ECCV 2020 Accepted Papers

The full list of 1,358 papers accepted at ECCV 2020 (European Conference on Computer Vision). Click any title for details, similar papers, and links to the original source. You can also search these papers by meaning, not just keywords.

1. End-to-End Object Detection with TransformersPoster17,886 citations
2. NeRF: Representing Scenes as Neural Radiance Fields for View SynthesisPoster12,384 citations
3. RAFT: Recurrent All-Pairs Field Transforms for Optical FlowPoster3,178 citations
4. Contrastive Multiview CodingPoster3,020 citations
5. UNITER: UNiversal Image-TExt Representation LearningPoster2,528 citations
6. Oscar: Object-Semantics Aligned Pre-training for Vision-Language TasksPoster2,351 citations
7. Object-Contextual Representations for Semantic SegmentationPoster1,902 citations
8. Contrastive Learning for Unpaired Image-to-Image TranslationPoster1,656 citations
9. Tracking Objects as PointsPoster1,495 citations
10. Big Transfer (BiT): General Visual Representation LearningPoster1,465 citations
11. Towards Real-Time Multi-Object TrackingPoster1,349 citations
12. Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3DPoster1,294 citations
13. Square Attack: a query-efficient black-box adversarial attack via random searchPoster1,243 citations
14. Rethinking Few-shot Image Classification: A Good Embedding is All You Need?Poster1,182 citations
15. Trajectron++: Dynamically-Feasible Trajectory Forecasting With Heterogeneous DataPoster1,175 citations
16. Convolutional Occupancy NetworksPoster1,174 citations
17. Single Path One-Shot Neural Architecture Search with Uniform SamplingPoster1,129 citations
18. SOLO: Segmenting Objects by LocationsPoster950 citations
19. Learning Enriched Features for Real Image Restoration and EnhancementPoster949 citations
20. Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic SegmentationPoster937 citations
21. Ocean: Object-aware Anchor-free TrackingPoster937 citations
22. Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware CluesPoster912 citations
23. PODNet: Pooled Outputs Distillation for Small-Tasks Incremental LearningPoster901 citations
24. Single Image Super-Resolution via a Holistic Attention NetworkPoster878 citations
25. Searching Efficient 3D Architectures with Sparse Point-Voxel ConvolutionPoster821 citations
26. Conditional Convolutions for Instance SegmentationPoster799 citations
27. Self-Challenging Improves Cross-Domain GeneralizationPoster785 citations
28. Multi-modal Transformer for Video RetrievalPoster782 citations
29. In-Domain GAN Inversion for Real Image EditingPoster774 citations
30. PointContrast: Unsupervised Pre-training for 3D Point Cloud UnderstandingPoster757 citations
31. Learning Data Augmentation Strategies for Object DetectionPoster752 citations
32. Learning Lane Graph Representations for Motion ForecastingPoster732 citations
33. GDumb: A Simple Approach that Questions Our Progress in Continual LearningPoster730 citations
34. Reflection Backdoor: A Natural Backdoor Attack on Deep Neural NetworksPoster719 citations
35. SCAN: Learning to Classify Images without LabelsPoster710 citations
36. Dynamic R-CNN: Towards High Quality Object Detection via Dynamic TrainingPoster655 citations
37. Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory PredictionPoster643 citations
38. Arbitrary-Oriented Object Detection with Circular Smooth LabelPoster632 citations
39. A Metric Learning Reality CheckPoster585 citations
40. Ultra Fast Structure-aware Deep Lane DetectionPoster585 citations
41. It is not the Journey but the Destination: Endpoint Conditioned Trajectory PredictionPoster580 citations
42. 3D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object DetectionPoster573 citations
43. Suppress and Balance: A Simple Gated Network for Salient Object DetectionPoster568 citations
44. Learning to Generate Novel Domains for Domain GeneralizationPoster556 citations
45. EPNet: Enhancing Point Features with Image Semantics for 3D Object DetectionPoster539 citations
46. Deep Local Shapes: Learning Local SDF Priors for Detailed 3D ReconstructionPoster537 citations
47. CosyPose: Consistent multi-view multi-object 6D pose estimationPoster532 citations
48. SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud SegmentationPoster531 citations
49. Towards Fast, Accurate and Stable 3D Dense Face AlignmentPoster527 citations
50. Probabilistic Anchor Assignment with IoU Prediction for Object DetectionPoster524 citations
51. I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB ImagePoster522 citations
52. Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-IdentificationPoster517 citations
53. Two-branch Recurrent Network for Isolating Deepfakes in VideosPoster513 citations
54. Semantic Flow for Fast and Accurate Scene ParsingPoster501 citations
55. V2VNet: Vehicle-to-Vehicle Communication for Joint Perception and PredictionPoster489 citations
56. TextCaps: a Dataset for Image Captioning with Reading ComprehensionPoster473 citations
57. Prototype Mixture Models for Few-shot Semantic SegmentationPoster469 citations
58. Minimum Class Confusion for Versatile Domain AdaptationPoster468 citations
59. Neural Point-Based GraphicsPoster468 citations
60. SRFlow: Learning the Super-Resolution Space with Normalizing FlowPoster462 citations
61. Unifying Deep Local and Global Features for Image SearchPoster459 citations
62. Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human PosePoster454 citations
63. ReActNet: Towards Precise Binary Neural Network with Generalized Activation FunctionsPoster452 citations
64. GRNet: Gridding Residual Network for Dense Point Cloud CompletionPoster447 citations
65. Know Your Surroundings: Exploiting Scene Information for Object TrackingPoster447 citations
66. Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and TrackingPoster444 citations
67. Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak SupervisionPoster444 citations
68. GRAB: A Dataset of Whole-Body Human Grasping of ObjectsPoster441 citations
69. Adversarial T-shirt! Evading Person Detectors in A Physical WorldPoster435 citations
70. Neural Voice Puppetry: Audio-driven Facial ReenactmentPoster435 citations
71. Real-World Blur Dataset for Learning and Benchmarking Deblurring AlgorithmsPoster435 citations
72. Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw PatchesPoster434 citations
73. Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic SegmentationPoster431 citations
74. Multi-Scale Positive Sample Refinement for Few-Shot Object DetectionPoster426 citations
75. Few-Shot Object Detection and Viewpoint Estimation for Objects in the WildPoster423 citations
76. Negative Margin Matters: Understanding Margin in Few-shot ClassificationPoster417 citations
77. BBS-Net: RGB-D Salient Object Detection with a Bifurcated Backbone Strategy NetworkPoster414 citations
78. Exploiting Deep Generative Prior for Versatile Image Restoration and ManipulationPoster413 citations
79. ScanRefer: 3D Object Localization in RGB-D Scans using Natural LanguagePoster413 citations
80. Disentangled Non-local Neural NetworksPoster412 citations
81. Non-Local Spatial Propagation Network for Depth CompletionPoster412 citations
82. Part-aware Prototype Network for Few-shot Semantic SegmentationPoster412 citations
83. A Broader Study of Cross-Domain Few-Shot LearningPoster409 citations
84. Decoupling GCN with DropGraph Module for Skeleton-Based Action RecognitionPoster404 citations
85. Identity-Guided Human Semantic Parsing for Person Re-IdentificationPoster404 citations
86. Rethinking Image Inpainting via a Mutual Encoder-Decoder with Feature EqualizationsPoster403 citations
87. What makes fake images detectable? Understanding properties that generalizePoster401 citations
88. Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic GuidancePoster394 citations
89. REMIND Your Neural Network to Prevent Catastrophic ForgettingPoster392 citations
90. Mining Cross-Image Semantics for Weakly Supervised Semantic SegmentationPoster390 citations
91. Learning Joint Spatial-Temporal Transformations for Video InpaintingPoster384 citations
92. RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous DrivingPoster381 citations
93. Instance Adaptive Self-Training for Unsupervised Domain AdaptationPoster380 citations
94. History Repeats Itself: Human Motion Prediction via Motion AttentionPoster375 citations
95. InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB ImagePoster374 citations
96. Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic SegmentationPoster369 citations
97. MEAD: A Large-scale Audio-visual Dataset for Emotional Talking-face GenerationPoster368 citations
98. Free View SynthesisPoster364 citations
99. Knowledge Distillation Meets Self-SupervisionPoster362 citations
100. House-GAN: Relational Generative Adversarial Networks for Graph-constrained House Layout GenerationPoster359 citations
101. Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed ClassificationPoster359 citations
102. BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage ModelsPoster358 citations
103. Prototype Rectification for Few-Shot LearningPoster358 citations
104. Feature Pyramid TransformerPoster347 citations
105. Whole-Body Human Pose Estimation in the WildPoster347 citations
106. Atlas: End-to-End 3D Scene Reconstruction from Posed ImagesPoster345 citations
107. ETH-XGaze: A Large Scale Dataset for Gaze Estimation under Extreme Head Pose and Gaze VariationPoster342 citations
108. STAR: Sparse Trained Articulated Human Body RegressorPoster341 citations
109. TVR: A Large-Scale Dataset for Video-Subtitle Moment RetrievalPoster340 citations
110. Making an Invisibility Cloak: Real World Adversarial Attacks on Object DetectorsPoster339 citations
111. ReferIt3D: Neural Listeners for Fine-Grained 3D Object Identification in Real-World ScenesPoster338 citations
112. Improving Semantic Segmentation via Decoupled Body and Edge SupervisionPoster337 citations
113. LatticeNet: Towards Lightweight Image Super-resolution with Lattice BlockPoster337 citations
114. Rethinking Bottleneck Structure for Efficient Mobile Network DesignPoster336 citations
115. Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous EnvironmentsPoster331 citations
116. Video Object Segmentation with Episodic Graph Memory NetworksPoster327 citations
117. Feature Space Augmentation for Long-Tailed DataPoster325 citations
118. Structured3D: A Large Photo-realistic Dataset for Structured 3D ModelingPoster325 citations
119. Collaborative Video Object Segmentation by Foreground-Background IntegrationPoster324 citations
120. Joint Disentangling and Adaptation for Cross-Domain Person Re-IdentificationPoster324 citations
121. Learning Gradient Fields for Shape GenerationPoster320 citations
122. SoundSpaces: Audio-Visual Navigation in 3D EnvironmentsPoster319 citations
123. PIoU Loss: Towards Accurate Oriented Object Detection in Complex EnvironmentsPoster317 citations
124. Learning to Optimize Domain Specific Normalization for Domain GeneralizationPoster316 citations
125. Self-Supervised Learning of Audio-Visual Objects from VideoPoster313 citations
126. MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task LearningPoster312 citations
127. Latent Embedding Feedback and Discriminative Features for Zero-Shot ClassificationPoster309 citations
128. Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed DatasetsPoster308 citations
