CVPR 2019 Accepted Papers

The full list of 1,294 papers accepted at CVPR 2019 (IEEE/CVF Conference on Computer Vision and Pattern Recognition). Click any title for details, similar papers, and links to the original source. You can also search these papers by meaning, not just keywords.

1. A Style-Based Generator Architecture for Generative Adversarial NetworksOral14,282 citations
2. ArcFace: Additive Angular Margin Loss for Deep Face RecognitionOral8,474 citations
3. Dual Attention Network for Scene SegmentationPoster7,468 citations
4. Generalized Intersection Over Union: A Metric and a Loss for Bounding Box RegressionPoster6,789 citations
5. Deep High-Resolution Representation Learning for Human Pose EstimationPoster6,183 citations
6. PointPillars: Fast Encoders for Object Detection From Point CloudsPoster4,630 citations
7. DeepSDF: Learning Continuous Signed Distance Functions for Shape RepresentationOral4,353 citations
8. MnasNet: Platform-Aware Neural Architecture Search for MobilePoster4,089 citations
9. Semantic Image Synthesis With Spatially-Adaptive NormalizationOral3,706 citations
10. Occupancy Networks: Learning 3D Reconstruction in Function SpaceOral3,382 citations
11. Selective Kernel NetworksPoster3,288 citations
12. Class-Balanced Loss Based on Effective Number of SamplesPoster3,212 citations
13. PointRCNN: 3D Object Proposal Generation and Detection From Point CloudPoster3,208 citations
14. AutoAugment: Learning Augmentation Strategies From DataOral3,054 citations
15. Deformable ConvNets V2: More Deformable, Better ResultsPoster2,819 citations
16. SiamRPN++: Evolution of Siamese Visual Tracking With Very Deep NetworksOral2,748 citations
17. GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question AnsweringOral2,286 citations
18. 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural NetworksPoster2,282 citations
19. PointConv: Deep Convolutional Networks on 3D Point CloudsPoster2,178 citations
20. Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action RecognitionPoster2,123 citations
21. NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object DetectionPoster2,118 citations
22. Expressive Body Capture: 3D Hands, Face, and Body From a Single ImageOral2,080 citations
23. Second-Order Attention Network for Single Image Super-ResolutionOral2,042 citations
24. Bag of Tricks for Image Classification with Convolutional Neural NetworksPoster2,019 citations
25. Panoptic SegmentationPoster2,011 citations
26. MVTec AD -- A Comprehensive Real-World Dataset for Unsupervised Anomaly DetectionPoster2,006 citations
27. Libra R-CNN: Towards Balanced Learning for Object DetectionPoster1,921 citations
28. Relational Knowledge DistillationPoster1,916 citations
29. Learning Implicit Fields for Generative Shape ModelingPoster1,851 citations
30. BASNet: Boundary-Aware Salient Object DetectionPoster1,782 citations
31. Fast Online Object Tracking and Segmentation: A Unifying ApproachPoster1,768 citations
32. LaSOT: A High-Quality Benchmark for Large-Scale Single Object TrackingPoster1,750 citations
33. Argoverse: 3D Tracking and Forecasting With Rich MapsOral1,736 citations
34. Hybrid Task Cascade for Instance SegmentationPoster1,727 citations
35. ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic SegmentationOral1,726 citations
36. Panoptic Feature Pyramid NetworksOral1,715 citations
37. Do Better ImageNet Models Transfer Better?Oral1,706 citations
38. FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture SearchOral1,699 citations
39. Large Scale Incremental LearningPoster1,682 citations
40. Meta-Learning With Differentiable Convex OptimizationOral1,664 citations
41. ATOM: Accurate Tracking by Overlap MaximizationOral1,659 citations
42. LVIS: A Dataset for Large Vocabulary Instance SegmentationPoster1,621 citations
43. Meta-Transfer Learning for Few-Shot LearningPoster1,552 citations
44. On the Continuity of Rotation Representations in Neural NetworksPoster1,552 citations
45. Filter Pruning via Geometric Median for Deep Convolutional Neural Networks AccelerationOral1,523 citations
46. Learning a Unified Classifier Incrementally via RebalancingPoster1,518 citations
47. Noise2Void - Learning Denoising From Single Noisy ImagesPoster1,486 citations
48. Improving Transferability of Adversarial Examples With Input DiversityPoster1,481 citations
49. Large-Scale Long-Tailed Recognition in an Open WorldOral1,471 citations
50. 3D Human Pose Estimation in Video With Temporal Convolutions and Semi-Supervised TrainingPoster1,464 citations
51. Multi-Label Image Recognition With Graph Convolutional NetworksPoster1,418 citations
52. End-To-End Multi-Task Learning With AttentionPoster1,416 citations
53. Actional-Structural Graph Convolutional Networks for Skeleton-Based Action RecognitionPoster1,391 citations
54. PVNet: Pixel-Wise Voting Network for 6DoF Pose EstimationOral1,355 citations
55. Pseudo-LiDAR From Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous DrivingPoster1,347 citations
56. Mask Scoring R-CNNOral1,341 citations
57. Towards VQA Models That Can ReadPoster1,328 citations
58. Learning RoI Transformer for Oriented Object Detection in Aerial ImagesPoster1,326 citations
59. Character Region Awareness for Text DetectionPoster1,294 citations
60. DenseFusion: 6D Object Pose Estimation by Iterative Dense FusionPoster1,292 citations
61. Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image SegmentationOral1,290 citations
62. HAQ: Hardware-Aware Automated Quantization With Mixed PrecisionOral1,273 citations
63. Deeper and Wider Siamese Networks for Real-Time Visual TrackingOral1,266 citations
64. Toward Convolutional Blind Denoising of Real PhotographsPoster1,266 citations
65. Cascaded Partial Decoder for Fast and Accurate Salient Object DetectionPoster1,258 citations
66. A Simple Pooling-Based Design for Real-Time Salient Object DetectionPoster1,257 citations
67. Bottom-Up Object Detection by Grouping Extreme and Center PointsPoster1,255 citations
68. SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical ConstraintsPoster1,245 citations
69. Importance Estimation for Neural Network PruningPoster1,237 citations
70. Relation-Shape Convolutional Neural Network for Point Cloud AnalysisOral1,206 citations
71. OK-VQA: A Visual Question Answering Benchmark Requiring External KnowledgePoster1,199 citations
72. Contrastive Adaptation Network for Unsupervised Domain AdaptationPoster1,190 citations
73. Feature Selective Anchor-Free Module for Single-Shot Object DetectionPoster1,167 citations
74. Feature Denoising for Improving Adversarial RobustnessPoster1,130 citations
75. Deep Modular Co-Attention Networks for Visual Question AnsweringPoster1,110 citations
76. Evading Defenses to Transferable Adversarial Examples by Translation-Invariant AttacksOral1,086 citations
77. From Coarse to Fine: Robust Hierarchical Localization at Large ScalePoster1,086 citations
78. Underexposed Photo Enhancement Using Deep Illumination EstimationOral1,084 citations
79. Progressive Image Deraining Networks: A Better and Simpler BaselinePoster1,077 citations
80. Domain Generalization by Solving Jigsaw PuzzlesOral1,075 citations
81. Skeleton-Based Action Recognition With Directed Graph Neural NetworksPoster1,067 citations
82. From Recognition to Cognition: Visual Commonsense ReasoningOral1,062 citations
83. Feedback Network for Image Super-ResolutionPoster1,053 citations
84. PointNetLK: Robust & Efficient Point Cloud Registration Using PointNetPoster1,046 citations
85. An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action RecognitionPoster1,042 citations
86. Joint Discriminative and Generative Learning for Person Re-IdentificationOral1,005 citations
87. Multi-Similarity Loss With General Pair Weighting for Deep Metric LearningPoster1,000 citations
88. Video Action Transformer NetworkOral955 citations
89. PointWeb: Enhancing Local Neighborhood Features for Point Cloud ProcessingPoster953 citations
90. Revisiting Self-Supervised Visual Representation LearningPoster942 citations
91. Auto-Encoding Scene Graphs for Image CaptioningOral939 citations
92. Taking a Closer Look at Domain Shift: Category-Level Adversaries for Semantics Consistent Domain AdaptationOral933 citations
93. Structured Knowledge Distillation for Semantic SegmentationOral929 citations
94. Learning Loss for Active LearningOral924 citations
95. GA-Net: Guided Aggregation Net for End-To-End Stereo MatchingOral915 citations
96. MS-TCN: Multi-Stage Temporal Convolutional Network for Action SegmentationPoster910 citations
97. D2-Net: A Trainable CNN for Joint Description and Detection of Local FeaturesPoster909 citations
98. Label Propagation for Deep Semi-Supervised LearningPoster889 citations
99. Pyramid Feature Attention Network for Saliency DetectionPoster873 citations
100. Variational Information Distillation for Knowledge TransferPoster873 citations
101. Multi-Task Multi-Sensor Fusion for 3D Object DetectionPoster870 citations
102. Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size EstimationOral870 citations
103. Strong-Weak Distribution Alignment for Adaptive Object DetectionPoster853 citations
104. PartNet: A Large-Scale Benchmark for Fine-Grained and Hierarchical Part-Level 3D Object UnderstandingPoster849 citations
105. Graph Attention Convolution for Point Cloud Semantic SegmentationPoster846 citations
106. Context-Aware Crowd CountingPoster838 citations
107. Enhanced Pix2pix Dehazing NetworkPoster836 citations
108. Generalized Zero- and Few-Shot Learning via Aligned Variational AutoencodersPoster834 citations
109. DVC: An End-To-End Deep Video Compression FrameworkOral832 citations
110. DFANet: Deep Feature Aggregation for Real-Time Semantic SegmentationPoster831 citations
111. Shape Robust Text Detection With Progressive Scale Expansion NetworkPoster827 citations
112. A General and Adaptive Robust Loss FunctionOral825 citations
113. Searching for a Robust Neural Architecture in Four GPU HoursPoster812 citations
114. Bidirectional Learning for Domain Adaptation of Semantic SegmentationPoster809 citations
115. DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-To-Image SynthesisPoster797 citations
116. Region Proposal by Guided AnchoringPoster796 citations
117. Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-IdentificationPoster780 citations
118. Group-Wise Correlation Stereo NetworkPoster776 citations
119. Unsupervised Embedding Learning via Invariant and Spreading Instance FeaturePoster760 citations
120. Mode Seeking Generative Adversarial Networks for Diverse Image SynthesisPoster756 citations
121. CANet: Class-Agnostic Segmentation Networks With Iterative Refinement and Attentive Few-Shot LearningPoster747 citations
122. Sliced Wasserstein Discrepancy for Unsupervised Domain AdaptationPoster743 citations
123. Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion SegmentationPoster742 citations
124. MirrorGAN: Learning Text-To-Image Generation by RedescriptionPoster741 citations
125. Weakly Supervised Learning of Instance Segmentation With Inter-Pixel RelationsOral736 citations
126. DeepVoxels: Learning Persistent 3D Feature EmbeddingsOral725 citations
127. Deep Stacked Hierarchical Multi-Patch Network for Image DeblurringPoster723 citations
128. Why ReLU Networks Yield High-Confidence Predictions Far Away From the Training Data and How to Mitigate the ProblemOral717 citations
