compositional LearningPoster118 citations
618. PV-RAFT: Point-Voxel Correlation Fields for Scene Flow Estimation of Point CloudsPoster118 citations
619. SceneGen: Learning To Generate Realistic Traffic ScenesPoster118 citations
620. Semantic Image MattingPoster118 citations
621. Watching You: Global-Guided Reciprocal Learning for Video-Based Person Re-IdentificationPoster118 citations
622. MOST: A Multi-Oriented Scene Text Detector With Localization RefinementPoster117 citations
623. Shallow Feature Matters for Weakly Supervised Object LocalizationPoster117 citations
624. Spatially Consistent Representation LearningPoster117 citations
625. iMiGUE: An Identity-Free Video Dataset for Micro-Gesture Understanding and Emotion AnalysisPoster117 citations
626. BRepNet: A Topological Message Passing System for Solid ModelsPoster116 citations
627. Bilateral Grid Learning for Stereo Matching NetworksPoster116 citations
628. Cross Modal Focal Loss for RGBD Face Anti-SpoofingPoster116 citations
629. DiNTS: Differentiable Neural Network Topology Search for 3D Medical Image SegmentationPoster116 citations
630. NeuTex: Neural Texture Mapping for Volumetric Neural RenderingPoster116 citations
631. On Self-Contact and Human PosePoster116 citations
632. Regularizing Neural Networks via Adversarial Model PerturbationPoster116 citations
633. AdderSR: Towards Energy Efficient Image Super-ResolutionPoster115 citations
634. DyCo3D: Robust Instance Segmentation of 3D Point Clouds Through Dynamic ConvolutionPoster115 citations
635. Group Collaborative Learning for Co-Salient Object DetectionPoster115 citations
636. Learning Cross-Modal Retrieval With Noisy LabelsPoster115 citations
637. Lifelong Person Re-Identification via Adaptive Knowledge AccumulationPoster115 citations
638. Permuted AdaIN: Reducing the Bias Towards Global Statistics in Image ClassificationPoster115 citations
639. Projecting Your View Attentively: Monocular Road Scene Layout Estimation via Cross-View TransformationPoster115 citations
640. Rethinking and Improving the Robustness of Image Style TransferPoster115 citations
641. Three Ways To Improve Semantic Segmentation With Self-Supervised Depth EstimationPoster115 citations
642. Transformation Invariant Few-Shot Object DetectionPoster115 citations
643. LiDAR-Based Panoptic Segmentation via Dynamic Shifting NetworkPoster114 citations
644. Look Closer To Segment Better: Boundary Patch Refinement for Instance SegmentationPoster114 citations
645. SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local ElementsPoster114 citations
646. Towards Compact CNNs via Collaborative CompressionPoster114 citations
647. Weakly Supervised Learning of Rigid 3D Scene FlowPoster114 citations
648. Adaptive Methods for Real-World Domain GeneralizationPoster113 citations
649. Diversifying Sample Generation for Accurate Data-Free QuantizationPoster113 citations
650. Mitigating Face Recognition Bias via Group Adaptive ClassifierPoster113 citations
651. Monocular 3D Object Detection: An Extrinsic Parameter Free ApproachPoster113 citations
652. Nutrition5k: Towards Automatic Nutritional Understanding of Generic FoodPoster113 citations
653. Temporal Modulation Network for Controllable Space-Time Video Super-ResolutionPoster113 citations
654. Trajectory Prediction With Latent Belief Energy-Based ModelPoster113 citations
655. Camera-Space Hand Mesh Recovery via Semantic Aggregation and Adaptive 2D-1D RegistrationPoster112 citations
656. Complementary Relation Contrastive DistillationPoster112 citations
657. From Rain Generation to Rain RemovalPoster112 citations
658. Removing the Background by Adding the Background: Towards Background Robust Self-Supervised Video Representation LearningPoster112 citations
659. Repurposing GANs for One-Shot Semantic Part SegmentationPoster112 citations
660. Roses Are Red, Violets Are Blue... but Should VQA Expect Them To?Poster112 citations
661. Stylized Neural PaintingPoster112 citations
662. Unsupervised Multi-Source Domain Adaptation for Person Re-IdentificationPoster112 citations
663. Differentiable Patch Selection for Image RecognitionPoster111 citations
664. Learning Invariant Representations and Risks for Semi-Supervised Domain AdaptationPoster111 citations
665. UPFlow: Upsampling Pyramid for Unsupervised Optical Flow LearningPoster111 citations
666. GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object DetectionPoster110 citations