129. DLow: Diversifying Latent Flows for Diverse Human Motion PredictionPoster305 citations
130. Guided Collaborative Training for Pixel-wise Semi-Supervised LearningPoster304 citations
131. Sub-center ArcFace: Boosting Face Recognition by Large-scale Noisy Web FacesPoster304 citations
132. Long-term Human Motion Prediction with Scene ContextPoster302 citations
133. Memory-augmented Dense Predictive Coding for Video Representation LearningPoster300 citations
134. Self-supervised Video Representation Learning by Pace PredictionPoster299 citations
135. DeepGMR: Learning Latent Gaussian Mixture Models for RegistrationPoster298 citations
136. Boundary-preserving Mask R-CNNPoster297 citations
137. Attention Guided Anomaly Localization in ImagesPoster295 citations
138. Component Divide-and-Conquer for Real-World Image Super-ResolutionPoster295 citations
139. Self-supervision with Superpixels: Training Few-shot Medical Image Segmentation without AnnotationPoster295 citations
140. Invertible Image RescalingPoster294 citations
141. Feature-metric Loss for Self-supervised Learning of Depth and EgomotionPoster293 citations
142. Clustering Driven Deep Autoencoder for Video Anomaly DetectionPoster290 citations
143. Dual Adversarial Network: Toward Real-world Noise Removal and Noise GenerationPoster290 citations
144. Improving One-stage Visual Grounding by Recursive Sub-query ConstructionPoster289 citations
145. A Single Stream Network for Robust and Real-time RGB-D Salient Object DetectionPoster284 citations
146. Image-based table recognition: data, model, and evaluationPoster284 citations
147. Connecting Vision and Language with Localized NarrativesPoster283 citations
148. Monocular Expressive Body Regression through Body-Driven AttentionPoster283 citations
149. MovieNet: A Holistic Dataset for Movie UnderstandingPoster283 citations
150. Hierarchical Dynamic Filtering Network for RGB-D Salient Object DetectionPoster277 citations
151. Bridging Knowledge Graphs to Generate Scene GraphsPoster275 citations
152. SPAN: Spatial Pyramid Attention Network for Image Manipulation LocalizationPoster275 citations
153. Learning Delicate Local Representations for Multi-Person Pose EstimationPoster274 citations
154. Adversarial Continual LearningPoster273 citations
155. Faster AutoAugment: Learning Augmentation Strategies Using BackpropagationPoster272 citations
156. Multi-Temporal Recurrent Neural Networks For Progressive Non-Uniform Single Image Deblurring With Incremental Temporal TrainingPoster272 citations
157. Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object DetectorPoster270 citations
158. TuiGAN: Learning Versatile Image-to-Image Translation with Two Unpaired ImagesPoster270 citations
159. Video Super-Resolution with Recurrent Structure-Detail NetworkPoster270 citations
160. DRG: Dual Relation Graph for Human-Object Interaction DetectionPoster268 citations
161. Improving Multispectral Pedestrian Detection by Addressing Modality Imbalance ProblemsPoster267 citations
162. Learning Open Set Network with Discriminative Reciprocal PointsPoster266 citations
163. Pillar-based Object Detection for Autonomous DrivingPoster265 citations
164. Dynamic ReLUPoster263 citations
165. NASA Neural Articulated Shape ApproximationPoster263 citations
166. Motion Guided 3D Pose Estimation from VideosPoster262 citations
167. Defocus Deblurring Using Dual-Pixel DataPoster261 citations
168. SegFix: Model-Agnostic Boundary Refinement for SegmentationPoster261 citations
169. BMBC: Bilateral Motion Estimation with Bilateral Cost Volume for Video InterpolationPoster258 citations
170. Improving Vision-and-Language Navigation with Image-Text Pairs from the WebPoster258 citations
171. TIDE: A General Toolbox for Identifying Object Detection ErrorsPoster258 citations
172. Side-Tuning: A Baseline for Network Adaptation via Additive Side NetworksPoster257 citations
173. Attention-Driven Dynamic Graph Convolutional Network for Multi-Label Image RecognitionPoster255 citations
174. Few-Shot Semantic Segmentation with Democratic Attention NetworksPoster254 citations
175. Embedding Propagation: Smoother Manifold for Few-Shot ClassificationPoster252 citations
176. Shape Prior Deformation for Categorical 6D Object Pose and Size EstimationPoster251 citations
177. Learning to Balance Specificity and Invariance for In and Out of Domain GeneralizationPoster247 citations
178. Gradient Centralization: A New Optimization Technique for Deep Neural NetworksPoster246 citations
179. Neural Predictor for Neural Architecture SearchPoster246 citations
180. Rethinking Pseudo-LiDAR RepresentationPoster245 citations
181. A Simple Way to Make Neural Networks Robust Against Diverse Image CorruptionsPoster244 citations
182. VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild EnvironmentPoster244 citations
183. Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text SpottingPoster243 citations
184. SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine ApproachPoster243 citations
185. Deep Hough Transform for Semantic Line DetectionPoster242 citations
186. End-to-End Low Cost Compressive Spectral Imaging with Spatial-Spectral Self-AttentionPoster242 citations
187. Captioning Images Taken by People Who Are BlindPoster241 citations
188. Highly Efficient Salient Object Detection with 100K ParametersPoster241 citations
189. EagleEye: Fast Sub-net Evaluation for Efficient Neural Network PruningPoster240 citations
190. Multiple Expert Brainstorming for Domain Adaptive Person Re-identificationPoster239 citations
191. Learning from Extrinsic and Intrinsic Supervisions for Domain GeneralizationPoster238 citations
192. SipMask: Spatial Information Preservation for Fast Image and Video Instance SegmentationPoster238 citations
193. CelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich AnnotationsPoster237 citations
194. Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling CostPoster237 citations
195. CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point BlendingPoster237 citations
196. Kernelized Memory Network for Video Object SegmentationPoster237 citations
197. Combining Implicit Function Learning and Parametric Models for 3D Human ReconstructionPoster236 citations
198. Points2Surf Learning Implicit Surfaces from Point CloudsPoster236 citations
199. Iterative Distance-Aware Similarity Matrix Convolution with Mutual-Supervised Point Elimination for Efficient Point Cloud RegistrationPoster235 citations
200. Bottom-Up Temporal Action Localization with Mutual RegularizationPoster234 citations
201. ContactPose: A Dataset of Grasps with Object Contact and Hand PosePoster234 citations
202. Federated Visual Classification with Real-World Data DistributionPoster234 citations
203. What Matters in Unsupervised Optical FlowPoster234 citations
204. PointPWC-Net: Cost Volume on Point Clouds for (Self-)Supervised Scene Flow EstimationPoster233 citations
205. H3DNet: 3D Object Detection Using Hybrid Geometric PrimitivesPoster232 citations
206. PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image RestorationPoster232 citations
207. Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output ObservationsPoster231 citations
208. Gait Lateral Network: Learning Discriminative and Compact Representations for Gait RecognitionPoster231 citations
209. Simulating Content Consistent Vehicle Datasets with Attribute DescentPoster231 citations
210. RobustScanner: Dynamically Enhancing Positional Clues for Robust Text RecognitionPoster230 citations
211. Contextual Diversity for Active LearningPoster229 citations
212. Perceive, Predict, and Plan: Safe Motion Planning Through Interpretable Semantic RepresentationsPoster229 citations
213. Rethinking the Distribution Gap of Person Re-identification with Camera-based Batch NormalizationPoster228 citations
214. Video-based Remote Physiological Measurement via Cross-verified Feature DisentanglingPoster228 citations
215. The Devil is in Classification: A Simple Framework for Long-tail Instance SegmentationPoster227 citations
216. Topology-Preserving Class-Incremental LearningPoster227 citations
217. Unsupervised Domain Adaptation with Noise Resistible Mutual-Training for Person Re-identificationPoster227 citations
218. Accurate RGB-D Salient Object Detection via Collaborative LearningPoster226 citations
219. FLOT: Scene Flow on Point Clouds guided by Optimal TransportPoster226 citations
220. Memory-Efficient Incremental Learning Through Feature AdaptationPoster226 citations
221. Meta-rPPG: Remote Heart Rate Estimation Using a Transductive Meta-LearnerPoster226 citations
222. Spatial-Angular Interaction for Light Field Image Super-ResolutionPoster225 citations
223. Visual Compositional Learning for Human-Object Interaction DetectionPoster225 citations
224. When Does Self-supervision Improve Few-shot Learning?Poster225 citations
225. NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture SearchPoster222 citations
226. Naive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene SegmentationPoster222 citations
227. REVISE: A Tool for Measuring and Mitigating Bias in Visual DatasetsPoster222 citations
228. BSL-1K: Scaling up co-articulated sign language recognition using mouthing cuesPoster221 citations
229. Blind Face Restoration via Deep Multi-scale Component DictionariesPoster220 citations
230. URVOS: Unified Referring Video Object Segmentation Network with a Large-Scale BenchmarkPoster220 citations
231. Few-shot Action Recognition with Permutation-invariant AttentionPoster219 citations
232. High-Resolution Image Inpainting with Iterative Confidence Feedback and Guided UpsamplingPoster219 citations
233. Hybrid Models for Open Set RecognitionPoster219 citations
234. Talking-head Generation with Rhythmic Head MotionPoster219 citations
235. ViTAA: Visual-Textual Attributes Alignment in Person Search by Natural LanguagePoster219 citations
236. DADA: Differentiable Automatic Data AugmentationPoster218 citations
237. Domain-invariant Stereo Matching NetworksPoster218 citations
238. Spike-FlowNet: Event-based Optical Flow Estimation with Energy-Efficient Hybrid Neural NetworksPoster218 citations
239. Unified Multisensory Perception: Weakly-Supervised Audio-Visual Video ParsingPoster218 citations
240. A Closer Look at Local Aggregation Operators in Point Cloud AnalysisPoster217 citations
241. SNE-RoadSeg: Incorporating Surface Normal Information into Semantic Segmentation for Accurate Freespace DetectionPoster217 citations
242. Segmenting Transparent Objects in the WildPoster217 citations
243. Smooth-AP: Smoothing the Path Towards Large-Scale Image RetrievalPoster217 citations
244. Consensus-Aware Visual-Semantic Embedding for Image-Text MatchingPoster216 citations
245. PointMixup: Augmentation for Point CloudsPoster216 citations
246. A unifying mutual information view of metric learning: cross-entropy vs. pairwise lossesPoster215 citations
247. Dual Mixup Regularized Learning for Adversarial Domain AdaptationPoster214 citations
248. Soft Anchor-Point Object DetectionPoster214 citations
249. TAO: A Large-Scale Benchmark for Tracking Any ObjectPoster214 citations
250. Boundary Content Graph Neural Network for Temporal Action Proposal GenerationPoster213 citations
251. Unified Image and Video Saliency ModelingPoster213 citations
252. Deep FusionNet for Point Cloud Semantic SegmentationPoster212 citations
253. Flow-edge Guided Video CompletionPoster212 citations
254. Post-Training Piecewise Linear Quantization for Deep Neural NetworksPoster212 citations