129. Explainability Methods for Graph Convolutional Neural NetworksOral716 citations
130. Knockoff Nets: Stealing Functionality of Black-Box ModelsPoster714 citations
131. Learning From Synthetic Data for Crowd Counting in the WildPoster712 citations
132. Towards Optimal Structured CNN Pruning via Generative Adversarial LearningPoster712 citations
133. OCGAN: One-Class Novelty Detection Using GANs With Constrained Latent RepresentationsPoster708 citations
134. Recurrent MVSNet for High-Resolution Multi-View Stereo Depth InferencePoster706 citations
135. CrowdPose: Efficient Crowded Scenes Pose Estimation and a New BenchmarkOral699 citations
136. MOTS: Multi-Object Tracking and SegmentationPoster699 citations
137. Revisiting Local Descriptor Based Image-To-Class Measure for Few-Shot LearningPoster698 citations
138. Spatial Attentive Single-Image Deraining With a High Quality Real Rain DatasetPoster698 citations
139. Semantic Graph Convolutional Networks for 3D Human Pose RegressionPoster694 citations
140. Learning Without MemorizingPoster693 citations
141. Stereo R-CNN Based 3D Object Detection for Autonomous DrivingPoster692 citations
142. Bounding Box Regression With Uncertainty for Accurate Object DetectionPoster674 citations
143. Depth-Aware Video Frame InterpolationPoster672 citations
144. Convolutional Mesh Regression for Single-Image Human Shape ReconstructionOral670 citations
145. PifPaf: Composite Fields for Human Pose EstimationPoster670 citations
146. Characterizing and Avoiding Negative TransferPoster661 citations
147. Edge-Labeling Graph Neural Network for Few-Shot LearningOral653 citations
148. Universal Domain AdaptationPoster651 citations
149. Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language NavigationOral649 citations
150. Unsupervised Event-Based Learning of Optical Flow, Depth, and EgomotionPoster648 citations
151. F-VAEGAN-D2: A Feature Generating Framework for Any-Shot LearningPoster647 citations
152. Blind Super-Resolution With Iterative Kernel CorrectionPoster646 citations
153. ManTra-Net: Manipulation Tracing Network for Detection and Localization of Image Forgeries With Anomalous FeaturesPoster645 citations
154. Attention Branch Network: Learning of Attention Mechanism for Visual ExplanationOral640 citations
155. SpotTune: Transfer Learning Through Adaptive Fine-TuningPoster640 citations
156. Pluralistic Image CompletionPoster637 citations
157. SR-LSTM: State Refinement for LSTM Towards Pedestrian Trajectory PredictionPoster636 citations
158. Learning Joint Reconstruction of Hands and Manipulated ObjectsPoster631 citations
159. Learning 3D Human Dynamics From VideoPoster630 citations
160. Long-Term Feature Banks for Detailed Video UnderstandingOral621 citations
161. FlowNet3D: Learning Scene Flow in 3D Point CloudsPoster620 citations
162. Latent Space Autoregression for Novelty DetectionPoster619 citations
163. Learning to Compose Dynamic Tree Structures for Visual ContextsOral618 citations
164. ABC: A Big CAD Model Dataset for Geometric Deep LearningPoster613 citations
165. Learning Pyramid-Context Encoder Network for High-Quality Image InpaintingPoster609 citations
166. Data Augmentation Using Learned Transformations for One-Shot Medical Image SegmentationOral608 citations
167. Grid R-CNNPoster607 citations
168. Task Agnostic Meta-Learning for Few-Shot LearningPoster603 citations
169. Salient Object Detection With Pyramid Attention and Salient EdgesPoster602 citations
170. DSFD: Dual Shot Face DetectorPoster600 citations
171. ESPNetv2: A Light-Weight, Power Efficient, and General Purpose Convolutional Neural NetworkPoster600 citations
172. Destruction and Construction Learning for Fine-Grained Image RecognitionPoster599 citations
173. Learning Correspondence From the Cycle-Consistency of TimeOral599 citations
174. See More, Know More: Unsupervised Video Object Segmentation With Co-Attention Siamese NetworksPoster598 citations
175. Cross-Modal Self-Attention Network for Referring Image SegmentationPoster597 citations
176. Graph-Based Global Reasoning NetworksPoster597 citations
177. Sim-To-Real via Sim-To-Sim: Data-Efficient Robotic Grasping via Randomized-To-Canonical Adaptation NetworksPoster596 citations
178. The Perfect Match: 3D Point Cloud Matching With Smoothed DensitiesPoster591 citations
179. Attention-Based Dropout Layer for Weakly Supervised Object LocalizationOral590 citations
180. Graph Convolutional Label Noise Cleaner: Train a Plug-And-Play Action Classifier for Anomaly DetectionPoster590 citations
181. Attentive Feedback Network for Boundary-Aware Salient Object DetectionPoster580 citations
182. Sea-Thru: A Method for Removing Water From Underwater ImagesPoster574 citations
183. Domain-Specific Batch Normalization for Unsupervised Domain AdaptationPoster571 citations
184. A Sufficient Condition for Convergences of Adam and RMSPropOral568 citations
185. Meta-SR: A Magnification-Arbitrary Network for Super-ResolutionPoster568 citations
186. Recurrent Back-Projection Network for Video Super-ResolutionPoster568 citations
187. 3D-SIS: 3D Semantic Instance Segmentation of RGB-D ScansOral566 citations
188. 3D Hand Shape and Pose Estimation From a Single RGB ImageOral565 citations
189. Probabilistic End-To-End Noise Correction for Learning With Noisy LabelsPoster564 citations
190. Self-Supervised Spatiotemporal Learning via Video Clip Order PredictionPoster563 citations
191. ESIR: End-To-End Scene Text Recognition via Iterative Image RectificationPoster561 citations
192. Shifting More Attention to Video Salient Object DetectionOral561 citations
193. FickleNet: Weakly and Semi-Supervised Semantic Image Segmentation Using Stochastic InferencePoster557 citations
194. Multi-Agent Tensor Fusion for Contextual Trajectory PredictionPoster554 citations
195. Unprocessing Images for Learned Raw DenoisingOral553 citations
196. TopNet: Structural Point Cloud DecoderPoster552 citations
197. Bi-Directional Cascade Network for Perceptual Edge DetectionPoster551 citations
198. UPSNet: A Unified Panoptic Segmentation NetworkOral548 citations
199. Progressive Feature Alignment for Unsupervised Domain AdaptationPoster544 citations
200. Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-Grained Image RecognitionPoster543 citations
201. Siamese Cascaded Region Proposal Networks for Real-Time Visual TrackingPoster537 citations
202. Classification-Reconstruction Learning for Open-Set RecognitionPoster531 citations
203. High-Level Semantic Feature Detection: A New Perspective for Pedestrian DetectionPoster530 citations
204. Global Second-Order Pooling Convolutional NetworksPoster529 citations
205. Improving Semantic Segmentation via Video Propagation and Label RelaxationOral529 citations
206. FEELVOS: Fast End-To-End Embedding Learning for Video Object SegmentationPoster528 citations
207. Learning Not to Learn: Training Deep Neural Networks With Biased DataPoster526 citations
208. Target-Aware Deep TrackingPoster523 citations
209. Learning to Reduce Dual-Level Discrepancy for Infrared-Visible Person Re-IdentificationPoster522 citations
210. Distilling Object Detectors With Fine-Grained Feature ImitationPoster521 citations
211. What Do Single-View 3D Reconstruction Networks Learn?Poster521 citations
212. Arbitrary Style Transfer With Style-Attentional NetworksPoster520 citations
213. IP102: A Large-Scale Benchmark Dataset for Insect Pest RecognitionOral519 citations
214. Modeling Point Clouds With Self-Attention and Gumbel Subset SamplingPoster519 citations
215. Semi-Supervised Transfer Learning for Image Rain RemovalPoster517 citations
216. DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing ImagesPoster516 citations
217. DeepView: View Synthesis With Learned Gradient DescentOral516 citations
218. Efficient Decision-Based Black-Box Adversarial Attacks on Face RecognitionPoster516 citations
219. End-To-End Interpretable Neural Motion PlannerOral514 citations
220. Deep Supervised Cross-Modal RetrievalPoster512 citations
221. CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-IdentificationOral511 citations
222. Peeking Into the Future: Predicting Future Person Activities and Locations in VideosPoster504 citations
223. Pyramidal Person Re-IDentification via Multi-Loss Dynamic TrainingPoster502 citations
224. Visual Tracking via Adaptive Spatially-Regularized Correlation FiltersOral498 citations
225. Quantization NetworksPoster492 citations
226. Hierarchical Cross-Modal Talking Face Generation With Dynamic Pixel-Wise LossPoster490 citations
227. Unsupervised Deep TrackingPoster487 citations
228. Unsupervised Person Re-Identification by Soft Multilabel LearningOral487 citations
229. Memory in Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity From Spatiotemporal DynamicsPoster483 citations
230. In Defense of Pre-Trained ImageNet Architectures for Real-Time Semantic Segmentation of Road-Driving ImagesPoster481 citations
231. Foreground-Aware Image InpaintingPoster480 citations
232. Object-Centric Auto-Encoders and Dummy Anomalies for Abnormal Event Detection in VideoPoster478 citations
233. Finding Task-Relevant Features for Few-Shot Learning by Category TraversalOral477 citations
234. Deep Plug-And-Play Super-Resolution for Arbitrary Blur KernelsPoster476 citations
235. Learning to Quantize Deep Networks by Optimizing Quantization Intervals With Task LossOral476 citations
236. Knowledge-Embedded Routing Network for Scene Graph GenerationPoster470 citations
237. Understanding the Limitations of CNN-Based Absolute Camera Pose RegressionPoster469 citations
238. Interaction-And-Aggregation Network for Person Re-IdentificationPoster466 citations
239. Task-Free Continual LearningPoster463 citations
240. C2AE: Class Conditioned Auto-Encoder for Open-Set RecognitionOral462 citations
241. Adaptive Pyramid Context Network for Semantic SegmentationPoster461 citations
242. RepMet: Representative-Based Metric Learning for Classification and Few-Shot Object DetectionPoster461 citations
243. Transferrable Prototypical Networks for Unsupervised Domain AdaptationOral461 citations
244. Events-To-Video: Bringing Modern Computer Vision to Event CamerasPoster460 citations
245. Perceive Where to Focus: Learning Visibility-Aware Part-Level Features for Partial Person Re-IdentificationPoster460 citations
246. DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene From Sparse LiDAR Data and Single Color ImagePoster459 citations
247. Variational Convolutional Neural Network PruningPoster455 citations
248. 3D Point Capsule NetworksPoster454 citations
249. Semi-Supervised Learning With Graph Learning-Convolutional NetworksPoster454 citations
250. Contrast Prior and Fluid Pyramid Integration for RGBD Salient Object DetectionPoster451 citations
251. Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial LearningPoster451 citations
252. DLOW: Domain Flow for Adaptation and GeneralizationOral450 citations
253. Dynamic Scene Deblurring With Parameter Selective Sharing and Nested Skip ConnectionsPoster443 citations
254. Animating Arbitrary Objects via Deep Motion TransferOral442 citations
255. Composing Text and Image for Image Retrieval - an Empirical OdysseyOral442 citations
256. Domain-Symmetric Networks for Adversarial Domain AdaptationPoster442 citations