667. Points As Queries: Weakly Semi-Supervised Object Detection by PointsPoster110 citations
668. Probabilistic Tracklet Scoring and Inpainting for Multiple Object TrackingPoster110 citations
669. Unveiling the Potential of Structure Preserving for Weakly Supervised Object LocalizationPoster110 citations
670. Multi-Shot Temporal Event Localization: A BenchmarkPoster109 citations
671. Self-Supervised Collision Handling via Generative 3D Garment Models for Virtual Try-OnPoster109 citations
672. SliceNet: Deep Dense Depth Estimation From a Single Indoor Panorama Using a Slice-Based RepresentationPoster109 citations
673. Temporal Query Networks for Fine-Grained Video UnderstandingPoster109 citations
674. Image Restoration for Under-Display CameraPoster108 citations
675. Multi-Target Domain Adaptation With Collaborative Consistency LearningPoster108 citations
676. Person Re-Identification Using Heterogeneous Local Graph Attention NetworksPoster108 citations
677. Polygonal Building Extraction by Frame Field LearningPoster108 citations
678. Positional Encoding As Spatial Inductive Bias in GANsPoster108 citations
679. Robust Representation Learning With Feedback for Single Image DerainingPoster108 citations
680. Closing the Loop: Joint Rain Generation and Removal via Disentangled Image TranslationPoster107 citations
681. Intrinsic Image HarmonizationPoster107 citations
682. MR Image Super-Resolution With Squeeze and Excitation Reasoning Attention NetworkPoster107 citations
683. Masksembles for Uncertainty EstimationPoster107 citations
684. Quantifying Explainers of Graph Neural Networks in Computational PathologyPoster107 citations
685. Reciprocal Transformations for Unsupervised Video Object SegmentationPoster107 citations
686. Tracking Pedestrian Heads in Dense CrowdPoster107 citations
687. Action Unit Memory Network for Weakly Supervised Temporal Action LocalizationPoster106 citations
688. GeoSim: Realistic Video Simulation via Geometry-Aware Composition for Self-DrivingPoster106 citations
689. Multi-Source Domain Adaptation With Collaborative Learning for Semantic SegmentationPoster106 citations
690. ReNAS: Relativistic Evaluation of Neural Architecture SearchPoster106 citations
691. SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning Over Traffic EventsPoster106 citations
692. Style-Based Point Generator With Adversarial Rendering for Point Cloud CompletionPoster106 citations
693. Temporal Action Segmentation From Timestamp SupervisionPoster106 citations
694. Test-Time Fast Adaptation for Dynamic Scene Deblurring via Meta-Auxiliary LearningPoster106 citations
695. Adversarial Robustness Under Long-Tailed DistributionPoster105 citations
696. MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments From a Single Moving CameraPoster105 citations
697. Rich Features for Perceptual Quality Assessment of UGC VideosPoster105 citations
698. Robust Reference-Based Super-Resolution via C2-MatchingPoster105 citations
699. Spatially-Adaptive Pixelwise Networks for Fast Image TranslationPoster105 citations
700. Uncertainty Guided Collaborative Training for Weakly Supervised Temporal Action DetectionPoster105 citations
701. Long-Tailed Multi-Label Visual Recognition by Collaborative Training on Uniform and Re-Balanced SamplingsPoster104 citations
702. Truly Shift-Invariant Convolutional Neural NetworksPoster104 citations
703. Wide-Depth-Range 6D Object Pose Estimation in SpacePoster104 citations
704. DeepI2P: Image-to-Point Cloud Registration via Deep ClassificationPoster103 citations
705. Domain-Specific Suppression for Adaptive Object DetectionPoster103 citations
706. Dynamic Transfer for Multi-Source Domain AdaptationPoster103 citations
707. Learning To Restore Hazy Video: A New Real-World Dataset and a New MethodPoster103 citations
708. Data-Free Knowledge Distillation for Image Super-ResolutionPoster102 citations
709. FrameExit: Conditional Early Exiting for Efficient Video RecognitionPoster102 citations
710. High-Fidelity and Arbitrary Face EditingPoster102 citations
711. Out-of-Distribution Detection Using Union of 1-Dimensional SubspacesPoster102 citations
712. Primitive Representation Learning for Scene Text RecognitionPoster102 citations
713. Sketch2Model: View-Aware 3D Modeling From Single Free-Hand SketchesPoster102 citations
714. Structured Multi-Level Interaction Network for Video Moment Localization via Language QueryPoster102 citations
715. Towards Efficient Tensor Decomposition-Based DNN Model Compression With Optimization FrameworkPoster102 citations
