CVPR 2018 Accepted Papers

The full list of 979 papers accepted at CVPR 2018 (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. Squeeze-and-Excitation NetworksPoster41,020 citations
2. MobileNetV2: Inverted Residuals and Linear BottlenecksPoster29,310 citations
3. The Unreasonable Effectiveness of Deep Features as a Perceptual MetricPoster14,258 citations
4. Non-Local Neural NetworksPoster12,595 citations
5. ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile DevicesPoster10,272 citations
6. Path Aggregation Network for Instance SegmentationPoster9,600 citations
7. Learning Transferable Architectures for Scalable Image RecognitionPoster7,963 citations
8. Cascade R-CNN: Delving Into High Quality Object DetectionPoster7,377 citations
9. Bottom-Up and Top-Down Attention for Image Captioning and Visual Question AnsweringPoster5,866 citations
10. Learning to Compare: Relation Network for Few-Shot LearningPoster5,544 citations
11. High-Resolution Image Synthesis and Semantic Manipulation With Conditional GANsPoster5,478 citations
12. Residual Dense Network for Image Super-ResolutionPoster5,376 citations
13. VoxelNet: End-to-End Learning for Point Cloud Based 3D Object DetectionPoster5,114 citations
14. StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image TranslationPoster5,010 citations
15. Unsupervised Feature Learning via Non-Parametric Instance DiscriminationPoster4,718 citations
16. Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only InferencePoster4,374 citations
17. Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and SemanticsPoster4,160 citations
18. A Closer Look at Spatiotemporal Convolutions for Action RecognitionPoster4,089 citations
19. Deep Image PriorPoster3,762 citations
20. Boosting Adversarial Attacks With MomentumPoster3,515 citations
21. CosFace: Large Margin Cosine Loss for Deep Face RecognitionPoster3,386 citations
22. High Performance Visual Tracking With Siamese Region Proposal NetworkPoster3,306 citations
23. DOTA: A Large-Scale Dataset for Object Detection in Aerial ImagesPoster3,187 citations
24. Frustum PointNets for 3D Object Detection From RGB-D DataPoster3,121 citations
25. Generative Image Inpainting With Contextual AttentionPoster3,105 citations
26. PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost VolumePoster3,033 citations
27. Robust Physical-World Attacks on Deep Learning Visual ClassificationPoster2,927 citations
28. Social GAN: Socially Acceptable Trajectories With Generative Adversarial NetworksPoster2,672 citations
29. Maximum Classifier Discrepancy for Unsupervised Domain AdaptationPoster2,553 citations
30. Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?Poster2,543 citations
31. AttnGAN: Fine-Grained Text to Image Generation With Attentional Generative Adversarial NetworksPoster2,322 citations
32. Person Transfer GAN to Bridge Domain Gap for Person Re-IdentificationPoster2,297 citations
33. End-to-End Recovery of Human Shape and PosePoster2,272 citations
34. Deep Mutual LearningPoster2,262 citations
35. Deep Ordinal Regression Network for Monocular Depth EstimationPoster2,236 citations
36. Real-World Anomaly Detection in Surveillance VideosPoster2,202 citations
37. Cascaded Pyramid Network for Multi-Person Pose EstimationPoster2,084 citations
38. Pyramid Stereo Matching NetworkPoster2,043 citations
39. DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial NetworksPoster2,010 citations
40. Learning to Adapt Structured Output Space for Semantic SegmentationPoster1,942 citations
41. Single-Shot Refinement Neural Network for Object DetectionPoster1,940 citations
42. 3D Semantic Segmentation With Submanifold Sparse Convolutional NetworksPoster1,932 citations
43. CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested ScenesPoster1,873 citations
44. DensePose: Dense Human Pose Estimation in the WildPoster1,827 citations
45. Deep Back-Projection Networks for Super-ResolutionPoster1,823 citations
46. Deep Layer AggregationPoster1,820 citations
47. COCO-Stuff: Thing and Stuff Classes in ContextPoster1,810 citations
48. Domain Adaptive Faster R-CNN for Object Detection in the WildPoster1,766 citations
49. DenseASPP for Semantic Segmentation in Street ScenesPoster1,744 citations
50. Harmonious Attention Network for Person Re-IdentificationPoster1,731 citations
51. Context Encoding for Semantic SegmentationPoster1,702 citations
52. Large-Scale Point Cloud Semantic Segmentation With Superpoint GraphsPoster1,671 citations
53. Relation Networks for Object DetectionPoster1,660 citations
54. PackNet: Adding Multiple Tasks to a Single Network by Iterative PruningPoster1,633 citations
55. Vision-and-Language Navigation: Interpreting Visually-Grounded Navigation Instructions in Real EnvironmentsPoster1,622 citations
56. Future Frame Prediction for Anomaly Detection – A New BaselinePoster1,611 citations
57. Learning to See in the DarkPoster1,610 citations
58. A Papier-Mâché Approach to Learning 3D Surface GenerationPoster1,593 citations
59. Domain Generalization With Adversarial Feature LearningPoster1,574 citations
60. Taskonomy: Disentangling Task Transfer LearningPoster1,541 citations
61. Scale-Recurrent Network for Deep Image DeblurringPoster1,538 citations
62. FoldingNet: Point Cloud Auto-Encoder via Deep Grid DeformationPoster1,525 citations
63. PIXOR: Real-Time 3D Object Detection From Point CloudsPoster1,479 citations
64. The INaturalist Species Classification and Detection DatasetPoster1,469 citations
65. GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera PosePoster1,463 citations
66. Dynamic Few-Shot Visual Learning Without ForgettingPoster1,450 citations
67. MoCoGAN: Decomposing Motion and Content for Video GenerationPoster1,438 citations
68. ISTA-Net: Interpretable Optimization-Inspired Deep Network for Image Compressive SensingPoster1,415 citations
69. Densely Connected Pyramid Dehazing NetworkPoster1,359 citations
70. MegaDepth: Learning Single-View Depth Prediction From Internet PhotosPoster1,322 citations
71. AVA: A Video Dataset of Spatio-Temporally Localized Atomic Visual ActionsPoster1,319 citations
72. Recovering Realistic Texture in Image Super-Resolution by Deep Spatial Feature TransformPoster1,313 citations
73. Neural 3D Mesh RendererPoster1,277 citations
74. Learning a Single Convolutional Super-Resolution Network for Multiple DegradationsPoster1,276 citations
75. Feature Generating Networks for Zero-Shot LearningPoster1,248 citations
76. Neural Motifs: Scene Graph Parsing With Global ContextPoster1,240 citations
77. Image-Image Domain Adaptation With Preserved Self-Similarity and Domain-Dissimilarity for Person Re-IdentificationPoster1,224 citations
78. SO-Net: Self-Organizing Network for Point Cloud AnalysisPoster1,202 citations
79. The Lovász-Softmax Loss: A Tractable Surrogate for the Optimization of the Intersection-Over-Union Measure in Neural NetworksPoster1,202 citations
80. Density-Aware Single Image De-Raining Using a Multi-Stream Dense NetworkPoster1,163 citations
81. Defense Against Adversarial Attacks Using High-Level Representation Guided DenoiserPoster1,144 citations
82. Real-Time Seamless Single Shot 6D Object Pose PredictionPoster1,120 citations
83. NISP: Pruning Networks Using Neuron Importance Score PropagationPoster1,103 citations
84. CondenseNet: An Efficient DenseNet Using Learned Group ConvolutionsPoster1,074 citations
85. “Zero-Shot” Super-Resolution Using Deep Internal LearningPoster1,067 citations
86. Interpretable Convolutional Neural NetworksPoster1,051 citations
87. Fast and Accurate Single Image Super-Resolution via Information Distillation NetworkPoster1,049 citations
88. PiCANet: Learning Pixel-Wise Contextual Attention for Saliency DetectionPoster1,035 citations
89. Gated Fusion Network for Single Image DehazingPoster1,032 citations
90. Learning Spatial-Temporal Regularized Correlation Filters for Visual TrackingPoster1,011 citations
91. The Perception-Distortion TradeoffPoster1,007 citations
92. Image Generation From Scene GraphsPoster1,000 citations
93. An Analysis of Scale Invariance in Object Detection ­ SNIPPoster994 citations
94. Gibson Env: Real-World Perception for Embodied AgentsPoster988 citations
95. Learning a Discriminative Feature Network for Semantic SegmentationPoster987 citations
96. Learning Pixel-Level Semantic Affinity With Image-Level Supervision for Weakly Supervised Semantic SegmentationPoster983 citations
97. A High-Quality Denoising Dataset for Smartphone CamerasPoster982 citations
98. Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video InterpolationPoster981 citations
99. VizWiz Grand Challenge: Answering Visual Questions From Blind PeoplePoster961 citations
100. LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow EstimationPoster959 citations
101. MAttNet: Modular Attention Network for Referring Expression ComprehensionPoster958 citations
102. Adversarially Learned One-Class Classifier for Novelty DetectionPoster931 citations
103. Image to Image Translation for Domain AdaptationPoster919 citations
104. Unsupervised Learning of Depth and Ego-Motion From Monocular Video Using 3D Geometric ConstraintsPoster919 citations
105. Low-Shot Learning From Imaginary DataPoster915 citations
106. SPLATNet: Sparse Lattice Networks for Point Cloud ProcessingPoster914 citations