257. Multi-Channel Attention Selection GAN With Cascaded Semantic Guidance for Cross-View Image TranslationOral441 citations
258. LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous DrivingPoster440 citations
259. Interpreting CNNs via Decision TreesPoster439 citations
260. Gaussian Temporal Awareness Networks for Action LocalizationOral438 citations
261. Spatial Fusion GAN for Image SynthesisPoster437 citations
262. Adapting Object Detectors via Selective Cross-Domain AlignmentPoster436 citations
263. Crowd Counting and Density Estimation by Trellis Encoder-Decoder NetworksPoster435 citations
264. TOUCHDOWN: Natural Language Navigation and Spatial Reasoning in Visual Street EnvironmentsPoster433 citations
265. SOSNet: Second Order Similarity Regularization for Local Descriptor LearningOral432 citations
266. 3D Hand Shape and Pose From Images in the WildOral431 citations
267. GS3D: An Efficient 3D Object Detection Framework for Autonomous DrivingPoster429 citations
268. Image Super-Resolution by Neural Texture TransferPoster428 citations
269. Multi-Adversarial Discriminative Deep Domain Generalization for Face Presentation Attack DetectionPoster428 citations
270. STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute EditingPoster427 citations
271. Capture, Learning, and Synthesis of 3D Speaking StylesPoster426 citations
272. Progressive Pose Attention Transfer for Person Image GenerationOral424 citations
273. AANet: Attribute Attention Network for Person Re-IdentificationsPoster420 citations
274. Leveraging the Invariant Side of Generative Zero-Shot LearningPoster418 citations
275. Depth-Attentional Features for Single-Image Rain RemovalPoster417 citations
276. Learning to Learn From Noisy Labeled DataPoster416 citations
277. Understanding the Disharmony Between Dropout and Batch Normalization by Variance ShiftPoster415 citations
278. GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face ReconstructionPoster414 citations
279. SelFlow: Self-Supervised Learning of Optical FlowOral410 citations
280. BAD SLAM: Bundle Adjusted Direct RGB-D SLAMOral409 citations
281. Monocular Total Capture: Posing Face, Body, and Hands in the WildOral405 citations
282. Learning Individual Styles of Conversational GesturePoster403 citations
283. "Double-DIP": Unsupervised Image Decomposition via Coupled Deep-Image-PriorsOral401 citations
284. Adaptive NMS: Refining Pedestrian Detection in a CrowdOral401 citations
285. Segmentation-Driven 6D Object Pose EstimationPoster401 citations
286. Rethinking Knowledge Graph Propagation for Zero-Shot LearningPoster399 citations
287. Feature Transfer Learning for Face Recognition With Under-Represented DataPoster396 citations
288. Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and DefensesOral392 citations
289. Pattern-Affinitive Propagation Across Depth, Surface Normal and Semantic SegmentationPoster392 citations
290. Strike (With) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar ObjectsPoster392 citations
291. Large-Scale Weakly-Supervised Pre-Training for Video Action RecognitionPoster391 citations
292. Robustness via Curvature Regularization, and Vice VersaPoster391 citations
293. Learning Active Contour Models for Medical Image SegmentationPoster389 citations
294. MAGSAC: Marginalizing Sample ConsensusPoster387 citations
295. Object-Driven Text-To-Image Synthesis via Adversarial TrainingPoster386 citations
296. Scene Graph Generation With External Knowledge and Image ReconstructionPoster386 citations
297. Separate to Adapt: Open Set Domain Adaptation via Progressive SeparationPoster386 citations
298. Exploring Object Relation in Mean Teacher for Cross-Domain DetectionPoster385 citations
299. MUREL: Multimodal Relational Reasoning for Visual Question AnsweringPoster385 citations
300. Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object DetectionPoster384 citations
301. FSA-Net: Learning Fine-Grained Structure Aggregation for Head Pose Estimation From a Single ImagePoster384 citations
302. Self-Supervised GANs via Auxiliary Rotation LossPoster384 citations
303. Dynamic Fusion With Intra- and Inter-Modality Attention Flow for Visual Question AnsweringOral383 citations
304. Learning to Remember: A Synaptic Plasticity Driven Framework for Continual LearningPoster383 citations
305. Pixel-Adaptive Convolutional Neural NetworksPoster383 citations
306. Transferable Interactiveness Knowledge for Human-Object Interaction DetectionPoster383 citations
307. Exploiting Edge Features for Graph Neural NetworksPoster381 citations
308. GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point CloudPoster381 citations
309. Generating 3D Adversarial Point CloudsPoster380 citations
310. Learning to Reconstruct People in Clothing From a Single RGB CameraPoster380 citations
311. Learning Regularity in Skeleton Trajectories for Anomaly Detection in VideosPoster379 citations
312. CrDoCo: Pixel-Level Domain Transfer With Cross-Domain ConsistencyPoster378 citations
313. Part-Regularized Near-Duplicate Vehicle Re-IdentificationPoster375 citations
314. COIN: A Large-Scale Dataset for Comprehensive Instructional Video AnalysisPoster374 citations
315. Uncertainty Guided Multi-Scale Residual Learning-Using a Cycle Spinning CNN for Single Image De-RainingPoster373 citations
316. MAN: Moment Alignment Network for Natural Language Moment Retrieval via Iterative Graph AdjustmentPoster372 citations
317. Knowledge Distillation via Instance Relationship GraphPoster371 citations
318. Self-Supervised Learning of 3D Human Pose Using Multi-View GeometryPoster371 citations
319. Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness Against Adversarial AttackPoster368 citations
320. Single Image Deraining: A Comprehensive Benchmark AnalysisPoster368 citations
321. ComDefend: An Efficient Image Compression Model to Defend Adversarial ExamplesPoster365 citations
322. Iterative Residual Refinement for Joint Optical Flow and Occlusion EstimationPoster365 citations
323. Pushing the Boundaries of View Extrapolation With Multiplane ImagesOral365 citations
324. Learning to Regress 3D Face Shape and Expression From an Image Without 3D SupervisionPoster363 citations
325. SIXray: A Large-Scale Security Inspection X-Ray Benchmark for Prohibited Item Discovery in Overlapping ImagesPoster359 citations
326. RAVEN: A Dataset for Relational and Analogical Visual REasoNingPoster357 citations
327. A-CNN: Annularly Convolutional Neural Networks on Point CloudsPoster356 citations
328. Deep Spectral Clustering Using Dual Autoencoder NetworkPoster356 citations
329. Fast Human Pose EstimationPoster356 citations
330. Temporal Cycle-Consistency LearningPoster356 citations
331. ADCrowdNet: An Attention-Injective Deformable Convolutional Network for Crowd UnderstandingPoster355 citations
332. Graph Convolutional TrackingOral354 citations
333. Learning to Transfer Examples for Partial Domain AdaptationPoster354 citations
334. Attention-Guided Unified Network for Panoptic SegmentationPoster353 citations
335. Densely Semantically Aligned Person Re-IdentificationPoster353 citations
336. Patch-Based Progressive 3D Point Set UpsamplingPoster353 citations
337. VERI-Wild: A Large Dataset and a New Method for Vehicle Re-Identification in the WildPoster352 citations
338. Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification From the Bottom UpPoster352 citations
339. Attentive Region Embedding Network for Zero-Shot LearningPoster351 citations
340. L3-Net: Towards Learning Based LiDAR Localization for Autonomous DrivingPoster351 citations
341. Adaptive Transfer Network for Cross-Domain Person Re-IdentificationPoster350 citations
342. Disentangling Adversarial Robustness and GeneralizationPoster350 citations
343. REPAIR: Removing Representation Bias by Dataset ResamplingPoster350 citations
344. NDDR-CNN: Layerwise Feature Fusing in Multi-Task CNNs by Neural Discriminative Dimensionality ReductionPoster347 citations
345. TraPHic: Trajectory Prediction in Dense and Heterogeneous Traffic Using Weighted InteractionsPoster347 citations
346. Deep Metric Learning to RankPoster343 citations
347. Attention-Guided Network for Ghost-Free High Dynamic Range ImagingPoster342 citations
348. Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question AnsweringPoster342 citations
349. ChamNet: Towards Efficient Network Design Through Platform-Aware Model AdaptationPoster341 citations
350. ROI-10D: Monocular Lifting of 2D Detection to 6D Pose and Metric ShapePoster338 citations
351. Rules of the Road: Predicting Driving Behavior With a Convolutional Model of Semantic InteractionsPoster338 citations
352. Deep Flow-Guided Video InpaintingPoster337 citations
353. Feature Distillation: DNN-Oriented JPEG Compression Against Adversarial ExamplesPoster337 citations
354. Fast Interactive Object Annotation With Curve-GCNPoster336 citations
355. MARS: Motion-Augmented RGB Stream for Action RecognitionPoster336 citations
356. H+O: Unified Egocentric Recognition of 3D Hand-Object Poses and InteractionsOral335 citations
357. Co-Occurrent Features in Semantic SegmentationPoster334 citations
358. Learning Actor Relation Graphs for Group Activity RecognitionPoster333 citations
359. Generating Classification Weights With GNN Denoising Autoencoders for Few-Shot LearningOral332 citations
360. Style Transfer by Relaxed Optimal Transport and Self-SimilarityPoster331 citations
361. Look More Than Once: An Accurate Detector for Text of Arbitrary ShapesPoster328 citations
362. Monocular 3D Object Detection Leveraging Accurate Proposals and Shape ReconstructionPoster328 citations
363. Polysemous Visual-Semantic Embedding for Cross-Modal RetrievalPoster328 citations
364. Collaborative Learning of Semi-Supervised Segmentation and Classification for Medical ImagesPoster327 citations
365. Learning Parallax Attention for Stereo Image Super-ResolutionPoster327 citations
366. Real-Time Self-Adaptive Deep StereoOral326 citations
367. Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering BandwidthOral325 citations
368. Ranked List Loss for Deep Metric LearningPoster325 citations
369. Dual Encoding for Zero-Example Video RetrievalPoster324 citations
370. Gait Recognition via Disentangled Representation LearningOral324 citations
371. Hierarchical Deep Stereo Matching on High-Resolution ImagesPoster324 citations
372. Re-Identification With Consistent Attentive Siamese NetworksPoster320 citations
373. Learning From Noisy Labels by Regularized Estimation of Annotator ConfusionPoster318 citations
374. Zoom to Learn, Learn to ZoomPoster318 citations
375. All About Structure: Adapting Structural Information Across Domains for Boosting Semantic SegmentationPoster317 citations
376. Associatively Segmenting Instances and Semantics in Point CloudsPoster316 citations
377. Learning a Deep ConvNet for Multi-Label Classification With Partial LabelsPoster316 citations
378. ContextDesc: Local Descriptor Augmentation With Cross-Modality ContextOral315 citations
379. Learning Semantic Segmentation From Synthetic Data: A Geometrically Guided Input-Output Adaptation ApproachPoster314 citations
380. Neural Illumination: Lighting Prediction for Indoor EnvironmentsOral313 citations
381. AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face RepresentationsOral312 citations