716. Bottom-Up Shift and Reasoning for Referring Image SegmentationPoster101 citations
717. CASTing Your Model: Learning To Localize Improves Self-Supervised RepresentationsPoster101 citations
718. DI-Fusion: Online Implicit 3D Reconstruction With Deep PriorsPoster101 citations
719. Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object DetectionPoster101 citations
720. Learning Compositional Radiance Fields of Dynamic Human HeadsPoster101 citations
721. Learning Optical Flow From a Few MatchesPoster101 citations
722. Regularization Strategy for Point Cloud via Rigidly Mixed SamplePoster101 citations
723. SMURF: Self-Teaching Multi-Frame Unsupervised RAFT With Full-Image WarpingPoster101 citations
724. UC2: Universal Cross-Lingual Cross-Modal Vision-and-Language Pre-TrainingPoster101 citations
725. A Multi-Task Network for Joint Specular Highlight Detection and RemovalPoster100 citations
726. Dual Contradistinctive Generative AutoencoderPoster100 citations
727. M3DSSD: Monocular 3D Single Stage Object DetectorPoster100 citations
728. Robust and Accurate Object Detection via Adversarial LearningPoster100 citations
729. SetVAE: Learning Hierarchical Composition for Generative Modeling of Set-Structured DataPoster100 citations
730. Towards Fast and Accurate Real-World Depth Super-Resolution: Benchmark Dataset and BaselinePoster100 citations
731. Variational Prototype Learning for Deep Face RecognitionPoster100 citations
732. View-Guided Point Cloud CompletionPoster100 citations
733. A Closer Look at Fourier Spectrum Discrepancies for CNN-Generated Images DetectionPoster99 citations
734. Every Annotation Counts: Multi-Label Deep Supervision for Medical Image SegmentationPoster99 citations
735. Learnable Companding Quantization for Accurate Low-Bit Neural NetworksPoster99 citations
736. PointGuard: Provably Robust 3D Point Cloud ClassificationPoster99 citations
737. Unsupervised Feature Learning by Cross-Level Instance-Group DiscriminationPoster99 citations
738. Ego-Exo: Transferring Visual Representations From Third-Person to First-Person VideosPoster98 citations
739. End-to-End Learning for Joint Image Demosaicing, Denoising and Super-ResolutionPoster98 citations
740. Few-Shot Object Detection via Classification Refinement and Distractor RetreatmentPoster98 citations
741. Hierarchical Layout-Aware Graph Convolutional Network for Unified Aesthetics AssessmentPoster98 citations
742. Learning Dynamics via Graph Neural Networks for Human Pose Estimation and TrackingPoster98 citations
743. Multi-Stage Aggregated Transformer Network for Temporal Language Localization in VideosPoster98 citations
744. On the Difficulty of Membership Inference AttacksPoster98 citations
745. RGB-D Local Implicit Function for Depth Completion of Transparent ObjectsPoster98 citations
746. The Multi-Temporal Urban Development SpaceNet DatasetPoster98 citations
747. Context Modeling in 3D Human Pose Estimation: A Unified PerspectivePoster97 citations
748. CorrNet3D: Unsupervised End-to-End Learning of Dense Correspondence for 3D Point CloudsPoster97 citations
749. Global2Local: Efficient Structure Search for Video Action SegmentationPoster97 citations
750. Learning To Fuse Asymmetric Feature Maps in Siamese TrackersPoster97 citations
751. ORDisCo: Effective and Efficient Usage of Incremental Unlabeled Data for Semi-Supervised Continual LearningPoster97 citations
752. SOLD2: Self-Supervised Occlusion-Aware Line Description and DetectionPoster97 citations
753. There Is More Than Meets the Eye: Self-Supervised Multi-Object Detection and Tracking With Sound by Distilling Multimodal KnowledgePoster97 citations
754. A Hyperbolic-to-Hyperbolic Graph Convolutional NetworkPoster96 citations
755. Continual Adaptation of Visual Representations via Domain Randomization and Meta-LearningPoster96 citations
756. Discriminative Appearance Modeling With Multi-Track Pooling for Real-Time Multi-Object TrackingPoster96 citations
757. Fair Feature Distillation for Visual RecognitionPoster96 citations
758. SMD-Nets: Stereo Mixture Density NetworksPoster96 citations
759. Visual Navigation With Spatial AttentionPoster96 citations
760. Distilling Audio-Visual Knowledge by Compositional Contrastive LearningPoster95 citations
761. Instance Level Affinity-Based Transfer for Unsupervised Domain AdaptationPoster94 citations
