ICCV 2019 Accepted Papers

The full list of 1,075 papers accepted at ICCV 2019 (IEEE/CVF International Conference on Computer Vision). Click any title for details, similar papers, and links to the original source. You can also search these papers by meaning, not just keywords.

1. Searching for MobileNetV3Oral10,859 citations
2. FCOS: Fully Convolutional One-Stage Object DetectionPoster7,221 citations
3. CutMix: Regularization Strategy to Train Strong Classifiers With Localizable FeaturesOral6,589 citations
4. SlowFast Networks for Video RecognitionOral4,462 citations
5. CenterNet: Keypoint Triplets for Object DetectionPoster4,174 citations
6. CCNet: Criss-Cross Attention for Semantic SegmentationPoster3,729 citations
7. KPConv: Flexible and Deformable Convolution for Point CloudsPoster3,401 citations
8. YOLACT: Real-Time Instance SegmentationOral2,970 citations
9. FaceForensics++: Learning to Detect Manipulated Facial ImagesPoster2,929 citations
10. Digging Into Self-Supervised Monocular Depth EstimationPoster2,896 citations
11. TSM: Temporal Shift Module for Efficient Video UnderstandingPoster2,510 citations
12. SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR SequencesOral2,413 citations
13. Free-Form Image Inpainting With Gated ConvolutionOral2,386 citations
14. Moment Matching for Multi-Source Domain AdaptationOral2,315 citations
15. DeepGCNs: Can GCNs Go As Deep As CNNs?Oral1,943 citations
16. Memorizing Normality to Detect Anomaly: Memory-Augmented Deep Autoencoder for Unsupervised Anomaly DetectionPoster1,892 citations
17. Habitat: A Platform for Embodied AI ResearchOral1,687 citations
18. Deep Hough Voting for 3D Object Detection in Point CloudsOral1,587 citations
19. AMASS: Archive of Motion Capture As Surface ShapesPoster1,579 citations
20. PANet: Few-Shot Image Semantic Segmentation With Prototype AlignmentOral1,571 citations
21. VideoBERT: A Joint Model for Video and Language Representation LearningPoster1,568 citations
22. Learning Discriminative Model Prediction for TrackingOral1,548 citations
23. PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human DigitizationPoster1,539 citations
24. Attention Augmented Convolutional NetworksPoster1,501 citations
25. Rethinking ImageNet Pre-TrainingPoster1,470 citations
26. HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video ClipsPoster1,412 citations
27. Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?Oral1,379 citations
28. Similarity-Preserving Knowledge DistillationOral1,344 citations
29. Tracking Without Bells and WhistlesPoster1,321 citations
30. EGNet: Edge Guidance Network for Salient Object DetectionPoster1,302 citations
31. RepPoints: Point Set Representation for Object DetectionPoster1,297 citations
32. Scale-Aware Trident Networks for Object DetectionOral1,247 citations
33. DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and BetterPoster1,241 citations
34. Learning to Reconstruct 3D Human Pose and Shape via Model-Fitting in the LoopPoster1,232 citations
35. Symmetric Cross Entropy for Robust Learning With Noisy LabelsPoster1,222 citations
36. Attention on Attention for Image CaptioningOral1,219 citations
37. Deep Closest Point: Learning Representations for Point Cloud RegistrationPoster1,194 citations
38. Omni-Scale Feature Learning for Person Re-IdentificationPoster1,193 citations
39. Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self DistillationPoster1,137 citations
40. S4L: Self-Supervised Semi-Supervised LearningOral1,125 citations
41. Invariant Information Clustering for Unsupervised Image Classification and SegmentationPoster1,113 citations
42. SinGAN: Learning a Generative Model From a Single Natural ImageOral1,110 citations
43. GridDehazeNet: Attention-Based Multi-Scale Network for Image DehazingPoster1,096 citations
44. SCRDet: Towards More Robust Detection for Small, Cluttered and Rotated ObjectsPoster1,074 citations
45. Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World DataOral1,063 citations
46. Confidence Regularized Self-TrainingOral1,037 citations
47. Everybody Dance NowPoster1,014 citations
48. Few-Shot Object Detection via Feature ReweightingPoster999 citations
49. Few-Shot Unsupervised Image-to-Image TranslationPoster995 citations
50. ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution BlocksPoster985 citations
51. STD: Sparse-to-Dense 3D Object Detector for Point CloudPoster983 citations
52. Video Object Segmentation Using Space-Time Memory NetworksOral935 citations
53. CARAFE: Content-Aware ReAssembly of FEaturesOral916 citations
54. Objects365: A Large-Scale, High-Quality Dataset for Object DetectionPoster910 citations
55. On the Efficacy of Knowledge DistillationPoster894 citations
56. Gated-SCNN: Gated Shape CNNs for Semantic SegmentationPoster862 citations
57. Semi-Supervised Domain Adaptation via Minimax EntropyPoster848 citations
58. Progressive Differentiable Architecture Search: Bridging the Depth Gap Between Search and EvaluationOral847 citations
59. Asymmetric Non-Local Neural Networks for Semantic SegmentationPoster828 citations
60. Fully Convolutional Geometric FeaturesPoster824 citations
61. Learning Lightweight Lane Detection CNNs by Self Attention DistillationPoster824 citations
62. Soft Rasterizer: A Differentiable Renderer for Image-Based 3D ReasoningOral820 citations
63. Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks With Octave ConvolutionPoster811 citations
64. Few-Shot Adversarial Learning of Realistic Neural Talking Head ModelsOral810 citations
65. FSGAN: Subject Agnostic Face Swapping and ReenactmentPoster808 citations
66. PointFlow: 3D Point Cloud Generation With Continuous Normalizing FlowsOral798 citations
67. A Comprehensive Overhaul of Feature DistillationPoster791 citations
68. BMN: Boundary-Matching Network for Temporal Action Proposal GenerationPoster791 citations
69. Video Classification With Channel-Separated Convolutional NetworksPoster784 citations
70. Expectation-Maximization Attention Networks for Semantic SegmentationOral783 citations
71. Real Image Denoising With Feature AttentionOral774 citations
72. Variational Adversarial Active LearningOral754 citations
73. What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model AnalysisOral729 citations
74. 6-DOF GraspNet: Variational Grasp Generation for Object ManipulationPoster714 citations
75. STGAT: Modeling Spatial-Temporal Interactions for Human Trajectory PredictionOral714 citations
76. Exploring the Limitations of Behavior Cloning for Autonomous DrivingOral703 citations
77. Data-Free Quantization Through Weight Equalization and Bias CorrectionOral702 citations
78. Generative Adversarial Networks for Extreme Learned Image CompressionPoster698 citations
79. Pose-Guided Feature Alignment for Occluded Person Re-IdentificationPoster696 citations
80. Local Relation Networks for Image RecognitionPoster690 citations
81. Correlation Congruence for Knowledge DistillationPoster688 citations
82. Visual Semantic Reasoning for Image-Text MatchingOral682 citations
83. An Empirical Study of Spatial Attention Mechanisms in Deep NetworksPoster679 citations
84. Bayesian Loss for Crowd Count Estimation With Point SupervisionOral675 citations
85. ABD-Net: Attentive but Diverse Person Re-IdentificationPoster672 citations
86. VaTeX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language ResearchOral669 citations
87. Efficient and Accurate Arbitrary-Shaped Text Detection With Pixel Aggregation NetworkPoster666 citations
88. Larger Norm More Transferable: An Adaptive Feature Norm Approach for Unsupervised Domain AdaptationOral656 citations
89. Meta R-CNN: Towards General Solver for Instance-Level Low-Shot LearningPoster651 citations
90. Mesh R-CNNPoster644 citations
91. Graph Convolutional Networks for Temporal Action LocalizationPoster640 citations
92. HAWQ: Hessian AWare Quantization of Neural Networks With Mixed-PrecisionPoster637 citations
93. M3D-RPN: Monocular 3D Region Proposal Network for Object DetectionOral635 citations
94. Video Instance SegmentationPoster635 citations
95. Toward Real-World Single Image Super-Resolution: A New Benchmark and a New ModelOral633 citations
96. Disentangling Monocular 3D Object DetectionPoster628 citations
97. Gaussian YOLOv3: An Accurate and Fast Object Detector Using Localization Uncertainty for Autonomous DrivingPoster617 citations
98. HoloGAN: Unsupervised Learning of 3D Representations From Natural ImagesPoster617 citations
99. Self-Similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-IdentificationOral606 citations
100. Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural NetworksPoster591 citations
101. Exploiting Spatial-Temporal Relationships for 3D Pose Estimation via Graph Convolutional NetworksPoster588 citations
102. Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose EstimationOral581 citations
103. Enforcing Geometric Constraints of Virtual Normal for Depth PredictionPoster577 citations
104. Learning Trajectory Dependencies for Human Motion PredictionOral572 citations
105. RGB-Infrared Cross-Modality Person Re-Identification via Joint Pixel and Feature AlignmentPoster568 citations
106. DPOD: 6D Pose Object Detector and RefinerPoster567 citations
107. Episodic Training for Domain GeneralizationOral565 citations
108. STM: SpatioTemporal and Motion Encoding for Action RecognitionPoster556 citations
109. MetaPruning: Meta Learning for Automatic Neural Network Channel PruningPoster555 citations
110. Attributing Fake Images to GANs: Learning and Analyzing GAN FingerprintsPoster551 citations
111. FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape From Single RGB ImagesPoster544 citations
112. Balanced Datasets Are Not Enough: Estimating and Mitigating Gender Bias in Deep Image RepresentationsPoster542 citations
113. Local Aggregation for Unsupervised Learning of Visual EmbeddingsOral542 citations
114. PU-GAN: A Point Cloud Upsampling Adversarial NetworkPoster538 citations
115. The Trajectron: Probabilistic Multi-Agent Trajectory Modeling With Dynamic Spatiotemporal GraphsPoster535 citations
116. CDPN: Coordinates-Based Disentangled Pose Network for Real-Time RGB-Based 6-DoF Object Pose EstimationOral533 citations
117. Understanding Deep Networks via Extremal Perturbations and Smooth MasksOral528 citations
118. Anomaly Detection in Video Sequence With Appearance-Motion CorrespondencePoster526 citations
119. Depth-Induced Multi-Scale Recurrent Attention Network for Saliency DetectionPoster526 citations
120. Boosting Few-Shot Visual Learning With Self-SupervisionPoster511 citations
121. Fast Point R-CNNPoster511 citations
122. Learning With Average Precision: Training Image Retrieval With a Listwise LossPoster503 citations
123. Stacked Cross Refinement Network for Edge-Aware Salient Object DetectionPoster502 citations
124. Scaling and Benchmarking Self-Supervised Visual Representation LearningPoster500 citations
125. Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization Without Accessing Target Domain DataPoster497 citations
126. SoftTriple Loss: Deep Metric Learning Without Triplet SamplingPoster497 citations
127. Coherent Semantic Attention for Image InpaintingPoster494 citations
128. Learnable Triangulation of Human PoseOral494 citations