382. Bringing a Blurry Frame Alive at High Frame-Rate With an Event CameraOral312 citations
383. DeepCaps: Going Deeper With Capsule NetworksOral312 citations
384. Cross-Task Weakly Supervised Learning From Instructional VideosPoster311 citations
385. Towards Rich Feature Discovery With Class Activation Maps Augmentation for Person Re-IdentificationPoster311 citations
386. Dissecting Person Re-Identification From the Viewpoint of ViewpointPoster310 citations
387. Lending Orientation to Neural Networks for Cross-View Geo-LocalizationPoster309 citations
388. Visual Attention Consistency Under Image Transforms for Multi-Label Image ClassificationPoster307 citations
389. Deep Tree Learning for Zero-Shot Face Anti-SpoofingOral305 citations
390. Neighbourhood Watch: Referring Expression Comprehension via Language-Guided Graph Attention NetworksPoster305 citations
391. Spatio-Temporal Dynamics and Semantic Attribute Enriched Visual Encoding for Video CaptioningPoster304 citations
392. Image Deformation Meta-Networks for One-Shot LearningOral303 citations
393. Large-Scale Interactive Object Segmentation With Human AnnotatorsPoster303 citations
394. RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose EstimationPoster303 citations
395. Attention Based Glaucoma Detection: A Large-Scale Database and CNN ModelPoster302 citations
396. Face Anti-Spoofing: Model Matters, so Does DataPoster302 citations
397. Attentive Single-Tasking of Multiple TasksPoster301 citations
398. Generalizable Person Re-Identification by Domain-Invariant Mapping NetworkPoster301 citations
399. C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object DetectionOral299 citations
400. ODE-Inspired Network Design for Single Image Super-ResolutionPoster299 citations
401. Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature AggregationPoster297 citations
402. Exploiting Temporal Context for 3D Human Pose Estimation in the WildPoster297 citations
403. X2CT-GAN: Reconstructing CT From Biplanar X-Rays With Generative Adversarial NetworksPoster297 citations
404. Dual Residual Networks Leveraging the Potential of Paired Operations for Image RestorationPoster295 citations
405. Memory-Attended Recurrent Network for Video CaptioningPoster294 citations
406. Scan2CAD: Learning CAD Model Alignment in RGB-D ScansOral294 citations
407. Semantic Projection Network for Zero- and Few-Label Semantic SegmentationPoster294 citations
408. Hierarchical Discrete Distribution Decomposition for Match Density EstimationPoster293 citations
409. HoloPose: Holistic 3D Human Reconstruction In-The-WildOral292 citations
410. Multi-Scale Geometric Consistency Guided Multi-View StereoPoster292 citations
411. Unsupervised Image CaptioningPoster292 citations
412. Iterative Alignment Network for Continuous Sign Language RecognitionPoster291 citations
413. Knowledge Adaptation for Efficient Semantic SegmentationPoster291 citations
414. Learning Linear Transformations for Fast Image and Video Style TransferPoster291 citations
415. Multispectral and Hyperspectral Image Fusion by MS/HS Fusion NetPoster291 citations
416. SPM-Tracker: Series-Parallel Matching for Real-Time Visual Object TrackingPoster290 citations
417. A Mutual Learning Method for Salient Object Detection With Intertwined Multi-SupervisionPoster289 citations
418. Graphical Contrastive Losses for Scene Graph ParsingPoster289 citations
419. Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain MappingOral287 citations
420. Towards Scene Understanding: Unsupervised Monocular Depth Estimation With Semantic-Aware RepresentationOral287 citations
421. Timeception for Complex Action RecognitionOral286 citations
422. RVOS: End-To-End Recurrent Network for Video Object SegmentationPoster285 citations
423. ToothNet: Automatic Tooth Instance Segmentation and Identification From Cone Beam CT ImagesPoster284 citations
424. Box-Driven Class-Wise Region Masking and Filling Rate Guided Loss for Weakly Supervised Semantic SegmentationPoster283 citations
425. Deep Video InpaintingPoster283 citations
426. Generative Dual Adversarial Network for Generalized Zero-Shot LearningPoster283 citations
427. Few-Shot Learning via Saliency-Guided Hallucination of SamplesPoster280 citations
428. Revisiting Perspective Information for Efficient Crowd CountingPoster280 citations
429. StoryGAN: A Sequential Conditional GAN for Story VisualizationPoster280 citations
430. Learning Monocular Depth Estimation Infusing Traditional Stereo KnowledgePoster278 citations
431. Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-LearningOral278 citations
432. Learning Unsupervised Video Object Segmentation Through Visual AttentionPoster277 citations
433. Learning the Depths of Moving People by Watching Frozen PeopleOral276 citations
434. Pose2Seg: Detection Free Human Instance SegmentationPoster276 citations
435. Efficient Parameter-Free Clustering Using First Neighbor RelationsOral275 citations
436. PlaneRCNN: 3D Plane Detection and Reconstruction From a Single ImageOral275 citations
437. Completeness Modeling and Context Separation for Weakly Supervised Temporal Action LocalizationPoster273 citations
438. Explainable and Explicit Visual Reasoning Over Scene GraphsPoster272 citations
439. VRSTC: Occlusion-Free Video Person Re-IdentificationPoster271 citations
440. HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-Scale Point CloudsPoster270 citations
441. LO-Net: Deep Real-Time Lidar OdometryPoster268 citations
442. Patch-Based Discriminative Feature Learning for Unsupervised Person Re-IdentificationPoster268 citations
443. Pushing the Envelope for RGB-Based Dense 3D Hand Pose Estimation via Neural RenderingPoster268 citations
444. DuDoNet: Dual Domain Network for CT Metal Artifact ReductionPoster267 citations
445. Blind Image Deblurring With Local Maximum Gradient PriorPoster266 citations
446. Fast and Robust Multi-Person 3D Pose Estimation From Multiple ViewsPoster266 citations
447. PCAN: 3D Attention Map Learning Using Contextual Information for Point Cloud Based RetrievalPoster266 citations
448. AET vs. AED: Unsupervised Representation Learning by Auto-Encoding Transformations Rather Than DataOral265 citations
449. Deep Multimodal Clustering for Unsupervised Audiovisual LearningPoster265 citations
450. Interactive Image Segmentation via Backpropagating Refinement SchemePoster263 citations
451. Practical Full Resolution Learned Lossless Image CompressionOral263 citations
452. Generating Multiple Hypotheses for 3D Human Pose Estimation With Mixture Density NetworkPoster262 citations
453. JSIS3D: Joint Semantic-Instance Segmentation of 3D Point Clouds With Multi-Task Pointwise Networks and Multi-Value Conditional Random FieldsOral262 citations
454. Point in, Box Out: Beyond Counting Persons in CrowdsOral262 citations
455. Self-Supervised Representation Learning by Rotation Feature DecouplingPoster262 citations
456. Semantics Disentangling for Text-To-Image GenerationOral262 citations
457. Soft Labels for Ordinal RegressionPoster262 citations
458. 2.5D Visual SoundOral261 citations
459. Deep Exemplar-Based Video ColorizationPoster261 citations
460. Dense Classification and Implanting for Few-Shot LearningPoster260 citations
461. An Iterative and Cooperative Top-Down and Bottom-Up Inference Network for Salient Object DetectionPoster259 citations
462. Learning Shape-Aware Embedding for Scene Text DetectionPoster259 citations
463. Self-Supervised Spatio-Temporal Representation Learning for Videos by Predicting Motion and Appearance StatisticsPoster259 citations
464. AdaFrame: Adaptive Frame Selection for Fast Video RecognitionPoster258 citations
465. Precise Detection in Densely Packed ScenesPoster257 citations
466. Snapshot Distillation: Teacher-Student Optimization in One GenerationPoster255 citations
467. Centripetal SGD for Pruning Very Deep Convolutional Networks With Complicated StructurePoster254 citations
468. Image Generation From LayoutOral252 citations
469. Multi-Granularity Generator for Temporal Action ProposalPoster252 citations
470. Predicting Future Frames Using Retrospective Cycle GANPoster252 citations
471. Residual Networks for Light Field Image Super-ResolutionOral252 citations
472. Fully Quantized Network for Object DetectionPoster251 citations
473. AE2-Nets: Autoencoder in Autoencoder NetworksOral249 citations
474. SparseFool: A Few Pixels Make a Big DifferencePoster249 citations
475. Unsupervised 3D Pose Estimation With Geometric Self-SupervisionPoster249 citations
476. DrivingStereo: A Large-Scale Dataset for Stereo Matching in Autonomous Driving ScenariosPoster248 citations
477. Seamless Scene SegmentationPoster247 citations
478. MFAS: Multimodal Fusion Architecture SearchPoster246 citations
479. Supervised Fitting of Geometric Primitives to 3D Point CloudsOral246 citations
480. Towards Universal Object Detection by Domain AttentionPoster246 citations
481. Grounded Video DescriptionOral243 citations
482. RL-GAN-Net: A Reinforcement Learning Agent Controlled GAN Network for Real-Time Point Cloud Shape CompletionPoster243 citations
483. A Poisson-Gaussian Denoising Dataset With Real Fluorescence Microscopy ImagesPoster242 citations
484. Event-Based High Dynamic Range Image and Very High Frame Rate Video Generation Using Conditional Generative Adversarial NetworksPoster241 citations
485. Linkage Based Face Clustering via Graph Convolution NetworkPoster241 citations
486. Overcoming Limitations of Mixture Density Networks: A Sampling and Fitting Framework for Multimodal Future PredictionPoster241 citations
487. Recurrent Neural Network for (Un-)Supervised Learning of Monocular Video Visual Odometry and DepthPoster241 citations
488. Learning Context Graph for Person SearchOral240 citations
489. Feature Space Perturbations Yield More Transferable Adversarial ExamplesPoster239 citations
490. Deep Geometric Prior for Surface ReconstructionPoster238 citations
491. Max-Sliced Wasserstein Distance and Its Use for GANsOral238 citations
492. Scene Memory Transformer for Embodied Agents in Long-Horizon TasksPoster238 citations
493. Weakly Supervised Video Moment Retrieval From Text QueriesPoster238 citations
494. Improved Road Connectivity by Joint Learning of Orientation and SegmentationPoster237 citations
495. A Generative Appearance Model for End-To-End Video Object SegmentationOral236 citations
496. ContactDB: Analyzing and Predicting Grasp Contact via Thermal ImagingOral236 citations
497. Learning Spatio-Temporal Representation With Local and Global DiffusionPoster236 citations
498. Neural Rerendering in the WildOral234 citations
499. Striking the Right Balance With UncertaintyOral234 citations
500. Hardness-Aware Deep Metric LearningOral233 citations
501. Density Map Regression Guided Detection Network for RGB-D Crowd Counting and LocalizationPoster231 citations
502. HorizonNet: Learning Room Layout With 1D Representation and Pano Stretch Data AugmentationPoster231 citations
503. Point Cloud Oversegmentation With Graph-Structured Deep Metric LearningPoster231 citations
504. Show, Control and Tell: A Framework for Generating Controllable and Grounded CaptionsPoster231 citations
505. Dense Intrinsic Appearance Flow for Human Pose TransferPoster230 citations
506. Geometry-Aware Symmetric Domain Adaptation for Monocular Depth EstimationPoster229 citations