107. The Power of Ensembles for Active Learning in Image ClassificationPoster907 citations
108. An Unsupervised Learning Model for Deformable Medical Image RegistrationPoster903 citations
109. Joint Optimization Framework for Learning With Noisy LabelsPoster899 citations
110. PointFusion: Deep Sensor Fusion for 3D Bounding Box EstimationPoster899 citations
111. Attentive Generative Adversarial Network for Raindrop Removal From a Single ImagePoster851 citations
112. Neural Sign Language TranslationPoster850 citations
113. Rethinking the Faster R-CNN Architecture for Temporal Action LocalizationPoster846 citations
114. A Twofold Siamese Network for Real-Time Object TrackingPoster843 citations
115. Generate to Adapt: Aligning Domains Using Generative Adversarial NetworksPoster839 citations
116. Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting With a Single Convolutional NetPoster834 citations
117. Embodied Question AnsweringPoster814 citations
118. Unsupervised Learning of Monocular Depth Estimation and Visual Odometry With Deep Feature ReconstructionPoster802 citations
119. Learning Rich Features for Image Manipulation DetectionPoster797 citations
120. Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary SupervisionPoster789 citations
121. Learning to Estimate 3D Human Pose and Shape From a Single Color ImagePoster785 citations
122. PU-Net: Point Cloud Upsampling NetworkPoster784 citations
123. VITON: An Image-Based Virtual Try-On NetworkPoster783 citations
124. Benchmarking 6DOF Outdoor Visual Localization in Changing ConditionsPoster780 citations
125. Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question AnsweringPoster772 citations
126. PPFNet: Global Context Aware Local Features for Robust 3D Point MatchingPoster764 citations
127. Detecting and Recognizing Human-Object InteractionsPoster757 citations
128. Progressive Attention Guided Recurrent Network for Salient Object DetectionPoster756 citations
129. Human Semantic Parsing for Person Re-IdentificationPoster753 citations
130. Mask-Guided Contrastive Attention Model for Person Re-IdentificationPoster752 citations
131. Zero-Shot Recognition via Semantic Embeddings and Knowledge GraphsPoster750 citations
132. GVCNN: Group-View Convolutional Neural Networks for 3D Shape RecognitionPoster749 citations
133. Learning Depth From Monocular Videos Using Direct MethodsPoster746 citations
134. Pointwise Convolutional Neural NetworksPoster742 citations
135. Camera Style Adaptation for Person Re-IdentificationPoster741 citations
136. Through-Wall Human Pose Estimation Using Radio SignalsPoster731 citations
137. Adversarial Complementary Learning for Weakly Supervised Object LocalizationPoster728 citations
138. End-to-End Dense Video Captioning With Masked TransformerPoster728 citations
139. Image Blind Denoising With Generative Adversarial Network Based Noise ModelingPoster728 citations
140. Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-IdentificationPoster728 citations
141. Tell Me Where to Look: Guided Attention Inference NetworkPoster719 citations
142. Features for Multi-Target Multi-Camera Tracking and Re-IdentificationPoster709 citations
143. Tangent Convolutions for Dense Prediction in 3DPoster704 citations
144. PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place RecognitionPoster702 citations
145. Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi-Supervised Semantic SegmentationPoster700 citations
146. Deep Video Super-Resolution Network Using Dynamic Upsampling Filters Without Explicit Motion CompensationPoster691 citations
147. Weakly-Supervised Semantic Segmentation Network With Deep Seeded Region GrowingPoster691 citations
148. Event-Based Vision Meets Deep Learning on Steering Prediction for Self-Driving CarsPoster686 citations
149. Learning to Find Good CorrespondencesPoster685 citations
150. Few-Shot Image Recognition by Predicting Parameters From ActivationsPoster680 citations
151. 2D/3D Pose Estimation and Action Recognition Using Multitask Deep LearningPoster678 citations
152. Cross-Domain Weakly-Supervised Object Detection Through Progressive Domain AdaptationPoster675 citations
153. Frame-Recurrent Video Super-ResolutionPoster675 citations
154. First-Person Hand Action Benchmark With RGB-D Videos and 3D Hand Pose AnnotationsPoster672 citations
155. GANerated Hands for Real-Time 3D Hand Tracking From Monocular RGBPoster669 citations
156. Repulsion Loss: Detecting Pedestrians in a CrowdPoster669 citations
157. Learning Attentions: Residual Attentional Siamese Network for High Performance Online Visual TrackingPoster667 citations
158. Low-Shot Learning With Imprinted WeightsPoster665 citations
159. FOTS: Fast Oriented Text Spotting With a Unified NetworkPoster664 citations
160. SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance SegmentationPoster662 citations
161. TieNet: Text-Image Embedding Network for Common Thorax Disease Classification and Reporting in Chest X-RaysPoster659 citations
162. FSRNet: End-to-End Learning Face Super-Resolution With Facial PriorsPoster658 citations
163. Large Scale Fine-Grained Categorization and Domain-Specific Transfer LearningPoster656 citations
164. VITAL: VIsual Tracking via Adversarial LearningPoster654 citations
165. Practical Block-Wise Neural Network Architecture GenerationPoster650 citations
166. RotationNet: Joint Object Categorization and Pose Estimation Using Multiviews From Unsupervised ViewpointsPoster645 citations
167. Collaborative and Adversarial Network for Unsupervised Domain AdaptationPoster636 citations
168. Mining Point Cloud Local Structures by Kernel Correlation and Graph PoolingPoster635 citations
169. Multi-Level Factorisation Net for Person Re-IdentificationPoster627 citations
170. PoseTrack: A Benchmark for Human Pose Estimation and TrackingPoster621 citations
171. BlockDrop: Dynamic Inference Paths in Residual NetworksPoster620 citations
172. VirtualHome: Simulating Household Activities via ProgramsPoster620 citations
173. Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and BodiesPoster617 citations
174. Conditional Probability Models for Deep Image CompressionPoster607 citations
175. Inferring Semantic Layout for Hierarchical Text-to-Image SynthesisPoster606 citations
176. SplineCNN: Fast Geometric Deep Learning With Continuous B-Spline KernelsPoster606 citations
177. A Pose-Sensitive Embedding for Person Re-Identification With Expanded Cross Neighborhood Re-RankingPoster604 citations
178. Deformable GANs for Pose-Based Human Image GenerationPoster604 citations
179. Rotation-Sensitive Regression for Oriented Scene Text DetectionPoster602 citations
180. Learning From Synthetic Data: Addressing Domain Shift for Semantic SegmentationPoster601 citations
181. Neural Baby TalkPoster601 citations
182. Deep Photo Enhancer: Unpaired Learning for Image Enhancement From Photographs With GANsPoster599 citations
183. Look at Boundary: A Boundary-Aware Face Alignment AlgorithmPoster599 citations
184. CleanNet: Transfer Learning for Scalable Image Classifier Training With Label NoisePoster598 citations
185. PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene ParsingPoster596 citations
186. DeepMVS: Learning Multi-View StereopsisPoster595 citations
187. Pix3D: Dataset and Methods for Single-Image 3D Shape ModelingPoster590 citations
188. InLoc: Indoor Visual Localization With Dense Matching and View SynthesisPoster582 citations
189. A Bi-Directional Message Passing Model for Salient Object DetectionPoster579 citations
190. Recurrent Slice Networks for 3D Segmentation of Point CloudsPoster573 citations
191. Generalized Zero-Shot Learning via Synthesized ExamplesPoster570 citations
192. Attention-Aware Compositional Network for Person Re-IdentificationPoster565 citations
193. Deep Parametric Continuous Convolutional Neural NetworksPoster561 citations
194. V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation From a Single Depth MapPoster557 citations
195. Partial Transfer Learning With Selective Adversarial NetworksPoster556 citations
196. Video Based Reconstruction of 3D People ModelsPoster553 citations
197. HATS: Histograms of Averaged Time Surfaces for Robust Event-Based Object ClassificationPoster550 citations
198. Wing Loss for Robust Facial Landmark Localisation With Convolutional Neural NetworksPoster548 citations
199. Deep Extreme Cut: From Extreme Points to Object SegmentationPoster545 citations
200. Translating and Segmenting Multimodal Medical Volumes With Cycle- and Shape-Consistency Generative Adversarial NetworkPoster543 citations
201. Revisiting Oxford and Paris: Large-Scale Image Retrieval BenchmarkingPoster542 citations
202. Disentangled Person Image GenerationPoster541 citations
203. Self-Supervised Adversarial Hashing Networks for Cross-Modal RetrievalPoster541 citations
204. Facial Expression Recognition by De-Expression Residue LearningPoster540 citations
205. Importance Weighted Adversarial Nets for Partial Domain AdaptationPoster539 citations
206. Efficient Interactive Annotation of Segmentation Datasets With Polygon-RNN++Poster537 citations
207. Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow RemovalPoster537 citations