129. Universally Slimmable Networks and Improved Training TechniquesPoster490 citations
130. Mixed High-Order Attention Network for Person Re-IdentificationPoster487 citations
131. Depth From Videos in the Wild: Unsupervised Monocular Depth Learning From Unknown CamerasPoster483 citations
132. ShellNet: Efficient Point Cloud Convolutional Neural Networks Using Concentric Shells StatisticsOral481 citations
133. Gaze360: Physically Unconstrained Gaze Estimation in the WildPoster475 citations
134. Exploring Randomly Wired Neural Networks for Image RecognitionOral472 citations
135. Pix2Vox: Context-Aware 3D Reconstruction From Single and Multi-View ImagesPoster471 citations
136. PIE: A Large-Scale Dataset and Models for Pedestrian Intention Estimation and Trajectory PredictionOral469 citations
137. TensorMask: A Foundation for Dense Object SegmentationPoster469 citations
138. Learning Two-View Correspondences and Geometry Using Order-Aware NetworkPoster468 citations
139. PRECOG: PREdiction Conditioned on Goals in Visual Multi-Agent SettingsPoster467 citations
140. Multi-Garment Net: Learning to Dress 3D People From ImagesPoster464 citations
141. Data-Free Learning of Student NetworksPoster463 citations
142. Learning the Model Update for Siamese TrackersPoster461 citations
143. Seeing What a GAN Cannot GenerateOral457 citations
144. StructureFlow: Image Inpainting via Structure-Aware Appearance FlowPoster455 citations
145. RankSRGAN: Generative Adversarial Networks With Ranker for Image Super-ResolutionOral454 citations
146. Entangled Transformer for Image CaptioningPoster452 citations
147. Relation-Aware Graph Attention Network for Visual Question AnsweringPoster451 citations
148. Camera Distance-Aware Top-Down Approach for 3D Multi-Person Pose Estimation From a Single RGB ImagePoster449 citations
149. Learning Aberrance Repressed Correlation Filters for Real-Time UAV TrackingPoster448 citations
150. Feature Weighting and Boosting for Few-Shot SegmentationPoster446 citations
151. IL2M: Class Incremental Learning With Dual MemoryPoster443 citations
152. Point-Based Multi-View Stereo NetworkOral439 citations
153. EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action RecognitionPoster438 citations
154. A Fast and Accurate One-Stage Approach to Visual GroundingOral437 citations
155. Clustered Object Detection in Aerial ImagesPoster432 citations
156. Photorealistic Style Transfer via Wavelet TransformsPoster426 citations
157. Racial Faces in the Wild: Reducing Racial Bias by Information Maximization Adaptation NetworkPoster426 citations
158. Learning Shape Templates With Structured Implicit FunctionsPoster425 citations
159. Meta-Learning to Detect Rare ObjectsPoster424 citations
160. DeepVCP: An End-to-End Deep Neural Network for Point Cloud RegistrationPoster420 citations
161. nocaps: novel object captioning at scalePoster420 citations
162. End-to-End Learning of Representations for Asynchronous Event-Based DataPoster418 citations
163. Scene Text Visual Question AnsweringPoster417 citations
164. HarDNet: A Low Memory Traffic NetworkPoster415 citations
165. Multi-Adversarial Faster-RCNN for Unrestricted Object DetectionPoster414 citations
166. 3D Scene Graph: A Structure for Unified Semantics, 3D Space, and CameraPoster413 citations
167. Domain Adaptation for Structured Output via Discriminative Patch RepresentationsOral413 citations
168. Miss Detection vs. False Alarm: Adversarial Learning for Small Object Segmentation in Infrared ImagesPoster412 citations
169. DeepHuman: 3D Human Reconstruction From a Single ImageOral405 citations
170. Probabilistic Face EmbeddingsPoster404 citations
171. GradNet: Gradient-Guided Network for Visual Object TrackingOral400 citations
172. Accurate Monocular 3D Object Detection via Color-Embedded 3D Reconstruction for Autonomous DrivingPoster396 citations
173. CAMP: Cross-Modal Adaptive Message Passing for Text-Image RetrievalPoster395 citations
174. Learning to Discover Novel Visual Categories via Deep Transfer ClusteringPoster395 citations
175. Deep Self-Learning From Noisy LabelsPoster393 citations
176. Pyramid Graph Networks With Connection Attentions for Region-Based One-Shot Semantic SegmentationPoster388 citations
177. AutoGAN: Neural Architecture Search for Generative Adversarial NetworksPoster386 citations
178. GANalyze: Toward Visual Definitions of Cognitive Image PropertiesPoster386 citations
179. Task2Vec: Task Embedding for Meta-LearningPoster386 citations
180. Learning Semantic-Specific Graph Representation for Multi-Label Image RecognitionPoster384 citations
181. Domain Adaptation for Semantic Segmentation With Maximum Squares LossPoster382 citations
182. SC-FEGAN: Face Editing Generative Adversarial Network With User's Sketch and ColorPoster382 citations
183. Human-Aware Motion DeblurringPoster377 citations
184. ThunderNet: Towards Real-Time Generic Object Detection on Mobile DevicesPoster377 citations
185. NLNL: Negative Learning for Noisy LabelsPoster373 citations
186. Tex2Shape: Detailed Full Human Body Geometry From a Single ImagePoster372 citations
187. SRM: A Style-Based Recalibration Module for Convolutional Neural NetworksPoster371 citations
188. Remote Heart Rate Measurement From Highly Compressed Facial Videos: An End-to-End Deep Learning Solution With Video EnhancementPoster370 citations
189. 3D Point Cloud Generative Adversarial Network Based on Tree Structured Graph ConvolutionsPoster369 citations
190. DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud ProcessingPoster368 citations
191. Texture Fields: Learning Texture Representations in Function SpaceOral368 citations
192. Unsupervised Pre-Training of Image Features on Non-Curated DataOral368 citations
193. Key.Net: Keypoint Detection by Handcrafted and Learned CNN FiltersPoster364 citations
194. Neural-Guided RANSAC: Learning Where to Sample Model HypothesesPoster361 citations
195. Resolving 3D Human Pose Ambiguities With 3D Scene ConstraintsPoster359 citations
196. ACFNet: Attentional Class Feature Network for Semantic SegmentationPoster357 citations
197. Human Uncertainty Makes Classification More RobustPoster357 citations
198. Zero-Shot Video Object Segmentation via Attentive Graph Neural NetworksOral353 citations
199. Context-Aware Emotion Recognition NetworksPoster352 citations
200. Adaptive Wing Loss for Robust Face Alignment via Heatmap RegressionPoster350 citations
201. GA-DAN: Geometry-Aware Domain Adaptation Network for Scene Text Detection and RecognitionPoster350 citations
202. Recursive Cascaded Networks for Unsupervised Medical Image RegistrationPoster350 citations
203. WoodScape: A Multi-Task, Multi-Camera Fisheye Dataset for Autonomous DrivingOral350 citations
204. VV-Net: Voxel VAE Net With Group Convolutions for Point Cloud SegmentationPoster348 citations
205. HACS: Human Action Clips and Segments Dataset for Recognition and Temporal LocalizationPoster347 citations
206. Dynamic Multi-Scale Filters for Semantic SegmentationPoster345 citations
207. LPD-Net: 3D Point Cloud Learning for Large-Scale Place Recognition and Environment AnalysisPoster345 citations
208. DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatchPoster342 citations
209. Progressive Fusion Video Super-Resolution Network via Exploiting Non-Local Spatio-Temporal CorrelationsOral337 citations
210. Deep Joint-Semantics Reconstructing Hashing for Large-Scale Unsupervised Cross-Modal RetrievalOral334 citations
211. Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View SynthesisPoster333 citations
212. Self-Ensembling With GAN-Based Data Augmentation for Domain Adaptation in Semantic SegmentationPoster328 citations
213. A Robust Learning Approach to Domain Adaptive Object DetectionPoster323 citations
214. Single-Stage Multi-Person Pose MachinesPoster320 citations
215. Bit-Flip Attack: Crushing Neural Network With Progressive Bit SearchPoster319 citations
216. Dynamic Curriculum Learning for Imbalanced Data ClassificationPoster319 citations
217. Image Inpainting With Learnable Bidirectional Attention MapsPoster319 citations
218. Symmetric Graph Convolutional Autoencoder for Unsupervised Graph Representation LearningPoster319 citations
219. O2U-Net: A Simple Noisy Label Detection Approach for Deep Neural NetworksPoster318 citations
220. Batch DropBlock Network for Person Re-Identification and BeyondPoster317 citations
221. Self-Supervised Learning With Geometric Constraints in Monocular Video: Connecting Flow, Depth, and CameraPoster317 citations
222. Meta-Sim: Learning to Generate Synthetic DatasetsOral316 citations
223. SSAP: Single-Shot Instance Segmentation With Affinity PyramidPoster316 citations
224. Selective Sparse Sampling for Fine-Grained Image RecognitionPoster316 citations
225. Auto-ReID: Searching for a Part-Aware ConvNet for Person Re-IdentificationPoster315 citations
226. Sequence Level Semantics Aggregation for Video Object DetectionOral315 citations
227. Dual Student: Breaking the Limits of the Teacher in Semi-Supervised LearningPoster314 citations
228. Occupancy Flow: 4D Reconstruction by Learning Particle DynamicsPoster314 citations
229. Spatial-Temporal Relation Networks for Multi-Object TrackingPoster313 citations
230. XRAI: Better Attributions Through RegionsPoster312 citations
231. Guided Curriculum Model Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image SegmentationPoster311 citations
232. Learning to Assemble Neural Module Tree Networks for Visual GroundingOral311 citations
233. Self-Supervised Monocular Depth HintsPoster311 citations
234. Optimizing Network Structure for 3D Human Pose EstimationPoster307 citations
235. Enhancing Adversarial Example Transferability With an Intermediate Level AttackPoster306 citations
236. Cross View Fusion for 3D Human Pose EstimationPoster305 citations
237. Crowd Counting With Deep Structured Scale Integration NetworkPoster305 citations
238. Self-Training With Progressive Augmentation for Unsupervised Cross-Domain Person Re-IdentificationPoster305 citations
239. Taking a HINT: Leveraging Explanations to Make Vision and Language Models More GroundedPoster305 citations
240. Boundary-Aware Feature Propagation for Scene SegmentationPoster304 citations
241. Implicit Surface Representations As Layers in Neural NetworksPoster304 citations
242. Occlusion Robust Face Recognition Based on Mask Learning With Pairwise Differential Siamese NetworkPoster303 citations
243. Cluster Alignment With a Teacher for Unsupervised Domain AdaptationPoster302 citations
244. ClothFlow: A Flow-Based Model for Clothed Person GenerationPoster301 citations
245. Learning Combinatorial Embedding Networks for Deep Graph MatchingOral301 citations
246. Pixel2Mesh++: Multi-View 3D Mesh Generation via DeformationPoster301 citations
247. Seeing Motion in the DarkOral299 citations
248. The Sound of MotionsPoster298 citations
249. FAMNet: Joint Learning of Feature, Affinity and Multi-Dimensional Assignment for Online Multiple Object TrackingOral293 citations
250. Cross-X Learning for Fine-Grained Visual CategorizationPoster292 citations
251. A Dual-Path Model With Adaptive Attention for Vehicle Re-IdentificationOral291 citations
252. Variable Rate Deep Image Compression With a Conditional AutoencoderOral289 citations
253. Learned Video CompressionPoster288 citations