762. Protecting Intellectual Property of Generative Adversarial Networks From Ambiguity AttacksPoster94 citations
763. Relevance-CAM: Your Model Already Knows Where To LookPoster94 citations
764. Safe Local Motion Planning With Self-Supervised Freespace ForecastingPoster94 citations
765. Slimmable Compressive Autoencoders for Practical Neural Image CompressionPoster94 citations
766. Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic ParsingPoster93 citations
767. Memory-Efficient Network for Large-Scale Video Compressive SensingPoster93 citations
768. OpenRooms: An Open Framework for Photorealistic Indoor Scene DatasetsPoster93 citations
769. RfD-Net: Point Scene Understanding by Semantic Instance ReconstructionPoster93 citations
770. Shelf-Supervised Mesh Prediction in the WildPoster93 citations
771. Siamese Natural Language Tracker: Tracking by Natural Language Descriptions With Siamese TrackersPoster93 citations
772. Weakly Supervised Video Salient Object DetectionPoster93 citations
773. Zero-Shot Adversarial QuantizationPoster93 citations
774. AIFit: Automatic 3D Human-Interpretable Feedback Models for Fitness TrainingPoster92 citations
775. KOALAnet: Blind Super-Resolution Using Kernel-Oriented Adaptive Local AdjustmentPoster92 citations
776. Learning a Facial Expression Embedding Disentangled From IdentityPoster92 citations
777. Radar-Camera Pixel Depth Association for Depth CompletionPoster92 citations
778. Spherical Confidence Learning for Face RecognitionPoster92 citations
779. 4D Panoptic LiDAR SegmentationPoster91 citations
780. AdaStereo: A Simple and Efficient Approach for Adaptive Stereo MatchingPoster91 citations
781. Capturing Omni-Range Context for Omnidirectional SegmentationPoster91 citations
782. Cross-View Regularization for Domain Adaptive Panoptic SegmentationPoster91 citations
783. Dual Attention Guided Gaze Target Detection in the WildPoster91 citations
784. Generative PointNet: Deep Energy-Based Learning on Unordered Point Sets for 3D Generation, Reconstruction and ClassificationPoster91 citations
785. I3Net: Implicit Instance-Invariant Network for Adapting One-Stage Object DetectorsPoster91 citations
786. Lifting 2D StyleGAN for 3D-Aware Face GenerationPoster91 citations
787. Multiple Instance Captioning: Learning Representations From Histopathology Textbooks and ArticlesPoster91 citations
788. Online Multiple Object Tracking With Cross-Task SynergyPoster91 citations
789. Practical Single-Image Super-Resolution Using Look-Up TablePoster91 citations
790. Rich Context Aggregation With Reflection Prior for Glass Surface DetectionPoster91 citations
791. Room-and-Object Aware Knowledge Reasoning for Remote Embodied Referring ExpressionPoster91 citations
792. Transferable Query Selection for Active Domain AdaptationPoster91 citations
793. Coarse-To-Fine Domain Adaptive Semantic Segmentation With Photometric Alignment and Category-Center RegularizationPoster90 citations
794. CondenseNet V2: Sparse Feature Reactivation for Deep NetworksPoster90 citations
795. Deep Learning in Latent Space for Video Prediction and CompressionPoster90 citations
796. Delving into Data: Effectively Substitute Training for Black-box AttackPoster90 citations
797. Efficient Feature Transformations for Discriminative and Generative Continual LearningPoster90 citations
798. Home Action Genome: Cooperative Compositional Action UnderstandingPoster90 citations
799. Incremental Few-Shot Instance SegmentationPoster90 citations
800. Invisible Perturbations: Physical Adversarial Examples Exploiting the Rolling Shutter EffectPoster90 citations
801. Cyclic Co-Learning of Sounding Object Visual Grounding and Sound SeparationPoster89 citations
802. Densely Connected Multi-Dilated Convolutional Networks for Dense Prediction TasksPoster89 citations
803. Post-Hoc Uncertainty Calibration for Domain Drift ScenariosPoster89 citations
804. Shared Cross-Modal Trajectory Prediction for Autonomous DrivingPoster89 citations
805. Uncertainty-Guided Model Generalization to Unseen DomainsPoster89 citations
806. Anycost GANs for Interactive Image Synthesis and EditingPoster88 citations
807. Cascaded Prediction Network via Segment Tree for Temporal Video GroundingPoster88 citations
808. DCT-Mask: Discrete Cosine Transform Mask Representation for Instance SegmentationPoster88 citations
809. Interpolation-Based Semi-Supervised Learning for Object DetectionPoster88 citations
810. Look Before You Speak: Visually Contextualized UtterancesPoster88 citations