208. A Variational U-Net for Conditional Appearance and Shape GenerationPoster536 citations
209. Data Distillation: Towards Omni-Supervised LearningPoster536 citations
210. Multimodal Explanations: Justifying Decisions and Pointing to the EvidencePoster535 citations
211. Deep Cocktail Network: Multi-Source Unsupervised Domain Adaptation With Category ShiftPoster528 citations
212. CartoonGAN: Generative Adversarial Networks for Photo CartoonizationPoster527 citations
213. Multi-Cue Correlation Filters for Robust Visual TrackingPoster520 citations
214. ST-GAN: Spatial Transformer Generative Adversarial Networks for Image CompositingPoster516 citations
215. Fast Video Object Segmentation by Reference-Guided Mask PropagationPoster512 citations
216. Single Image Dehazing via Conditional Generative Adversarial NetworkPoster511 citations
217. Deep Depth Completion of a Single RGB-D ImagePoster507 citations
218. Detect Globally, Refine Locally: A Novel Approach to Saliency DetectionPoster507 citations
219. Learning a Discriminative Filter Bank Within a CNN for Fine-Grained RecognitionPoster504 citations
220. Ordinal Depth Supervision for 3D Human Pose EstimationPoster503 citations
221. Dual Attention Matching Network for Context-Aware Feature Sequence Based Person Re-IdentificationPoster502 citations
222. Deep Progressive Reinforcement Learning for Skeleton-Based Action RecognitionPoster500 citations
223. Tips and Tricks for Visual Question Answering: Learnings From the 2017 ChallengePoster500 citations
224. A Generative Adversarial Approach for Zero-Shot Learning From Noisy TextsPoster499 citations
225. Context-Aware Synthesis for Video Frame InterpolationPoster499 citations
226. IQA: Visual Question Answering in Interactive EnvironmentsPoster499 citations
227. PointGrid: A Deep Network for 3D Shape UnderstandingPoster499 citations
228. Geometry-Aware Learning of Maps for Camera LocalizationPoster498 citations
229. MaskLab: Instance Segmentation by Refining Object Detection With Semantic and Direction FeaturesPoster497 citations
230. Shift: A Zero FLOP, Zero Parameter Alternative to Spatial ConvolutionsPoster494 citations
231. 3D Human Pose Estimation in the Wild by Adversarial LearningPoster493 citations
232. Learning Convolutional Networks for Content-Weighted Image CompressionPoster490 citations
233. Convolutional Image CaptioningPoster489 citations
234. Direction-Aware Spatial Context Features for Shadow DetectionPoster484 citations
235. Efficient Parametrization of Multi-Domain Deep Neural NetworksPoster483 citations
236. Improved Lossy Image Compression With Priming and Spatially Adaptive Bit Rates for Recurrent NetworksPoster483 citations
237. Functional Map of the WorldPoster482 citations
238. Nonlinear 3D Face Morphable ModelPoster478 citations
239. Robust Classification With Convolutional Prototype LearningPoster478 citations
240. Look, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval With Generative ModelsPoster476 citations
241. Generative Adversarial PerturbationsPoster470 citations
242. Burst Denoising With Kernel Prediction NetworksPoster467 citations
243. Dynamic Scene Deblurring Using Spatially Variant Recurrent Neural NetworksPoster466 citations
244. Learning Steerable Filters for Rotation Equivariant CNNsPoster465 citations
245. CodeSLAM — Learning a Compact, Optimisable Representation for Dense Visual SLAMPoster463 citations
246. Scale-Transferrable Object DetectionPoster463 citations
247. Triplet-Center Loss for Multi-View 3D Object RetrievalPoster461 citations
248. Exploit the Unknown Gradually: One-Shot Video-Based Person Re-Identification by Stepwise LearningPoster456 citations
249. Pose Transferrable Person Re-IdentificationPoster456 citations
250. Learning Less Is More - 6D Camera Localization via 3D Surface RegressionPoster455 citations
251. Occluded Pedestrian Detection Through Guided Attention in CNNsPoster455 citations
252. Thoracic Disease Identification and Localization With Limited SupervisionPoster455 citations
253. Context Contrasted Feature and Gated Multi-Scale Aggregation for Scene SegmentationPoster450 citations
254. Appearance-and-Relation Networks for Video ClassificationPoster449 citations
255. Efficient Video Object Segmentation via Network ModulationPoster449 citations
256. Weakly Supervised Action Localization by Sparse Temporal Pooling NetworkPoster449 citations
257. DecideNet: Counting Varying Density Crowds Through Attention Guided Detection and Density EstimationPoster448 citations
258. Diversity Regularized Spatiotemporal Attention for Video-Based Person Re-IdentificationPoster443 citations
259. 3D-RCNN: Instance-Level 3D Object Reconstruction via Render-and-ComparePoster439 citations
260. DVQA: Understanding Data Visualizations via Question AnsweringPoster439 citations
261. Graph-Cut RANSACPoster433 citations
262. CLIP-Q: Deep Network Compression Learning by In-Parallel Pruning-QuantizationPoster432 citations
263. MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep NetworksPoster432 citations
264. Fully Convolutional Adaptation Networks for Semantic SegmentationPoster429 citations
265. Multi-Agent Diverse Generative Adversarial NetworksPoster429 citations
266. Attentional ShapeContextNet for Point Cloud RecognitionPoster428 citations
267. Compressed Video Action RecognitionPoster428 citations
268. GeoNet: Geometric Neural Network for Joint Depth and Surface Normal EstimationPoster428 citations
269. Learning and Using the Arrow of TimePoster427 citations
270. A Revised Underwater Image Formation ModelPoster422 citations
271. Multi-Oriented Scene Text Detection via Corner Localization and Region SegmentationPoster420 citations
272. Deflecting Adversarial Attacks With Pixel DeflectionPoster418 citations
273. Multi-Level Fusion Based 3D Object Detection From Monocular ImagesPoster417 citations
274. Multi-Content GAN for Few-Shot Font Style TransferPoster416 citations
275. Reconstruction Network for Video CaptioningPoster416 citations
276. Single Image Reflection Separation With Perceptual LossesPoster416 citations
277. A Unifying Contrast Maximization Framework for Event Cameras, With Applications to Motion, Depth, and Optical Flow EstimationPoster415 citations
278. Deep Cauchy Hashing for Hamming Space RetrievalPoster415 citations
279. Crowd Counting via Adversarial Cross-Scale Consistency PursuitPoster414 citations
280. Convolutional Sequence to Sequence Model for Human DynamicsPoster409 citations
281. Learning Semantic Concepts and Order for Image and Sentence MatchingPoster409 citations
282. MegDet: A Large Mini-Batch Object DetectorPoster408 citations
283. Structured Attention Guided Convolutional Neural Fields for Monocular Depth EstimationPoster407 citations
284. Style Aggregated Network for Facial Landmark DetectionPoster406 citations
285. Toward Driving Scene Understanding: A Dataset for Learning Driver Behavior and Causal ReasoningPoster406 citations
286. In-Place Activated BatchNorm for Memory-Optimized Training of DNNsPoster404 citations
287. Photographic Text-to-Image Synthesis With a Hierarchically-Nested Adversarial NetworkPoster401 citations
288. Normalized Cut Loss for Weakly-Supervised CNN SegmentationPoster399 citations
289. Super-FAN: Integrated Facial Landmark Localization and Super-Resolution of Real-World Low Resolution Faces in Arbitrary Poses With GANsPoster399 citations
290. Learning for Disparity Estimation Through Feature ConstancyPoster398 citations
291. Learning to Localize Sound Source in Visual ScenesPoster397 citations
292. Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action RecognitionPoster396 citations
293. FeaStNet: Feature-Steered Graph Convolutions for 3D Shape AnalysisPoster393 citations
294. Memory Matching Networks for One-Shot Image RecognitionPoster392 citations
295. Boosting Self-Supervised Learning via Knowledge TransferPoster391 citations
296. RoadTracer: Automatic Extraction of Road Networks From Aerial ImagesPoster391 citations
297. Iterative Learning With Open-Set Noisy LabelsPoster389 citations
298. On the Robustness of Semantic Segmentation Models to Adversarial AttacksPoster386 citations
299. Recognizing Human Actions as the Evolution of Pose Estimation MapsPoster386 citations
300. PoTion: Pose MoTion Representation for Action RecognitionPoster381 citations
301. Avatar-Net: Multi-Scale Zero-Shot Style Transfer by Feature DecorationPoster379 citations
302. Deep Spatial Feature Reconstruction for Partial Person Re-Identification: Alignment-Free ApproachPoster379 citations
303. Improved Fusion of Visual and Language Representations by Dense Symmetric Co-Attention for Visual Question AnsweringPoster379 citations
304. Multi-View Harmonized Bilinear Network for 3D Object RecognitionPoster377 citations
305. SfSNet: Learning Shape, Reflectance and Illuminance of Faces `in the Wild'Poster377 citations
306. Multi-Label Zero-Shot Learning With Structured Knowledge GraphsPoster376 citations
307. Occlusion Aware Unsupervised Learning of Optical FlowPoster376 citations
308. Synthesizing Images of Humans in Unseen PosesPoster376 citations
309. ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D ScansPoster375 citations
310. Weakly-Supervised Semantic Segmentation by Iteratively Mining Common Object FeaturesPoster375 citations