254. Global-Local Temporal Representations for Video Person Re-IdentificationPoster286 citations
255. Overcoming Catastrophic Forgetting With Unlabeled Data in the WildPoster285 citations
256. Joint Monocular 3D Vehicle Detection and TrackingPoster284 citations
257. l-Net: Reconstruct Hyperspectral Images From a Snapshot MeasurementPoster283 citations
258. Depth Completion From Sparse LiDAR Data With Depth-Normal ConstraintsPoster282 citations
259. Relation Distillation Networks for Video Object DetectionPoster280 citations
260. SCSampler: Sampling Salient Clips From Video for Efficient Action RecognitionOral280 citations
261. Integral Object Mining via Online Attention AccumulationPoster279 citations
262. Interpolated Convolutional Networks for 3D Point Cloud UnderstandingOral278 citations
263. Diversity With Cooperation: Ensemble Methods for Few-Shot ClassificationPoster277 citations
264. Pose-Aware Multi-Level Feature Network for Human Object Interaction DetectionOral276 citations
265. Towards High-Resolution Salient Object DetectionPoster275 citations
266. Better to Follow, Follow to Be Better: Towards Precise Supervision of Feature Super-Resolution for Small Object DetectionPoster274 citations
267. RANet: Ranking Attention Network for Fast Video Object SegmentationPoster274 citations
268. Video Compression With Rate-Distortion AutoencodersPoster274 citations
269. PointCloud Saliency MapsOral272 citations
270. Robust Multi-Modality Multi-Object TrackingPoster272 citations
271. Constructing Self-Motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial ApproachPoster271 citations
272. Occlusion-Aware Networks for 3D Human Pose Estimation in VideoPoster271 citations
273. Escaping Plato's Cave: 3D Shape From Adversarial RenderingPoster270 citations
274. Few-Shot Image Recognition With Knowledge TransferPoster270 citations
275. Free-Form Video Inpainting With 3D Gated Convolution and Temporal PatchGANPoster270 citations
276. MeteorNet: Deep Learning on Dynamic 3D Point Cloud SequencesOral270 citations
277. Adversarial Representation Learning for Text-to-Image MatchingPoster267 citations
278. Mask-ShadowGAN: Learning to Remove Shadows From Unpaired DataPoster267 citations
279. End-to-End Hand Mesh Recovery From a Monocular RGB ImagePoster265 citations
280. DADA: Depth-Aware Domain Adaptation in Semantic SegmentationPoster263 citations
281. Self-Training and Adversarial Background Regularization for Unsupervised Domain Adaptive One-Stage Object DetectionOral263 citations
282. Significance-Aware Information Bottleneck for Domain Adaptive Semantic SegmentationPoster262 citations
283. Generative Adversarial Minority OversamplingPoster260 citations
284. Auto-FPN: Automatic Network Architecture Adaptation for Object Detection Beyond ClassificationPoster259 citations
285. P-MVSNet: Learning Patch-Wise Matching Confidence Aggregation for Multi-View StereoPoster259 citations
286. Sparse and Imperceivable Adversarial AttacksPoster259 citations
287. Second-Order Non-Local Attention Networks for Person Re-IdentificationPoster255 citations
288. TextDragon: An End-to-End Framework for Arbitrary Shaped Text SpottingPoster255 citations
289. Dynamic Graph Attention for Referring Expression ComprehensionOral254 citations
290. InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-PastingPoster253 citations
291. Vehicle Re-Identification With Viewpoint-Aware Metric LearningPoster253 citations
292. Foreground-Aware Pyramid Reconstruction for Alignment-Free Occluded Person Re-IdentificationPoster252 citations
293. Mask-Guided Attention Network for Occluded Pedestrian DetectionPoster252 citations
294. Towards Multi-Pose Guided Virtual Try-On NetworkPoster252 citations
295. Deep Optics for Monocular Depth Estimation and 3D Object DetectionPoster251 citations
296. AMP: Adaptive Masked Proxies for Few-Shot SegmentationPoster250 citations
297. Beyond Human Parts: Dual Part-Aligned Representations for Person Re-IdentificationPoster250 citations
298. Indices Matter: Learning to Index for Deep Image MattingPoster250 citations
299. Lifelong GAN: Continual Learning for Conditional Image GenerationPoster250 citations
300. Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and AdaptationPoster248 citations
301. Few-Shot Adaptive Gaze EstimationOral248 citations
302. Hierarchy Parsing for Image CaptioningPoster248 citations
303. Transductive Episodic-Wise Adaptive Metric for Few-Shot LearningPoster248 citations
304. Multi-Level Bottom-Top and Top-Bottom Feature Fusion for Crowd CountingPoster247 citations
305. Spatio-Temporal Filter Adaptive Network for Video DeblurringPoster247 citations
306. Deep Mesh Reconstruction From Single RGB Images via Topology Modification NetworksPoster246 citations
307. Deep Single-Image Portrait RelightingPoster246 citations
308. Joint Learning of Saliency Detection and Weakly Supervised Semantic SegmentationPoster246 citations
309. Motion Guided Attention for Video Salient Object DetectionPoster246 citations
310. Hierarchical Point-Edge Interaction Network for Point Cloud Semantic SegmentationPoster245 citations
311. Perspective-Guided Convolution Networks for Crowd CountingPoster245 citations
312. Human Motion Prediction via Spatio-Temporal InpaintingPoster244 citations
313. Drive&Act: A Multi-Modal Dataset for Fine-Grained Driver Behavior Recognition in Autonomous VehiclesPoster243 citations
314. One-Shot Neural Architecture Search via Self-Evaluated Template NetworkPoster243 citations
315. Temporal Attentive Alignment for Large-Scale Video Domain AdaptationOral243 citations
316. USIP: Unsupervised Stable Interest Point Detection From 3D Point CloudsPoster243 citations
317. DANet: Divergent Activation for Weakly Supervised Object LocalizationPoster242 citations
318. Deep Comprehensive Correlation Mining for Image ClusteringPoster242 citations
319. Joint Group Feature Selection and Discriminative Filter Learning for Robust Visual Object TrackingPoster242 citations
320. Transferable Contrastive Network for Generalized Zero-Shot LearningPoster241 citations
321. Weakly Aligned Cross-Modal Learning for Multispectral Pedestrian DetectionPoster241 citations
322. Dual Attention Matching for Audio-Visual Event LocalizationOral240 citations
323. Co-Separating Sounds of Visual ObjectsPoster239 citations
324. Drop to Adapt: Learning Discriminative Features for Unsupervised Domain AdaptationPoster239 citations
325. Image Generation From Small Datasets via Batch Statistics AdaptationPoster239 citations
326. Unsupervised Multi-Task Feature Learning on Point CloudsPoster239 citations
327. Prior-Aware Neural Network for Partially-Supervised Multi-Organ Segmentation238 citations
328. Selectivity or Invariance: Boundary-Aware Salient Object DetectionPoster237 citations
329. How Do Neural Networks See Depth in Single Images?Poster236 citations
330. Shadow Removal via Shadow Image DecompositionPoster236 citations
331. Structured Prediction Helps 3D Human Motion ModellingPoster236 citations
332. Instance-Guided Context Rendering for Cross-Domain Person Re-IdentificationPoster233 citations
333. Temporal Recurrent Networks for Online Action DetectionPoster233 citations
334. Controllable Video Captioning With POS Sequence Guidance Based on Gated Fusion NetworkPoster232 citations
335. Distillation-Based Training for Multi-Exit ArchitecturesOral232 citations
336. What Would You Expect? Anticipating Egocentric Actions With Rolling-Unrolling LSTMs and Modality AttentionOral231 citations
337. Learning Relationships for Multi-View 3D Object RecognitionPoster230 citations
338. 'Skimming-Perusal' Tracking: A Framework for Real-Time and Robust Long-Term TrackingPoster229 citations
339. Knowledge Distillation via Route Constrained OptimizationOral229 citations
340. Deep Tensor ADMM-Net for Snapshot Compressive ImagingPoster228 citations
341. Improved Conditional VRNNs for Video PredictionPoster228 citations
342. Few-Shot Learning With Embedded Class Models and Shot-Free Meta TrainingPoster227 citations
343. 3D-LaneNet: End-to-End 3D Multiple Lane DetectionPoster226 citations
344. Specifying Object Attributes and Relations in Interactive Scene GenerationOral226 citations
345. DenseRaC: Joint 3D Pose and Shape Estimation by Dense Render-and-CompareOral224 citations
346. Incremental Learning Using Conditional Adversarial NetworksPoster224 citations
347. Neural Inter-Frame Compression for Video CodingPoster224 citations
348. Cross-Domain Adaptation for Animal Pose EstimationOral223 citations
349. Convolutional Character NetworksPoster222 citations
350. A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation From a Single Depth ImagePoster221 citations
351. Learning a Mixture of Granularity-Specific Experts for Fine-Grained CategorizationPoster221 citations
352. Unsupervised Out-of-Distribution Detection by Maximum Classifier DiscrepancyPoster221 citations
353. Task-Driven Modular Networks for Zero-Shot Compositional LearningPoster219 citations
354. AdaptIS: Adaptive Instance Selection NetworkPoster217 citations
355. Self-Guided Network for Fast Image DenoisingPoster217 citations
356. Grouped Spatial-Temporal Aggregation for Efficient Action RecognitionPoster215 citations
357. Person-in-WiFi: Fine-Grained Person Perception Using WiFiPoster215 citations
358. From Open Set to Closed Set: Counting Objects by Spatial Divide-and-ConquerPoster214 citations
359. Human Mesh Recovery From Monocular Images via a Skeleton-Disentangled RepresentationPoster214 citations
360. Language-Conditioned Graph Networks for Relational ReasoningPoster214 citations
361. Relational Attention Network for Crowd CountingPoster214 citations
362. Scalable Verified Training for Provably Robust Image ClassificationPoster214 citations
363. Progressive Reconstruction of Visual Structure for Image InpaintingPoster213 citations
364. Detecting the Unexpected via Image ResynthesisPoster212 citations
365. End-to-End Wireframe ParsingPoster212 citations
366. Graph-Based Object Classification for Neuromorphic Vision SensingPoster210 citations
367. Noise Flow: Noise Modeling With Conditional Normalizing FlowsOral209 citations
368. TASED-Net: Temporally-Aggregating Spatial Encoder-Decoder Network for Video Saliency DetectionPoster209 citations
369. Unpaired Image Captioning via Scene Graph AlignmentsPoster209 citations
370. Extreme View SynthesisOral208 citations
371. SSF-DAN: Separated Semantic Feature Based Domain Adaptation Network for Semantic SegmentationPoster208 citations
372. Weakly-Supervised Action Localization With Background ModelingPoster208 citations
373. 3C-Net: Category Count and Center Loss for Weakly-Supervised Action LocalizationPoster207 citations
374. Adversarial Robustness vs. Model Compression, or Both?Poster207 citations
375. CAMEL: A Weakly Supervised Learning Framework for Histopathology Image Segmentation207 citations
376. Presence-Only Geographical Priors for Fine-Grained Image ClassificationPoster207 citations
377. Topological Map Extraction From Overhead ImagesPoster206 citations
378. PAMTRI: Pose-Aware Multi-Task Learning for Vehicle Re-Identification Using Highly Randomized Synthetic DataPoster205 citations
379. Transferability and Hardness of Supervised Classification TasksOral205 citations