255. JSTASR: Joint Size and Transparency-Aware Snow Removal Algorithm Based on Modified Partial Convolution and Veiling Effect RemovalPoster211 citations
256. Object as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of HotspotsPoster211 citations
257. ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component AnalysisPoster211 citations
258. Virtual Multi-view Fusion for 3D Semantic SegmentationPoster211 citations
259. STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in VideosPoster210 citations
260. Weakly Supervised Semantic Segmentation with Boundary ExplorationPoster210 citations
261. XingGAN for Person Image GenerationPoster210 citations
262. UnionDet: Union-Level Detector Towards Real-Time Human-Object Interaction DetectionPoster209 citations
263. Cross-Modal Weighting Network for RGB-D Salient Object DetectionPoster208 citations
264. Efficient Neighbourhood Consensus Networks via Submanifold Sparse ConvolutionsPoster208 citations
265. Kinematic 3D Object Detection in Monocular VideoPoster208 citations
266. Spatial-Adaptive Network for Single Image DenoisingPoster208 citations
267. Content-Aware Unsupervised Deep Homography EstimationPoster207 citations
268. Learning to Detect Open Classes for Universal Domain AdaptationPoster207 citations
269. Reducing the Sim-to-Real Gap for Event CamerasPoster206 citations
270. Deep Spiking Neural Network: Energy Efficiency Through Time based CodingPoster205 citations
271. Prior-based Domain Adaptive Object Detection for Hazy and Rainy ConditionsPoster205 citations
272. SemanticAdv: Generating Adversarial Examples via Attribute-conditioned Image EditingPoster203 citations
273. Learning Feature Descriptors using Camera Pose SupervisionPoster201 citations
274. Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency CheckingPoster200 citations
275. Fully Convolutional Networks for Continuous Sign Language RecognitionPoster200 citations
276. Self-supervised Single-view 3D Reconstruction via Semantic ConsistencyPoster200 citations
277. Hard negative examples are hard, but usefulPoster199 citations
278. On the Effectiveness of Image Rotation for Open Set Domain AdaptationPoster199 citations
279. Self-supervising Fine-grained Region Similarities for Large-scale Image LocalizationPoster199 citations
280. Learning What to Learn for Video Object SegmentationPoster198 citations
281. Learning Progressive Joint Propagation for Human Motion PredictionPoster197 citations
282. Learning to Learn with Variational Information Bottleneck for Domain GeneralizationPoster196 citations
283. Few-Shot Scene-Adaptive Anomaly DetectionPoster195 citations
284. PiP: Planning-informed Trajectory Prediction for Autonomous DrivingPoster195 citations
285. Region Graph Embedding Network for Zero-Shot LearningPoster195 citations
286. CLAWS: Clustering Assisted Weakly Supervised Learning with Normalcy Suppression for Anomalous Event DetectionPoster194 citations
287. Joint Visual and Temporal Consistency for Unsupervised Domain Adaptive Person Re-IdentificationPoster194 citations
288. Side-Aware Boundary Localization for More Precise Object DetectionPoster194 citations
289. Stable Low-rank Tensor Decomposition for Compression of Convolutional Neural NetworkPoster194 citations
290. AR-Net: Adaptive Frame Resolution for Efficient Action RecognitionPoster193 citations
291. Face Anti-Spoofing with Human Material PerceptionPoster193 citations
292. Guiding Monocular Depth Estimation Using Depth-Attention VolumePoster193 citations
293. Implicit Latent Variable Model for Scene-Consistent Motion ForecastingPoster193 citations
294. BCNet: Learning Body and Cloth Shape from A Single ImagePoster191 citations
295. Intra-class Feature Variation Distillation for Semantic SegmentationPoster191 citations
296. Multiple Sound Sources Localization from Coarse to FinePoster191 citations
297. Progressive Transformers for End-to-End Sign Language ProductionPoster191 citations
298. Learning Visual Representations with Caption AnnotationsPoster190 citations
299. SF-Net: Single-Frame Supervision for Temporal Action LocalizationPoster190 citations
300. Unpaired Learning of Deep Image DenoisingPoster190 citations
301. Content-Consistent Matching for Domain Adaptive Semantic SegmentationPoster188 citations
302. Occupancy Anticipation for Efficient Exploration and NavigationPoster188 citations
303. Event-based Asynchronous Sparse Convolutional NetworksPoster187 citations
304. Linguistic Structure Guided Context Modeling for Referring Image SegmentationPoster187 citations
305. StyleGAN2 Distillation for Feed-forward Image ManipulationPoster186 citations
306. Temporal Aggregate Representations for Long-Range Video UnderstandingPoster186 citations
307. MuCAN: Multi-Correspondence Aggregation Network for Video Super-ResolutionPoster185 citations
308. Weakly Supervised 3D Hand Pose Estimation via Biomechanical ConstraintsPoster185 citations
309. Fast Bi-layer Neural Synthesis of One-Shot Realistic Head AvatarsPoster184 citations
310. The Devil is in the Details: Self-Supervised Attention for Vehicle Re-IdentificationPoster184 citations
311. Appearance-Preserving 3D Convolution for Video-based Person Re-identificationPoster183 citations
312. CLOTH3D: Clothed 3D HumansPoster182 citations
313. Synthesize then Compare: Detecting Failures and Anomalies for Semantic SegmentationPoster182 citations
314. Associative Alignment for Few-shot Image ClassificationPoster181 citations
315. A Comprehensive Study of Weight Sharing in Graph Networks for 3D Human Pose EstimationPoster180 citations
316. Challenge-Aware RGBT TrackingPoster180 citations
317. Face Anti-Spoofing via Disentangled Representation LearningPoster180 citations
318. Interpretable and Generalizable Person Re-Identification with Query-Adaptive Convolution and Temporal LiftingPoster180 citations
319. Scene Text Image Super-resolution in the wildPoster180 citations
320. Attract, Perturb, and Explore: Learning a Feature Alignment Network for Semi-supervised Domain AdaptationPoster179 citations
321. Boundary-Aware Cascade Networks for Temporal Action SegmentationPoster179 citations
322. Leveraging Seen and Unseen Semantic Relationships for Generative Zero-Shot LearningPoster178 citations
323. Patch-wise Attack for Fooling Deep Neural NetworkPoster178 citations
324. VPN: Learning Video-Pose Embedding for Activities of Daily LivingPoster178 citations
325. Point-Set Anchors for Object Detection, Instance Segmentation and Pose EstimationPoster177 citations
326. Selecting Relevant Features from a Multi-domain Representation for Few-shot ClassificationPoster177 citations
327. Detail Preserved Point Cloud Completion via Separated Feature AggregationPoster176 citations
328. Two-Stream Consensus Network for Weakly-Supervised Temporal Action LocalizationPoster176 citations
329. BorderDet: Border Feature for Dense Object DetectionPoster175 citations
330. Efficient Spatio-Temporal Recurrent Neural Network for Video DeblurringPoster175 citations
331. JSENet: Joint Semantic Segmentation and Edge Detection Network for 3D Point CloudsPoster175 citations
332. Contextual-Relation Consistent Domain Adaptation for Semantic SegmentationPoster174 citations
333. MotionSqueeze: Neural Motion Feature Learning for Video UnderstandingPoster174 citations
334. Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free CasesPoster173 citations
335. Efficient Semantic Video Segmentation with Per-frame InferencePoster172 citations
336. Generative Low-bitwidth Data Free QuantizationPoster172 citations
337. ParSeNet: A Parametric Surface Fitting Network for 3D Point CloudsPoster172 citations
338. An Ensemble of Epoch-wise Empirical Bayes for Few-shot LearningPoster171 citations
339. Progressively Guided Alternate Refinement Network for RGB-D Salient Object DetectionPoster171 citations
340. Self6D: Self-Supervised Monocular 6D Object Pose EstimationPoster171 citations
341. On Disentangling Spoof Trace for Generic Face Anti-SpoofingPoster170 citations
342. Bias-based Universal Adversarial Patch Attack for Automatic Check-outPoster169 citations
343. Foley Music: Learning to Generate Music from VideosPoster168 citations
344. RGB-D Salient Object Detection with Cross-Modality Modulation and SelectionPoster168 citations
345. Shape and Viewpoint without KeypointsPoster168 citations
346. A Balanced and Uncertainty-aware Approach for Partial Domain AdaptationPoster166 citations
347. Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry ConsistencyPoster166 citations
348. Differentiable Hierarchical Graph Grouping for Multi-Person Pose EstimationPoster165 citations
349. Asynchronous Interaction Aggregation for Action DetectionPoster164 citations
350. Deep Fashion3D: A Dataset and Benchmark for 3D Garment Reconstruction from Single ImagesPoster163 citations
351. Behind the Scene: Revealing the Secrets of Pre-trained Vision-and-Language ModelsPoster162 citations
352. FeatMatch: Feature-Based Augmentation for Semi-Supervised LearningPoster162 citations
353. Learning Object Relation Graph and Tentative Policy for Visual NavigationPoster162 citations
354. Learning with Privileged Information for Efficient Image Super-ResolutionPoster162 citations
355. Contrastive Learning for Weakly Supervised Phrase GroundingPoster161 citations
356. Domain Adaptive Object Detection via Asymmetric Tri-way Faster-RCNNPoster161 citations
357. Comprehensive Image Captioning via Scene Graph DecompositionPoster160 citations
358. Content Adaptive and Error Propagation Aware Deep Video CompressionPoster160 citations
359. Cross-Attention in Coupled Unmixing Nets for Unsupervised Hyperspectral Super-ResolutionPoster160 citations
360. Funnel Activation for Visual RecognitionPoster160 citations
361. Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the WildPoster160 citations
362. Weakly Supervised 3D Human Pose and Shape Reconstruction with Normalizing FlowsPoster160 citations
363. Rewriting a Deep Generative ModelPoster159 citations
364. Unpaired Image-to-Image Translation using Adversarial Consistency LossPoster159 citations
365. Multi-Task Curriculum Framework for Open-Set Semi-Supervised LearningPoster158 citations
366. DHP: Differentiable Meta Pruning via HyperNetworksPoster157 citations
367. Encoding Structure-Texture Relation with P-Net for Anomaly Detection in Retinal ImagesPoster157 citations
368. Physics-based Feature Dehazing NetworksPoster157 citations
369. Unsupervised Domain Adaptation in the Dissimilarity Space for Person Re-identificationPoster156 citations
370. Jointly De-biasing Face Recognition and Demographic Attribute EstimationPoster155 citations
371. PUGeo-Net: A Geometry-centric Network for 3D Point Cloud UpsamplingPoster155 citations
372. TSIT: A Simple and Versatile Framework for Image-to-Image TranslationPoster155 citations
373. Guidance and Evaluation: Semantic-Aware Image Inpainting for Mixed ScenesPoster154 citations
374. Learning Event-Driven Video Deblurring and InterpolationPoster154 citations
375. AdvPC: Transferable Adversarial Perturbations on 3D Point CloudsPoster153 citations
376. Detecting Human-Object Interactions with Action Co-occurrence PriorsPoster153 citations
377. Neural Design Network: Graphic Layout Generation with ConstraintsPoster152 citations
378. A Consistently Fast and Globally Optimal Solution to the Perspective-n-Point ProblemPoster151 citations