311. Conditional Generative Adversarial Network for Structured Domain AdaptationPoster374 citations
312. Learning to Segment Every ThingPoster372 citations
313. Unsupervised Training for 3D Morphable Model RegressionPoster372 citations
314. DoubleFusion: Real-Time Capture of Human Performances With Inner Body Shapes From a Single Depth SensorPoster371 citations
315. Zero-Shot Visual Recognition Using Semantics-Preserving Adversarial Embedding NetworksPoster370 citations
316. Progressively Complementarity-Aware Fusion Network for RGB-D Salient Object DetectionPoster369 citations
317. SketchyGAN: Towards Diverse and Realistic Sketch to Image SynthesisPoster369 citations
318. ROAD: Reality Oriented Adaptation for Semantic Segmentation of Urban ScenesPoster365 citations
319. End-to-End Flow Correlation Tracking With Spatial-Temporal AttentionPoster361 citations
320. AON: Towards Arbitrarily-Oriented Text RecognitionPoster360 citations
321. Towards Faster Training of Global Covariance Pooling Networks by Iterative Matrix Square Root NormalizationPoster360 citations
322. CVM-Net: Cross-View Matching Network for Image-Based Ground-to-Aerial Geo-LocalizationPoster357 citations
323. Cross-Modal Deep Variational Hand Pose EstimationPoster357 citations
324. Weakly Supervised Instance Segmentation Using Class Peak ResponsePoster357 citations
325. PieAPP: Perceptual Image-Error Assessment Through Pairwise PreferencePoster355 citations
326. Universal Denoising Networks : A Novel CNN Architecture for Image DenoisingPoster354 citations
327. TextureGAN: Controlling Deep Image Synthesis With Texture PatchesPoster353 citations
328. PairedCycleGAN: Asymmetric Style Transfer for Applying and Removing MakeupPoster348 citations
329. Monocular 3D Pose and Shape Estimation of Multiple People in Natural Scenes - The Importance of Multiple Scene ConstraintsPoster346 citations
330. Unsupervised Domain Adaptation With Similarity LearningPoster346 citations
331. Semantic Visual LocalizationPoster345 citations
332. Deep Marching Cubes: Learning Explicit Surface RepresentationsPoster344 citations
333. Gaze Prediction in Dynamic 360° Immersive VideosPoster344 citations
334. Hand PointNet: 3D Hand Pose Estimation Using Point SetsPoster343 citations
335. Leveraging Unlabeled Data for Crowd Counting by Learning to RankPoster342 citations
336. Fast and Accurate Online Video Object Segmentation via Tracking PartsPoster337 citations
337. Towards High Performance Video Object DetectionPoster337 citations
338. Encoding Crowd Interaction With Deep Neural Network for Pedestrian Trajectory PredictionPoster336 citations
339. Resource Aware Person Re-Identification Across Multiple ResolutionsPoster335 citations
340. Real-Time Monocular Depth Estimation Using Synthetic Data With Domain Adaptation via Image Style TransferPoster334 citations
341. Blazingly Fast Video Object Segmentation With Pixel-Wise Metric LearningPoster328 citations
342. Revisiting Video Saliency: A Large-Scale Benchmark and a New ModelPoster328 citations
343. Smooth Neighbors on Teacher Graphs for Semi-Supervised LearningPoster327 citations
344. EPINET: A Fully-Convolutional Neural Network Using Epipolar Geometry for Depth From Light Field ImagesPoster325 citations
345. Net2Vec: Quantifying and Explaining How Concepts Are Encoded by Filters in Deep Neural NetworksPoster323 citations
346. Towards Open-Set Identity Preserving Face SynthesisPoster323 citations
347. Crowd Counting With Deep Negative Correlation LearningPoster320 citations
348. Video Captioning via Hierarchical Reinforcement LearningPoster320 citations
349. Detect-and-Track: Efficient Pose Estimation in VideosPoster315 citations
350. LayoutNet: Reconstructing the 3D Room Layout From a Single RGB ImagePoster312 citations
351. Motion-Appearance Co-Memory Networks for Video Question AnsweringPoster310 citations
352. Joint Pose and Expression Modeling for Facial Expression RecognitionPoster308 citations
353. Learning Monocular 3D Human Pose Estimation From Multi-View ImagesPoster308 citations
354. Self-Supervised Multi-Level Face Model Learning for Monocular Reconstruction at Over 250 HzPoster308 citations
355. Attentive Fashion Grammar Network for Fashion Landmark Detection and Clothing Category ClassificationPoster307 citations
356. Adversarially Occluded Samples for Person Re-IdentificationPoster305 citations
357. Towards Effective Low-Bitwidth Convolutional Neural NetworksPoster304 citations
358. Adversarial Feature Augmentation for Unsupervised Domain AdaptationPoster303 citations
359. Beyond the Pixel-Wise Loss for Topology-Aware DelineationPoster301 citations
360. Towards Pose Invariant Face Recognition in the WildPoster300 citations
361. “Learning-Compression” Algorithms for Neural Net PruningPoster299 citations
362. Structure Inference Net: Object Detection Using Scene-Level Context and Instance-Level RelationshipsPoster298 citations
363. Deep Learning of Graph MatchingPoster297 citations
364. MiCT: Mixed 3D/2D Convolutional Tube for Human Action RecognitionPoster295 citations
365. Attention Clusters: Purely Attention Based Local Feature Integration for Video ClassificationPoster292 citations
366. Fast End-to-End Trainable Guided FilterPoster291 citations
367. From Source to Target and Back: Symmetric Bi-Directional Adaptive GANPoster291 citations
368. Min-Entropy Latent Model for Weakly Supervised Object DetectionPoster291 citations
369. Preserving Semantic Relations for Zero-Shot LearningPoster291 citations
370. Deformable Shape Completion With Graph Convolutional AutoencodersPoster290 citations
371. Mean-Variance Loss for Deep Age Estimation From a FacePoster290 citations
372. Defense Against Universal Adversarial PerturbationsPoster289 citations
373. Hallucinated-IQA: No-Reference Image Quality Assessment via Adversarial LearningPoster289 citations
374. Long-Term On-Board Prediction of People in Traffic Scenes Under UncertaintyPoster288 citations
375. Face Aging With Identity-Preserved Conditional Generative Adversarial NetworksPoster287 citations
376. Multi-Frame Quality Enhancement for Compressed VideoPoster287 citations
377. Recurrent Saliency Transformation Network: Incorporating Multi-Stage Visual Cues for Small Organ SegmentationPoster285 citations
378. Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose EstimationPoster284 citations
379. SBNet: Sparse Blocks Network for Fast InferencePoster282 citations
380. Image Super-Resolution via Dual-State Recurrent NetworksPoster281 citations
381. An End-to-End TextSpotter With Explicit Alignment and AttentionPoster280 citations
382. Generative Modeling Using the Sliced Wasserstein DistancePoster280 citations
383. Group Consistent Similarity Learning via Deep CRF for Person Re-IdentificationPoster280 citations
384. Learning 3D Shape Completion From Laser Scan Data With Weak SupervisionPoster280 citations
385. Semantic Video Segmentation by Gated Recurrent Flow PropagationPoster279 citations
386. Deep Adversarial Metric LearningPoster277 citations
387. Depth-Based 3D Hand Pose Estimation: From Current Achievements to Future GoalsPoster277 citations
388. Referring Image Segmentation via Recurrent Refinement NetworksPoster275 citations
389. Bidirectional Attentive Fusion With Context Gating for Dense Video CaptioningPoster272 citations
390. Cross-Domain Self-Supervised Multi-Task Feature Learning Using Synthetic ImageryPoster272 citations
391. Divide and Grow: Capturing Huge Diversity in Crowd Images With Incrementally Growing CNNPoster271 citations
392. UV-GAN: Adversarial Facial UV Map Completion for Pose-Invariant Face RecognitionPoster271 citations
393. Iterative Visual Reasoning Beyond ConvolutionsPoster270 citations
394. Between-Class Learning for Image ClassificationPoster269 citations
395. Seeing Voices and Hearing Faces: Cross-Modal Biometric MatchingPoster269 citations
396. Interactive Image Segmentation With Latent DiversityPoster267 citations
397. Natural and Effective Obfuscation by Head InpaintingPoster266 citations
398. Decorrelated Batch NormalizationPoster265 citations
399. End-to-End Learning of Motion Representation for Video UnderstandingPoster265 citations
400. PlaneNet: Piece-Wise Planar Reconstruction From a Single RGB ImagePoster265 citations
401. Context-Aware Deep Feature Compression for High-Speed Visual TrackingPoster263 citations
402. Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual ReasoningPoster262 citations
403. Distort-and-Recover: Color Enhancement Using Deep Reinforcement LearningPoster261 citations
404. Neural Kinematic Networks for Unsupervised Motion RetargettingPoster261 citations
405. Single-Shot Object Detection With Enriched SemanticsPoster261 citations
406. Visual to Sound: Generating Natural Sound for Videos in the WildPoster261 citations
407. Ring Loss: Convex Feature Normalization for Face RecognitionPoster260 citations
408. Video Person Re-Identification With Competitive Snippet-Similarity Aggregation and Co-Attentive Snippet EmbeddingPoster260 citations
409. Single View Stereo MatchingPoster259 citations
410. Grounding Referring Expressions in Images by Variational ContextPoster257 citations
411. HSA-RNN: Hierarchical Structure-Adaptive RNN for Video SummarizationPoster257 citations