507. Graphonomy: Universal Human Parsing via Graph Transfer LearningPoster228 citations
508. Learning to SamplePoster228 citations
509. Multi-Source Weak Supervision for Saliency DetectionPoster227 citations
510. Audio Visual Scene-Aware DialogPoster226 citations
511. Label Efficient Semi-Supervised Learning via Graph FilteringPoster226 citations
512. ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous DrivingPoster224 citations
513. Doodle to Search: Practical Zero-Shot Sketch-Based Image RetrievalOral224 citations
514. Object-Aware Aggregation With Bidirectional Temporal Graph for Video CaptioningPoster224 citations
515. Arbitrary Shape Scene Text Detection With Adaptive Text Region RepresentationOral222 citations
516. Speech2Face: Learning the Face Behind a VoicePoster222 citations
517. Barrage of Random Transforms for Adversarially Robust DefenseOral221 citations
518. CollaGAN: Collaborative GAN for Missing Image Data ImputationOral221 citations
519. SiCloPe: Silhouette-Based Clothed PeopleOral221 citations
520. Unified Visual-Semantic Embeddings: Bridging Vision and Language With Structured Meaning RepresentationsOral221 citations
521. Amodal Instance Segmentation With KINS DatasetPoster220 citations
522. Hyperspectral Image Reconstruction Using a Deep Spatial-Spectral PriorPoster218 citations
523. PoseFix: Model-Agnostic General Human Pose Refinement NetworkPoster218 citations
524. ClusterNet: Deep Hierarchical Cluster Network With Rigorously Rotation-Invariant Representation for Point Cloud AnalysisPoster217 citations
525. Recurrent Attentive Zooming for Joint Crowd Counting and Precise LocalizationPoster216 citations
526. A Dataset and Benchmark for Large-Scale Multi-Modal Face Anti-SpoofingPoster215 citations
527. A Theory of Fermat Paths for Non-Line-Of-Sight Shape ReconstructionOral215 citations
528. AdaptiveFace: Adaptive Margin and Sampling for Face RecognitionPoster215 citations
529. Attention-Aware Multi-Stroke Style TransferPoster215 citations
530. Effective Aesthetics Prediction With Multi-Level Spatially Pooled FeaturesPoster215 citations
531. Language-Driven Temporal Activity Localization: A Semantic Matching Reinforcement Learning ModelOral215 citations
532. Semantic Correlation Promoted Shape-Variant Context for SegmentationOral215 citations
533. A Relation-Augmented Fully Convolutional Network for Semantic Segmentation in Aerial ScenesPoster214 citations
534. FastDraw: Addressing the Long Tail of Lane Detection by Adapting a Sequential Prediction NetworkPoster212 citations
535. Improving Referring Expression Grounding With Cross-Modal Attention-Guided ErasingPoster212 citations
536. Improving the Performance of Unimodal Dynamic Hand-Gesture Recognition With Multimodal TrainingPoster212 citations
537. Inverse Cooking: Recipe Generation From Food ImagesPoster210 citations
538. Leveraging Shape Completion for 3D Siamese TrackingPoster210 citations
539. Partial Order Pruning: For Best Speed/Accuracy Trade-Off in Neural Architecture SearchPoster210 citations
540. Representation Flow for Action RecognitionPoster209 citations
541. Collaborative Global-Local Networks for Memory-Efficient Segmentation of Ultra-High Resolution ImagesOral208 citations
542. LSTA: Long Short-Term Attention for Egocentric Action RecognitionPoster208 citations
543. Cycle-Consistency for Robust Visual Question AnsweringOral207 citations
544. Unsupervised Domain Adaptation Using Feature-Whitening and Consensus LossPoster207 citations
545. Single Image Reflection Removal Exploiting Misaligned Training Data and Network EnhancementsPoster206 citations
546. A Neural Temporal Model for Human Motion PredictionPoster205 citations
547. The Regretful Agent: Heuristic-Aided Navigation Through Progress EstimationOral205 citations
548. Automatic Adaptation of Object Detectors to New Domains Using Self-TrainingPoster204 citations
549. Devil Is in the Edges: Learning Semantic Boundaries From Noisy AnnotationsOral204 citations
550. Towards High-Fidelity Nonlinear 3D Face Morphable ModelPoster204 citations
551. D3TW: Discriminative Differentiable Dynamic Time Warping for Weakly Supervised Action Alignment and SegmentationPoster201 citations
552. Modeling Local Geometric Structure of 3D Point Clouds Using Geo-CNNPoster201 citations
553. What and How Well You Performed? A Multitask Learning Approach to Action Quality AssessmentOral201 citations
554. APDrawingGAN: Generating Artistic Portrait Drawings From Face Photos With Hierarchical GANsOral200 citations
555. Camera Lens Super-ResolutionPoster200 citations
556. Engaging Image Captioning via PersonalityPoster200 citations
557. STEP: Spatio-Temporal Progressive Learning for Video Action DetectionOral200 citations
558. A Variational Pan-Sharpening With Local Gradient ConstraintsPoster199 citations
559. An End-To-End Network for Panoptic SegmentationPoster199 citations
560. Attentive Relational Networks for Mapping Images to Scene GraphsPoster199 citations
561. Self-Supervised Convolutional Subspace Clustering NetworkPoster199 citations
562. Spherical Fractal Convolutional Neural Networks for Point Cloud RecognitionPoster197 citations
563. Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary CellsPoster196 citations
564. Deep Fitting Degree Scoring Network for Monocular 3D Object DetectionPoster195 citations
565. Fast and Flexible Indoor Scene Synthesis via Deep Convolutional Generative ModelsPoster195 citations
566. Scalable Convolutional Neural Network for Image Compressed SensingPoster195 citations
567. Tactical Rewind: Self-Correction via Backtracking in Vision-And-Language NavigationOral194 citations
568. UnOS: Unified Unsupervised Optical-Flow and Stereo-Depth Estimation by Watching VideosPoster194 citations
569. Embodied Question Answering in Photorealistic Environments With Point Cloud PerceptionOral193 citations
570. Low-Rank Tensor Completion With a New Tensor Nuclear Norm Induced by Invertible Linear TransformsPoster193 citations
571. Out-Of-Distribution Detection for Generalized Zero-Shot Action RecognitionPoster193 citations
572. Selective Sensor Fusion for Neural Visual-Inertial OdometryPoster192 citations
573. Structured Binary Neural Networks for Accurate Image Classification and Semantic SegmentationPoster192 citations
574. Good News, Everyone! Context Driven Entity-Aware Captioning for News ImagesPoster191 citations
575. Learning to Detect Human-Object Interactions With KnowledgePoster191 citations
576. Multi-Person Pose Estimation With Enhanced Channel-Wise and Spatial InformationPoster189 citations
577. Non-Local Meets Global: An Integrated Paradigm for Hyperspectral DenoisingOral189 citations
578. Variational Autoencoders Pursue PCA Directions (by Accident)Poster189 citations
579. Few-Shot Learning With Localization in Realistic SettingsOral188 citations
580. ScratchDet: Training Single-Shot Object Detectors From ScratchOral188 citations
581. Side Window FilteringOral188 citations
582. Unsupervised Domain-Specific Deblurring via Disentangled RepresentationsPoster188 citations
583. EV-Gait: Event-Based Robust Gait Recognition Using Dynamic Vision SensorsPoster186 citations
584. Interpretable and Fine-Grained Visual Explanations for Convolutional Neural NetworksPoster186 citations
585. Meta-Learning Convolutional Neural Architectures for Multi-Target Concrete Defect Classification With the COncrete DEfect BRidge IMage DatasetPoster186 citations
586. Streamlined Dense Video CaptioningOral186 citations
587. DistillHash: Unsupervised Deep Hashing by Distilling Data PairsPoster185 citations
588. Attribute-Driven Feature Disentangling and Temporal Aggregation for Video Person Re-IdentificationPoster184 citations
589. Regularizing Activation Distribution for Training Binarized Deep NetworksPoster184 citations
590. Distraction-Aware Shadow DetectionPoster183 citations
591. Few-Shot Adaptive Faster R-CNNPoster183 citations
592. Iterative Normalization: Beyond Standardization Towards Efficient WhiteningPoster183 citations
593. FOCNet: A Fractional Optimal Control Network for Image DenoisingPoster182 citations
594. Gradient Matching Generative Networks for Zero-Shot LearningOral182 citations
595. Octree Guided CNN With Spherical Kernels for 3D Point CloudsPoster182 citations
596. Self-Calibrating Deep Photometric Stereo NetworksOral182 citations
597. Image-To-Image Translation via Group-Wise Deep Whitening-And-Coloring TransformationOral181 citations
598. Recurrent Neural Networks With Intra-Frame Iterations for Video DeblurringPoster181 citations
599. Rethinking the Evaluation of Video SummariesPoster181 citations
600. Accel: A Corrective Fusion Network for Efficient Semantic Segmentation on VideoOral180 citations
601. Unsupervised Part-Based Disentangling of Object Shape and AppearanceOral180 citations
602. A Late Fusion CNN for Digital MattingPoster179 citations
603. Customizable Architecture Search for Semantic SegmentationPoster179 citations
604. Discovering Fair Representations in the Data DomainPoster179 citations
605. DuLa-Net: A Dual-Projection Network for Estimating Room Layouts From a Single RGB PanoramaPoster179 citations
606. FML: Face Model Learning From VideosOral179 citations
607. In the Wild Human Pose Estimation Using Explicit 2D Features and Intermediate 3D RepresentationsOral178 citations
608. SCOPS: Self-Supervised Co-Part SegmentationPoster178 citations
609. A Neural Network Based on SPD Manifold Learning for Skeleton-Based Hand Gesture RecognitionPoster177 citations
610. Exploiting Kernel Sparsity and Entropy for Interpretable CNN CompressionPoster177 citations
611. FineGAN: Unsupervised Hierarchical Disentanglement for Fine-Grained Object Generation and DiscoveryOral177 citations
612. Deep Defocus Map Estimation Using Domain AdaptationPoster175 citations
613. Photo Wake-Up: 3D Character Animation From a Single PhotoPoster175 citations
614. A Bayesian Perspective on the Deep Image PriorPoster174 citations
615. Adversarial Attacks Beyond the Image SpaceOral174 citations
616. InverseRenderNet: Learning Single Image Inverse RenderingPoster174 citations
617. PEPSI : Fast Image Inpainting With Parallel Decoding NetworkPoster174 citations
618. Query-Guided End-To-End Person SearchPoster174 citations
619. Unsupervised Learning of Dense Shape CorrespondenceOral174 citations
620. CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View DepthPoster173 citations
621. Detailed Human Shape Estimation From a Single Image by Hierarchical Mesh DeformationOral173 citations
622. Light Field Messaging With Deep Photographic SteganographyPoster173 citations
623. Monocular Depth Estimation Using Relative Depth MapsPoster173 citations
624. Neural Task Graphs: Generalizing to Unseen Tasks From a Single Video DemonstrationOral173 citations
625. Representation Similarity Analysis for Efficient Task Taxonomy & Transfer LearningPoster173 citations
626. Semantically Tied Paired Cycle Consistency for Zero-Shot Sketch-Based Image RetrievalPoster173 citations
627. Towards Accurate One-Stage Object Detection With AP-LossPoster173 citations
628. Binary Ensemble Neural Network: More Bits per Network or More Networks per Bit?Poster172 citations
629. Fast, Diverse and Accurate Image Captioning Guided by Part-Of-SpeechOral172 citations