379. Adaptive Mixture Regression Network with Local Counting Map for Crowd CountingPoster151 citations
380. Curriculum Manager for Source Selection in Multi-Source Domain AdaptationPoster151 citations
381. Learning to Combine: Knowledge Aggregation for Multi-Source Domain AdaptationPoster151 citations
382. Deep Shape from PolarizationPoster150 citations
383. Forecasting Human-Object Interaction: Joint Prediction of Motor Attention and Actions in First Person VideoPoster150 citations
384. Temporal Complementary Learning for Video Person Re-IdentificationPoster150 citations
385. SOLAR: Second-Order Loss and Attention for Image RetrievalPoster149 citations
386. Weakly-Supervised Action Localization with Expectation-Maximization Multi-Instance LearningPoster149 citations
387. Diverse and Admissible Trajectory Prediction through Multimodal Context UnderstandingPoster148 citations
388. Towards Streaming PerceptionPoster148 citations
389. Improving Deep Video Compression by Resolution-adaptive Flow CodingPoster147 citations
390. Lifespan Age Transformation SynthesisPoster146 citations
391. Large-scale Pretraining for Visual Dialog: A Simple State-of-the-Art BaselinePoster145 citations
392. Learning What Makes a Difference from Counterfactual Examples and Gradient SupervisionPoster145 citations
393. RadarNet: Exploiting Radar for Robust Perception of Dynamic ObjectsPoster145 citations
394. The Hessian Penalty: A Weak Prior for Unsupervised DisentanglementPoster145 citations
395. YOLO in the Dark - Domain Adaptation Method for Merging Multiple Models -Poster145 citations
396. Corner Proposal Network for Anchor-free, Two-stage Object DetectionPoster144 citations
397. Hand-Transformer: Non-Autoregressive Structured Modeling for 3D Hand Pose EstimationPoster144 citations
398. Pyramid Multi-view Stereo Net with Self-adaptive View AggregationPoster144 citations
399. Stochastic Fine-grained Labeling of Multi-state Sign Glosses for Continuous Sign Language RecognitionPoster144 citations
400. Category Level Object Pose Estimation via Neural Analysis-by-SynthesisPoster143 citations
401. SSN: Shape Signature Networks for Multi-class Object Detection from Point CloudsPoster143 citations
402. Collaborative Training between Region Proposal Localization and Classification for Domain Adaptive Object DetectionPoster142 citations
403. Invertible Zero-Shot Recognition FlowsPoster142 citations
404. Actions as Moving PointsPoster141 citations
405. VisualCOMET: Reasoning about the Dynamic Context of a Still ImagePoster141 citations
406. Cascade Graph Neural Networks for RGB-D Salient Object DetectionPoster140 citations
407. Event Enhanced High-Quality Image RecoveryPoster140 citations
408. Imbalanced Continual Learning with Partitioning Reservoir SamplingPoster140 citations
409. Conditional Sequential Modulation for Efficient Global Image RetouchingPoster139 citations
410. DSA: More Efficient Budgeted Pruning via Differentiable Sparsity AllocationPoster139 citations
411. A Differentiable Recurrent Surface for Asynchronous Event-Based DataPoster138 citations
412. Multiview Detection with Feature Perspective TransformationPoster138 citations
413. Guided Saliency Feature Learning for Person Re-identification in Crowded ScenesPoster137 citations
414. Spatial Attention Pyramid Network for Unsupervised Domain AdaptationPoster137 citations
415. An LSTM Approach to Temporal 3D Object Detection in LiDAR Point CloudsPoster136 citations
416. Asymmetric Two-Stream Architecture for Accurate RGB-D Saliency DetectionPoster136 citations
417. Fast Video Object Segmentation using the Global Context ModulePoster136 citations
418. From Shadow Segmentation to Shadow RemovalPoster136 citations
419. Gradient-Induced Co-Saliency DetectionPoster136 citations
420. MatryODShka: Real-time 6DoF Video View Synthesis using Multi-Sphere ImagesPoster136 citations
421. Large Scale Holistic Video UnderstandingPoster135 citations
422. Rethinking Class Activation Mapping for Weakly Supervised Object LocalizationPoster135 citations
423. Discrete Point Flow Networks for Efficient Point Cloud GenerationPoster134 citations
424. Fashionpedia: Ontology, Segmentation, and an Attribute Localization DatasetPoster134 citations
425. Deep Reflectance Volumes: Relightable Reconstructions from Multi-View Photometric ImagesPoster133 citations
426. More Classifiers, Less Forgetting: A Generic Multi-classifier Paradigm for Incremental LearningPoster133 citations
427. Object-and-Action Aware Model for Visual Language NavigationPoster133 citations
428. SIZER: A Dataset and Model for Parsing 3D Clothing and Learning Size Sensitive 3D ClothingPoster133 citations
429. Gen-LaneNet: A Generalized and Scalable Approach for 3D Lane DetectionPoster132 citations
430. SMAP: Single-Shot Multi-Person Absolute 3D Pose EstimationPoster132 citations
431. Style Transfer for Co-Speech Gesture Animation: A Multi-Speaker Conditional-Mixture ApproachPoster132 citations
432. Two-phase Pseudo Label Densification for Self-training based Domain AdaptationPoster132 citations
433. Box2Seg: Attention Weighted Loss and Discriminative Feature Learning for Weakly Supervised SegmentationPoster131 citations
434. Deep Graph Matching via Blackbox Differentiation of Combinatorial SolversPoster131 citations
435. Feature Normalized Knowledge Distillation for Image ClassificationPoster131 citations
436. Do Not Mask What You Do Not Need to Mask: a Parser-Free Virtual Try-OnPoster129 citations
437. PatchAttack: A Black-box Texture-based Attack with Reinforcement LearningPoster129 citations
438. Weakly Supervised 3D Object Detection from Lidar Point CloudPoster129 citations
439. Hierarchical Kinematic Human Mesh RecoveryPoster128 citations
440. Model-Agnostic Boundary-Adversarial Sampling for Test-Time Generalization in Few-Shot learningPoster128 citations
441. Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the LoopPoster128 citations
442. DeepSFM: Structure From Motion Via Deep Bundle AdjustmentPoster127 citations
443. Generalizing Person Re-Identification by Camera-Aware Invariance Learning and Cross-Domain MixupPoster127 citations
444. Generative Sparse Detection Networks for 3D Single-shot Object DetectionPoster127 citations
445. WeightNet: Revisiting the Design Space of Weight NetworksPoster127 citations
446. Inter-Image Communication for Weakly Supervised LocalizationPoster126 citations
447. Wavelet-Based Dual-Branch Network for Image DemoiréingPoster126 citations
448. Semi-Supervised Segmentation based on Error-Correcting SupervisionPoster125 citations
449. Curriculum DeepSDFPoster124 citations
450. Info3D: Representation Learning on 3D Objects using Mutual Information Maximization and Contrastive LearningPoster123 citations
451. Learning Modality Interaction for Temporal Sentence Localization and Event Captioning in VideosPoster123 citations
452. Shuffle and Attend: Video Domain AdaptationPoster123 citations
453. ForkGAN: Seeing into the Rainy NightPoster122 citations
454. Omni-sourced Webly-supervised Learning for Video RecognitionPoster122 citations
455. Table Structure Recognition using Top-Down and Bottom-Up CuesPoster122 citations
456. Amplifying Key Cues for Human-Object-Interaction DetectionPoster121 citations
457. GANwriting: Content-Conditioned Generation of Styled Handwritten Word ImagesPoster121 citations
458. Learning Canonical Representations for Scene Graph to Image GenerationPoster121 citations
459. Learning and Aggregating Deep Local Descriptors for Instance-level RecognitionPoster121 citations
460. NAS-Count: Counting-by-Density with Neural Architecture SearchPoster121 citations
461. Spatially Adaptive Inference with Stochastic Feature Sampling and InterpolationPoster121 citations
462. Structured Landmark Detection via Topology-Adapting Deep Graph LearningPoster121 citations
463. DH3D: Deep Hierarchical 3D Descriptors for Robust Large-Scale 6DoF RelocalizationPoster120 citations
464. Adversarial Robustness on In- and Out-Distribution Improves ExplainabilityPoster119 citations
465. Contact and Human Dynamics from Monocular VideoPoster119 citations
466. HardGAN: A Haze-Aware Representation Distillation GAN for Single Image DehazingPoster119 citations
467. Practical Deep Raw Image Denoising on Mobile DevicesPoster119 citations
468. Procedure Planning in Instructional VideosPoster119 citations
469. Quantization Guided JPEG Artifact CorrectionPoster119 citations
470. Speech-driven Facial Animation using Cascaded GANs for Learning of Motion and TexturePoster119 citations
471. The Mapillary Traffic Sign Dataset for Detection and Classification on a Global ScalePoster119 citations
472. Adversarial Background-Aware Loss for Weakly-supervised Temporal Activity LocalizationPoster118 citations
473. COCO-FUNIT: Few-Shot Unsupervised Image Translation with a Content Conditioned Style EncoderPoster118 citations
474. DSDNet: Deep Structured self-Driving NetworkPoster118 citations
475. Graph-PCNN: Two Stage Human Pose Estimation with Graph Pose RefinementPoster117 citations
476. CycAs: Self-supervised Cycle Association for Learning Re-identifiable DescriptionsPoster116 citations
477. Deep Credible Metric Learning for Unsupervised Domain Adaptation Person Re-identificationPoster116 citations
478. PatchNets: Patch-Based Generalizable Deep Implicit 3D Shape RepresentationsPoster116 citations
479. Aligning and Projecting Images to Class-conditional Generative NetworksPoster115 citations
480. Orientation-aware Vehicle Re-identification with Semantics-guided Part Attention NetworkPoster115 citations
481. Towards Recognizing Unseen Categories in Unseen DomainsPoster115 citations
482. World-Consistent Video-to-Video SynthesisPoster115 citations
483. CONFIG: Controllable Neural Face Image GenerationPoster114 citations
484. Contextual Heterogeneous Graph Network for Human-Object Interaction DetectionPoster114 citations
485. Dual Refinement Underwater Object Detection NetworkPoster114 citations
486. Fairness by Learning Orthogonal Disentangled RepresentationsPoster114 citations
487. Inherent Adversarial Robustness of Deep Spiking Neural Networks: Effects of Discrete Input Encoding and Non-Linear ActivationsPoster114 citations
488. RANSAC-Flow: Generic Two-stage Image AlignmentPoster114 citations
489. Grounded Situation RecognitionPoster113 citations
490. Label-Driven Reconstruction for Domain Adaptation in Semantic SegmentationPoster113 citations
491. Mining Inter-Video Proposal Relations for Video Object DetectionPoster113 citations
492. PROFIT: A Novel Training Method for sub-4-bit MobileNet ModelsPoster113 citations
493. Social Adaptive Module for Weakly-supervised Group Activity RecognitionPoster113 citations
494. A Generic Graph-based Neural Architecture Encoding Scheme for Predictor-based NASPoster112 citations
495. Quaternion Equivariant Capsule Networks for 3D Point CloudsPoster112 citations
496. SPARK: Spatial-aware Online Incremental Attack Against Visual TrackingPoster112 citations
497. Learning Feature Embeddings for Discriminant Model based TrackingPoster111 citations
498. Multimodal Shape Completion via Conditional Generative Adversarial NetworksPoster110 citations
499. PG-Net: Pixel to Global Matching Network for Visual TrackingPoster110 citations
500. Autoregressive Unsupervised Image SegmentationPoster109 citations
501. Counterfactual Vision-and-Language Navigation via Adversarial Path SamplerPoster109 citations
502. Meta-Sim2: Unsupervised Learning of Scene Structure for Synthetic Data GenerationPoster109 citations