380. Grounded Human-Object Interaction Hotspots From VideoPoster204 citations
381. Toyota Smarthome: Real-World Activities of Daily LivingPoster204 citations
382. Learning to Paint With Model-Based Deep Reinforcement LearningPoster203 citations
383. VTNFP: An Image-Based Virtual Try-On Network With Body and Clothing Feature PreservationPoster203 citations
384. DUP-Net: Denoiser and Upsampler Network for 3D Adversarial Point Clouds DefensePoster202 citations
385. Counterfactual Critic Multi-Agent Training for Scene Graph GenerationOral200 citations
386. Context-Aware Image Matting for Simultaneous Foreground and Alpha EstimationPoster199 citations
387. Monocular 3D Human Pose Estimation by Generation and Ordinal RankingPoster198 citations
388. Variational Few-Shot LearningPoster195 citations
389. Neural 3D Morphable Models: Spiral Convolutional Networks for 3D Shape Representation Learning and GenerationPoster194 citations
390. Content and Style Disentanglement for Artistic Style TransferPoster193 citations
391. Switchable Whitening for Deep Representation LearningPoster193 citations
392. 3D Instance Segmentation via Multi-Task Metric LearningOral192 citations
393. Adaptive Density Map Generation for Crowd CountingPoster192 citations
394. RelGAN: Multi-Domain Image-to-Image Translation via Relative AttributesPoster190 citations
395. Adversarial Defense by Restricting the Hidden Space of Deep Neural NetworksPoster189 citations
396. Learning Joint 2D-3D Representations for Depth CompletionPoster189 citations
397. Event-Based Motion Segmentation by Motion CompensationPoster188 citations
398. Robust Change CaptioningOral188 citations
399. Self-Critical Attention Learning for Person Re-IdentificationPoster188 citations
400. Symmetry-Constrained Rectification Network for Scene Text RecognitionPoster186 citations
401. A Novel Unsupervised Camera-Aware Domain Adaptation Framework for Person Re-IdentificationPoster185 citations
402. LayoutVAE: Stochastic Scene Layout Generation From a Label SetPoster185 citations
403. Towards Adversarially Robust Object DetectionPoster185 citations
404. WSOD2: Learning Bottom-Up and Top-Down Objectness Distillation for Weakly-Supervised Object DetectionPoster185 citations
405. Bilinear Attention Networks for Person RetrievalPoster184 citations
406. Fine-Grained Action Retrieval Through Multiple Parts-of-Speech EmbeddingsPoster184 citations
407. Three-D Safari: Learning to Estimate Zebra Pose, Shape, and Texture From Images "In the Wild"Poster184 citations
408. Collect and Select: Semantic Alignment Metric Learning for Few-Shot LearningPoster183 citations
409. Copy-and-Paste Networks for Deep Video InpaintingPoster183 citations
410. Sampling-Free Epistemic Uncertainty Estimation Using Approximated Variance PropagationOral183 citations
411. Attribute Attention for Semantic Disambiguation in Zero-Shot LearningPoster181 citations
412. Relation Parsing Neural Network for Human-Object Interaction DetectionPoster181 citations
413. Deep Clustering by Gaussian Mixture Variational Autoencoders With Graph EmbeddingPoster180 citations
414. Detecting Photoshopped Faces by Scripting PhotoshopPoster180 citations
415. SROBB: Targeted Perceptual Loss for Single Image Super-ResolutionPoster180 citations
416. Self-Supervised Difference Detection for Weakly-Supervised Semantic SegmentationPoster180 citations
417. Zero-Shot Grounding of Objects From Natural Language QueriesOral180 citations
418. Bridging the Domain Gap for Ground-to-Aerial Image MatchingPoster179 citations
419. Kernel Modeling Super-Resolution on Real Low-Resolution ImagesPoster178 citations
420. Spectral Feature Transformation for Person Re-IdentificationPoster178 citations
421. Active Learning for Deep Detection Neural NetworksPoster176 citations
422. Adaptive Context Network for Scene ParsingPoster176 citations
423. No-Frills Human-Object Interaction Detection: Factorization, Layout Encodings, and Training TechniquesPoster176 citations
424. On Network Design Spaces for Visual RecognitionPoster175 citations
425. Total Denoising: Unsupervised Learning of 3D Point Cloud CleaningPoster175 citations
426. ARGAN: Attentive Recurrent Generative Adversarial Network for Shadow Detection and RemovalPoster174 citations
427. Live Face De-Identification in VideoOral174 citations
428. Self-Supervised Moving Vehicle Tracking With Stereo SoundPoster174 citations
429. Improved Techniques for Training Adaptive Deep NetworksPoster172 citations
430. Improving Pedestrian Attribute Recognition With Weakly-Supervised Multi-Scale Attribute-Specific LocalizationPoster172 citations
431. Convolutional Sequence Generation for Skeleton-Based Action SynthesisPoster171 citations
432. LIP: Local Importance-Based PoolingPoster171 citations
433. RIO: 3D Object Instance Re-Localization in Changing Indoor EnvironmentsOral171 citations
434. COCO-GAN: Generation by Parts via Conditional CoordinatingOral170 citations
435. Deep Residual Learning in the JPEG Transform DomainPoster170 citations
436. Image Synthesis From Reconfigurable Layout and StylePoster170 citations
437. Localization of Deep Inpainting Using High-Pass Fully Convolutional NetworkPoster170 citations
438. Making the Invisible Visible: Action Recognition Through Walls and OcclusionsPoster170 citations
439. Robust Person Re-Identification by Modelling Feature UncertaintyPoster169 citations
440. Rethinking Zero-Shot Learning: A Conditional Visual Classification PerspectivePoster167 citations
441. HistoSegNet: Semantic Segmentation of Histological Tissue Type in Whole Slide Images166 citations
442. Interactive Sketch & Fill: Multiclass Sketch-to-Image TranslationPoster166 citations
443. Multi-Agent Reinforcement Learning Based Frame Sampling for Effective Untrimmed Video RecognitionOral165 citations
444. SegSort: Segmentation by Discriminative Sorting of SegmentsPoster165 citations
445. Co-Segmentation Inspired Attention Networks for Video-Based Person Re-IdentificationPoster164 citations
446. Detecting Unseen Visual Relations Using AnalogiesPoster164 citations
447. HEMlets Pose: Learning Part-Centric Heatmap Triplets for Accurate 3D Human Pose EstimationPoster164 citations
448. Neural Inverse Rendering of an Indoor Scene From a Single ImagePoster164 citations
449. Disentangled Image MattingPoster163 citations
450. Learn to Scale: Generating Multipolar Normalized Density Maps for Crowd CountingPoster163 citations
451. Unsupervised Domain Adaptation via Regularized Conditional AlignmentOral163 citations
452. Bilateral Adversarial Training: Towards Fast Training of More Robust Models Against Adversarial AttacksPoster162 citations
453. Learning Spatial Awareness to Improve Crowd CountingOral162 citations
454. Learning to See Moving Objects in the DarkPoster162 citations
455. Multi-Angle Point Cloud-VAE: Unsupervised Feature Learning for 3D Point Clouds From Multiple Angles by Joint Self-Reconstruction and Half-to-Half PredictionPoster162 citations
456. Re-ID Driven Localization Refinement for Person SearchPoster162 citations
457. AutoFocus: Efficient Multi-Scale InferencePoster161 citations
458. Deep Parametric Indoor Lighting EstimationPoster161 citations
459. Unsupervised Deep Learning for Structured Shape MatchingOral161 citations
460. GODS: Generalized One-Class Discriminative Subspaces for Anomaly DetectionPoster160 citations
461. Learning Compositional Neural Information Fusion for Human ParsingPoster160 citations
462. Deep Contextual Attention for Human-Object Interaction DetectionPoster159 citations
463. Deep Floor Plan Recognition Using a Multi-Task Network With Room-Boundary-Guided AttentionPoster159 citations
464. Towards Precise End-to-End Weakly Supervised Object Detection NetworkPoster159 citations
465. CamNet: Coarse-to-Fine Retrieval for Camera Re-LocalizationPoster158 citations
466. Embedded Block Residual Network: A Recursive Restoration Model for Single-Image Super-ResolutionPoster158 citations
467. Reciprocal Multi-Layer Subspace Learning for Multi-View ClusteringPoster158 citations
468. Guessing Smart: Biased Sampling for Efficient Black-Box Adversarial AttacksPoster157 citations
469. ShapeMask: Learning to Segment Novel Objects by Refining Shape PriorsOral156 citations
470. What Else Can Fool Deep Learning? Addressing Color Constancy Errors on Deep Neural Network PerformancePoster155 citations
471. GarNet: A Two-Stream Network for Fast and Accurate 3D Cloth DrapingPoster154 citations
472. Semi-Supervised Video Salient Object Detection Using Pseudo-LabelsPoster154 citations
473. Deep Learning for Seeing Through Window With RaindropsPoster153 citations
474. Deep Reinforcement Active Learning for Human-in-the-Loop Person Re-IdentificationOral153 citations
475. 3DPeople: Modeling the Geometry of Dressed HumansPoster152 citations
476. Efficient Learning on Point Clouds With Basis Point SetsPoster152 citations
477. MonoLoco: Monocular 3D Pedestrian Localization and Uncertainty EstimationPoster152 citations
478. Moulding Humans: Non-Parametric 3D Human Shape Estimation From Single ImagesPoster152 citations
479. See-Through-Text Grouping for Referring Image SegmentationPoster152 citations
480. Towards Unconstrained End-to-End Text SpottingOral152 citations
481. BAE-NET: Branched Autoencoder for Shape Co-SegmentationPoster151 citations
482. Ground-to-Aerial Image Geo-Localization With a Hard Exemplar Reweighting Triplet LossPoster151 citations
483. Where Is My Mirror?Poster151 citations
484. Generative Multi-View Human Action RecognitionOral150 citations
485. Learning Compositional Representations for Few-Shot RecognitionPoster149 citations
486. InGAN: Capturing and Retargeting the "DNA" of a Natural ImageOral148 citations
487. Towards Bridging Semantic Gap to Improve Semantic SegmentationPoster148 citations
488. Onion-Peel Networks for Deep Video CompletionPoster147 citations
489. Physics-Based Rendering for Improving Robustness to RainPoster147 citations
490. Semantic Stereo Matching With Pyramid Cost VolumesPoster147 citations
491. Attentional Neural Fields for Crowd CountingPoster146 citations
492. Bayesian Graph Convolution LSTM for Skeleton Based Action RecognitionPoster146 citations
493. Deep Multi-Model Fusion for Single-Image DehazingPoster146 citations
494. Ego-Pose Estimation and Forecasting As Real-Time PD ControlPoster145 citations
495. Holistic++ Scene Understanding: Single-View 3D Holistic Scene Parsing and Human Pose Estimation With Human-Object Interaction and Physical CommonsensePoster145 citations
496. Understanding Human Gaze Communication by Spatio-Temporal Graph ReasoningPoster145 citations
497. Few-Shot Learning With Global Class RepresentationsPoster144 citations
498. Tag2Pix: Line Art Colorization Using Text Tag With SECat and Changing LossPoster144 citations
499. Towards Unsupervised Image Captioning With Shared Multimodal EmbeddingsPoster144 citations
500. Unsupervised Person Re-Identification by Camera-Aware Similarity Consistency LearningPoster144 citations
501. Learning Rich Features at High-Speed for Single-Shot Object DetectionPoster143 citations
502. Anchor Diffusion for Unsupervised Video Object SegmentationPoster142 citations
503. Co-Mining: Deep Face Recognition With Noisy LabelsOral142 citations
504. Exploiting Temporal Consistency for Real-Time Video Depth EstimationPoster142 citations