412. Variational Autoencoders for Deforming 3D Mesh ModelsPoster257 citations
413. CNN in MRF: Video Object Segmentation via Inference in a CNN-Based Higher-Order Spatio-Temporal MRFPoster256 citations
414. Unsupervised Sparse Dirichlet-Net for Hyperspectral Image Super-ResolutionPoster256 citations
415. Mobile Video Object Detection With Temporally-Aware Feature MapsPoster255 citations
416. Transductive Unbiased Embedding for Zero-Shot LearningPoster254 citations
417. Local Descriptors Optimized for Average PrecisionPoster253 citations
418. Monocular Relative Depth Perception With Web Stereo Data SupervisionPoster253 citations
419. Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark DetectorsPoster252 citations
420. Finding Tiny Faces in the Wild With Generative Adversarial NetworkPoster251 citations
421. Multi-Evidence Filtering and Fusion for Multi-Label Classification, Object Detection and Semantic Segmentation Based on Weakly Supervised LearningPoster251 citations
422. Improving Object Localization With Fitness NMS and Bounded IoU LossPoster247 citations
423. Temporal Deformable Residual Networks for Action Segmentation in VideosPoster247 citations
424. Deep Semantic Face DeblurringPoster245 citations
425. Learning Spatial-Aware Regressions for Visual TrackingPoster245 citations
426. Separating Style and Content for Generalized Style TransferPoster245 citations
427. Discriminability Objective for Training Descriptive CaptionsPoster244 citations
428. Future Person Localization in First-Person VideosPoster242 citations
429. Salient Object Detection Driven by Fixation PredictionPoster242 citations
430. Deep Adversarial Subspace ClusteringPoster241 citations
431. Visual Grounding via Accumulated AttentionPoster241 citations
432. Cube Padding for Weakly-Supervised Saliency Prediction in 360° VideosPoster240 citations
433. Lightweight Probabilistic Deep NetworksPoster237 citations
434. Crafting a Toolchain for Image Restoration by Deep Reinforcement LearningPoster235 citations
435. When Will You Do What? - Anticipating Temporal Occurrences of ActivitiesPoster235 citations
436. Learning to Parse Wireframes in Images of Man-Made EnvironmentsPoster233 citations
437. Multi-View Consistency as Supervisory Signal for Learning Shape and Pose PredictionPoster232 citations
438. Unsupervised Discovery of Object Landmarks as Structural RepresentationsPoster232 citations
439. Learning Dual Convolutional Neural Networks for Low-Level VisionPoster230 citations
440. PhaseNet for Video Frame InterpolationPoster230 citations
441. Pose-Guided Photorealistic Face RotationPoster228 citations
442. Video Rain Streak Removal by Multiscale Convolutional Sparse CodingPoster228 citations
443. Cross-View Image Synthesis Using Conditional GANsPoster227 citations
444. Unsupervised Cross-Dataset Person Re-Identification by Transfer Learning of Spatial-Temporal PatternsPoster227 citations
445. Jointly Localizing and Describing Events for Dense Video CaptioningPoster226 citations
446. Weakly-Supervised Action Segmentation With Iterative Soft Boundary AssignmentPoster225 citations
447. Erase or Fill? Deep Joint Recurrent Rain Removal and Reconstruction in VideosPoster224 citations
448. Learning Face Age Progression: A Pyramid Architecture of GANsPoster224 citations
449. WILDTRACK: A Multi-Camera HD Dataset for Dense Unscripted Pedestrian DetectionPoster222 citations
450. Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling PerspectivePoster219 citations
451. SeGAN: Segmenting and Generating the InvisiblePoster219 citations
452. AdaDepth: Unsupervised Content Congruent Adaptation for Depth EstimationPoster218 citations
453. Extreme 3D Face Reconstruction: Seeing Through OcclusionsPoster218 citations
454. Wide Compression: Tensor Ring NetsPoster217 citations
455. Arbitrary Style Transfer With Deep Feature ReshufflePoster216 citations
456. Duplex Generative Adversarial Network for Unsupervised Domain AdaptationPoster216 citations
457. FaceID-GAN: Learning a Symmetry Three-Player GAN for Identity-Preserving Face SynthesisPoster216 citations
458. LEGO: Learning Edge With Geometry All at Once by Watching VideosPoster215 citations
459. NAG: Network for Adversary GenerationPoster213 citations
460. Learning Deep Structured Active Contours End-to-EndPoster212 citations
461. Deep Regression Forests for Age EstimationPoster211 citations
462. Improving Landmark Localization With Semi-Supervised LearningPoster211 citations
463. Low-Latency Video Semantic SegmentationPoster211 citations
464. Unsupervised Person Image Synthesis in Arbitrary PosesPoster211 citations
465. Glimpse Clouds: Human Activity Recognition From Unstructured Feature PointsPoster210 citations
466. Rethinking Feature Distribution for Loss Functions in Image ClassificationPoster210 citations
467. Dense 3D Regression for Hand Pose EstimationPoster209 citations
468. Learning to Generate Time-Lapse Videos Using Multi-Stage Dynamic Generative Adversarial NetworksPoster209 citations
469. Robust Video Content Alignment and Compensation for Rain Removal in a CNN FrameworkPoster209 citations
470. Human-Centric Indoor Scene Synthesis Using Stochastic GrammarPoster207 citations
471. Flow Guided Recurrent Neural Encoder for Video Salient Object DetectionPoster205 citations
472. Recurrent Pixel Embedding for Instance GroupingPoster205 citations
473. Actor and Observer: Joint Modeling of First and Third-Person VideosPoster204 citations
474. End-to-End Weakly-Supervised Semantic AlignmentPoster204 citations
475. Super-Resolving Very Low-Resolution Face Images With Supplementary AttributesPoster204 citations
476. Deep Lesion Graphs in the Wild: Relationship Learning and Organization of Significant Radiology Image Findings in a Diverse Large-Scale Lesion DatabasePoster200 citations
477. Eliminating Background-Bias for Robust Person Re-IdentificationPoster200 citations
478. Visual Feature Attribution Using Wasserstein GANsPoster199 citations
479. Correlation Tracking via Joint Discrimination and Reliability LearningPoster198 citations
480. Hyperparameter Optimization for Tracking With Continuous Deep Q-LearningPoster198 citations
481. Semi-Parametric Image SynthesisPoster198 citations
482. Visual Question Generation as Dual Task of Visual Question AnsweringPoster198 citations
483. Actor and Action Video Segmentation From a SentencePoster197 citations
484. M3: Multimodal Memory Modelling for Video CaptioningPoster197 citations
485. Discriminative Learning of Latent Features for Zero-Shot RecognitionPoster196 citations
486. Learning Intrinsic Image Decomposition From Watching the WorldPoster196 citations
487. Anatomical Priors in Convolutional Networks for Unsupervised Biomedical SegmentationPoster195 citations
488. Learning a Discriminative Prior for Blind Image DeblurringPoster195 citations
489. LSTM Pose MachinesPoster191 citations
490. Learning to Evaluate Image CaptioningPoster191 citations
491. Audio to Body DynamicsPoster189 citations
492. Boosting Domain Adaptation by Discovering Latent DomainsPoster189 citations
493. Exploring Disentangled Feature Representation Beyond Face IdentificationPoster188 citations
494. Single-Image Depth Estimation Based on Fourier Domain AnalysisPoster188 citations
495. Emotional Attention: A Study of Image Sentiment and Visual AttentionPoster187 citations
496. Empirical Study of the Topology and Geometry of Deep NetworksPoster185 citations
497. MapNet: An Allocentric Spatial Memory for Mapping EnvironmentsPoster185 citations
498. Pose-Robust Face Recognition via Deep Residual Equivariant MappingPoster185 citations
499. Very Large-Scale Global SfM by Distributed Motion AveragingPoster183 citations
500. DA-GAN: Instance-Level Image Translation by Deep Attention Generative Adversarial NetworksPoster182 citations
501. Learning From Millions of 3D Scans for Large-Scale 3D Face RecognitionPoster182 citations
502. What Makes a Video a Video: Analyzing Temporal Information in Video Understanding Models and DatasetsPoster181 citations
503. Dynamic-Structured Semantic Propagation NetworkPoster180 citations
504. HydraNets: Specialized Dynamic Architectures for Efficient InferencePoster180 citations
505. ICE-BA: Incremental, Consistent and Efficient Bundle Adjustment for Visual-Inertial SLAMPoster180 citations
506. Zero-Shot Sketch-Image HashingPoster180 citations
507. Gesture Recognition: Focus on the HandsPoster179 citations
508. MovieGraphs: Towards Understanding Human-Centric Situations From VideosPoster179 citations
509. Attend and Interact: Higher-Order Object Interactions for Video UnderstandingPoster178 citations
510. Conditional Image-to-Image TranslationPoster178 citations
511. Deep Group-Shuffling Random Walk for Person Re-IdentificationPoster178 citations
512. Learning Descriptor Networks for 3D Shape Synthesis and AnalysisPoster176 citations
513. Sliced Wasserstein Distance for Learning Gaussian Mixture ModelsPoster176 citations
514. 3D Pose Estimation and 3D Model Retrieval for Objects in the WildPoster175 citations
515. A Hybrid l1-l0 Layer Decomposition Model for Tone MappingPoster175 citations
516. Dynamic Zoom-In Network for Fast Object Detection in Large ImagesPoster175 citations
517. Geometric Robustness of Deep Networks: Analysis and ImprovementPoster175 citations