503. Sat2Graph: Road Graph Extraction through Graph-Tensor EncodingPoster109 citations
504. Targeted Attack for Deep Hashing based RetrievalPoster109 citations
505. CLNet: A Compact Latent Network for Fast Adjusting Siamese TrackersPoster108 citations
506. LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow EstimationPoster108 citations
507. Weakly-Supervised Crowd Counting Learns from Sorting rather than LocationsPoster108 citations
508. A Boundary Based Out-of-Distribution Classifier for Generalized Zero-Shot LearningPoster107 citations
509. Efficient Adversarial Attacks for Visual Object TrackingPoster107 citations
510. Human Body Model Fitting by Learned Gradient DescentPoster107 citations
511. Learning Disentangled Representations via Mutual Information EstimationPoster107 citations
512. Monocular Real-Time Volumetric Performance CapturePoster107 citations
513. PlugNet: Degradation Aware Scene Text Recognition Supervised by a Pluggable Super-Resolution UnitPoster107 citations
514. VisualEchoes: Spatial Image Representation Learning through EcholocationPoster107 citations
515. RobustFusion: Human Volumetric Capture with Data-driven Visual Cues using a RGBD CameraPoster106 citations
516. Spatially Aware Multimodal Transformers for TextVQAPoster106 citations
517. A Large-scale Annotated Mechanical Components Benchmark for Classification and Retrieval Tasks with Deep Neural NetworksPoster105 citations
518. Class-wise Dynamic Graph Convolution for Semantic SegmentationPoster105 citations
519. GIQA: Generated Image Quality AssessmentPoster104 citations
520. Guided Deep Decoder: Unsupervised Image Pair FusionPoster104 citations
521. Learning Graph-Convolutional Representations for Point Cloud DenoisingPoster104 citations
522. Reparameterizing Convolutions for Incremental Multi-Task Learning without Task InterferencePoster104 citations
523. Sparse Adversarial Attack via Perturbation FactorizationPoster104 citations
524. Segment as Points for Efficient Online Multi-Object Tracking and SegmentationPoster103 citations
525. Sep-Stereo: Visually Guided Stereophonic Audio Generation by Associating Source SeparationPoster103 citations
526. Towards End-to-end Video-based Eye-TrackingPoster103 citations
527. Towards causal benchmarking of bias in face analysis algorithmsPoster103 citations
528. VQA-LOL: Visual Question Answering under the Lens of LogicPoster103 citations
529. Adapting Object Detectors with Conditional Domain NormalizationPoster102 citations
530. Few-shot Compositional Font Generation with Dual MemoryPoster102 citations
531. Peeking into occluded joints: A novel framework for crowd pose estimationPoster102 citations
532. PAMS: Quantized Super-Resolution via Parameterized Max ScalePoster101 citations
533. Are Labels Necessary for Neural Architecture Search?Poster100 citations
534. BIRNAT: Bidirectional Recurrent Neural Networks with Adversarial Training for Video Snapshot Compressive ImagingPoster100 citations
535. Context-Aware RCNN: A Baseline for Action Detection in VideosPoster100 citations
536. DeepFit: 3D Surface Fitting via Neural Network Weighted Least SquaresPoster99 citations
537. GATCluster: Self-Supervised Gaussian-Attention Network for Image ClusteringPoster99 citations
538. Semantic Curiosity for Active Visual LearningPoster99 citations
539. VLANet: Video-Language Alignment Network for Weakly-Supervised Video Moment RetrievalPoster99 citations
540. DDGCN: A Dynamic Directed Graph Convolutional Network for Action RecognitionPoster98 citations
541. Fast Adaptation to Super-Resolution Networks via Meta-LearningPoster98 citations
542. Multitask Learning Strengthens Adversarial RobustnessPoster98 citations
543. SimAug: Learning Robust Representations from Simulation for Trajectory PredictionPoster98 citations
544. VCNet: A Robust Approach to Blind Image InpaintingPoster98 citations
545. Deep Hough-Transform Line PriorsPoster97 citations
546. Geometry Constrained Weakly Supervised Object LocalizationPoster97 citations
547. View-Invariant Probabilistic Embedding for Human PosePoster97 citations
548. Weighing Counts: Sequential Crowd Counting by Reinforcement LearningPoster97 citations
549. Domain Adaptive Semantic Segmentation Using Weak LabelsPoster96 citations
550. Joint Learning of Social Groups, Individuals Action and Sub-group Activities in VideosPoster96 citations
551. Online Meta-Learning for Multi-Source and Semi-Supervised Domain AdaptationPoster96 citations
552. P²Net: Patch-match and Plane-regularization for Unsupervised Indoor Depth EstimationPoster96 citations
553. Semi-Supervised Crowd Counting via Self-Training on Surrogate TasksPoster96 citations
554. Human Interaction Learning on 3D Skeleton Point Clouds for Video Violence RecognitionPoster95 citations
555. Mask2CAD: 3D Shape Prediction by Learning to Segment and RetrievePoster95 citations
556. MimicDet: Bridging the Gap Between One-Stage and Two-Stage Object DetectionPoster95 citations
557. Probabilistic Future Prediction for Video Scene UnderstandingPoster95 citations
558. Differentiable Joint Pruning and Quantization for Hardware EfficiencyPoster94 citations
559. Improving 3D Object Detection through Progressive Population Based AugmentationPoster94 citations
560. Label Propagation with Augmented Anchors: A Simple Semi-Supervised Learning baseline for Unsupervised Domain AdaptationPoster94 citations
561. Learning latent representations across multiple data domains using Lifelong VAEGANPoster94 citations
562. Reducing Language Biases in Visual Question Answering with Visually-Grounded Question EncoderPoster94 citations
563. Robust Re-Identification by Multiple Views Knowledge DistillationPoster94 citations
564. TAFSSL: Task-Adaptive Feature Sub-Space Learning for few-shot classificationPoster94 citations
565. Fashion Captioning: Towards Generating Accurate Descriptions with Semantic RewardsPoster93 citations
566. MutualNet: Adaptive ConvNet via Mutual Learning from Network Width and ResolutionPoster93 citations
567. Backpropagated Gradient Representations for Anomaly DetectionPoster92 citations
568. Shonan Rotation Averaging: Global Optimality by Surfing SO(p)(n)Poster92 citations
569. SoftPoolNet: Shape Descriptor for Point Cloud Completion and ClassificationPoster92 citations
570. Improving Object Detection with Selective Self-Supervised Self-TrainingPoster91 citations
571. Improving the Transferability of Adversarial Examples with Resized-Diverse-Inputs, Diversity-Ensemble and Region FittingPoster91 citations
572. Learning Monocular Visual Odometry via Self-Supervised Long-Term ModelingPoster91 citations
573. Neural Re-Rendering of Humans from a Single ImagePoster91 citations
574. Spatiotemporal Attacks for Embodied AgentsPoster91 citations
575. Temporal Coherence or Temporal Motion: Which is More Critical for Video-based Person Re-identification?Poster91 citations
576. Binarized Neural Network for Single Image Super ResolutionPoster90 citations
577. Global Distance-distributions Separation for Unsupervised Person Re-identificationPoster90 citations
578. Learning Visual Commonsense for Robust Scene Graph GenerationPoster90 citations
579. Learning from Scale-Invariant Examples for Domain Adaptation in Semantic SegmentationPoster90 citations
580. AtlantaNet: Inferring the 3D Indoor Layout from a Single 360(∘) Image beyond the Manhattan World AssumptionPoster89 citations
581. CPGAN: Content-Parsing Generative Adversarial Networks for Text-to-Image SynthesisPoster89 citations
582. Character Region Attention For Text SpottingPoster89 citations
583. Edge-aware Graph Representation Learning and Reasoning for Face ParsingPoster89 citations
584. Learning Joint Visual Semantic Matching Embeddings for Language-guided RetrievalPoster89 citations
585. Learning to Count in the Crowd from Limited Labeled DataPoster88 citations
586. Online Invariance Selection for Local Feature DescriptorsPoster88 citations
587. Tensor Low-Rank Reconstruction for Semantic SegmentationPoster88 citations
588. Explainable Face RecognitionPoster87 citations
589. HTML: A Parametric Hand Texture Model for 3D Hand Reconstruction and PersonalizationPoster87 citations
590. LIMP: Learning Latent Shape Representations with Metric Preservation PriorsPoster87 citations
591. MINI-Net: Multiple Instance Ranking Network for Video Highlight DetectionPoster87 citations
592. SESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing ObjectsPoster87 citations
593. Semi-supervised Semantic Segmentation via Strong-weak Dual-branch NetworkPoster87 citations
594. BATS: Binary ArchitecTure SearchPoster86 citations
595. A Unified Framework for Shot Type Classification Based on Subject Centric LensPoster85 citations
596. Active Visual Information Gathering for Vision-Language NavigationPoster85 citations
597. Face Super-Resolution Guided by 3D Facial PriorsPoster85 citations
598. OnlineAugment: Online Data Augmentation with Less Domain KnowledgePoster85 citations
599. Learning Where to Focus for Efficient Video Object DetectionPoster84 citations
600. Learning to Compose Hypercolumns for Visual CorrespondencePoster84 citations
601. Progressive Point Cloud Deconvolution Generation NetworkPoster84 citations
602. RubiksNet: Learnable 3D-Shift for Efficient Video Action RecognitionPoster84 citations
603. Adversarial Self-Supervised Learning for Semi-Supervised 3D Action RecognitionPoster83 citations
604. Angle-based Search Space Shrinking for Neural Architecture SearchPoster83 citations
605. Boosting Decision-based Black-box Adversarial Attacks with Random Sign FlipPoster83 citations
606. Deep Plastic Surgery: Robust and Controllable Image Editing with Human-Drawn SketchesPoster83 citations
607. Online Continual Learning under Extreme Memory ConstraintsPoster83 citations
608. Crowdsampling the Plenoptic FunctionPoster82 citations
609. Global and Local Enhancement Networks for Paired and Unpaired Image EnhancementPoster82 citations
610. Polysemy Deciphering Network for Human-Object Interaction DetectionPoster82 citations
611. Synthesizing Coupled 3D Face Modalities by Trunk-Branch Generative Adversarial NetworksPoster82 citations
612. Unsupervised Shape and Pose Disentanglement for 3D MeshesPoster82 citations
613. Context-Gated ConvolutionPoster81 citations
614. Object Detection with a Unified Label Space from Multiple DatasetsPoster81 citations
615. Pseudo RGB-D for Self-Improving Monocular SLAM and Depth PredictionPoster81 citations
616. Splitting vs. Merging: Mining Object Regions with Discrepancy and Intersection Loss for Weakly Supervised Semantic SegmentationPoster81 citations
617. Towards Generalization Across Depth for Monocular 3D Object DetectionPoster81 citations
618. CoReNet: Coherent 3D Scene Reconstruction from a Single RGB ImagePoster80 citations
619. Empowering Relational Network by Self-Attention Augmented Conditional Random Fields for Group Activity RecognitionPoster80 citations
620. GAN Slimming: All-in-One GAN Compression by A Unified Optimization FrameworkPoster80 citations
621. High-Fidelity Synthesis with Disentangled RepresentationPoster80 citations
622. Learning Stereo from Single ImagesPoster80 citations
623. Adaptive Offline Quintuplet Loss for Image-Text MatchingPoster79 citations
624. Adversarial Semantic Data Augmentation for Human Pose EstimationPoster79 citations
625. All at Once: Temporally Adaptive Multi-Frame Interpolation with Advanced Motion ModelingPoster79 citations