811. Multi-view Depth Estimation using Epipolar Spatio-Temporal NetworksPoster88 citations
812. Revamping Cross-Modal Recipe Retrieval With Hierarchical Transformers and Self-Supervised LearningPoster88 citations
813. TransFill: Reference-Guided Image Inpainting by Merging Multiple Color and Spatial TransformationsPoster88 citations
814. UnrealPerson: An Adaptive Pipeline Towards Costless Person Re-IdentificationPoster88 citations
815. Contrastive Neural Architecture Search With Neural Architecture ComparatorsPoster87 citations
816. Joint Negative and Positive Learning for Noisy LabelsPoster87 citations
817. PointNetLK RevisitedPoster87 citations
818. Shot Contrastive Self-Supervised Learning for Scene Boundary DetectionPoster87 citations
819. Spatio-temporal Contrastive Domain Adaptation for Action RecognitionPoster87 citations
820. To the Point: Efficient 3D Object Detection in the Range Image With Graph Convolution KernelsPoster87 citations
821. Towards Unified Surgical Skill AssessmentPoster87 citations
822. Understanding Failures of Deep Networks via Robust Feature ExtractionPoster87 citations
823. Deep Polarization Imaging for 3D Shape and SVBRDF AcquisitionPoster86 citations
824. Diverse Semantic Image Synthesis via Probability Distribution ModelingPoster86 citations
825. Dogfight: Detecting Drones From Drones VideosPoster86 citations
826. Jigsaw Clustering for Unsupervised Visual Representation LearningPoster86 citations
827. L2M-GAN: Learning To Manipulate Latent Space Semantics for Facial Attribute EditingPoster86 citations
828. Learning From the Master: Distilling Cross-Modal Advanced Knowledge for Lip ReadingPoster86 citations
829. Learning by Aligning Videos in TimePoster86 citations
830. Multi-Modal Relational Graph for Cross-Modal Video Moment RetrievalPoster86 citations
831. OTCE: A Transferability Metric for Cross-Domain Cross-Task RepresentationsPoster86 citations
832. Semi-Supervised Video Deraining With Dynamical Rain GeneratorPoster86 citations
833. Sewer-ML: A Multi-Label Sewer Defect Classification Dataset and BenchmarkPoster86 citations
834. Simulating Unknown Target Models for Query-Efficient Black-Box AttacksPoster86 citations
835. Sketch, Ground, and Refine: Top-Down Dense Video CaptioningPoster86 citations
836. Sparse Auxiliary Networks for Unified Monocular Depth Prediction and CompletionPoster86 citations
837. Spoken Moments: Learning Joint Audio-Visual Representations From Video DescriptionsPoster86 citations
838. StylePeople: A Generative Model of Fullbody Human AvatarsPoster86 citations
839. DRANet: Disentangling Representation and Adaptation Networks for Unsupervised Cross-Domain AdaptationPoster85 citations
840. EvDistill: Asynchronous Events To End-Task Learning via Bidirectional Reconstruction-Guided Cross-Modal Knowledge DistillationPoster85 citations
841. Explore Image Deblurring via Encoded Blur Kernel SpacePoster85 citations
842. Glancing at the Patch: Anomaly Localization With Global and Local Feature ComparisonPoster85 citations
843. HLA-Face: Joint High-Low Adaptation for Low Light Face DetectionPoster85 citations
844. Human-Like Controllable Image Captioning With Verb-Specific Semantic RolesPoster85 citations
845. Learning the Predictability of the FuturePoster85 citations
846. More Photos Are All You Need: Semi-Supervised Learning for Fine-Grained Sketch Based Image RetrievalPoster85 citations
847. Rethinking Text Segmentation: A Novel Dataset and a Text-Specific Refinement ApproachPoster85 citations
848. S3: Neural Shape, Skeleton, and Skinning Fields for 3D Human ModelingPoster85 citations
849. Towards Bridging Event Captioner and Sentence Localizer for Weakly Supervised Dense Event CaptioningPoster85 citations
850. UV-Net: Learning From Boundary RepresentationsPoster85 citations
851. Adaptive Image Transformer for One-Shot Object DetectionPoster84 citations
852. Curriculum Graph Co-Teaching for Multi-Target Domain AdaptationPoster84 citations
853. Improving Weakly Supervised Visual Grounding by Contrastive Knowledge DistillationPoster84 citations
854. Navigating the GAN Parameter Space for Semantic Image EditingPoster84 citations
855. Semantic Scene Completion via Integrating Instances and Scene In-the-LoopPoster84 citations
856. StickyPillars: Robust and Efficient Feature Matching on Point Clouds Using Graph Neural NetworksPoster84 citations
857. Towards Accurate Text-Based Image Captioning With Content Diversity ExplorationPoster84 citations