505. Learning Single Camera Depth Estimation Using Dual-PixelsOral142 citations
506. SPGNet: Semantic Prediction Guidance for Scene ParsingPoster142 citations
507. xR-EgoPose: Egocentric 3D Human Pose From an HMD CameraOral142 citations
508. Learning Deep Priors for Image DehazingPoster140 citations
509. Addressing Model Vulnerability to Distributional Shifts Over Image Transformation SetsPoster139 citations
510. JPEG Artifacts Reduction via Deep Convolutional Sparse CodingPoster139 citations
511. SBSGAN: Suppression of Inter-Domain Background Shift for Person Re-IdentificationPoster139 citations
512. DynamoNet: Dynamic Action and Motion NetworkOral138 citations
513. Explaining the Ambiguity of Object Detection and 6D Pose From Visual DataPoster138 citations
514. A Learned Representation for Scalable Vector GraphicsPoster137 citations
515. Action Assessment by Joint Relation GraphsOral137 citations
516. C3DPO: Canonical 3D Pose Networks for Non-Rigid Structure From MotionOral137 citations
517. Counting With Focus for FreePoster137 citations
518. Object Guided External Memory Network for Video Object DetectionPoster137 citations
519. Semantic-Aware Knowledge Preservation for Zero-Shot Sketch-Based Image RetrievalPoster137 citations
520. Expert Sample Consensus Applied to Camera Re-LocalizationPoster136 citations
521. PARN: Position-Aware Relation Networks for Few-Shot LearningPoster136 citations
522. Reflective Decoding Network for Image CaptioningPoster136 citations
523. Beyond Cartesian Representations for Local DescriptorsPoster135 citations
524. Dynamic Points Agglomeration for Hierarchical Point Sets LearningPoster135 citations
525. Explicit Shape Encoding for Real-Time Instance SegmentationPoster135 citations
526. Recurrent U-Net for Resource-Constrained SegmentationPoster135 citations
527. Single-Network Whole-Body Pose EstimationPoster135 citations
528. Weakly Supervised Temporal Action Localization Through Contrast Based Evaluation NetworksPoster135 citations
529. Multinomial Distribution Learning for Effective Neural Architecture SearchOral134 citations
530. Universal Perturbation Attack Against Image RetrievalPoster134 citations
531. Align, Attend and Locate: Chest X-Ray Diagnosis via Contrast Induced Attention Network With Limited Supervision133 citations
532. DAGMapper: Learning to Map by Discovering Lane TopologyPoster133 citations
533. Discriminative Feature Learning With Consistent Attention Regularization for Person Re-IdentificationPoster133 citations
534. Distilling Knowledge From a Deep Pose Regressor NetworkPoster133 citations
535. Semantic Adversarial Attacks: Parametric Transformations That Fool Deep ClassifiersPoster133 citations
536. Universal Semi-Supervised Semantic SegmentationPoster133 citations
537. Weakly Supervised Object Detection With Segmentation CollaborationPoster132 citations
538. Deep Learning for Light Field Saliency DetectionPoster131 citations
539. Deep Metric Learning With Tuplet Margin LossPoster131 citations
540. Imitation Learning for Human Pose PredictionPoster131 citations
541. Online Model Distillation for Efficient Video InferencePoster131 citations
542. Photo-Realistic Facial Details Synthesis From Single ImageOral131 citations
543. TexturePose: Supervising Human Mesh Estimation With Texture ConsistencyPoster131 citations
544. Unsupervised Graph Association for Person Re-IdentificationPoster131 citations
545. FDA: Feature Disruptive AttackPoster130 citations
546. LADN: Local Adversarial Disentangling Network for Facial Makeup and De-MakeupPoster130 citations
547. Controllable Artistic Text Style Transfer via Shape-Matching GANOral129 citations
548. Deep Blind Hyperspectral Image FusionPoster129 citations
549. Predicting 3D Human Dynamics From VideoPoster129 citations
550. C-MIDN: Coupled Multiple Instance Detection Network With Segmentation Guidance for Weakly Supervised Object DetectionPoster128 citations
551. Learning Feature-to-Feature Translator by Alternating Back-Propagation for Generative Zero-Shot LearningPoster127 citations
552. Wasserstein GAN With Quadratic Transport CostPoster126 citations
553. Deep SR-ITM: Joint Learning of Super-Resolution and Inverse Tone-Mapping for 4K UHD HDR ApplicationsOral125 citations
554. FW-GAN: Flow-Navigated Warping GAN for Video Virtual Try-OnPoster125 citations
555. MIC: Mining Interclass Characteristics for Improved Metric LearningPoster125 citations
556. Stochastic Attraction-Repulsion Embedding for Large Scale Image LocalizationPoster125 citations
557. Boundless: Generative Adversarial Networks for Image ExtensionPoster124 citations
558. MMAct: A Large-Scale Dataset for Cross Modal Human Action UnderstandingPoster124 citations
559. Pushing the Frontiers of Unconstrained Crowd Counting: New Dataset and Benchmark MethodPoster124 citations
560. Guided Image-to-Image Translation With Bi-Directional Feature TransformationPoster123 citations
561. NOTE-RCNN: NOise Tolerant Ensemble RCNN for Semi-Supervised Object DetectionPoster123 citations
562. Saliency-Guided Attention Network for Image-Sentence MatchingPoster123 citations
563. Through-Wall Human Mesh Recovery Using Radio SignalsPoster123 citations
564. Bayesian Relational Memory for Semantic Visual NavigationPoster122 citations
565. Deep Meta Learning for Real-Time Target-Aware Visual TrackingPoster122 citations
566. Learning Filter Basis for Convolutional Neural Network CompressionPoster122 citations
567. Modeling Inter and Intra-Class Relations in the Triplet Loss for Zero-Shot LearningPoster122 citations
568. Hyperpixel Flow: Semantic Correspondence With Multi-Layer Neural FeaturesPoster121 citations
569. DSConv: Efficient Convolution OperatorPoster120 citations
570. Learning Fixed Points in Generative Adversarial Networks: From Image-to-Image Translation to Disease Detection and LocalizationPoster120 citations
571. Weakly Supervised Energy-Based Learning for Action SegmentationOral120 citations
572. ACE: Adapting to Changing Environments for Semantic SegmentationPoster119 citations
573. Align2Ground: Weakly Supervised Phrase Grounding Guided by Image-Caption AlignmentPoster119 citations
574. Canonical Surface Mapping via Geometric Cycle ConsistencyPoster119 citations
575. Hallucinating IDT Descriptors and I3D Optical Flow Features for Action Recognition With CNNsPoster119 citations
576. Leveraging Long-Range Temporal Relationships Between Proposals for Video Object DetectionPoster119 citations
577. Universal Adversarial Perturbation via Prior Driven Uncertainty ApproximationOral119 citations
578. Disentangling Propagation and Generation for Video PredictionPoster118 citations
579. Employing Deep Part-Object Relationships for Salient Object DetectionPoster118 citations
580. Fashion Retrieval via Graph Reasoning Networks on a Similarity PyramidOral118 citations
581. Talking With Hands 16.2M: A Large-Scale Dataset of Synchronized Body-Finger Motion and Audio for Conversational Motion Analysis and SynthesisPoster118 citations
582. Scene Graph Prediction With Limited LabelsPoster117 citations
583. Semantics-Enhanced Adversarial Nets for Text-to-Image SynthesisPoster117 citations
584. Adversarial Fine-Grained Composition Learning for Unseen Attribute-Object RecognitionPoster116 citations
585. Predicting the Future: A Jointly Learnt Model for Action AnticipationPoster116 citations
586. Attacking Optical FlowPoster115 citations
587. Floor-SP: Inverse CAD for Floorplans by Sequential Room-Wise Shortest PathPoster115 citations
588. Learning to Collocate Neural Modules for Image CaptioningPoster115 citations
589. Many Task Learning With Task RoutingOral115 citations
590. Watch, Listen and Tell: Multi-Modal Weakly Supervised Dense Event CaptioningPoster115 citations
591. Fashion++: Minimal Edits for Outfit ImprovementPoster114 citations
592. Very Long Natural Scenery Image Prediction by OutpaintingPoster114 citations
593. Learning Similarity Conditions Without Explicit SupervisionPoster113 citations
594. Progressive Sparse Local Attention for Video Object DetectionPoster113 citations
595. Spatio-Temporal Fusion Based Convolutional Sequence Learning for Lip ReadingPoster113 citations
596. Joint Syntax Representation Learning and Visual Cue Translation for Video CaptioningPoster112 citations
597. Learning an Event Sequence Embedding for Dense Event-Based Deep StereoOral112 citations
598. Equivariant Multi-View NetworksOral111 citations
599. Fair Loss: Margin-Aware Reinforcement Learning for Deep Face RecognitionPoster111 citations
600. Towards Interpretable Face RecognitionOral111 citations
601. Adaptive Reconstruction Network for Weakly Supervised Referring Expression GroundingPoster110 citations
602. Diverse Image Synthesis From Semantic Layouts via Conditional IMLEPoster110 citations
603. Multimodal Style Transfer via Graph CutsPoster110 citations
604. U-CAM: Visual Explanation Using Uncertainty Based Class Activation MapsPoster110 citations
605. Co-Evolutionary Compression for Unpaired Image TranslationPoster109 citations
606. Enriched Feature Guided Refinement Network for Object DetectionPoster109 citations
607. Online Hyper-Parameter Learning for Auto-Augmentation StrategyPoster109 citations
608. DeceptionNet: Network-Driven Domain RandomizationPoster108 citations
609. Efficient Segmentation: Learning Downsampling Near Semantic BoundariesPoster108 citations
610. MVSCRF: Learning Multi-View Stereo With Conditional Random FieldsPoster108 citations
611. Vision-Infused Deep Audio InpaintingPoster108 citations
612. DeCaFA: Deep Convolutional Cascade for Face Alignment in the WildPoster107 citations
613. Dynamic Context Correspondence Network for Semantic AlignmentPoster107 citations
614. End-to-End CAD Model Retrieval and 9DoF Alignment in 3D ScansPoster106 citations
615. SceneGraphNet: Neural Message Passing for 3D Indoor Scene AugmentationPoster106 citations
616. AGSS-VOS: Attention Guided Single-Shot Video Object SegmentationPoster105 citations
617. Aligning Latent Spaces for 3D Hand Pose EstimationPoster105 citations
618. SO-HandNet: Self-Organizing Network for 3D Hand Pose Estimation With Semi-Supervised LearningPoster105 citations
619. Shape-Aware Human Pose and Shape Reconstruction Using Multi-View ImagesPoster105 citations
620. Unsupervised Video Interpolation Using Cycle ConsistencyPoster105 citations
621. Joint Acne Image Grading and Counting via Label Distribution Learning104 citations
622. Neural Turtle Graphics for Modeling City Road LayoutsOral104 citations
623. Stochastic Filter Groups for Multi-Task CNNs: Learning Specialist and Generalist Convolution KernelsOral104 citations
624. Hierarchical Shot DetectorPoster103 citations
625. Multi-View Stereo by Temporal Nonparametric FusionPoster103 citations
626. Aggregation via Separation: Boosting Facial Landmark Detector With Semi-Supervised Style TranslationPoster102 citations
627. Delving Into Robust Object Detection From Unmanned Aerial Vehicles: A Deep Nuisance Disentanglement ApproachPoster102 citations
628. Spectral Regularization for Combating Mode Collapse in GANsPoster102 citations
629. Transformable Bottleneck NetworksOral102 citations
630. A Deep Cybersickness Predictor Based on Brain Signal Analysis for Virtual Reality ContentsPoster101 citations