626. Deep Vectorization of Technical DrawingsPoster79 citations
627. DiVA: Diverse Visual Feature Aggregation for Deep Metric LearningPoster79 citations
628. Energy-Based Models for Deep Probabilistic RegressionPoster79 citations
629. Toward Unsupervised, Multi-Object Discovery in Large-Scale Image CollectionsPoster79 citations
630. Adaptive Variance Based Label Distribution Learning For Facial Age EstimationPoster78 citations
631. Handcrafted Outlier Detection RevisitedPoster78 citations
632. Improving Face Recognition from Hard Samples via Distribution Distillation LossPoster78 citations
633. Learning Object Placement by Inpainting for Compositional Data AugmentationPoster78 citations
634. Off-Policy Reinforcement Learning for Efficient and Effective GAN Architecture SearchPoster78 citations
635. Task-Aware Quantization Network for JPEG Image CompressionPoster78 citations
636. UFO²: A Unified Framework towards Omni-supervised Object DetectionPoster78 citations
637. Weakly Supervised Instance Segmentation by Learning Annotation Consistent InstancesPoster78 citations
638. Detecting Natural Disasters, Damage, and Incidents in the WildPoster77 citations
639. InfoFocus: 3D Object Detection for Autonomous Driving with Dynamic Information ModelingPoster77 citations
640. Learning 3D Part Assembly from a Single ImagePoster77 citations
641. One-Pixel Signature: Characterizing CNN Models for Backdoor DetectionPoster77 citations
642. Unsupervised 3D Human Pose Representation with Viewpoint and Pose DisentanglementPoster77 citations
643. Circumventing Outliers of AutoAugment with Knowledge DistillationPoster76 citations
644. DeepHandMesh: A Weakly-supervised Deep Encoder-Decoder Framework for High-fidelity Hand Mesh ModelingPoster76 citations
645. Global-and-Local Relative Position Embedding for Unsupervised Video SummarizationPoster75 citations
646. HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose EstimationPoster75 citations
647. Multi-view Action Recognition using Cross-view Video PredictionPoster75 citations
648. NAS-DIP: Learning Deep Image Prior with Neural Architecture SearchPoster75 citations
649. SODA: Story Oriented Dense Video Captioning Evaluation FrameworkPoster75 citations
650. TENet: Triple Excitation Network for Video Salient Object DetectionPoster75 citations
651. Towards Practical and Efficient High-Resolution HDR Deghosting with CNNPoster75 citations
652. EfficientFCN: Holistically-guided Decoding for Semantic SegmentationPoster74 citations
653. Employing Multi-Estimations for Weakly-Supervised Semantic SegmentationPoster74 citations
654. Matching Guided DistillationPoster74 citations
655. Occlusion-Aware Depth Estimation with Adaptive Normal ConstraintsPoster74 citations
656. Personalized Face Modeling for Improved Face Reconstruction and Motion RetargetingPoster74 citations
657. Progressive Refinement Network for Occluded Pedestrian DetectionPoster74 citations
658. The Group Loss for Deep Metric LearningPoster74 citations
659. Adaptive Task Sampling for Meta-LearningPoster73 citations
660. Conditional Entropy Coding for Efficient Video CompressionPoster73 citations
661. Faster Person Re-IdentificationPoster73 citations
662. HARD-Net: Hardness-AwaRe Discrimination Network for 3D Early Activity PredictionPoster73 citations
663. Photon-Efficient 3D Imaging with A Non-Local Neural NetworkPoster73 citations
664. SceneCAD: Predicting Object Alignments and Layouts in RGB-D ScansPoster73 citations
665. Search What You Want: Barrier Panelty NAS for Mixed Precision QuantizationPoster73 citations
666. Solving the Blind Perspective-n-Point Problem End-To-End With Robust Differentiable Geometric OptimizationPoster73 citations
667. HoughNet: Integrating near and long-range evidence for bottom-up object detectionPoster72 citations
668. Learning Discriminative Feature with CRF for Unsupervised Video Object SegmentationPoster72 citations
669. Length-Controllable Image CaptioningPoster72 citations
670. Robust Tracking against Adversarial AttacksPoster72 citations
671. Simultaneous Detection and Tracking with Motion Modelling for Multiple Object TrackingPoster72 citations
672. Task-conditioned Domain Adaptation for Pedestrian Detection in Thermal ImageryPoster72 citations
673. A Cordial Sync: Going Beyond Marginal Policies for Multi-Agent Embodied TasksPoster71 citations
674. FHDe²Net: Full High Definition Demoireing NetworkPoster71 citations
675. Learning Semantic Neural Tree for Human ParsingPoster71 citations
676. Multimodal Memorability: Modeling Effects of Semantics and Decay on Video MemorabilityPoster71 citations
677. Regional Homogeneity: Towards Learning Transferable Universal Adversarial Perturbations Against DefensesPoster71 citations
678. Renovating Parsing R-CNN for Accurate Multiple Human ParsingPoster71 citations
679. Solving Long-tailed Recognition with Deep Realistic Taxonomic ClassifierPoster71 citations
680. AutoSTR: Efficient Backbone Search for Scene Text RecognitionPoster70 citations
681. Deformable Style TransferPoster70 citations
682. Dynamic and Static Context-aware LSTM for Multi-agent Motion PredictionPoster70 citations
683. End-to-End Trainable Deep Active Contour Models for Automated Image Segmentation: Delineating Buildings in Aerial ImageryPoster70 citations
684. HMQ: Hardware Friendly Mixed Precision Quantization Block for CNNsPoster70 citations
685. Inclusive GAN: Improving Data and Minority Coverage in Generative ModelsPoster70 citations
686. Seeing the Un-Scene: Learning Amodal Semantic Maps for Room NavigationPoster70 citations
687. CLIFFNet for Monocular Depth Estimation with Hierarchical Embedding LossPoster69 citations
688. Class-Incremental Domain AdaptationPoster69 citations
689. Environment-agnostic Multitask Learning for Natural Language Grounded NavigationPoster69 citations
690. Exclusivity-Consistency Regularized Knowledge Distillation for Face RecognitionPoster69 citations
691. Knowledge Transfer via Dense Cross-Layer Mutual-DistillationPoster69 citations
692. On Modulating the Gradient for Meta-LearningPoster69 citations
693. SumGraph: Video Summarization via Recursive Graph ModelingPoster69 citations
694. 3D-Rotation-Equivariant Quaternion Neural NetworksPoster68 citations
695. JGR-P2O: Joint Graph Reasoning based Pixel-to-Offset Prediction Network for 3D Hand Pose Estimation from a Single Depth ImagePoster68 citations
696. Meshing Point Clouds with Predicted Intrinsic-Extrinsic Ratio GuidancePoster68 citations
697. Optical Flow Distillation: Towards Efficient and Stable Video Style TransferPoster68 citations
698. OS2D: One-Stage One-Shot Object Detection by Matching Anchor FeaturesPoster67 citations
699. Online Ensemble Model Compression using Knowledge DistillationPoster67 citations
700. Segmentations-Leak: Membership Inference Attacks and Defenses in Semantic Image SegmentationPoster67 citations
701. SeqHAND: RGB-Sequence-Based 3D Hand Pose and Shape EstimationPoster67 citations
702. TP-LSD: Tri-Points Based Line Segment DetectorPoster67 citations
703. Multi-person 3D Pose Estimation in Crowded Scenes Based on Multi-View GeometryPoster66 citations
704. Neural Dense Non-Rigid Structure from Motion with Latent Space ConstraintsPoster66 citations
705. Password-conditioned Anonymization and Deanonymization with Face Identity TransformersPoster66 citations
706. Active Crowd Counting with Limited SupervisionPoster65 citations
707. An Attention-driven Two-stage Clustering Method for Unsupervised Person Re-IdentificationPoster65 citations
708. Continuous Adaptation for Interactive Object Segmentation by Learning from CorrectionsPoster65 citations
709. DOPE: Distillation Of Part Experts for whole-body 3D pose estimation in the wildPoster65 citations
710. Distance-Normalized Unified Representation for Monocular 3D Object DetectionPoster65 citations
711. Joint Bilateral Learning for Real-time Universal Photorealistic Style TransferPoster65 citations
712. Learning Predictive Models from Observation and InteractionPoster65 citations
713. Learning Trailer Moments in Full-Length Movies with Co-Contrastive AttentionPoster65 citations
714. NeuRoRA: Neural Robust Rotation AveragingPoster65 citations
715. Rethinking Image Deraining via Rain Streaks and VaporsPoster65 citations
716. Single-Shot Neural Relighting and SVBRDF EstimationPoster65 citations
717. Unsupervised Sketch to Photo SynthesisPoster65 citations
718. Weakly-supervised 3D Shape Completion in the WildPoster65 citations
719. 3D Human Shape and Pose from a Single Low-Resolution Image with Self-Supervised LearningPoster64 citations
720. Improving Query Efficiency of Black-box Adversarial AttackPoster64 citations
721. Learning to See in the Dark with EventsPoster64 citations
722. PhraseClick: Toward Achieving Flexible Interactive Segmentation by Phrase and ClickPoster64 citations
723. RD-GAN: Few/Zero-Shot Chinese Character Style Transfer via Radical Decomposition and RenderingPoster64 citations
724. Semantic Equivalent Adversarial Data Augmentation for Visual Question AnsweringPoster64 citations
725. Training Interpretable Convolutional Neural Networks by Differentiating Class-specific FiltersPoster64 citations
726. BézierSketch: A generative model for scalable vector sketchesPoster63 citations
727. Directional Temporal Modeling for Action RecognitionPoster63 citations
728. Dynamic Group Convolution for Accelerating Convolutional Neural NetworksPoster63 citations
729. Early Exit Or Not: Resource-Efficient Blind Quality Enhancement for Compressed ImagesPoster63 citations
730. GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware SupervisionPoster63 citations
731. In-Home Daily-Life Captioning Using Radio SignalsPoster63 citations
732. Journey Towards Tiny Perceptual Super-ResolutionPoster63 citations
733. PointTriNet: Learned Triangulation of 3D Point SetsPoster63 citations
734. TopoGAN: A Topology-Aware Generative Adversarial NetworkPoster63 citations
735. What is Learned in Deep Uncalibrated Photometric Stereo?Poster63 citations
736. 3D Bird Reconstruction: a Dataset, Model, and Shape Recovery from a Single ViewPoster62 citations
737. Dense RepPoints: Representing Visual Objects with Dense Point SetsPoster62 citations
738. LEMMA: A Multi-view Dataset for LEarning Multi-agent Multi-task ActivitiesPoster62 citations
739. Local Correlation Consistency for Knowledge DistillationPoster62 citations
740. Momentum Batch Normalization for Deep Learning with Small Batch SizePoster62 citations
741. Self-supervised Outdoor Scene RelightingPoster62 citations
742. Take an Emotion Walk: Perceiving Emotions from Gaits Using Hierarchical Attention Pooling and Affective MappingPoster62 citations
743. Unsupervised Monocular Depth Estimation for Night-time Images using Adversarial Domain Feature AdaptationPoster62 citations
744. Adaptive Object Detection with Dual Multi-Label PredictionPoster61 citations
745. BroadFace: Looking at Tens of Thousands of People at Once for Face RecognitionPoster61 citations
746. PieNet: Personalized Image Enhancement NetworkPoster61 citations
747. Boosting Weakly Supervised Object Detection with Progressive Knowledge TransferPoster60 citations
748. Learning Noise-Aware Encoder-Decoder from Noisy Labels by Alternating Back-Propagation for Saliency DetectionPoster60 citations
749. Sketching Image Gist: Human-Mimetic Hierarchical Scene Graph GenerationPoster60 citations
750. URIE: Universal Image Enhancement for Visual Recognition in the WildPoster60 citations