630. Refine and Distill: Exploiting Cycle-Inconsistency and Knowledge Distillation for Unsupervised Monocular Depth EstimationPoster172 citations
631. Video Summarization by Learning From Unpaired DataPoster172 citations
632. Local Relationship Learning With Person-Specific Shape Regularization for Facial Action Unit DetectionPoster171 citations
633. Neural RGB(r)D Sensing: Depth and Uncertainty From a Video CameraOral170 citations
634. Fast Spatio-Temporal Residual Network for Video Super-ResolutionPoster169 citations
635. GCAN: Graph Convolutional Adversarial Network for Unsupervised Domain AdaptationPoster169 citations
636. Learning Cross-Modal Embeddings With Adversarial Networks for Cooking Recipes and Food ImagesPoster169 citations
637. Learning to Generate Synthetic Data via CompositingPoster169 citations
638. Unsupervised Moving Object Detection via Contextual Information SeparationPoster169 citations
639. DMC-Net: Generating Discriminative Motion Cues for Fast Compressed Video Action RecognitionPoster168 citations
640. Stochastic Class-Based Hard Example Mining for Deep Metric LearningPoster168 citations
641. DeepLight: Learning Illumination for Unconstrained Mobile Mixed RealityPoster167 citations
642. Fast Spatially-Varying Indoor Lighting EstimationOral167 citations
643. Progressive Teacher-Student Learning for Early Action PredictionPoster166 citations
644. Adaptive Weighting Multi-Field-Of-View CNN for Semantic Segmentation in PathologyPoster165 citations
645. Wide-Area Crowd Counting via Ground-Plane Density Maps and Multi-View Fusion CNNsPoster165 citations
646. Large-Scale Few-Shot Learning: Knowledge Transfer With Class HierarchyPoster164 citations
647. Mask-Guided Portrait Editing With Conditional GANsPoster164 citations
648. Natural and Realistic Single Image Super-Resolution With Explicit Natural Manifold DiscriminationPoster164 citations
649. SFNet: Learning Object-Aware Semantic CorrespondenceOral164 citations
650. Single Image Depth Estimation Trained via Depth From Defocus CuesPoster164 citations
651. Focus Is All You Need: Loss Functions for Event-Based VisionPoster163 citations
652. Robust Facial Landmark Detection via Occlusion-Adaptive Deep NetworksPoster163 citations
653. Sequence-To-Sequence Domain Adaptation Network for Robust Text Image RecognitionPoster163 citations
654. d-SNE: Domain Adaptation Using Stochastic Neighborhood EmbeddingOral163 citations
655. Divide and Conquer the Embedding Space for Metric LearningPoster162 citations
656. FilterReg: Robust and Efficient Probabilistic Point-Set Registration Using Gaussian Filter and Twist ParameterizationOral162 citations
657. Leveraging Heterogeneous Auxiliary Tasks to Assist Crowd CountingPoster162 citations
658. Learning to Cluster Faces on an Affinity GraphOral161 citations
659. When Color Constancy Goes Wrong: Correcting Improperly White-Balanced ImagesPoster161 citations
660. Learning Metrics From Teachers: Compact Networks for Image EmbeddingPoster160 citations
661. Learning-Based Sampling for Natural Image MattingPoster160 citations
662. Robust Histopathology Image Analysis: To Label or to Synthesize?Oral160 citations
663. Dense Depth Posterior (DDP) From Single Image and Sparse RangePoster159 citations
664. Less Is More: Learning Highlight Detection From Video DurationPoster159 citations
665. Look Back and Predict Forward in Image CaptioningPoster159 citations
666. R2GAN: Cross-Modal Recipe Retrieval With Generative Adversarial NetworkPoster159 citations
667. Social-IQ: A Question Answering Benchmark for Artificial Social IntelligenceOral159 citations
668. Coloring With Limited Data: Few-Shot Colorization via Memory Augmented NetworksPoster158 citations
669. Learning Attraction Field Representation for Robust Line Segment DetectionPoster158 citations
670. Deep Rigid Instance Scene FlowPoster157 citations
671. Detect-To-Retrieve: Efficient Regional Aggregation for Image SearchPoster157 citations
672. Parsing R-CNN for Instance-Level Human AnalysisPoster157 citations
673. Towards Natural and Accurate Future Motion Prediction of Humans and AnimalsPoster157 citations
674. Curls & Whey: Boosting Black-Box Adversarial AttacksOral156 citations
675. Convolutional Relational Machine for Group Activity RecognitionPoster155 citations
676. LaSO: Label-Set Operations Networks for Multi-Label Few-Shot LearningOral154 citations
677. RENAS: Reinforced Evolutionary Neural Architecture SearchPoster154 citations
678. Revealing Scenes by Inverting Structure From Motion ReconstructionsOral154 citations
679. Efficient Online Multi-Person 2D Pose Tracking With Recurrent Spatio-Temporal Affinity FieldsOral153 citations
680. Inverse Path Tracing for Joint Material and Lighting EstimationOral153 citations
681. Triangulation Learning Network: From Monocular to Stereo 3D Object DetectionPoster153 citations
682. 3DN: 3D Deformation NetworkPoster152 citations
683. Kernel Transformer Networks for Compact Spherical ConvolutionPoster152 citations
684. RegularFace: Deep Face Recognition via Exclusive RegularizationPoster152 citations
685. Spatial-Aware Graph Relation Network for Large-Scale Object DetectionPoster151 citations
686. Unequal-Training for Deep Face Recognition With Long-Tailed Noisy DataPoster151 citations
687. Attribute-Aware Face Aging With Wavelet-Based Generative Adversarial NetworksPoster150 citations
688. Connecting Touch and Vision via Cross-Modal PredictionPoster150 citations
689. NM-Net: Mining Reliable Neighbors for Robust Feature CorrespondencesOral150 citations
690. Networks for Joint Affine and Non-Parametric Image RegistrationPoster150 citations
691. Sliced Wasserstein Generative ModelsPoster150 citations
692. A Compact Embedding for Facial Expression SimilarityPoster148 citations
693. Reducing Uncertainty in Undersampled MRI Reconstruction With Active AcquisitionPoster147 citations
694. TAFE-Net: Task-Aware Feature Embeddings for Low Shot LearningPoster147 citations
695. Object Counting and Instance Segmentation With Image-Level SupervisionPoster146 citations
696. Single Image Reflection Removal Beyond LinearityPoster146 citations
697. Acoustic Non-Line-Of-Sight ImagingOral145 citations
698. DARNet: Deep Active Ray Network for Building SegmentationPoster145 citations
699. Efficient Neural Network CompressionPoster145 citations
700. CLEVR-Ref+: Diagnosing Visual Reasoning With Referring ExpressionsPoster144 citations
701. HetConv: Heterogeneous Kernel-Based Convolutions for Deep CNNsPoster144 citations
702. Learning Channel-Wise Interactions for Binary Convolutional Neural NetworksPoster144 citations
703. MVF-Net: Multi-View 3D Face Morphable Model RegressionPoster144 citations
704. Recursive Visual Attention in Visual DialogOral144 citations
705. Structural Relational Reasoning of Point CloudsPoster144 citations
706. UniformFace: Learning Deep Equidistributed Representation for Face RecognitionPoster144 citations
707. Vision-Based Navigation With Language-Based Assistance via Imitation Learning With Indirect InterventionPoster144 citations
708. 3D Local Features for Direct Pairwise RegistrationPoster143 citations
709. Reasoning Visual Dialogs With Structural and Partial ObservationsOral143 citations
710. TraVeLGAN: Image-To-Image Translation by Transformation Vector LearningPoster143 citations
711. Cyclic Guidance for Weakly Supervised Joint Detection and SegmentationPoster142 citations
712. Deep Sky Modeling for Single Image Outdoor Lighting EstimationOral142 citations
713. Aggregation Cross-Entropy for Sequence RecognitionOral141 citations
714. Detection Based Defense Against Adversarial Examples From the Steganalysis Point of ViewPoster141 citations
715. Iterative Reorganization With Weak Spatial Constraints: Solving Arbitrary Jigsaw Puzzles for Unsupervised Representation LearningPoster141 citations
716. TextureNet: Consistent Local Parametrizations for Learning From High-Resolution Signals on MeshesOral141 citations
717. Unsupervised Person Image Generation With Semantic Parsing TransformationOral141 citations
718. BridgeNet: A Continuity-Aware Probabilistic Network for Age EstimationPoster140 citations
719. Deep Transfer Learning for Multiple Class Novelty DetectionPoster140 citations
720. Disentangling Latent Hands for Image Synthesis and Pose EstimationPoster140 citations
721. PointFlowNet: Learning Representations for Rigid Motion Estimation From Point CloudsPoster140 citations
722. Rob-GAN: Generator, Discriminator, and Adversarial AttackerPoster140 citations
723. Wide-Context Semantic Image ExtrapolationPoster140 citations
724. Unsupervised Learning of Action Classes With Continuous Temporal EmbeddingPoster139 citations
725. Weakly-Supervised Discovery of Geometry-Aware Representation for 3D Human Pose EstimationOral139 citations
726. Adaptive Confidence Smoothing for Generalized Zero-Shot LearningPoster138 citations
727. Context-Aware Visual Compatibility PredictionPoster138 citations
728. MSCap: Multi-Style Image Captioning With Unpaired Stylized TextPoster138 citations
729. Time-Conditioned Action Anticipation in One ShotPoster138 citations
730. Multi-Level Context Ultra-Aggregation for Stereo MatchingPoster137 citations
731. Shape2Motion: Joint Analysis of Motion Parts and Attributes From 3D ShapesOral137 citations
732. The Pros and Cons: Rank-Aware Temporal Attention for Skill Determination in Long VideosPoster137 citations
733. CapSal: Leveraging Captioning to Boost Semantics for Salient Object DetectionPoster136 citations
734. Disentangled Representation Learning for 3D Face ShapePoster136 citations
735. Coordinate-Based Texture Inpainting for Pose-Guided Human Image GenerationPoster135 citations
736. Frame-Consistent Recurrent Video Deraining With Dual-Level FlowPoster135 citations
737. TransGaGa: Geometry-Aware Unsupervised Image-To-Image TranslationPoster135 citations
738. Efficient Featurized Image Pyramid Network for Single Shot DetectorPoster134 citations
739. Compressing Convolutional Neural Networks via Factorized Convolutional FiltersPoster133 citations
740. Cross-Modal Relationship Inference for Grounding Referring ExpressionsPoster133 citations
741. Deep Incremental Hashing Network for Efficient Image RetrievalPoster133 citations
742. Deep Metric Learning Beyond Binary SupervisionOral133 citations
743. Fully Automatic Video Colorization With Self-Regularization and DiversityPoster133 citations
744. Locating Objects Without Bounding BoxesOral133 citations
745. EventNet: Asynchronous Recursive Event ProcessingPoster132 citations
746. Factor Graph AttentionPoster132 citations
747. VizWiz-Priv: A Dataset for Recognizing the Presence and Purpose of Private Visual Information in Images Taken by Blind PeoplePoster132 citations
748. Collaborative Spatiotemporal Feature Learning for Video Action RecognitionPoster131 citations
749. Grounding Human-To-Vehicle Advice for Self-Driving VehiclesPoster131 citations
750. Distant Supervised Centroid Shift: A Simple and Efficient Approach to Visual Domain AdaptationPoster130 citations
751. MeshAdv: Adversarial Meshes for Visual RecognitionOral130 citations
752. Multi-Target Embodied Question AnsweringPoster130 citations
753. SpherePHD: Applying CNNs on a Spherical PolyHeDron Representation of 360deg ImagesPoster130 citations
754. Towards Instance-Level Image-To-Image TranslationPoster130 citations