631. An Internal Learning Approach to Video InpaintingPoster101 citations
632. EM-Fusion: Dynamic Object-Level SLAM With Probabilistic Data AssociationPoster101 citations
633. Transferable Representation Learning in Vision-and-Language NavigationPoster101 citations
634. Visualization of Convolutional Neural Networks for Monocular Depth EstimationPoster101 citations
635. Mop Moire Patterns Using MopNetPoster100 citations
636. Shapeglot: Learning Language for Shape DifferentiationPoster100 citations
637. TAPA-MVS: Textureless-Aware PAtchMatch Multi-View StereoPoster100 citations
638. ViSiL: Fine-Grained Spatio-Temporal Video Similarity LearningOral100 citations
639. Adversarial Defense via Learning to Generate Diverse AttacksPoster99 citations
640. Compositional Video PredictionPoster99 citations
641. Learning Object-Specific Distance From a Monocular ImagePoster99 citations
642. Orientation-Aware Semantic Segmentation on Icosahedron SpheresPoster99 citations
643. SANet: Scene Agnostic Network for Camera LocalizationPoster99 citations
644. Attribute Manipulation Generative Adversarial Networks for Fashion ImagesPoster98 citations
645. DMM-Net: Differentiable Mask-Matching Network for Video Object SegmentationPoster98 citations
646. Transductive Learning for Zero-Shot Object DetectionOral98 citations
647. ClusterSLAM: A SLAM Backend for Simultaneous Rigid Body Clustering and Motion EstimationPoster97 citations
648. Deep Meta Functionals for Shape RepresentationPoster97 citations
649. Recover and Identify: A Generative Dual Model for Cross-Resolution Person Re-IdentificationPoster97 citations
650. Recursive Visual Sound Separation Using Minus-Plus NetPoster97 citations
651. Wavelet Domain Style Transfer for an Effective Perception-Distortion Tradeoff in Single Image Super-ResolutionOral97 citations
652. Asymmetric Cross-Guided Attention Network for Actor and Action Video Segmentation From Natural Language QueryPoster96 citations
653. AutoDispNet: Improving Disparity Estimation With AutoMLPoster95 citations
654. Skeleton-Aware 3D Human Shape Reconstruction From Point CloudsPoster95 citations
655. Temporal Structure Mining for Weakly Supervised Action DetectionPoster95 citations
656. Fooling Network Interpretation in Image ClassificationPoster94 citations
657. SpaceNet MVOI: A Multi-View Overhead Imagery DatasetPoster94 citations
658. A Closed-Form Solution to Universal Style TransferPoster93 citations
659. Accelerate CNN via Recursive Bayesian PruningPoster93 citations
660. AM-LFS: AutoML for Loss Function SearchPoster92 citations
661. DF2Net: A Dense-Fine-Finer Network for Detailed 3D Face ReconstructionPoster92 citations
662. DewarpNet: Single-Image Document Unwarping With Stacked 3D and 2D Regression NetworksPoster92 citations
663. Dynamic Kernel Distillation for Efficient Pose Estimation in VideosPoster92 citations
664. GeoStyle: Discovering Fashion Trends and EventsPoster92 citations
665. Compact Trilinear Interaction for Visual Question AnsweringPoster91 citations
666. Computational Hyperspectral Imaging Based on Dimension-Discriminative Low-Rank Tensor RecoveryPoster91 citations
667. Gated2Depth: Real-Time Dense Lidar From Gated ImagesOral91 citations
668. Looking to Relations for Future Trajectory ForecastPoster91 citations
669. Multi-Modality Latent Interaction Network for Visual Question AnsweringPoster91 citations
670. Physical Adversarial Textures That Fool Visual Object TrackingPoster91 citations
671. Teacher Supervises Students How to Learn From Partially Labeled Images for Facial Landmark DetectionPoster91 citations
672. Tell, Draw, and Repeat: Generating and Modifying Images Based on Continual Linguistic InstructionPoster91 citations
673. Action Recognition With Spatial-Temporal Discriminative Filter BanksPoster90 citations
674. Fingerspelling Recognition in the Wild With Iterative Visual AttentionPoster90 citations
675. Gaussian Affinity for Max-Margin Class Imbalanced LearningPoster90 citations
676. Generative Modeling for Small-Data Object DetectionOral90 citations
677. Guided Super-Resolution As Pixel-to-Pixel TransformationPoster90 citations
678. Non-Local ConvLSTM for Video Compression Artifact ReductionPoster90 citations
679. Optimizing the F-Measure for Threshold-Free Salient Object DetectionPoster90 citations
680. SPLINE-Net: Sparse Photometric Stereo Through Lighting Interpolation and Normal Estimation NetworksPoster90 citations
681. VrR-VG: Refocusing Visually-Relevant RelationshipsPoster90 citations
682. CDTB: A Color and Depth Visual Object Tracking Dataset and BenchmarkPoster89 citations
683. Semi-Supervised Learning by Augmented Distribution AlignmentOral89 citations
684. Uncertainty-Aware Audiovisual Activity Recognition Using Deep Bayesian Variational InferenceOral89 citations
685. Deep Graphical Feature Learning for the Feature Matching ProblemPoster88 citations
686. ERL-Net: Entangled Representation Learning for Single Image De-RainingPoster88 citations
687. Evaluating Robustness of Deep Image Super-Resolution Against Adversarial AttacksPoster88 citations
688. Fine-Grained Segmentation Networks: Self-Supervised Segmentation for Improved Long-Term Visual LocalizationPoster88 citations
689. SENSE: A Shared Encoder Network for Scene-Flow EstimationOral88 citations
690. AttPool: Towards Hierarchical Feature Representation in Graph Convolutional Networks via Attention MechanismPoster87 citations
691. Moving Indoor: Unsupervised Video Depth Learning in Challenging EnvironmentsPoster87 citations
692. Progressive-X: Efficient, Anytime, Multi-Model Fitting AlgorithmPoster87 citations
693. Convolutional Approximations to the General Non-Line-of-Sight Imaging OperatorOral86 citations
694. GLAMpoints: Greedily Learned Accurate Match Points86 citations
695. LAP-Net: Level-Aware Progressive Network for Image DehazingPoster86 citations
696. Make a Face: Towards Arbitrary High Fidelity Face ManipulationPoster86 citations
697. Targeted Mismatch Adversarial Attack: Query With a Flower to Retrieve the TowerPoster86 citations
698. A Quaternion-Based Certifiably Optimal Solution to the Wahba Problem With OutliersOral85 citations
699. Deep Meta Metric LearningPoster85 citations
700. FiNet: Compatible and Diverse Fashion Image InpaintingOral85 citations
701. Temporal Knowledge Propagation for Image-to-Video Person Re-IdentificationPoster85 citations
702. CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule RoutingPoster84 citations
703. Fast and Practical Neural Architecture SearchPoster84 citations
704. Metric Learning With HORDE: High-Order Regularizer for Deep EmbeddingsPoster84 citations
705. Sequential Latent Spaces for Modeling the Intention During Diverse Image CaptioningPoster84 citations
706. Unsupervised Learning of Landmarks by Descriptor Vector ExchangePoster84 citations
707. Attract or Distract: Exploit the Margin of Open SetPoster83 citations
708. Evolving Space-Time Neural Architectures for VideosPoster83 citations
709. Hyperspectral Image Reconstruction Using Deep External and Internal LearningPoster83 citations
710. Learning to Reconstruct 3D Manhattan Wireframes From a Single ImageOral83 citations
711. Sequential Adversarial Learning for Self-Supervised Deep Visual OdometryPoster83 citations
712. ACMM: Aligned Cross-Modal Memory for Few-Shot Image and Sentence MatchingPoster82 citations
713. Asynchronous Single-Photon 3D ImagingOral82 citations
714. On the Design of Black-Box Adversarial Examples by Leveraging Gradient-Free Optimization and Operator Splitting MethodPoster82 citations
715. Scalable Place Recognition Under Appearance Change for Autonomous DrivingOral82 citations
716. Creativity Inspired Zero-Shot LearningPoster81 citations
717. Deep Non-Rigid Structure From MotionOral81 citations
718. Dual Directed Capsule Network for Very Low Resolution Image RecognitionPoster81 citations
719. Joint Demosaicking and Denoising by Fine-Tuning of Bursts of Raw ImagesPoster81 citations
720. Making History Matter: History-Advantage Sequence Training for Visual DialogPoster81 citations
721. Learning Robust Facial Landmark Detection via Hierarchical Structured EnsemblePoster80 citations
722. Video Face Clustering With Unknown Number of ClustersPoster80 citations
723. A Dataset of Multi-Illumination Images in the WildPoster79 citations
724. Zero-Shot Anticipation for Instructional ActivitiesPoster79 citations
725. A Graph-Based Framework to Bridge Movies and SynopsesOral78 citations
726. Dynamic Anchor Feature Selection for Single-Shot Object DetectionPoster78 citations
727. Fast Object Detection in Compressed VideoPoster78 citations
728. Monocular Neural Image Based Rendering With Continuous View ControlPoster78 citations
729. SplitNet: Sim2Sim and Task2Task Transfer for Embodied Visual NavigationPoster78 citations
730. Vehicle Re-Identification in Aerial Imagery: Dataset and ApproachPoster78 citations
731. Cascaded Context Pyramid for Full-Resolution 3D Semantic Scene CompletionOral77 citations
732. Contextual Attention for Hand Detection in the WildPoster77 citations
733. GAN-Based Projector for Faster Recovery With Convergence Guarantees in Linear Inverse ProblemsPoster77 citations
734. Situational Fusion of Visual Representation for Visual NavigationPoster77 citations
735. Unsupervised High-Resolution Depth Learning From Videos With Dual NetworksPoster77 citations
736. DistInit: Learning Video Representations Without a Single Labeled VideoPoster75 citations
737. Embodied Amodal Recognition: Learning to Move to Perceive ObjectsPoster75 citations
738. Face-to-Parameter Translation for Game Character Auto-CreationPoster75 citations
739. ForkNet: Multi-Branch Volumetric Semantic Completion From a Single Depth ImagePoster75 citations
740. Group-Wise Deep Object Co-Segmentation With Co-Attention Recurrent Neural NetworkPoster75 citations
741. Local Supports Global: Deep Camera Relocalization With Sequence EnhancementPoster75 citations
742. SkyScapes Fine-Grained Semantic Understanding of Aerial ScenesPoster75 citations
743. Analyzing the Variety Loss in the Context of Probabilistic Trajectory PredictionPoster74 citations
744. Dynamic PET Image Reconstruction Using Nonnegative Matrix Factorization Incorporated With Deep Image PriorOral74 citations
745. Not All Parts Are Created Equal: 3D Pose Estimation by Modeling Bi-Directional Dependencies of Body PartsOral74 citations
746. AdvIT: Adversarial Frames Identifier Based on Temporal Consistency in VideosPoster73 citations
747. Delving Deep Into Hybrid Annotations for 3D Human Recovery in the WildPoster73 citations
748. Improving Adversarial Robustness via Guided Complement EntropyPoster73 citations
749. Siamese Networks: The Tale of Two ManifoldsOral73 citations
750. Attention-Based Autism Spectrum Disorder Screening With Privileged ModalityPoster72 citations
751. View Confusion Feature Learning for Person Re-IdentificationPoster72 citations
752. View N-Gram Network for 3D Object RetrievalPoster72 citations
753. CFSNet: Toward a Controllable Feature Space for Image RestorationPoster71 citations
754. Defending Against Universal Perturbations With Shared Adversarial TrainingPoster71 citations
755. Customizing Student Networks From Heterogeneous Teachers via Adaptive Knowledge AmalgamationPoster70 citations