751. Weakly Supervised Learning with Side Information for Noisy Labeled ImagesPoster60 citations
752. APRICOT: A Dataset of Physical Adversarial Attacks on Object DetectionPoster59 citations
753. Do Not Disturb Me: Person Re-identification Under the Interference of Other PedestriansPoster59 citations
754. Enabling Deep Residual Networks for Weakly Supervised Object DetectionPoster59 citations
755. GAN-based Garment Generation Using Sewing Pattern ImagesPoster59 citations
756. Interactive Multi-Dimension Modulation with Dynamic Controllable Residual Learning for Image RestorationPoster59 citations
757. Malleable 2.5D Convolution: Learning Receptive Fields along the Depth-axis for RGB-D Scene ParsingPoster59 citations
758. Mind the Discriminability: Asymmetric Adversarial Domain AdaptationPoster59 citations
759. Self-supervised Keypoint Correspondences for Multi-Person Pose Estimation and Tracking in VideosPoster59 citations
760. An Asymmetric Modeling for Action AssessmentPoster58 citations
761. DELTAS: Depth Estimation by Learning Triangulation And densification of Sparse pointsPoster58 citations
762. Hierarchical Visual-Textual Graph for Temporal Activity Localization via LanguagePoster58 citations
763. Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object InteractionPoster58 citations
764. Monocular 3D Object Detection via Feature Domain AdaptationPoster58 citations
765. Multi-Loss Rebalancing Algorithm for Monocular Depth EstimationPoster58 citations
766. Nighttime Defogging Using High-Low Frequency Decomposition and Grayscale-Color NetworksPoster58 citations
767. Yet Another Intermediate-Level AttackPoster58 citations
768. Channel selection using Gumbel SoftmaxPoster57 citations
769. Collaborative Learning of Gesture Recognition and 3D Hand Pose Estimation with Multi-Order Feature AnalysisPoster57 citations
770. DA4AD: End-to-End Deep Attention-based Visual Localization for Autonomous DrivingPoster57 citations
771. End-to-end Interpretable Learning of Non-blind Image DeblurringPoster57 citations
772. Improving Optical Flow on a Pyramid LevelPoster57 citations
773. Label-Efficient Learning on Point Clouds using Approximate Convex DecompositionsPoster57 citations
774. Learning to Exploit Multiple Vision Modalities by Using Grafted NetworksPoster57 citations
775. Multi-level Wavelet-based Generative Adversarial Network for Perceptual Quality Enhancement of Compressed VideoPoster57 citations
776. Surface Normal Estimation of Tilted Images via Spatial RectifierPoster57 citations
777. TF-NAS: Rethinking Three Search Freedoms of Latency-Constrained Differentiable Neural Architecture SearchPoster57 citations
778. 3D Human Shape Reconstruction from a Polarization ImagePoster56 citations
779. AttentionNAS: Spatiotemporal Attention Cell Search for Video ClassificationPoster56 citations
780. CSCL: Critical Semantic-Consistent Learning for Unsupervised Domain AdaptationPoster56 citations
781. Cyclic Functional Mapping: Self-supervised Correspondence between Non-isometric Deformable ShapesPoster56 citations
782. Deep Image Clustering with Category-Style RepresentationPoster56 citations
783. Learning Memory Augmented Cascading Network for Compressed Sensing of ImagesPoster56 citations
784. Learning Multi-layer Latent Variable Model via Variational Optimization of Short Run MCMC for Approximate InferencePoster56 citations
785. SG-VAE: Scene Grammar Variational Autoencoder to generate new indoor scenesPoster56 citations
786. Accurate Polarimetric BRDF for Real Polarization Scene RenderingPoster55 citations
787. Domain-Specific Mappings for Generative Adversarial Style TransferPoster55 citations
788. Learning Disentangled Feature Representation for Hybrid-distorted Image RestorationPoster55 citations
789. RetrieveGAN: Image Synthesis via Differentiable Patch RetrievalPoster55 citations
790. Semantic Object Prediction and Spatial Sound Super-Resolution with Binaural SoundsPoster55 citations
791. Beyond Monocular Deraining: Stereo Image Deraining via Semantic UnderstandingPoster54 citations
792. Differentiable Feature Aggregation Search for Knowledge DistillationPoster54 citations
793. Dynamic Low-light Imaging with Quanta Image SensorsPoster54 citations
794. Efficient Attention Mechanism for Visual Dialog that can Handle All the Interactions between Multiple InputsPoster54 citations
795. Estimating People Flows to Better Count Them in Crowded ScenesPoster54 citations
796. Finding It at Another Side: A Viewpoint-Adapted Matching Encoder for Change CaptioningPoster54 citations
797. Graph-Based Social Relation ReasoningPoster54 citations
798. Learning Architectures for Binary NetworksPoster54 citations
799. Monocular Differentiable Rendering for Self-Supervised 3D Object DetectionPoster54 citations
800. Motion Capture from Internet VideosPoster54 citations
801. Reversing the cycle: self-supervised deep stereo through enhanced monocular distillationPoster54 citations
802. Short-Term and Long-Term Context Aggregation Network for Video InpaintingPoster54 citations
803. Soft Expert Reward Learning for Vision-and-Language NavigationPoster54 citations
804. Adversarial Ranking Attack and DefensePoster53 citations
805. Character-Preserving Coherent Story VisualizationPoster53 citations
806. Fully Trainable and Interpretable Non-Local Sparse Models for Image RestorationPoster53 citations
807. GMNet: Graph Matching Network for Large Scale Part Semantic Segmentation in the WildPoster53 citations
808. Joint 3D Layout and Depth Prediction from a Single Indoor Panorama ImagePoster53 citations
809. Learning to Generate Grounded Visual Captions without Localization SupervisionPoster53 citations
810. TexMesh: Reconstructing Detailed Human Texture and Geometry from RGB-D VideoPoster53 citations
811. Visual Question Answering on Image SetsPoster53 citations
812. Visual Relation Grounding in VideosPoster53 citations
813. Accelerating CNN Training by Pruning Activation GradientsPoster52 citations
814. Compare and Reweight: Distinctive Image Captioning Using Similar Images SetsPoster52 citations
815. Connecting the Dots: Detecting Adversarial Perturbations Using Context InconsistencyPoster52 citations
816. ExchNet: A Unified Hashing Network for Large-Scale Fine-Grained Image RetrievalPoster52 citations
817. Learning Camera-Aware Noise ModelsPoster52 citations
818. Low Light Video Enhancement using Synthetic Data Produced with an Intermediate Domain MappingPoster52 citations
819. Attentive Prototype Few-shot Learning with Capsule Network-based EmbeddingPoster51 citations
820. CenterNet Heatmap Propagation for Real-time Video Object DetectionPoster51 citations
821. DEMEA: Deep Mesh Autoencoders for Non-Rigidly Deforming ObjectsPoster51 citations
822. DVI: Depth Guided Video Inpainting for Autonomous DrivingPoster51 citations
823. Design and Interpretation of Universal Adversarial Patches in Face DetectionPoster51 citations
824. Full-Body Awareness from Partial ObservationsPoster51 citations
825. NormalGAN: Learning Detailed 3D Human from a Single RGB-D ImagePoster51 citations
826. Polarimetric Multi-View Inverse RenderingPoster51 citations
827. Prime-Aware Adaptive DistillationPoster51 citations
828. Representative Graph Neural NetworkPoster51 citations
829. TRADI: Tracking Deep Neural network Weight DistributionsPoster51 citations
830. DPDist: Comparing Point Clouds Using Deep Point Cloud DistancePoster50 citations
831. DTVNet: Dynamic Time-lapse Video Generation via Single Still ImagePoster50 citations
832. Deep Learning-based Pupil Center Detection for Fast and Accurate Eye Tracking SystemPoster50 citations
833. End-to-end Dynamic Matching Network for Multi-view Multi-person 3d Pose EstimationPoster50 citations
834. Explaining Image Classifiers using Statistical Fault LocalizationPoster50 citations
835. Learning and Memorizing Representative Prototypes for 3D Point Cloud Semantic and Instance SegmentationPoster50 citations
836. Occlusion-Aware Siamese Network for Human Pose EstimationPoster50 citations
837. Open-Edit: Open-Domain Image Manipulation with Open-Vocabulary InstructionsPoster50 citations
838. Reconstructing NBA PlayersPoster50 citations
839. Stochastic Frequency Masking to Improve Super-Resolution and Denoising NetworksPoster50 citations
840. A Closer Look at Generalisation in RAVENPoster49 citations
841. DataMix: Efficient Privacy-Preserving Edge-Cloud InferencePoster49 citations
842. Deformation-Aware 3D Model Embedding and RetrievalPoster49 citations
843. Learning to Plan with Uncertain Topological MapsPoster49 citations
844. Multi-View Optimization of Local Feature GeometryPoster49 citations
845. PT2PC: Learning to Generate 3D Point Cloud Shapes from Part Tree ConditionsPoster49 citations
846. Stereo Event-based Particle Tracking Velocimetry for 3D Fluid Flow ReconstructionPoster49 citations
847. Supervised Edge Attention Network for Accurate Image Instance SegmentationPoster49 citations
848. Appearance Consensus Driven Self-Supervised Human Mesh RecoveryPoster48 citations
849. Efficient Non-Line-of-Sight Imaging from Transient SinogramsPoster48 citations
850. Modeling 3D Shapes by Reinforcement LearningPoster48 citations
851. OneGAN: Simultaneous Unsupervised Learning of Conditional Image Generation, Foreground Segmentation, and Fine-Grained ClusteringPoster48 citations
852. PatchPerPix for Instance SegmentationPoster48 citations
853. Privacy Preserving Structure-from-MotionPoster48 citations
854. Enhanced Sparse Model for Blind DeblurringPoster47 citations
855. HDNet: Human Depth Estimation for Multi-Person Camera-Space LocalizationPoster47 citations
856. MetaDistiller: Network Self-Boosting via Meta-Learned Top-Down DistillationPoster47 citations
857. Piggyback GAN: Efficient Lifelong Learning for Image Conditioned GenerationPoster47 citations
858. Traffic Accident Benchmark for Causality RecognitionPoster47 citations
859. A Flexible Recurrent Residual Pyramid Network for Video Frame InterpolationPoster46 citations
860. Attention-Based Query Expansion LearningPoster46 citations
861. Attentive NormalizationPoster46 citations
862. Beyond Controlled Environments: 3D Camera Re-Localization in Changing Indoor ScenesPoster46 citations
863. Deep Decomposition Learning for Inverse Imaging ProblemsPoster46 citations
864. Feature Representation Matters: End-to-End Learning for Reference-based Image Super-resolutionPoster46 citations
865. Fully Embedding Fast Convolutional Networks on Pixel Processor ArraysPoster46 citations
866. Key Frame Proposal Network for Efficient Pose Estimation in VideosPoster46 citations
867. S2DNAS: Transforming Static CNN Model for Dynamic Inference via Neural Architecture SearchPoster46 citations
868. Single View Metrology in the WildPoster46 citations
869. Sparse-to-Dense Depth Completion Revisited: Sampling Strategy and Graph ConstructionPoster46 citations
870. Deep Multi Depth Panoramas for View SynthesisPoster45 citations
871. Extending and Analyzing Self-Supervised Learning Across DomainsPoster45 citations
872. Learning to Factorize and Relight a CityPoster45 citations
873. One-Shot Unsupervised Cross-Domain DetectionPoster45 citations
874. Practical Poisoning Attacks on Neural NetworksPoster45 citations
875. SceneSketcher: Fine-Grained Image Retrieval with Scene SketchesPoster45 citations
876. Self-Supervised Multi-Task Procedure Learning from Instructional VideosPoster45 citations