755. Attending to Discriminative Certainty for Domain AdaptationPoster129 citations
756. Residual Regression With Semantic Prior for Crowd CountingPoster129 citations
757. Self-Supervised Representation Learning From Videos for Facial Action Unit DetectionOral129 citations
758. Textured Neural AvatarsOral129 citations
759. Unsupervised Face Normalization With Extreme Pose and Expression in the WildPoster129 citations
760. Distilled Person Re-Identification: Towards a More Scalable SystemPoster128 citations
761. RF-Net: An End-To-End Image Matching Network Based on Receptive FieldPoster128 citations
762. Video Generation From Single Semantic Label MapPoster128 citations
763. Self-Supervised 3D Hand Pose Estimation Through Training by FittingOral127 citations
764. Single-Image Piece-Wise Planar 3D Reconstruction via Associative EmbeddingPoster127 citations
765. Video Relationship Reasoning Using Gated Spatio-Temporal Energy GraphPoster127 citations
766. Balanced Self-Paced Learning for Generative Adversarial Clustering NetworkOral126 citations
767. Blind Geometric Distortion Correction on Images Through Deep LearningPoster126 citations
768. Describing Like Humans: On Diversity in Image CaptioningPoster126 citations
769. Detecting Overfitting of Deep Generative Networks via Latent RecoveryPoster126 citations
770. Diverse Generation for Multi-Agent Sports GamesOral126 citations
771. Mixed Effects Neural Networks (MeNets) With Applications to Gaze EstimationPoster126 citations
772. BeautyGlow: On-Demand Makeup Transfer Framework With Reversible Generative NetworkPoster125 citations
773. Putting Humans in a Scene: Learning Affordance in 3D Indoor EnvironmentsPoster125 citations
774. SimulCap : Single-View Human Performance Capture With Cloth SimulationPoster125 citations
775. Generalized Zero-Shot Recognition Based on Visually Semantic EmbeddingPoster124 citations
776. Large Scale High-Resolution Land Cover Mapping With Multi-Resolution DataPoster124 citations
777. Large-Scale Distributed Second-Order Optimization Using Kronecker-Factored Approximate Curvature for Deep Convolutional Neural NetworksPoster124 citations
778. Scan2Mesh: From Unstructured Range Scans to 3D MeshesPoster124 citations
779. Speed Invariant Time Surface for Learning to Detect Corner Points With Event-Based CamerasPoster124 citations
780. Towards Real Scene Super-Resolution With Raw ImagesPoster124 citations
781. Beyond Tracking: Selecting Memory and Refining Poses for Deep Visual OdometryOral123 citations
782. Spatiotemporal CNN for Video Object SegmentationPoster122 citations
783. Structured Pruning of Neural Networks With Budget-Aware RegularizationPoster122 citations
784. Adversarial Defense by Stratified Convolutional Sparse CodingPoster121 citations
785. Mitigating Information Leakage in Image Representations: A Maximum Entropy ApproachOral121 citations
786. PartNet: A Recursive Part Decomposition Network for Fine-Grained and Hierarchical Shape SegmentationPoster121 citations
787. A Structured Model for Action DetectionPoster120 citations
788. Blending-Target Domain Adaptation by Adversarial Meta-Adaptation NetworksOral120 citations
789. Improving Few-Shot User-Specific Gaze Adaptation via Gaze Redirection SynthesisPoster120 citations
790. MetaCleaner: Learning to Hallucinate Clean Representations for Noisy-Labeled Visual RecognitionPoster120 citations
791. Art2Real: Unfolding the Reality of Artworks via Semantically-Aware Image-To-Image TranslationPoster119 citations
792. DAVANet: Stereo Deblurring With View AggregationOral119 citations
793. Decorrelated Adversarial Learning for Age-Invariant Face RecognitionPoster119 citations
794. Depth Coefficients for Depth CompletionPoster119 citations
795. LP-3DCNN: Unveiling Local Phase in 3D Convolutional Neural NetworksPoster119 citations
796. Leveraging Crowdsourced GPS Data for Road Extraction From Aerial ImageryPoster119 citations
797. StereoDRNet: Dilated Residual StereoNetPoster119 citations
798. All You Need Is a Few Shifts: Designing Efficient Convolutional Neural Networks for Image ClassificationPoster118 citations
799. Dance With Flow: Two-In-One Stream Action DetectionPoster118 citations
800. Discovering Visual Patterns in Art Collections With Spatially-Consistent Feature LearningPoster118 citations
801. Efficient Video Classification Using Fewer FramesOral118 citations
802. Generalising Fine-Grained Sketch-Based Image RetrievalPoster118 citations
803. Generalizing Eye Tracking With Bayesian Adversarial LearningPoster118 citations
804. Re-Ranking via Metric Fusion for Object Retrieval and Person Re-IdentificationPoster118 citations
805. Robustness of 3D Deep Learning in an Adversarial SettingPoster118 citations
806. Reasoning-RCNN: Unifying Adaptive Global Reasoning Into Large-Scale Object DetectionOral117 citations
807. 3D Guided Fine-Grained Face ManipulationPoster116 citations
808. Information Maximizing Visual Question GenerationPoster116 citations
809. Towards Social Artificial Intelligence: Nonverbal Social Signal Prediction in a Triadic InteractionOral116 citations
810. Adversarial Inference for Multi-Sentence Video DescriptionOral115 citations
811. Deep Single Image Camera Calibration With Radial DistortionPoster115 citations
812. Explicit Bias Discovery in Visual Question Answering ModelsPoster115 citations
813. Exploring Context and Visual Pattern of Relationship for Scene Graph GenerationPoster115 citations
814. SDRSAC: Semidefinite-Based Randomized Approach for Robust Point Cloud Registration Without CorrespondencesOral114 citations
815. You Look Twice: GaterNet for Dynamic Filter Selection in CNNsPoster114 citations
816. Beyond Volumetric Albedo -- A Surface Optimization Framework for Non-Line-Of-Sight ImagingPoster113 citations
817. Bilateral Cyclic Constraint and Adaptive Regularization for Unsupervised Monocular Depth PredictionPoster113 citations
818. Facial Emotion Distribution Learning by Exploiting Low-Rank Label Correlations LocallyPoster113 citations
819. Geometry-Aware Distillation for Indoor Semantic SegmentationPoster113 citations
820. Metric Learning for Image RegistrationPoster113 citations
821. SAIL-VOS: Semantic Amodal Instance Level Video Object Segmentation - A Synthetic Dataset and BaselinesPoster113 citations
822. Attention-Based Adaptive Selection of Operations for Image Restoration in the Presence of Unknown Combined DistortionsPoster112 citations
823. C3AE: Exploring the Limits of Compact Model for Age EstimationPoster112 citations
824. Dense Relational Captioning: Triple-Stream Networks for Relationship-Based CaptioningPoster112 citations
825. Dissimilarity Coefficient Based Weakly Supervised Object DetectionPoster112 citations
826. PA3D: Pose-Action 3D Machine for Video RecognitionPoster112 citations
827. TACNet: Transition-Aware Context Network for Spatio-Temporal Action DetectionPoster112 citations
828. A Content Transformation Block for Image Style TransferPoster111 citations
829. Nesti-Net: Normal Estimation for Unstructured 3D Point Clouds Using Convolutional Neural NetworksPoster111 citations
830. Text2Scene: Generating Compositional Scenes From Textual DescriptionsOral111 citations
831. Co-Saliency Detection via Mask-Guided Fully Convolutional Networks With Multi-Scale Label SmoothingPoster110 citations
832. Modulating Image Restoration With Continual Levels via Adaptive Feature Modification LayersOral110 citations
833. PPGNet: Learning Point-Pair Graph for Line Segment DetectionPoster110 citations
834. Content-Aware Multi-Level Guidance for Interactive Instance SegmentationPoster109 citations
835. Deep Network Interpolation for Continuous Imagery Effect TransitionPoster109 citations
836. Signal-To-Noise Ratio: A Robust Distance Metric for Deep Metric LearningPoster109 citations
837. Answer Them All! Toward Universal Visual Question Answering ModelsPoster108 citations
838. Hyperspectral Image Super-Resolution With Optimized RGB GuidancePoster108 citations
839. On Exploring Undetermined Relationships for Visual Relationship DetectionPoster108 citations
840. S4Net: Single Stage Salient-Instance SegmentationPoster108 citations
841. CrossInfoNet: Multi-Task Information Sharing Based Hand Pose EstimationPoster107 citations
842. Sensitive-Sample Fingerprinting of Deep Neural NetworksPoster107 citations
843. Object Tracking by Reconstruction With View-Specific Discriminative Correlation FiltersPoster106 citations
844. Point-To-Pose Voting Based Hand Pose Estimation Using Residual Permutation Equivariant LayerPoster106 citations
845. Toward Realistic Image Compositing With Adversarial LearningPoster105 citations
846. Towards Robust Curve Text Detection With Conditional Spatial ExpansionPoster105 citations
847. A Cross-Season Correspondence Dataset for Robust Semantic SegmentationPoster104 citations
848. A Skeleton-Bridged Deep Learning Approach for Generating Meshes of Complex Topologies From Single RGB ImagesOral104 citations
849. Combining 3D Morphable Models: A Large Scale Face-And-Head ModelOral104 citations
850. Learning View Priors for Single-View 3D ReconstructionPoster104 citations
851. Model-Blind Video Denoising via Frame-To-Frame TrainingPoster104 citations
852. Quasi-Unsupervised Color ConstancyPoster104 citations
853. Example-Guided Style-Consistent Image Synthesis From Semantic LabelingPoster102 citations
854. Guided Stereo MatchingPoster102 citations
855. Learning to Synthesize Motion BlurOral102 citations
856. WarpGAN: Automatic Caricature GenerationOral102 citations
857. Bridging Stereo Matching and Optical Flow via Spatiotemporal CorrespondencePoster101 citations
858. Not Using the Car to See the Sidewalk -- Quantifying and Controlling the Effects of Context in Classification and SegmentationPoster101 citations
859. Deeply-Supervised Knowledge SynergyPoster100 citations
860. Learning Image and Video Compression Through Spatial-Temporal Energy CompactionPoster100 citations
861. Learning to Calibrate Straight Lines for Fisheye Image RectificationPoster100 citations
862. On Finding Gray PixelsPoster100 citations
863. Relational Action ForecastingOral100 citations
864. SeerNet: Predicting Convolutional Neural Network Feature-Map Sparsity Through Low-Bit QuantizationPoster100 citations
865. Multi-Level Multimodal Common Semantic Space for Image-Phrase GroundingPoster99 citations
866. Pedestrian Detection With Autoregressive Network PhasesPoster99 citations
867. Privacy Preserving Image-Based LocalizationPoster99 citations
868. Semantically Aligned Bias Reducing Zero Shot LearningPoster99 citations
869. Face Parsing With RoI Tanh-WarpingPoster98 citations
870. Object Instance Annotation With Deep Extreme Level Set EvolutionPoster98 citations
871. Two Body Problem: Collaborative Visual Task CompletionOral98 citations
872. IM-Net for High Resolution Video Frame InterpolationOral97 citations
873. Interactive Full Image Segmentation by Considering All Regions JointlyPoster97 citations
874. RGBD Based Dimensional Decomposition Residual Network for 3D Semantic Scene CompletionPoster97 citations
875. ROI Pooled Correlation Filters for Visual TrackingPoster97 citations
876. Steady-State Non-Line-Of-Sight ImagingOral97 citations
877. Bringing Alive Blurred MomentsOral96 citations
878. Complete the Look: Scene-Based Complementary Product RecommendationPoster96 citations