518. Re-Weighted Adversarial Adaptation Network for Unsupervised Domain AdaptationPoster174 citations
519. NeuralNetwork-Viterbi: A Framework for Weakly Supervised Video LearningPoster173 citations
520. Learning Compact Recurrent Neural Networks With Block-Term Tensor DecompositionPoster171 citations
521. Disentangling 3D Pose in a Dendritic CNN for Unconstrained 2D Face AlignmentPoster170 citations
522. Who's Better? Who's Best? Pairwise Deep Ranking for Skill DeterminationPoster170 citations
523. Detail-Preserving Pooling in Deep NetworksPoster169 citations
524. SYQ: Learning Symmetric Quantization for Efficient Deep Neural NetworksPoster169 citations
525. Art of Singular Vectors and Universal Adversarial PerturbationsPoster168 citations
526. Deep Texture Manifold for Ground Terrain RecognitionPoster168 citations
527. DocUNet: Document Image Unwarping via a Stacked U-NetPoster168 citations
528. Creating Capsule Wardrobes From Fashion ImagesPoster167 citations
529. Learning Attribute Representations With Localization for Flexible Fashion SearchPoster167 citations
530. Person Re-Identification With Cascaded Pairwise ConvolutionsPoster167 citations
531. Two-Step Quantization for Low-Bit Neural NetworksPoster167 citations
532. End-to-End Deep Kronecker-Product Matching for Person Re-IdentificationPoster166 citations
533. Feature Mapping for Learning Fast and Accurate 3D Pose Inference From Synthetic ImagesPoster166 citations
534. Language-Based Image Editing With Recurrent Attentive ModelsPoster164 citations
535. MoNet: Deep Motion Exploitation for Video Object SegmentationPoster164 citations
536. Dynamic Video Segmentation NetworkPoster163 citations
537. Matryoshka Networks: Predicting 3D Geometry via Nested Shape LayersPoster163 citations
538. Dense Decoder Shortcut Connections for Single-Pass Semantic SegmentationPoster162 citations
539. Edit Probability for Scene Text RecognitionPoster162 citations
540. Enhancing the Spatial Resolution of Stereo Images Using a Parallax PriorPoster162 citations
541. Weakly Supervised Coupled Networks for Visual Sentiment AnalysisPoster161 citations
542. Convolutional Neural Networks With Alternately Updated CliquePoster160 citations
543. Interleaved Structured Sparse Convolutional Neural NetworksPoster160 citations
544. Seeing Small Faces From Robust Anchor's PerspectivePoster160 citations
545. Eye In-Painting With Exemplar Generative Adversarial NetworksPoster159 citations
546. LiDAR-Video Driving Dataset: Learning Driving Policies EffectivelyPoster158 citations
547. Low-Shot Learning With Large-Scale DiffusionPoster158 citations
548. Parallel Attention: A Unified Framework for Visual Object Discovery Through Dialogs and QueriesPoster158 citations
549. A PID Controller Approach for Stochastic Optimization of Deep NetworksPoster157 citations
550. Anticipating Traffic Accidents With Adaptive Loss and Large-Scale Incident DBPoster157 citations
551. Factoring Shape, Pose, and Layout From the 2D Image of a 3D ScenePoster157 citations
552. Lions and Tigers and Bears: Capturing Non-Rigid, 3D, Articulated Shape From ImagesPoster154 citations
553. MX-LSTM: Mixing Tracklets and Vislets to Jointly Forecast Trajectories and Head PosesPoster153 citations
554. From Lifestyle Vlogs to Everyday InteractionsPoster152 citations
555. SINT++: Robust Visual Tracking via Adversarial Positive Instance GenerationPoster152 citations
556. Learning Superpixels With Segmentation-Aware Affinity LossPoster151 citations
557. Modeling Facial Geometry Using Compositional VAEsPoster151 citations
558. Neural Style Transfer via Meta NetworksPoster151 citations
559. W2F: A Weakly-Supervised to Fully-Supervised Framework for Object DetectionPoster150 citations
560. Learning to Extract a Video Sequence From a Single Motion-Blurred ImagePoster149 citations
561. Lose the Views: Limited Angle CT Reconstruction via Implicit Sinogram CompletionPoster149 citations
562. Revisiting Salient Object Detection: Simultaneous Detection, Ranking, and Subitizing of Multiple Salient ObjectsPoster149 citations
563. SketchMate: Deep Hashing for Million-Scale Human Sketch RetrievalPoster149 citations
564. Are You Talking to Me? Reasoned Visual Dialog Generation Through Adversarial LearningPoster148 citations
565. Im2Struct: Recovering 3D Shape Structure From a Single RGB ImagePoster148 citations
566. Improvements to Context Based Self-Supervised LearningPoster148 citations
567. Self-Supervised Feature Learning by Learning to Spot ArtifactsPoster148 citations
568. ClusterNet: Detecting Small Objects in Large Scenes by Exploiting Spatio-Temporal InformationPoster147 citations
569. On the Duality Between Retinex and Image DehazingPoster147 citations
570. Weakly and Semi Supervised Human Body Part Parsing via Pose-Guided Knowledge TransferPoster147 citations
571. Geometry Guided Convolutional Neural Networks for Self-Supervised Video Representation LearningPoster146 citations
572. SemStyle: Learning to Generate Stylised Image Captions Using Unaligned TextPoster146 citations
573. Mining on Manifolds: Metric Learning Without LabelsPoster145 citations
574. Towards Universal Representation for Unseen Action RecognitionPoster145 citations
575. Unsupervised Deep Generative Adversarial Hashing NetworkPoster144 citations
576. A Perceptual Measure for Deep Single Image Camera CalibrationPoster143 citations
577. A2-RL: Aesthetics Aware Reinforcement Learning for Image CroppingPoster142 citations
578. Image Correction via Deep Reciprocating HDR TransformationPoster142 citations
579. Optimizing Video Object Detection via a Scale-Time LatticePoster141 citations
580. Pixels, Voxels, and Views: A Study of Shape Representations for Single View 3D Object Shape PredictionPoster141 citations
581. Zigzag Learning for Weakly Supervised Object DetectionPoster141 citations
582. Accurate and Diverse Sampling of Sequences Based on a “Best of Many” Sample ObjectivePoster140 citations
583. Direct Shape Regression Networks for End-to-End Face AlignmentPoster140 citations
584. Unsupervised Learning and Segmentation of Complex Activities From VideoPoster140 citations
585. Learning Markov Clustering Networks for Scene Text DetectionPoster139 citations
586. Learning to Sketch With Shortcut Cycle ConsistencyPoster139 citations
587. 3D Human Sensing, Action and Emotion Recognition in Robot Assisted Therapy of Children With AutismPoster137 citations
588. 4DFAB: A Large Scale 4D Database for Facial Expression Analysis and Biometric ApplicationsPoster137 citations
589. Towards Human-Machine Cooperation: Self-Supervised Sample Mining for Object DetectionPoster136 citations
590. CRRN: Multi-Scale Guided Concurrent Reflection Removal NetworkPoster135 citations
591. LIME: Live Intrinsic Material EstimationPoster135 citations
592. Clinical Skin Lesion Diagnosis Using Representations Inspired by Dermatologist CriteriaPoster134 citations
593. Real-Time Rotation-Invariant Face Detection With Progressive Calibration NetworksPoster134 citations
594. Sim2Real Viewpoint Invariant Visual Servoing by Recurrent ControlPoster134 citations
595. Visual Question Answering With Memory-Augmented NetworksPoster134 citations
596. Partially Shared Multi-Task Convolutional Neural Network With Local Constraint for Face Attribute LearningPoster133 citations
597. Demo2Vec: Reasoning Object Affordances From Online VideosPoster132 citations
598. Instance Embedding Transfer to Unsupervised Video Object SegmentationPoster132 citations
599. Missing Slice Recovery for Tensors Using a Low-Rank Model in Embedded SpacePoster132 citations
600. HashGAN: Deep Learning to Hash With Pair Conditional Wasserstein GANPoster131 citations
601. Motion-Guided Cascaded Refinement Network for Video Object SegmentationPoster131 citations
602. Recurrent Scene Parsing With Perspective Understanding in the LoopPoster131 citations
603. Learning to Look Around: Intelligently Exploring Unseen Environments for Unknown TasksPoster130 citations
604. Stereoscopic Neural Style TransferPoster130 citations
605. Analysis of Hand Segmentation in the WildPoster129 citations
606. Disentangling Features in 3D Face Shapes for Joint Face Reconstruction and RecognitionPoster129 citations
607. Deep End-to-End Time-of-Flight ImagingPoster128 citations
608. Detach and Adapt: Learning Cross-Domain Disentangled Deep RepresentationPoster127 citations
609. Learning Structure and Strength of CNN Filters for Small Sample Size TrainingPoster127 citations
610. R-FCN-3000 at 30fps: Decoupling Detection and ClassificationPoster127 citations
611. Revisiting Deep Intrinsic Image DecompositionsPoster127 citations
612. Soccer on Your TabletopPoster127 citations
613. Feature Space Transfer for Data AugmentationPoster126 citations
614. Finding Beans in Burgers: Deep Semantic-Visual Embedding With LocalizationPoster126 citations
615. Learning to Act Properly: Predicting and Explaining Affordances From ImagesPoster125 citations
616. Referring RelationshipsPoster125 citations
617. Zero-Shot Kernel LearningPoster125 citations
618. Interpret Neural Networks by Identifying Critical Data Routing PathsPoster122 citations
619. Quantization of Fully Convolutional Networks for Accurate Biomedical Image SegmentationPoster122 citations