877. Toward Fine-grained Facial Expression ManipulationPoster45 citations
878. Unsupervised Learning of Category-Specific Symmetric 3D Keypoints from Point SetsPoster45 citations
879. Zero-Shot Image Super-Resolution with Depth Guided Internal Degradation LearningPoster45 citations
880. AiR: Attention with Reasoning CapabilityPoster44 citations
881. Controlling Style and Semantics in Weakly-Supervised Image GenerationPoster44 citations
882. Deep Positional and Relational Feature Learning for Rotation-Invariant Point Cloud AnalysisPoster44 citations
883. GINet: Graph Interaction Network for Scene ParsingPoster44 citations
884. PSConv: Squeezing Feature Pyramid into One Compact Poly-Scale Convolutional LayerPoster44 citations
885. Preserving Semantic Neighborhoods for Robust Cross-modal RetrievalPoster44 citations
886. Representation Learning on Visual-Symbolic Graphs for Video UnderstandingPoster44 citations
887. Rotation-robust Intersection over Union for 3D Object DetectionPoster44 citations
888. Structure-Aware Human-Action GenerationPoster44 citations
889. Unsupervised Learning of Optical Flow with Deep Feature SimilarityPoster44 citations
890. Anatomy-Aware Siamese Network: Exploiting Semantic Asymmetry for Accurate Pelvic Fracture Detection in X-ray ImagesPoster43 citations
891. Anti-Bandit Neural Architecture Search for Model DefensePoster43 citations
892. Deep Image Compression using Decoder Side InformationPoster43 citations
893. Domain2Vec: Domain Embedding for Unsupervised Domain AdaptationPoster43 citations
894. Large-Scale Few-Shot Learning via Multi-Modal Knowledge DiscoveryPoster43 citations
895. Learning Flow-based Feature Warping for Face Frontalization with Illumination Inconsistent SupervisionPoster43 citations
896. Multi-Source Open-Set Deep Adversarial Domain AdaptationPoster43 citations
897. Neural Batch Sampling with Reinforcement Learning for Semi-Supervised Anomaly DetectionPoster43 citations
898. NoiseRank: Unsupervised Label Noise Reduction with Dependence ModelsPoster43 citations
899. S2DNet: Learning Image Features for Accurate Sparse-to-Dense MatchingPoster43 citations
900. Unsupervised Video Object Segmentation with Joint Hotspot TrackingPoster43 citations
901. Video Object Detection via Object-level Temporal AggregationPoster43 citations
902. Adaptive Computationally Efficient Network for Monocular 3D Hand Pose EstimationPoster42 citations
903. Adaptive Video Highlight Detection by Learning from User HistoryPoster42 citations
904. Image Classification in the Dark using Quanta Image SensorsPoster42 citations
905. Meta-Learning with Network PruningPoster42 citations
906. Pix2Surf: Learning Parametric 3D Surface Models of Objects from ImagesPoster42 citations
907. SEN: A Novel Feature Normalization Dissimilarity Measure for Prototypical Few-Shot Learning NetworksPoster42 citations
908. You Are Here: Geolocation by Embedding Maps and ImagesPoster42 citations
909. Adaptive Text Recognition through Visual MatchingPoster41 citations
910. AutoSimulate: (Quickly) Learning Synthetic Data GenerationPoster41 citations
911. Knowledge-Based Video Question Answering with Unsupervised Scene DescriptionsPoster41 citations
912. Mapillary Planet-Scale Depth DatasetPoster41 citations
913. Motion-Excited Sampler: Video Adversarial Attack with Sparked PriorPoster41 citations
914. PointAR: Efficient Lighting Estimation for Mobile Augmented RealityPoster41 citations
915. Sound2Sight: Generating Visual Dynamics from Sound and ContextPoster41 citations
916. Stochastic Bundle Adjustment for Efficient and Scalable 3D ReconstructionPoster41 citations
917. Structure-Aware Generation Network for Recipe Generation from ImagesPoster41 citations
918. Vectorizing World Buildings: Planar Graph Reconstruction by Primitive Detection and Relationship InferencePoster41 citations
919. A Competence-aware Curriculum for Visual Concepts Learning via Question AnsweringPoster40 citations
920. Dual Adversarial Network for Deep Active LearningPoster40 citations
921. Expressive Telepresence via Modular Codec AvatarsPoster40 citations
922. Full-Time Monocular Road Detection Using Zero-Distribution Prior of Angle of PolarizationPoster40 citations
923. Interactive Video Object Segmentation Using Global and Local Transfer ModulesPoster40 citations
924. Making Affine Correspondences Work in Camera Geometry ComputationPoster40 citations
925. Mitigating Embedding and Class Assignment Mismatch in Unsupervised Image ClassificationPoster40 citations
926. Open-set Adversarial DefensePoster40 citations
927. Suppressing Mislabeled Data via Grouping and Self-AttentionPoster40 citations
928. Symbiotic Adversarial Learning for Attribute-based Person SearchPoster40 citations
929. Towards Unique and Informative Captioning of ImagesPoster40 citations
930. 3D Scene Reconstruction from a Single ViewportPoster39 citations
931. Beyond 3DMM Space: Towards Fine-grained 3D Face ReconstructionPoster39 citations
932. Count- and Similarity-aware R-CNN for Pedestrian DetectionPoster39 citations
933. Coupling Explicit and Implicit Surface Representations for Generative 3D ModelingPoster39 citations
934. Du²Net: Learning Depth Estimation from Dual-Cameras and Dual-PixelsPoster39 citations
935. FairALM: Augmented Lagrangian Method for Training Fair Models with Little RegretPoster39 citations
936. Indirect Local Attacks for Context-aware Semantic Segmentation NetworksPoster39 citations
937. Microscopy Image Restoration with Deep Wiener-Kolmogorov FiltersPoster39 citations
938. Semantic Relation Preserving Knowledge Distillation for Image-to-Image TranslationPoster39 citations
939. CAFE-GAN: Arbitrary Face Attribute Editing with Complementary Attention FeaturePoster38 citations
940. Defocus Blur Detection via Depth DistillationPoster38 citations
941. Impact of base dataset design on few-shot image classificationPoster38 citations
942. Multi-Agent Embodied Question Answering in Interactive EnvironmentsPoster38 citations
943. Proposal-based Video CompletionPoster38 citations
944. Sketch-Guided Object Localization in Natural ImagesPoster38 citations
945. Temporal Distinct Representation Learning for Action RecognitionPoster38 citations
946. A Generalization of Otsu’s Method and Minimum Error ThresholdingPoster37 citations
947. AutoMix: Mixup Networks for Sample Interpolation via Cooperative Barycenter LearningPoster37 citations
948. Discriminative Partial Domain Adversarial NetworkPoster37 citations
949. Duality Diagram Similarity: a generic framework for initialization selection in task transfer learningPoster37 citations
950. Learning to Predict Context-adaptive Convolution for Semantic SegmentationPoster37 citations
951. Learning to Scale Multilingual Representations for Vision-Language TasksPoster37 citations
952. Propagating Over Phrase Relations for One-Stage Visual GroundingPoster37 citations
953. Semantic View SynthesisPoster37 citations
954. Uncertainty-Aware Weakly Supervised Action Detection from Untrimmed VideosPoster37 citations
955. Adversarial Generative Grammars for Human Activity PredictionPoster36 citations
956. Co-Heterogeneous and Adaptive Segmentation from Multi-Source and Multi-Phase CT Imaging Data: A Study on Pathological Liver and Lesion SegmentationPoster36 citations
957. Invertible Neural BRDF for Object Inverse RenderingPoster36 citations
958. Learning Attentive and Hierarchical Representations for 3D Shape RecognitionPoster36 citations
959. Learning Object Permanence from VideoPoster36 citations
960. LevelSet R-CNN: A Deep Variational Method for Instance SegmentationPoster36 citations
961. ProxyBNN: Learning Binarized Neural Networks via Proxy MatricesPoster36 citations
962. Can You Read Me Now? Content Aware Rectification using Angle SupervisionPoster35 citations
963. Commonality-Parsing Network across Shape and Appearance for Partially Supervised Instance SegmentationPoster35 citations
964. Cross-Task Transfer for Geotagged Audiovisual Aerial Scene RecognitionPoster35 citations
965. Deep Complementary Joint Model for Complex Scene Registration and Few-shot Segmentation on Medical ImagesPoster35 citations
966. Deep near-light photometric stereo for spatially varying reflectancesPoster35 citations
967. Disambiguating Monocular Depth Estimation with a Single TransientPoster35 citations
968. Hierarchical Context Embedding for Region-based Object DetectionPoster35 citations
969. Hierarchical Style-based Networks for Motion SynthesisPoster35 citations
970. Improving Monocular Depth Estimation by Leveraging Structural Awareness and Complementary DatasetsPoster35 citations
971. Manifold Projection for Adversarial Defense on Face RecognitionPoster35 citations
972. Online Multi-modal Person Search in VideosPoster35 citations
973. SeqXY2SeqZ: Structure Learning for 3D Shapes by Sequentially Predicting 1D Occupancy Segments From 2D CoordinatesPoster35 citations
974. Sequential Deformation for Accurate Scene Text DetectionPoster35 citations
975. Spiral Generative Network for Image ExtrapolationPoster35 citations
976. TRRNet: Tiered Relation Reasoning for Compositional Visual Question AnsweringPoster35 citations
977. Entropy Minimisation Framework for Event-based Vision Model EstimationPoster34 citations
978. GeoLayout: Geometry Driven Room Layout Estimation Based on Depth Maps of PlanesPoster34 citations
979. Learning Disentangled Representations with Latent Variation PredictabilityPoster34 citations
980. Learning Pairwise Inter-Plane Relations for Piecewise Planar ReconstructionPoster34 citations
981. Learning with Noisy Class Labels for Instance SegmentationPoster34 citations
982. Privacy Preserving Visual SLAMPoster34 citations
983. Reflection Separation via Multi-bounce Polarization State TracingPoster34 citations
984. SMART: Simultaneous Multi-Agent Recurrent Trajectory PredictionPoster34 citations
985. Self-Supervised CycleGAN for Object-Preserving Image-to-Image Domain AdaptationPoster34 citations
986. SimPose: Effectively Learning DensePose and Surface Normals of People from Simulated DataPoster34 citations
987. TANet: Towards Fully Automatic Tooth ArrangementPoster34 citations
988. Towards Content-Independent Multi-Reference Super-Resolution: Adaptive Pattern Matching and Feature AggregationPoster34 citations
989. Weight Excitation: Built-in Attention Mechanisms in Convolutional Neural NetworksPoster34 citations
990. Disentangling Multiple Features in Video Sequences using Gaussian Processes in Variational AutoencodersPoster33 citations
991. Explanation-based Weakly-supervised Learning of Visual Relations with Graph NetworksPoster33 citations
992. Generating Handwriting via Decoupled Style DescriptorsPoster33 citations
993. GeoGraph: Graph-based multi-view object detection with geometric cues end-to-endPoster33 citations
994. Learning Structural Similarity of User Interface Layouts using Graph NetworksPoster33 citations
995. Null-sampling for Interpretable and Fair RepresentationsPoster33 citations
996. OID: Outlier Identifying and Discarding in Blind Image DeblurringPoster33 citations
997. Regression of Instance Boundary by Aggregated CNN and GCNPoster33 citations
998. Resolution Switchable Networks for Runtime Efficient Image RecognitionPoster33 citations
999. AE-OT-GAN: Training GANs from data specific latent distributionPoster32 citations
1000. CAD-Deform: Deformable Fitting of CAD Models to 3D ScansPoster32 citations

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