756. Explaining Neural Networks Semantically and QuantitativelyOral70 citations
757. Fast Video Object Segmentation via Dynamic Targeting NetworkPoster70 citations
758. Multi-Class Part Parsing With Joint Boundary-Semantic AwarenessOral70 citations
759. OmniMVS: End-to-End Learning for Omnidirectional Stereo MatchingPoster70 citations
760. StartNet: Online Detection of Action Start in Untrimmed VideosPoster70 citations
761. Why Does a Visual Question Have Different Answers?Poster70 citations
762. 3D Face Modeling From Diverse Raw Scan DataOral69 citations
763. Deep Supervised Hashing With Anchor GraphPoster69 citations
764. 3D Scene Reconstruction With Multi-Layer Depth and Epipolar TransformersPoster68 citations
765. G3raphGround: Graph-Based Language GroundingPoster68 citations
766. UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task DistillationOral68 citations
767. VideoMem: Constructing, Analyzing, Predicting Short-Term and Long-Term Video MemorabilityPoster68 citations
768. CIIDefence: Defeating Adversarial Attacks by Fusing Class-Specific Image Inpainting and Image DenoisingPoster67 citations
769. Composite Shape Modeling via Latent Space FactorizationPoster67 citations
770. Image Aesthetic Assessment Based on Pairwise Comparison A Unified Approach to Score Regression, Binary Classification, and PersonalizationPoster67 citations
771. Label-PEnet: Sequential Label Propagation and Enhancement Networks for Weakly Supervised Instance SegmentationPoster67 citations
772. Personalized Fashion DesignPoster67 citations
773. TextPlace: Visual Place Recognition and Topological Localization Through Reading Scene TextsPoster67 citations
774. Bayesian Optimized 1-Bit CNNsPoster66 citations
775. Discriminative Feature Transformation for Occluded Pedestrian DetectionPoster66 citations
776. On the Over-Smoothing Problem of CNN Based Disparity EstimationPoster66 citations
777. SpatialSense: An Adversarially Crowdsourced Benchmark for Spatial Relation RecognitionPoster66 citations
778. A Deep Step Pattern Representation for Multimodal Retinal Image RegistrationPoster65 citations
779. Bridging the Gap Between Detection and Tracking: A Unified ApproachPoster65 citations
780. Face De-Occlusion Using 3D Morphable Model and Generative Adversarial NetworkPoster65 citations
781. Language-Agnostic Visual-Semantic EmbeddingsPoster65 citations
782. Object-Aware Instance Labeling for Weakly Supervised Object DetectionOral65 citations
783. Two-Stream Action Recognition-Oriented Video Super-ResolutionPoster65 citations
784. CompoNet: Learning to Generate the Unseen by Part Synthesis and CompositionPoster64 citations
785. From Strings to Things: Knowledge-Enabled VQA Model That Can Read and ReasonOral64 citations
786. Mono-SF: Multi-View Geometry Meets Single-View Depth for Monocular Scene Flow Estimation of Dynamic Traffic ScenesPoster64 citations
787. Unsupervised Microvascular Image Segmentation Using an Active Contours Mimicking Neural Network64 citations
788. Zero-Shot Emotion Recognition via Affective Structural EmbeddingPoster64 citations
789. A Geometry-Inspired Decision-Based AttackPoster63 citations
790. Chinese Street View Text: Large-Scale Chinese Text Reading With Partially Supervised LearningPoster63 citations
791. Deep Elastic Networks With Model Selection for Multi-Task LearningPoster63 citations
792. Enhancing Low Light Videos by Exploring High Sensitivity Camera NoisePoster63 citations
793. Fully Convolutional Pixel Adaptive Image DenoiserPoster63 citations
794. Learning to Rank Proposals for Object DetectionPoster63 citations
795. MONET: Multiview Semi-Supervised Keypoint Detection via Epipolar DivergencePoster63 citations
796. Photo-Realistic Monocular Gaze Redirection Using Generative Adversarial NetworksPoster63 citations
797. FACSIMILE: Fast and Accurate Scans From an Image in Less Than a SecondPoster62 citations
798. Hilbert-Based Generative Defense for Adversarial ExamplesPoster62 citations
799. Adversarial Learning With Margin-Based Triplet Embedding RegularizationPoster61 citations
800. Cap2Det: Learning to Amplify Weak Caption Supervision for Object DetectionPoster61 citations
801. SVD: A Large-Scale Short Video Dataset for Near-Duplicate Video RetrievalPoster61 citations
802. Semantic-Transferable Weakly-Supervised Endoscopic Lesions Segmentation61 citations
803. advPattern: Physical-World Attacks on Deep Person Re-Identification via Adversarially Transformable PatternsPoster61 citations
804. A Delay Metric for Video Object Detection: What Average Precision Fails to TellPoster60 citations
805. A Neural Network for Detailed Human Depth Estimation From a Single ImageOral60 citations
806. Deep Multiple-Attribute-Perceived Network for Real-World Texture RecognitionPoster60 citations
807. EvalNorm: Estimating Batch Normalization Statistics for EvaluationPoster60 citations
808. Surface Networks via General CoversPoster60 citations
809. Unsupervised Procedure Learning via Joint Dynamic SummarizationOral60 citations
810. Anchor Loss: Modulating Loss Scale Based on Prediction DifficultyOral59 citations
811. Bayesian Adaptive Superpixel SegmentationPoster59 citations
812. Deep Head Pose Estimation Using Synthetic Images and Partial Adversarial Domain Adaption for Continuous Label SpacesPoster59 citations
813. Geometric Disentanglement for Generative Latent Shape ModelsPoster59 citations
814. Is This the Right Place? Geometric-Semantic Pose Verification for Indoor Visual LocalizationPoster59 citations
815. On Boosting Single-Frame 3D Human Pose Estimation via Monocular VideosPoster59 citations
816. Prior Guided Dropout for Robust Visual Localization in Dynamic EnvironmentsPoster59 citations
817. Self-Supervised Representation Learning From Multi-Domain DataPoster59 citations
818. Structured Modeling of Joint Deep Feature and Prediction Refinement for Salient Object DetectionPoster59 citations
819. 3D-RelNet: Joint Object and Relational Network for 3D PredictionPoster58 citations
820. Distill Knowledge From NRSfM for Weakly Supervised 3D Pose LearningPoster58 citations
821. Hierarchical Self-Attention Network for Action Localization in VideosPoster58 citations
822. Neighborhood Preserving Hashing for Scalable Video RetrievalPoster58 citations
823. GLoSH: Global-Local Spherical Harmonics for Intrinsic Image DecompositionOral57 citations
824. S2GAN: Share Aging Factors Across Ages and Share Aging Trends Among IndividualsOral57 citations
825. Scoot: A Perceptual Metric for Facial SketchesPoster57 citations
826. UprightNet: Geometry-Aware Camera Orientation Estimation From Single ImagesPoster57 citations
827. A Differential Volumetric Approach to Multi-View Photometric StereoPoster56 citations
828. Face Video Deblurring Using 3D Facial PriorsOral56 citations
829. Human Attention in Image Captioning: Dataset and AnalysisPoster56 citations
830. SILCO: Show a Few Images, Localize the Common ObjectPoster56 citations
831. DUAL-GLOW: Conditional Flow-Based Generative Model for Modality Transfer55 citations
832. Laplace Landmark LocalizationPoster55 citations
833. Learning Temporal Action Proposals With Fewer LabelsPoster54 citations
834. Multi-Stage Pathological Image Classification Using Semantic Segmentation54 citations
835. Unsupervised Collaborative Learning of Keyframe Detection and Visual Odometry Towards Monocular Deep SLAMPoster54 citations
836. Attentional Feature-Pair Relation Networks for Accurate Face RecognitionPoster53 citations
837. Frame-to-Frame Aggregation of Active Regions in Web Videos for Weakly Supervised Semantic SegmentationPoster53 citations
838. FrameNet: Learning Local Canonical Frames of 3D Surfaces From a Single RGB ImagePoster53 citations
839. HBONet: Harmonious Bottleneck on Two Orthogonal DimensionsPoster53 citations
840. MVP Matching: A Maximum-Value Perfect Matching for Mining Hard Samples, With Application to Person Re-IdentificationPoster53 citations
841. Normalized Wasserstein for Mixture Distributions With Applications in Adversarial Learning and Domain AdaptationPoster53 citations
842. Perceptual Deep Depth Super-ResolutionPoster53 citations
843. Homography From Two Orientation- and Scale-Covariant FeaturesPoster52 citations
844. Person Search by Text Attribute Query As Zero-Shot LearningPoster52 citations
845. Conditional Coupled Generative Adversarial Networks for Zero-Shot Domain AdaptationPoster51 citations
846. DSIC: Deep Stereo Image CompressionOral50 citations
847. Dual Adversarial Inference for Text-to-Image SynthesisPoster50 citations
848. Generating Diverse and Descriptive Image Captions Using Visual ParaphrasesPoster50 citations
849. PLMP - Point-Line Minimal Problems in Complete Multi-View VisibilityOral50 citations
850. Self-Supervised Deep Depth DenoisingPoster50 citations
851. Self-Supervised Representation Learning via Neighborhood-Relational EncodingPoster50 citations
852. Towards Photorealistic Reconstruction of Highly Multiplexed Lensless ImagesOral50 citations
853. AVT: Unsupervised Learning of Transformation Equivariant Representations by Autoencoding Variational TransformationsPoster49 citations
854. Continual Learning by Asymmetric Loss Approximation With Single-Side OverestimationPoster49 citations
855. Differentiable Learning-to-Group Channels via Groupable Convolutional Neural NetworksPoster49 citations
856. Few-Shot Generalization for Single-Image 3D Reconstruction via PriorsPoster48 citations
857. Learning an Effective Equivariant 3D Descriptor Without SupervisionPoster48 citations
858. Learning to Jointly Generate and Separate ReflectionsPoster48 citations
859. A Camera That CNNs: Towards Embedded Neural Networks on Pixel Processor ArraysOral47 citations
860. Maximum-Margin Hamming HashingPoster47 citations
861. Memory-Based Neighbourhood Embedding for Visual RecognitionOral47 citations
862. Phrase Localization Without Paired Training ExamplesOral47 citations
863. SynDeMo: Synergistic Deep Feature Alignment for Joint Learning of Depth and Ego-MotionPoster47 citations
864. Transferable Semi-Supervised 3D Object Detection From RGB-D DataPoster47 citations
865. Budget-Aware Adapters for Multi-Domain LearningPoster46 citations
866. Learning Motion in Feature Space: Locally-Consistent Deformable Convolution Networks for Fine-Grained Action DetectionOral46 citations
867. Shape Reconstruction Using Differentiable Projections and Deep PriorsPoster46 citations
868. Attention-Aware Polarity Sensitive Embedding for Affective Image RetrievalPoster45 citations
869. M2FPA: A Multi-Yaw Multi-Pitch High-Quality Dataset and Benchmark for Facial Pose AnalysisPoster45 citations
870. MultiSeg: Semantically Meaningful, Scale-Diverse Segmentations From Minimal User InputPoster45 citations
871. Resource Constrained Neural Network Architecture Search: Will a Submodularity Assumption Help?Poster45 citations
872. View Independent Generative Adversarial Network for Novel View SynthesisOral45 citations
873. Visualizing the Invisible: Occluded Vehicle Segmentation and RecoveryPoster45 citations
874. AFD-Net: Aggregated Feature Difference Learning for Cross-Spectral Image Patch MatchingOral44 citations
875. Deep CG2Real: Synthetic-to-Real Translation via Image DisentanglementPoster44 citations