858. ARVo: Learning All-Range Volumetric Correspondence for Video DeblurringPoster83 citations
859. Layerwise Optimization by Gradient Decomposition for Continual LearningPoster83 citations
860. Neural Deformation Graphs for Globally-Consistent Non-Rigid ReconstructionPoster83 citations
861. On Semantic Similarity in Video RetrievalPoster83 citations
862. PML: Progressive Margin Loss for Long-Tailed Age ClassificationPoster83 citations
863. Spk2ImgNet: Learning To Reconstruct Dynamic Scene From Continuous Spike StreamPoster83 citations
864. Towards Accurate 3D Human Motion Prediction From Incomplete ObservationsPoster83 citations
865. Cross-View Cross-Scene Multi-View Crowd CountingPoster82 citations
866. DualAST: Dual Style-Learning Networks for Artistic Style TransferPoster82 citations
867. Effective Sparsification of Neural Networks With Global Sparsity ConstraintPoster82 citations
868. EventZoom: Learning To Denoise and Super Resolve Neuromorphic EventsPoster82 citations
869. MaxUp: Lightweight Adversarial Training With Data Augmentation Improves Neural Network TrainingPoster82 citations
870. Modeling Multi-Label Action Dependencies for Temporal Action LocalizationPoster82 citations
871. Restoring Extremely Dark Images in Real TimePoster82 citations
872. Self-Supervised Learning for Semi-Supervised Temporal Action ProposalPoster82 citations
873. Single Image Depth Prediction With Wavelet DecompositionPoster82 citations
874. StereoPIFu: Depth Aware Clothed Human Digitization via Stereo VisionPoster82 citations
875. TransNAS-Bench-101: Improving Transferability and Generalizability of Cross-Task Neural Architecture SearchPoster82 citations
876. When Human Pose Estimation Meets Robustness: Adversarial Algorithms and BenchmarksPoster82 citations
877. Adaptive Convolutions for Structure-Aware Style TransferPoster81 citations
878. FCPose: Fully Convolutional Multi-Person Pose Estimation With Dynamic Instance-Aware ConvolutionsPoster81 citations
879. Learning Semantic Person Image Generation by Region-Adaptive NormalizationPoster81 citations
880. NeuroMorph: Unsupervised Shape Interpolation and Correspondence in One GoPoster81 citations
881. PWCLO-Net: Deep LiDAR Odometry in 3D Point Clouds Using Hierarchical Embedding Mask OptimizationPoster81 citations
882. Probabilistic Modeling of Semantic Ambiguity for Scene Graph GenerationPoster81 citations
883. Regressive Domain Adaptation for Unsupervised Keypoint DetectionPoster81 citations
884. Representative Batch Normalization With Feature CalibrationPoster81 citations
885. Rethinking Class Relations: Absolute-Relative Supervised and Unsupervised Few-Shot LearningPoster81 citations
886. Rethinking Style Transfer: From Pixels to Parameterized BrushstrokesPoster81 citations
887. Spatial-Temporal Correlation and Topology Learning for Person Re-Identification in VideosPoster81 citations
888. Temporally-Weighted Hierarchical Clustering for Unsupervised Action SegmentationPoster81 citations
889. Unsupervised Learning of 3D Object Categories From Videos in the WildPoster81 citations
890. Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware RegressionPoster80 citations
891. Multi-Scale Aligned Distillation for Low-Resolution DetectionPoster80 citations
892. ProSelfLC: Progressive Self Label Correction for Training Robust Deep Neural NetworksPoster80 citations
893. Self-Supervised Pillar Motion Learning for Autonomous DrivingPoster80 citations
894. Visual Semantic Role Labeling for Video UnderstandingPoster80 citations
895. Visualizing Adapted Knowledge in Domain TransferPoster80 citations
896. A Self-Boosting Framework for Automated Radiographic Report GenerationPoster79 citations
897. Body Meshes as PointsPoster79 citations
898. Differentiable SLAM-Net: Learning Particle SLAM for Visual NavigationPoster79 citations
899. Divide-and-Conquer for Lane-Aware Diverse Trajectory PredictionPoster79 citations
900. Interpretable Social Anchors for Human Trajectory Forecasting in CrowdsPoster79 citations
901. Introvert: Human Trajectory Prediction via Conditional 3D AttentionPoster79 citations
902. Neural Architecture Search With Random LabelsPoster79 citations
903. RangeIoUDet: Range Image Based Real-Time 3D Object Detector Optimized by Intersection Over UnionPoster79 citations
904. Scalability vs. Utility: Do We Have To Sacrifice One for the Other in Data Importance Quantification?Poster79 citations