620. Rotation Averaging and Strong DualityPoster121 citations
621. Blind Predicting Similar Quality Map for Image Quality AssessmentPoster120 citations
622. Controllable Video Generation With Sparse TrajectoriesPoster120 citations
623. Regularizing RNNs for Caption Generation by Reconstructing the Past With the PresentPoster120 citations
624. Deep Learning Under Privileged Information Using Heteroscedastic DropoutPoster119 citations
625. SobolevFusion: 3D Reconstruction of Scenes Undergoing Free Non-Rigid MotionPoster119 citations
626. Focal Visual-Text Attention for Visual Question AnsweringPoster118 citations
627. High-Speed Tracking With Multi-Kernel Correlation FiltersPoster118 citations
628. Human Pose Estimation With Parsing Induced LearnerPoster117 citations
629. Learning Deep Sketch AbstractionPoster117 citations
630. Im2Flow: Motion Hallucination From Static Images for Action RecognitionPoster116 citations
631. Action Sets: Weakly Supervised Action Segmentation Without Ordering ConstraintsPoster115 citations
632. Deeply Learned Filter Response Functions for Hyperspectral ReconstructionPoster115 citations
633. Hashing as Tie-Aware Learning to RankPoster115 citations
634. Left-Right Comparative Recurrent Model for Stereo MatchingPoster115 citations
635. RayNet: Learning Volumetric 3D Reconstruction With Ray PotentialsPoster115 citations
636. Finding "It": Weakly-Supervised Reference-Aware Visual Grounding in Instructional VideosPoster114 citations
637. Learning Latent Super-Events to Detect Multiple Activities in VideosPoster114 citations
638. People, Penguins and Petri Dishes: Adapting Object Counting Models to New Visual Domains and Object Types Without ForgettingPoster114 citations
639. Efficient and Deep Person Re-Identification Using Multi-Level SimilarityPoster113 citations
640. Knowledge Aided Consistency for Weakly Supervised Phrase GroundingPoster113 citations
641. Robust Facial Landmark Detection via a Fully-Convolutional Local-Global Context NetworkPoster112 citations
642. Connecting Pixels to Privacy and Utility: Automatic Redaction of Private Information in ImagesPoster111 citations
643. Geometry-Aware Scene Text Detection With Instance Transformation NetworkPoster111 citations
644. Good View Hunting: Learning Photo Composition From Dense View PairsPoster110 citations
645. Improving Occlusion and Hard Negative Handling for Single-Stage Pedestrian DetectorsPoster110 citations
646. Explicit Loss-Error-Aware Quantization for Low-Bit Deep Neural NetworksPoster109 citations
647. Learning Time/Memory-Efficient Deep Architectures With Budgeted Super NetworksPoster108 citations
648. Multi-Scale Weighted Nuclear Norm Image RestorationPoster108 citations
649. On the Importance of Label Quality for Semantic SegmentationPoster108 citations
650. Human Appearance TransferPoster106 citations
651. Reinforcement Cutting-Agent Learning for Video Object SegmentationPoster105 citations
652. Surface NetworksPoster105 citations
653. Multi-Scale Location-Aware Kernel Representation for Object DetectionPoster103 citations
654. Free Supervision From Video GamesPoster102 citations
655. OLÉ: Orthogonal Low-Rank Embedding - A Plug and Play Geometric Loss for Deep LearningPoster102 citations
656. Texture Mapping for 3D Reconstruction With RGB-D SensorPoster102 citations
657. Augmented Skeleton Space Transfer for Depth-Based Hand Pose EstimationPoster101 citations
658. Recognize Actions by Disentangling Components of DynamicsPoster101 citations
659. TOM-Net: Learning Transparent Object Matting From a Single ImagePoster101 citations
660. Two Can Play This Game: Visual Dialog With Discriminative Question Generation and AnsweringPoster101 citations
661. CarFusion: Combining Point Tracking and Part Detection for Dynamic 3D Reconstruction of VehiclesPoster100 citations
662. Learning to Detect Features in Texture ImagesPoster100 citations
663. GroupCap: Group-Based Image Captioning With Structured Relevance and Diversity ConstraintsPoster99 citations
664. Defocus Blur Detection via Multi-Stream Bottom-Top-Bottom Fully Convolutional NetworkPoster98 citations
665. SGAN: An Alternative Training of Generative Adversarial NetworksPoster98 citations
666. Differential Attention for Visual Question AnsweringPoster97 citations
667. Global Versus Localized Generative Adversarial NetsPoster97 citations
668. Inferring Shared Attention in Social Scene VideosPoster97 citations
669. Learning by Asking QuestionsPoster97 citations
670. Deep Spatio-Temporal Random Fields for Efficient Video SegmentationPoster96 citations
671. Sparse, Smart Contours to Represent and Edit ImagesPoster96 citations
672. Webly Supervised Learning Meets Zero-Shot Learning: A Hybrid Approach for Fine-Grained ClassificationPoster96 citations
673. Weakly Supervised Learning of Single-Cell Feature EmbeddingsPoster95 citations
674. Hierarchical Novelty Detection for Visual Object RecognitionPoster94 citations
675. CNN Based Learning Using Reflection and Retinex Models for Intrinsic Image DecompositionPoster93 citations
676. Disentangling Factors of Variation by Mixing ThemPoster93 citations
677. Generative Adversarial Learning Towards Fast Weakly Supervised DetectionPoster93 citations
678. Learning Generative ConvNets via Multi-Grid Modeling and SamplingPoster93 citations
679. A Constrained Deep Neural Network for Ordinal RegressionPoster92 citations
680. Deep Reinforcement Learning of Region Proposal Networks for Object DetectionPoster92 citations
681. Fooling Vision and Language Models Despite Localization and Attention MechanismPoster92 citations
682. Logo Synthesis and Manipulation With Clustered Generative Adversarial NetworksPoster92 citations
683. Non-Blind Deblurring: Handling Kernel Uncertainty With CNNsPoster91 citations
684. A Two-Step Disentanglement MethodPoster89 citations
685. Revisiting Knowledge Transfer for Training Object Class DetectorsPoster89 citations
686. Classification-Driven Dynamic Image EnhancementPoster88 citations
687. Learning Visual Knowledge Memory Networks for Visual Question AnsweringPoster88 citations
688. Bootstrapping the Performance of Webly Supervised Semantic SegmentationPoster87 citations
689. Inferring Light Fields From ShadowsPoster87 citations
690. SeedNet: Automatic Seed Generation With Deep Reinforcement Learning for Robust Interactive SegmentationPoster87 citations
691. Self-Supervised Learning of Geometrically Stable Features Through Probabilistic IntrospectionPoster87 citations
692. Who Let the Dogs Out? Modeling Dog Behavior From Visual DataPoster87 citations
693. Multi-Shot Pedestrian Re-Identification via Sequential Decision MakingPoster86 citations
694. Object Referring in Videos With Language and Human GazePoster86 citations
695. Teaching Categories to Human Learners With Visual ExplanationsPoster86 citations
696. A Memory Network Approach for Story-Based Temporal Summarization of 360° VideosPoster85 citations
697. Optimizing Filter Size in Convolutional Neural Networks for Facial Action Unit RecognitionPoster84 citations
698. A Network Architecture for Point Cloud Classification via Automatic Depth Images GenerationPoster82 citations
699. Deep Density Clustering of Unconstrained FacesPoster82 citations
700. Every Smile Is Unique: Landmark-Guided Diverse Smile GenerationPoster82 citations
701. Video Representation Learning Using Discriminative PoolingPoster82 citations
702. Where and Why Are They Looking? Jointly Inferring Human Attention and Intentions in Complex TasksPoster82 citations
703. Structured Uncertainty Prediction NetworksPoster81 citations
704. Decoupled NetworksPoster80 citations
705. Geometry-Aware Deep Network for Single-Image Novel View SynthesisPoster80 citations
706. Im2Pano3D: Extrapolating 360° Structure and Semantics Beyond the Field of ViewPoster80 citations
707. A Certifiably Globally Optimal Solution to the Non-Minimal Relative Pose ProblemPoster79 citations
708. Tracking Multiple Objects Outside the Line of Sight Using Speckle ImagingPoster78 citations
709. Trust Your Model: Light Field Depth Estimation With Inline Occlusion HandlingPoster78 citations
710. AMNet: Memorability Estimation With AttentionPoster77 citations
711. Hierarchical Recurrent Attention Networks for Structured Online MapsPoster77 citations
712. Multi-Task Adversarial Network for Disentangled Feature LearningPoster77 citations
713. Real-World Repetition Estimation by Div, Grad and CurlPoster77 citations
714. CBMV: A Coalesced Bidirectional Matching Volume for Disparity EstimationPoster76 citations
715. Coding Kendall's Shape Trajectories for 3D Action RecognitionPoster76 citations
716. Fine-Grained Video Captioning for Sports NarrativePoster76 citations
717. Hybrid Camera Pose EstimationPoster76 citations
718. InverseFaceNet: Deep Monocular Inverse Face RenderingPoster76 citations
719. Mesoscopic Facial Geometry Inference Using Deep Neural NetworksPoster76 citations
720. NestedNet: Learning Nested Sparse Structures in Deep Neural NetworksPoster76 citations
721. Scalable and Effective Deep CCA via Soft DecorrelationPoster76 citations
722. A Hierarchical Generative Model for Eye Image Synthesis and Eye Gaze EstimationPoster75 citations
723. Geometry Aware Constrained Optimization Techniques for Deep LearningPoster75 citations