879. Deep ChArUco: Dark ChArUco Marker Pose EstimationPoster96 citations
880. Learning to Minify Photometric StereoPoster96 citations
881. Multi-Person Articulated Tracking With Spatial and Temporal EmbeddingsPoster96 citations
882. Progressive Attention Memory Network for Movie Story Question AnsweringPoster96 citations
883. Does Learning Specific Features for Related Parts Help Human Pose Estimation?Poster95 citations
884. Learning Instance Activation Maps for Weakly Supervised Instance SegmentationPoster95 citations
885. PMS-Net: Robust Haze Removal Based on Patch Map for Single ImagesPoster95 citations
886. SceneCode: Monocular Dense Semantic Reconstruction Using Learned Encoded Scene RepresentationsPoster95 citations
887. AdaGraph: Unifying Predictive and Continuous Domain Adaptation Through GraphsOral94 citations
888. Circulant Binary Convolutional Networks: Enhancing the Performance of 1-Bit DCNNs With Circulant Back PropagationPoster94 citations
889. Fully Learnable Group Convolution for Acceleration of Deep Neural NetworksPoster94 citations
890. Label-Noise Robust Generative Adversarial NetworksOral94 citations
891. Noise-Aware Unsupervised Deep Lidar-Stereo FusionPoster94 citations
892. Social Relation Recognition From Videos via Multi-Scale Spatial-Temporal ReasoningPoster94 citations
893. Spot and Learn: A Maximum-Entropy Patch Sampler for Few-Shot Image ClassificationPoster94 citations
894. Dense 3D Face Decoding Over 2500FPS: Joint Texture & Shape Convolutional Mesh DecodersPoster93 citations
895. Depth From a Polarisation + RGB Stereo PairPoster93 citations
896. Learning to Adapt for StereoPoster93 citations
897. T-Net: Parametrizing Fully Convolutional Nets With a Single High-Order TensorPoster93 citations
898. Action Recognition From Single Timestamp Supervision in Untrimmed VideosPoster92 citations
899. Local Features and Visual Words Emerge in ActivationsPoster92 citations
900. Occlusion-Net: 2D/3D Occluded Keypoint Localization Using Graph NetworksPoster92 citations
901. Variational Prototyping-Encoder: One-Shot Learning With Prototypical ImagesPoster92 citations
902. Context and Attribute Grounded Dense CaptioningPoster91 citations
903. Event Cameras, Contrast Maximization and Reward Functions: An AnalysisPoster91 citations
904. Photometric Mesh Optimization for Video-Aligned 3D Object ReconstructionPoster91 citations
905. Simultaneously Optimizing Weight and Quantizer of Ternary Neural Network Using Truncated Gaussian ApproximationPoster91 citations
906. Inverse Discriminative Networks for Handwritten Signature VerificationPoster90 citations
907. On the Intrinsic Dimensionality of Image RepresentationsPoster90 citations
908. SoDeep: A Sorting Deep Net to Learn Ranking Loss SurrogatesOral90 citations
909. A Perceptual Prediction Framework for Self Supervised Event SegmentationPoster89 citations
910. DeepMapping: Unsupervised Map Estimation From Multiple Point CloudsOral89 citations
911. Not All Areas Are Equal: Transfer Learning for Semantic Segmentation via Hierarchical Region SelectionOral89 citations
912. All-Weather Deep Outdoor Lighting EstimationPoster88 citations
913. DeFusionNET: Defocus Blur Detection via Recurrently Fusing and Refining Multi-Scale Deep FeaturesPoster88 citations
914. Multi-Step Prediction of Occupancy Grid Maps With Recurrent Neural NetworksPoster88 citations
915. Noise-Tolerant Paradigm for Training Face Recognition CNNsPoster88 citations
916. Pointing Novel Objects in Image CaptioningPoster88 citations
917. Using Unknown Occluders to Recover Hidden ScenesPoster88 citations
918. ELASTIC: Improving CNNs With Dynamic Scaling PoliciesOral87 citations
919. A Simple Baseline for Audio-Visual Scene-Aware DialogPoster86 citations
920. Convolutional Recurrent Network for Road Boundary ExtractionPoster86 citations
921. Deep Surface Normal Estimation With Hierarchical RGB-D FusionPoster86 citations
922. DeepCO3: Deep Instance Co-Segmentation by Co-Peak Search and Co-Saliency DetectionOral86 citations
923. Estimating 3D Motion and Forces of Person-Object Interactions From Monocular VideoOral86 citations
924. Learning for Single-Shot Confidence Calibration in Deep Neural Networks Through Stochastic InferencesPoster86 citations
925. Temporal Transformer Networks: Joint Learning of Invariant and Discriminative Time WarpingPoster86 citations
926. ZigZagNet: Fusing Top-Down and Bottom-Up Context for Object SegmentationPoster86 citations
927. High Flux Passive Imaging With Single-Photon SensorsOral85 citations
928. Learning Binary Code for Personalized Fashion RecommendationPoster85 citations
929. Progressive Ensemble Networks for Zero-Shot RecognitionPoster85 citations
930. Handwriting Recognition in Low-Resource Scripts Using Adversarial LearningPoster84 citations
931. QATM: Quality-Aware Template Matching for Deep LearningPoster84 citations
932. Reliable and Efficient Image Cropping: A Grid Anchor Based ApproachPoster84 citations
933. Kervolutional Neural NetworksOral83 citations
934. Learning Spatial Common Sense With Geometry-Aware Recurrent NetworksOral83 citations
935. Unsupervised Deep Epipolar Flow for Stationary or Dynamic ScenesPoster83 citations
936. Unsupervised Multi-Modal Neural Machine TranslationPoster83 citations
937. Accelerating Convolutional Neural Networks via Activation Map CompressionPoster82 citations
938. Image-Question-Answer Synergistic Network for Visual DialogPoster82 citations
939. Ensemble Deep Manifold Similarity Learning Using Hard ProxiesPoster81 citations
940. Homomorphic Latent Space Interpolation for Unpaired Image-To-Image TranslationOral81 citations
941. LiFF: Light Field Features in Scale and DepthPoster81 citations
942. Adaptively Connected Neural NetworksPoster80 citations
943. End-To-End Supervised Product Quantization for Image Search and RetrievalPoster80 citations
944. Learning Single-Image Depth From Videos Using Quality Assessment NetworksPoster80 citations
945. Learning Video Representations From Correspondence ProposalsOral80 citations
946. Phase-Only Image Based Kernel Estimation for Single Image Blind DeblurringPoster80 citations
947. Fast Single Image Reflection Suppression via Convex OptimizationPoster79 citations
948. Fast User-Guided Video Object Segmentation by Interaction-And-Propagation NetworksPoster79 citations
949. Learning Multi-Class Segmentations From Single-Class DatasetsPoster78 citations
950. OICSR: Out-In-Channel Sparsity Regularization for Compact Deep Neural NetworksPoster78 citations
951. Spherical Regression: Learning Viewpoints, Surface Normals and 3D Rotations on N-SpheresPoster78 citations
952. Trust Region Based Adversarial Attack on Neural NetworksPoster78 citations
953. Which Way Are You Going? Imitative Decision Learning for Path Forecasting in Dynamic ScenesOral78 citations
954. A Theoretically Sound Upper Bound on the Triplet Loss for Improving the Efficiency of Deep Distance Metric LearningPoster77 citations
955. Divergence Triangle for Joint Training of Generator Model, Energy-Based Model, and Inferential ModelOral77 citations
956. Face-Focused Cross-Stream Network for Deception Detection in VideosPoster77 citations
957. Hybrid-Attention Based Decoupled Metric Learning for Zero-Shot Image RetrievalPoster77 citations
958. Multi-Task Learning of Hierarchical Vision-Language RepresentationPoster77 citations
959. Triply Supervised Decoder Networks for Joint Detection and SegmentationPoster77 citations
960. Unsupervised Image Matching and Object Discovery as OptimizationPoster77 citations
961. Dynamic Recursive Neural NetworkPoster76 citations
962. Holistic and Comprehensive Annotation of Clinically Significant Findings on Diverse CT Images: Learning From Radiology Reports and Label OntologyOral76 citations
963. RePr: Improved Training of Convolutional FiltersOral76 citations
964. Reflection Removal Using a Dual-Pixel SensorPoster76 citations
965. Self-Critical N-Step Training for Image CaptioningPoster76 citations
966. Enhancing Diversity of Defocus Blur Detectors via Cross-Ensemble NetworkOral75 citations
967. LAEO-Net: Revisiting People Looking at Each Other in VideosPoster75 citations
968. On Stabilizing Generative Adversarial Training With NoisePoster75 citations
969. Photon-Flooded Single-Photon 3D CamerasOral75 citations
970. Privacy Protection in Street-View Panoramas Using Depth and Multi-View ImageryPoster75 citations
971. Unifying Heterogeneous Classifiers With DistillationPoster75 citations
972. Learning Joint Gait Representation via Quintuplet Loss MinimizationOral74 citations
973. Semantic Alignment: Finding Semantically Consistent Ground-Truth for Facial Landmark DetectionPoster74 citations
974. Atlas of Digital Pathology: A Generalized Hierarchical Histological Tissue Type-Annotated Database for Deep LearningPoster73 citations
975. Robust Video Stabilization by Optimization in CNN Weight SpacePoster73 citations
976. Defense Against Adversarial Images Using Web-Scale Nearest-Neighbor SearchOral72 citations
977. Hierarchical Disentanglement of Discriminative Latent Features for Zero-Shot LearningPoster72 citations
978. Marginalized Latent Semantic Encoder for Zero-Shot LearningPoster72 citations
979. Object Discovery in Videos as Foreground Motion ClusteringPoster72 citations
980. CRAVES: Controlling Robotic Arm With a Vision-Based Economic SystemPoster71 citations
981. SSN: Learning Sparse Switchable Normalization via SparsestMaxPoster71 citations
982. SketchGAN: Joint Sketch Completion and Recognition With Generative Adversarial NetworkPoster71 citations
983. Student Becoming the Master: Knowledge Amalgamation for Joint Scene Parsing, Depth Estimation, and MorePoster71 citations
984. A Variational Auto-Encoder Model for Stochastic Point ProcessesPoster70 citations
985. Bayesian Hierarchical Dynamic Model for Human Action RecognitionPoster70 citations
986. Hybrid Scene Compression for Visual LocalizationPoster70 citations
987. Led3D: A Lightweight and Efficient Deep Approach to Recognizing Low-Quality 3D FacesPoster70 citations
988. Non-Adversarial Image Synthesis With Generative Latent Nearest NeighborsPoster70 citations
989. Reversible GANs for Memory-Efficient Image-To-Image TranslationPoster70 citations
990. SIGNet: Semantic Instance Aided Unsupervised 3D Geometry PerceptionPoster70 citations
991. Training Deep Learning Based Image Denoisers From Undersampled Measurements Without Ground Truth and Without Image PriorPoster70 citations
992. Im2Pencil: Controllable Pencil Illustration From PhotographsPoster68 citations
993. Learning to Extract Flawless Slow Motion From Blurry VideosPoster68 citations
994. LiveSketch: Query Perturbations for Guided Sketch-Based Visual SearchPoster68 citations
995. A Local Block Coordinate Descent Algorithm for the CSC ModelPoster67 citations
996. Joint Face Detection and Facial Motion Retargeting for Multiple FacesPoster67 citations
997. Learning Transformation SynchronizationPoster67 citations
998. MHP-VOS: Multiple Hypotheses Propagation for Video Object SegmentationOral67 citations
999. Tracking by Animation: Unsupervised Learning of Multi-Object Attentive TrackersPoster67 citations
1000. Disentangling Latent Space for VAE by Label Relevant/Irrelevant DimensionsPoster66 citations

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