876. Elaborate Monocular Point and Line SLAM With Robust InitializationPoster44 citations
877. FAB: A Robust Facial Landmark Detection Framework for Motion-Blurred VideosPoster44 citations
878. Variational Uncalibrated Photometric Stereo Under General LightingPoster44 citations
879. Face Alignment With Kernel Density Deep Neural NetworkPoster43 citations
880. Joint Embedding of 3D Scan and CAD ObjectsPoster43 citations
881. Learning Local Descriptors With a CDF-Based Dynamic Soft MarginOral43 citations
882. Markerless Outdoor Human Motion Capture Using Multiple Autonomous Micro Aerial VehiclesPoster43 citations
883. RainFlow: Optical Flow Under Rain Streaks and Rain Veiling EffectPoster43 citations
884. Reasoning About Human-Object Interactions Through Dual Attention NetworksPoster43 citations
885. Revisiting Radial Distortion Absolute PosePoster43 citations
886. A Weakly Supervised Fine Label Classifier Enhanced by Coarse SupervisionPoster42 citations
887. Generative Adversarial Training for Weakly Supervised Cloud MattingPoster42 citations
888. GraphX-Convolution for Point Cloud Deformation in 2D-to-3D ConversionPoster42 citations
889. Algebraic Characterization of Essential Matrices and Their Averaging in Multiview SettingsPoster41 citations
890. On the Global Optima of Kernelized Adversarial Representation LearningPoster41 citations
891. Patchwork: A Patch-Wise Attention Network for Efficient Object Detection and Segmentation in Video StreamsPoster41 citations
892. Sharpen Focus: Learning With Attention Separability and ConsistencyPoster41 citations
893. Deep Appearance MapsPoster40 citations
894. Dilated Convolutional Neural Networks for Sequential Manifold-Valued Data40 citations
895. Geometry Normalization Networks for Accurate Scene Text DetectionPoster40 citations
896. HiPPI: Higher-Order Projected Power Iterations for Scalable Multi-MatchingPoster40 citations
897. Information Entropy Based Feature Pooling for Convolutional Neural NetworksPoster40 citations
898. Joint Prediction for Kinematic Trajectories in Vehicle-Pedestrian-Mixed ScenesPoster40 citations
899. Once a MAN: Towards Multi-Target Attack via Learning Multi-Target Adversarial Network OncePoster40 citations
900. Spatiotemporal Feature Residual Propagation for Action PredictionPoster40 citations
901. Unsupervised Robust Disentangling of Latent Characteristics for Image SynthesisPoster40 citations
902. A Decoupled 3D Facial Shape Model by Adversarial TrainingOral39 citations
903. Context-Aware Feature and Label Fusion for Facial Action Unit Intensity Estimation With Partially Labeled DataPoster39 citations
904. Language Features Matter: Effective Language Representations for Vision-Language TasksPoster39 citations
905. Learning Across Tasks and DomainsPoster39 citations
906. Multi-View Image FusionPoster39 citations
907. Privacy Preserving Image Queries for Camera LocalizationOral39 citations
908. The LogBarrier Adversarial Attack: Making Effective Use of Decision Boundary InformationPoster39 citations
909. Understanding Generalized Whitening and Coloring Transform for Universal Style TransferOral39 citations
910. Cascaded Parallel Filtering for Memory-Efficient Image-Based LocalizationPoster38 citations
911. Permutation-Invariant Feature Restructuring for Correlation-Aware Image Set-Based RecognitionPoster38 citations
912. Towards Interpretable Object Detection by Unfolding Latent StructuresOral38 citations
913. Approximated Bilinear Modules for Temporal ModelingPoster37 citations
914. Attention Bridging Network for Knowledge TransferPoster37 citations
915. Calibration Wizard: A Guidance System for Camera Calibration Based on Modelling Geometric and Corner UncertaintyOral37 citations
916. Conservative Wasserstein Training for Pose EstimationPoster37 citations
917. GSLAM: A General SLAM Framework and BenchmarkPoster37 citations
918. Quasi-Globally Optimal and Efficient Vanishing Point Estimation in Manhattan WorldOral37 citations
919. ViCo: Word Embeddings From Visual Co-OccurrencesPoster37 citations
920. Bidirectional One-Shot Unsupervised Domain MappingPoster36 citations
921. Large-Scale Tag-Based Font Retrieval With Generative Feature LearningPoster36 citations
922. Spatial Correspondence With Generative Adversarial Network: Learning Depth From Monocular VideosPoster36 citations
923. No Fear of the Dark: Image Retrieval Under Varying Illumination ConditionsPoster35 citations
924. Simultaneous Multi-View Instance Detection With Learned Geometric Soft-ConstraintsPoster35 citations
925. Teacher Guided Architecture SearchPoster35 citations
926. Cross-View Policy Learning for Street NavigationPoster34 citations
927. Detecting 11K Classes: Large Scale Object Detection Without Fine-Grained Bounding BoxesPoster34 citations
928. ELF: Embedded Localisation of Features in Pre-Trained CNNPoster34 citations
929. Learning With Unsure Data for Medical Image DiagnosisPoster34 citations
930. SegEQA: Video Segmentation Based Visual Attention for Embodied Question AnsweringPoster34 citations
931. Bayes-Factor-VAE: Hierarchical Bayesian Deep Auto-Encoder Models for Factor DisentanglementOral33 citations
932. CompenNet++: End-to-End Full Projector CompensationPoster33 citations
933. DiscoNet: Shapes Learning on Disconnected Manifolds for 3D EditingPoster33 citations
934. Learning Perspective Undistortion of PortraitsOral33 citations
935. Mixture-Kernel Graph Attention Network for Situation RecognitionPoster33 citations
936. Object-Driven Multi-Layer Scene Decomposition From a Single ImagePoster33 citations
937. Occlusion-Shared and Feature-Separated Network for Occlusion Relationship ReasoningPoster33 citations
938. Probabilistic Deep Ordinal Regression Based on Gaussian ProcessesPoster33 citations
939. Sampling Wisely: Deep Image Embedding by Top-K Precision OptimizationPoster33 citations
940. Semi-Supervised Monocular 3D Face Reconstruction With End-to-End Shape-Preserved Domain TransferOral33 citations
941. Non-Local Intrinsic Decomposition With Near-Infrared PriorsPoster32 citations
942. Semi-Supervised Skin Detection by Network With Mutual GuidancePoster32 citations
943. Unsupervised Neural Quantization for Compressed-Domain Similarity SearchOral32 citations
944. Better and Faster: Exponential Loss for Image Patch MatchingPoster31 citations
945. Dynamic-Net: Tuning the Objective Without Re-Training for Synthesis TasksPoster31 citations
946. Global Feature Guided Local PoolingPoster31 citations
947. Learning to Caption Images Through a Lifetime by Asking QuestionsPoster31 citations
948. Adversarial Feedback LoopPoster30 citations
949. An Alarm System for Segmentation Algorithm Based on Shape Model30 citations
950. Block Annotation: Better Image Annotation With Sub-Image DecompositionPoster30 citations
951. Convex Shape Prior for Multi-Object Segmentation Using a Single Level Set FunctionPoster30 citations
952. Domain-Adaptive Single-View 3D ReconstructionOral30 citations
953. Generating Easy-to-Understand Referring Expressions for Target IdentificationsPoster30 citations
954. Learning Local RGB-to-CAD Correspondences for Object Pose EstimationPoster30 citations
955. Point-to-Point Video GenerationPoster30 citations
956. View-Consistent 4D Light Field Superpixel SegmentationOral30 citations
957. A Bayesian Optimization Framework for Neural Network CompressionPoster29 citations
958. Closed-Form Optimal Two-View Triangulation Based on Angular ErrorsPoster29 citations
959. Deep End-to-End Alignment and Refinement for Time-of-Flight RGB-D ModulePoster29 citations
960. Domain Intersection and Domain DifferencePoster29 citations
961. Fast Image Restoration With Multi-Bin Trainable Linear UnitsPoster29 citations
962. Is an Affine Constraint Needed for Affine Subspace Clustering?Poster29 citations
963. Restoration of Non-Rigidly Distorted Underwater Images Using a Combination of Compressive Sensing and Local Polynomial Image RepresentationsOral29 citations
964. Unpaired Image-to-Speech Synthesis With Multimodal Information BottleneckPoster29 citations
965. Agile Depth Sensing Using Triangulation Light CurtainsOral28 citations
966. Learning Meshes for Dense Visual SLAMPoster28 citations
967. An Efficient Solution to the Homography-Based Relative Pose Problem With a Common Reference DirectionOral27 citations
968. Controlling Neural Networks via Energy DissipationPoster27 citations
969. Learning Implicit Generative Models by Matching Perceptual FeaturesOral27 citations
970. Linearized Multi-Sampling for Differentiable Image TransformationOral27 citations
971. POD: Practical Object Detection With Scale-Sensitive NetworkPoster27 citations
972. Exploring Overall Contextual Information for Image Captioning in Human-Like Cognitive StylePoster26 citations
973. Goal-Driven Sequential Data AbstractionPoster26 citations
974. Polarimetric Relative Pose EstimationPoster26 citations
975. PuppetGAN: Cross-Domain Image Manipulation by DemonstrationOral26 citations
976. Scaling Object Detection by Transferring Classification WeightsOral26 citations
977. AdaTransform: Adaptive Data TransformationOral25 citations
978. Adaptative Inference Cost With Convolutional Neural Mixture ModelsPoster25 citations
979. Consensus Maximization Tree Search RevisitedOral25 citations
980. Accelerate Learning of Deep Hashing With Gradient AttentionPoster24 citations
981. EMPNet: Neural Localisation and Mapping Using Embedded Memory PointsPoster24 citations
982. Efficient and Robust Registration on the 3D Special Euclidean GroupPoster24 citations
983. Program-Guided Image ManipulatorsPoster24 citations
984. Proximal Mean-Field for Neural Network QuantizationPoster24 citations
985. Adaptive Activation Thresholding: Dynamic Routing Type Behavior for Interpretability in Convolutional Neural NetworksPoster23 citations
986. Enhancing 2D Representation via Adjacent Views for 3D Shape RetrievalPoster23 citations
987. Gravity as a Reference for Estimating a Person's Height From VideoPoster23 citations
988. Incremental Class Discovery for Semantic Segmentation With RGBD SensingPoster23 citations
989. Rescan: Inductive Instance Segmentation for Indoor RGBD ScansPoster23 citations
990. Small Steps and Giant Leaps: Minimal Newton Solvers for Deep LearningPoster23 citations
991. Floorplan-Jigsaw: Jointly Estimating Scene Layout and Aligning Partial ScansPoster22 citations
992. IMP: Instance Mask Projection for High Accuracy Semantic Segmentation of ThingsPoster22 citations
993. Recognizing Part Attributes With Insufficient DataPoster22 citations
994. Deep Depth From Aberration MapPoster21 citations
995. Fast Computation of Content-Sensitive Superpixels and Supervoxels Using Q-DistancesPoster21 citations
996. GP2C: Geometric Projection Parameter Consensus for Joint 3D Pose and Focal Length Estimation in the WildPoster21 citations
997. Identity From Here, Pose From There: Self-Supervised Disentanglement and Generation of Objects Using Unlabeled VideosPoster21 citations
998. Joint Learning of Semantic Alignment and Object Landmark DetectionPoster21 citations
999. Joint Optimization for Cooperative Image CaptioningPoster21 citations
1000. Pro-Cam SSfM: Projector-Camera System for Structure and Spectral Reflectance From MotionPoster21 citations

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