905. Semi-Supervised Domain Adaptation Based on Dual-Level Domain Mixing for Semantic SegmentationPoster79 citations
906. Coarse-To-Fine Person Re-Identification With Auxiliary-Domain Classification and Second-Order Information BottleneckPoster78 citations
907. Exploiting Semantic Embedding and Visual Feature for Facial Action Unit DetectionPoster78 citations
908. Joint Deep Model-Based MR Image and Coil Sensitivity Reconstruction Network (Joint-ICNet) for Fast MRIPoster78 citations
909. Learning To Segment Rigid Motions From Two FramesPoster78 citations
910. LiBRe: A Practical Bayesian Approach to Adversarial DetectionPoster78 citations
911. Light Field Super-Resolution With Zero-Shot LearningPoster78 citations
912. Neural Splines: Fitting 3D Surfaces With Infinitely-Wide Neural NetworksPoster78 citations
913. Person30K: A Dual-Meta Generalization Network for Person Re-IdentificationPoster78 citations
914. Spatially-Invariant Style-Codes Controlled Makeup TransferPoster78 citations
915. A Sliced Wasserstein Loss for Neural Texture SynthesisPoster77 citations
916. Cross-Modal Center Loss for 3D Cross-Modal RetrievalPoster77 citations
917. ECKPN: Explicit Class Knowledge Propagation Network for Transductive Few-Shot LearningPoster77 citations
918. Image Inpainting With External-Internal Learning and Monochromic BottleneckPoster77 citations
919. Lipstick Ain't Enough: Beyond Color Matching for In-the-Wild Makeup TransferPoster77 citations
920. Multi-View Multi-Person 3D Pose Estimation With Plane Sweep StereoPoster77 citations
921. Part-Aware Panoptic SegmentationPoster77 citations
922. Pose-Guided Human Animation From a Single Image in the WildPoster77 citations
923. Scene-Aware Generative Network for Human Motion SynthesisPoster77 citations
924. Strengthen Learning Tolerance for Weakly Supervised Object LocalizationPoster77 citations
925. User-Guided Line Art Flat Filling With Split Filling MechanismPoster77 citations
926. Vx2Text: End-to-End Learning of Video-Based Text Generation From Multimodal InputsPoster77 citations
927. 3D Spatial Recognition Without Spatially Labeled 3DPoster76 citations
928. Anticipating Human Actions by Correlating Past With the Future With Jaccard Similarity MeasuresPoster76 citations
929. Convolutional Hough Matching NetworksPoster76 citations
930. IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object TrackingPoster76 citations
931. Learning a Self-Expressive Network for Subspace ClusteringPoster76 citations
932. Point Cloud Instance Segmentation Using Probabilistic EmbeddingsPoster76 citations
933. Scalable Differential Privacy With Sparse Network FinetuningPoster76 citations
934. The Lottery Ticket Hypothesis for Object RecognitionPoster76 citations
935. ATSO: Asynchronous Teacher-Student Optimization for Semi-Supervised Image SegmentationPoster75 citations
936. Abstract Spatial-Temporal Reasoning via Probabilistic Abduction and ExecutionPoster75 citations
937. Accurate Few-Shot Object Detection With Support-Query Mutual Guidance and Hybrid LossPoster75 citations
938. Inferring CAD Modeling Sequences Using Zone GraphsPoster75 citations
939. LiDAR-Aug: A General Rendering-Based Augmentation Framework for 3D Object DetectionPoster75 citations
940. Neural Descent for Visual 3D Human Pose and ShapePoster75 citations
941. Revisiting Superpixels for Active Learning in Semantic Segmentation With Realistic Annotation CostsPoster75 citations
942. Zillow Indoor Dataset: Annotated Floor Plans With 360deg Panoramas and 3D Room LayoutsPoster75 citations
943. Content-Aware GAN CompressionPoster74 citations
944. Dictionary-Guided Scene Text RecognitionPoster74 citations
945. Ensembling With Deep Generative ViewsPoster74 citations
946. HR-NAS: Searching Efficient High-Resolution Neural Architectures With Lightweight TransformersPoster74 citations
947. Progressive Temporal Feature Alignment Network for Video InpaintingPoster74 citations
948. Removing Diffraction Image Artifacts in Under-Display Camera via Dynamic Skip Connection NetworkPoster74 citations
949. Self-Supervised Learning on 3D Point Clouds by Learning Discrete Generative ModelsPoster74 citations
950. ViPNAS: Efficient Video Pose Estimation via Neural Architecture SearchPoster74 citations
951. Zero-Shot Single Image Restoration Through Controlled Perturbation of Koschmieder's ModelPoster74 citations
952. Efficient Multi-Stage Video Denoising With Recurrent Spatio-Temporal FusionPoster73 citations
953. High-Speed Image Reconstruction Through Short-Term Plasticity for Spiking CamerasPoster73 citations
954. Normalized Avatar Synthesis Using StyleGAN and Perceptual RefinementPoster73 citations
955. Spatial Feature Calibration and Temporal Fusion for Effective One-Stage Video Instance SegmentationPoster73 citations
956. Teachers Do More Than Teach: Compressing Image-to-Image ModelsPoster73 citations
957. CLCC: Contrastive Learning for Color ConstancyPoster72 citations
958. DOTS: Decoupling Operation and Topology in Differentiable Architecture SearchPoster72 citations
959. Deep Lucas-Kanade Homography for Multimodal Image AlignmentPoster72 citations
960. Depth-Aware Mirror SegmentationPoster72 citations
961. IQDet: Instance-Wise Quality Distribution Sampling for Object DetectionPoster72 citations
962. Monocular Real-Time Full Body Capture With Inter-Part CorrelationsPoster72 citations
963. OPANAS: One-Shot Path Aggregation Network Architecture Search for Object DetectionPoster72 citations
964. Probabilistic 3D Human Shape and Pose Estimation From Multiple Unconstrained Images in the WildPoster72 citations
965. Prototype-Guided Saliency Feature Learning for Person SearchPoster72 citations
966. Reconstructing 3D Human Pose by Watching Humans in the MirrorPoster72 citations
967. All Labels Are Not Created Equal: Enhancing Semi-Supervision via Label Grouping and Co-TrainingPoster71 citations
968. Conditional Bures Metric for Domain AdaptationPoster71 citations
969. Convolutional Dynamic Alignment Networks for Interpretable ClassificationsPoster71 citations
970. DyGLIP: A Dynamic Graph Model With Link Prediction for Accurate Multi-Camera Multiple Object TrackingPoster71 citations
971. Faster Meta Update Strategy for Noise-Robust Deep LearningPoster71 citations
972. HDMapGen: A Hierarchical Graph Generative Model of High Definition MapsPoster71 citations
973. Representation Learning via Global Temporal Alignment and Cycle-ConsistencyPoster71 citations
974. ANR: Articulated Neural Rendering for Virtual AvatarsPoster70 citations
975. Enriching ImageNet With Human Similarity Judgments and Psychological EmbeddingsPoster70 citations
976. Few-Shot Open-Set Recognition by Transformation ConsistencyPoster70 citations
977. Fine-Grained Angular Contrastive Learning With Coarse LabelsPoster70 citations
978. Hybrid Message Passing With Performance-Driven Structures for Facial Action Unit DetectionPoster70 citations
979. KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape ControlPoster70 citations
980. Learning To Relate Depth and Semantics for Unsupervised Domain AdaptationPoster70 citations
981. Mutual CRF-GNN for Few-Shot LearningPoster70 citations
982. Point2Skeleton: Learning Skeletal Representations from Point CloudsPoster70 citations
983. SelfAugment: Automatic Augmentation Policies for Self-Supervised LearningPoster70 citations
984. 3D Shape Generation With Grid-Based Implicit FunctionsPoster69 citations
985. Animating Pictures With Eulerian Motion FieldsPoster69 citations
986. CAMERAS: Enhanced Resolution and Sanity Preserving Class Activation Mapping for Image SaliencyPoster69 citations
987. Combinatorial Learning of Graph Edit Distance via Dynamic EmbeddingPoster69 citations
988. Learnable Motion Coherence for Correspondence PruningPoster69 citations
989. Learning To Reconstruct High Speed and High Dynamic Range Videos From EventsPoster69 citations
990. Residential Floor Plan Recognition and ReconstructionPoster69 citations
991. Self-Supervised Learning of Depth Inference for Multi-View StereoPoster69 citations
992. Vectorization and Rasterization: Self-Supervised Learning for Sketch and HandwritingPoster69 citations
993. GAIA: A Transfer Learning System of Object Detection That Fits Your NeedsPoster68 citations
994. Learning Affinity-Aware Upsampling for Deep Image MattingPoster68 citations
995. MetaSCI: Scalable and Adaptive Reconstruction for Video Compressive SensingPoster68 citations
996. Nighttime Visibility Enhancement by Increasing the Dynamic Range and Suppression of Light EffectsPoster68 citations
997. Relation-aware Instance Refinement for Weakly Supervised Visual GroundingPoster68 citations
998. UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable RenderingPoster68 citations
999. WOAD: Weakly Supervised Online Action Detection in Untrimmed VideosPoster68 citations
1000. Weakly Supervised Action Selection Learning in VideoPoster68 citations

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