724. Weakly Supervised Phrase Localization With Multi-Scale Anchored Transformer NetworkPoster75 citations
725. Beyond Grobner Bases: Basis Selection for Minimal SolversPoster74 citations
726. Deep Material-Aware Cross-Spectral Stereo MatchingPoster74 citations
727. Dynamic Feature Learning for Partial Face RecognitionPoster74 citations
728. Tensorize, Factorize and Regularize: Robust Visual Relationship LearningPoster74 citations
729. Document Enhancement Using Visibility DetectionPoster73 citations
730. A Low Power, High Throughput, Fully Event-Based Stereo SystemPoster72 citations
731. Light Field Intrinsics With a Deep Encoder-Decoder NetworkPoster72 citations
732. Multistage Adversarial Losses for Pose-Based Human Image SynthesisPoster72 citations
733. End-to-End Learning of Keypoint Detector and Descriptor for Pose Invariant 3D MatchingPoster71 citations
734. Learning Deep Descriptors With Scale-Aware Triplet NetworksPoster71 citations
735. Learning Facial Action Units From Web Images With Scalable Weakly Supervised ClusteringPoster71 citations
736. Learning Strict Identity Mappings in Deep Residual NetworksPoster71 citations
737. Interpretable Video Captioning via Trajectory Structured LocalizationPoster70 citations
738. Learning to Promote Saliency DetectorsPoster70 citations
739. GAGAN: Geometry-Aware Generative Adversarial NetworksPoster69 citations
740. SSNet: Scale Selection Network for Online 3D Action PredictionPoster68 citations
741. Zoom and Learn: Generalizing Deep Stereo Matching to Novel DomainsPoster68 citations
742. Automatic 3D Indoor Scene Modeling From Single PanoramaPoster67 citations
743. Going From Image to Video Saliency: Augmenting Image Salience With Dynamic Attentional PushPoster67 citations
744. Residual Parameter Transfer for Deep Domain AdaptationPoster67 citations
745. Structure Preserving Video PredictionPoster67 citations
746. Fast Spectral Ranking for Similarity SearchPoster66 citations
747. Geometry-Aware Network for Non-Rigid Shape Prediction From a Single ViewPoster66 citations
748. DeLS-3D: Deep Localization and Segmentation With a 3D Semantic MapPoster65 citations
749. FFNet: Video Fast-Forwarding via Reinforcement LearningPoster65 citations
750. Excitation Backprop for RNNsPoster64 citations
751. One-Shot Action Localization by Learning Sequence Matching NetworkPoster64 citations
752. Tagging Like Humans: Diverse and Distinct Image AnnotationPoster64 citations
753. Two-Stream Convolutional Networks for Dynamic Texture SynthesisPoster64 citations
754. Weakly-Supervised Deep Convolutional Neural Network Learning for Facial Action Unit Intensity EstimationPoster64 citations
755. Aperture Supervision for Monocular Depth EstimationPoster63 citations
756. Classifier Learning With Prior Probabilities for Facial Action Unit RecognitionPoster63 citations
757. Weakly Supervised Facial Action Unit Recognition Through Adversarial TrainingPoster63 citations
758. xUnit: Learning a Spatial Activation Function for Efficient Image RestorationPoster63 citations
759. Deep Diffeomorphic Transformer NetworksPoster62 citations
760. Density Adaptive Point Set RegistrationPoster62 citations
761. Efficient Optimization for Rank-Based Loss FunctionsPoster62 citations
762. Image Restoration by Estimating Frequency Distribution of Local PatchesPoster62 citations
763. Polarimetric Dense Monocular SLAMPoster62 citations
764. A Deeper Look at Power NormalizationsPoster61 citations
765. Aligning Infinite-Dimensional Covariance Matrices in Reproducing Kernel Hilbert Spaces for Domain AdaptationPoster61 citations
766. Cross-Dataset Adaptation for Visual Question AnsweringPoster61 citations
767. Feature Super-Resolution: Make Machine See More ClearlyPoster61 citations
768. CLEAR: Cumulative LEARning for One-Shot One-Class Image RecognitionPoster60 citations
769. Deep Cross-Media Knowledge TransferPoster60 citations
770. IVQA: Inverse Visual Question AnsweringPoster60 citations
771. Multi-Image Semantic Matching by Mining Consistent FeaturesPoster60 citations
772. The Best of Both Worlds: Combining CNNs and Geometric Constraints for Hierarchical Motion SegmentationPoster59 citations
773. Wasserstein Introspective Neural NetworksPoster59 citations
774. What Have We Learned From Deep Representations for Action Recognition?Poster59 citations
775. An Efficient and Provable Approach for Mixture Proportion Estimation Using Linear Independence AssumptionPoster58 citations
776. LAMV: Learning to Align and Match Videos With Kernelized Temporal LayersPoster58 citations
777. Optimal Structured Light à La CartePoster58 citations
778. Scalable Dense Non-Rigid Structure-From-Motion: A Grassmannian PerspectivePoster58 citations
779. Towards Dense Object Tracking in a 2D Honeybee HivePoster58 citations
780. Deep Hashing via Discrepancy MinimizationPoster57 citations
781. Egocentric Activity Recognition on a BudgetPoster57 citations
782. Facelet-Bank for Fast Portrait ManipulationPoster57 citations
783. Kernelized Subspace Pooling for Deep Local DescriptorsPoster57 citations
784. Learning Distributions of Shape Trajectories From Longitudinal Datasets: A Hierarchical Model on a Manifold of DiffeomorphismsPoster57 citations
785. Learning to Understand Image BlurPoster57 citations
786. End-to-End Convolutional Semantic EmbeddingsPoster55 citations
787. Improving Color Reproduction Accuracy on CamerasPoster55 citations
788. Efficient Large-Scale Approximate Nearest Neighbor Search on OpenCL FPGAPoster54 citations
789. Five-Point Fundamental Matrix Estimation for Uncalibrated CamerasPoster54 citations
790. Making Convolutional Networks Recurrent for Visual Sequence LearningPoster54 citations
791. Probabilistic Plant Modeling via Multi-View Image-to-Image TranslationPoster54 citations
792. A Robust Method for Strong Rolling Shutter Effects Correction Using Lines With Automatic Feature SelectionPoster53 citations
793. Bilateral Ordinal Relevance Multi-Instance Regression for Facial Action Unit Intensity EstimationPoster53 citations
794. DS*: Tighter Lifting-Free Convex Relaxations for Quadratic Matching ProblemsPoster53 citations
795. DeepVoting: A Robust and Explainable Deep Network for Semantic Part Detection Under Partial OcclusionPoster53 citations
796. LDMNet: Low Dimensional Manifold Regularized Neural NetworksPoster53 citations
797. Pseudo Mask Augmented Object DetectionPoster53 citations
798. Stacked Latent Attention for Multimodal ReasoningPoster53 citations
799. Unifying Identification and Context Learning for Person RecognitionPoster53 citations
800. View Extrapolation of Human Body From a Single ImagePoster53 citations
801. Generating a Fusion Image: One's Identity and Another's ShapePoster52 citations
802. Learning Intelligent Dialogs for Bounding Box AnnotationPoster52 citations
803. Wrapped Gaussian Process Regression on Riemannian ManifoldsPoster52 citations
804. Active Fixation Control to Predict Saccade SequencesPoster51 citations
805. Non-Linear Temporal Subspace Representations for Activity RecognitionPoster51 citations
806. Baseline Desensitizing in Translation AveragingPoster50 citations
807. Link and Code: Fast Indexing With Graphs and Compact Regression CodesPoster50 citations
808. Motion Segmentation by Exploiting Complementary Geometric ModelsPoster49 citations
809. Planar Shape Detection at Structural ScalesPoster49 citations
810. Alive Caricature From 2D to 3DPoster48 citations
811. Fight Ill-Posedness With Ill-Posedness: Single-Shot Variational Depth Super-Resolution From ShadingPoster48 citations
812. FlipDial: A Generative Model for Two-Way Visual DialoguePoster48 citations
813. Unsupervised Textual Grounding: Linking Words to Image ConceptsPoster48 citations
814. Matching Pixels Using Co-Occurrence StatisticsPoster47 citations
815. Perturbative Neural NetworksPoster47 citations
816. Radially-Distorted Conjugate TranslationsPoster47 citations
817. Recurrent Residual Module for Fast Inference in VideosPoster46 citations
818. Reward Learning From Narrated DemonstrationsPoster46 citations
819. Occlusion-Aware Rolling Shutter Rectification of 3D ScenesPoster45 citations
820. Bidirectional Retrieval Made SimplePoster44 citations
821. Learning Answer Embeddings for Visual Question AnsweringPoster44 citations
822. Intrinsic Image Transformation via Scale Space DecompositionPoster43 citations
823. PoseFlow: A Deep Motion Representation for Understanding Human Behaviors in VideosPoster43 citations
824. Uncalibrated Photometric Stereo Under Natural IlluminationPoster43 citations
825. Jerk-Aware Video Acceleration MagnificationPoster42 citations
826. MoNet: Moments Embedding NetworkPoster42 citations
827. Structured Set Matching Networks for One-Shot Part LabelingPoster42 citations
828. Towards a Mathematical Understanding of the Difficulty in Learning With Feedforward Neural NetworksPoster42 citations
829. Visual Question Reasoning on General Dependency TreePoster42 citations
830. Sparse Photometric 3D Face Reconstruction Guided by Morphable ModelsPoster41 citations
831. Structure From Recurrent Motion: From Rigidity to RecurrencyPoster41 citations
832. What Do Deep Networks Like to See?Poster41 citations
833. Beyond Trade-Off: Accelerate FCN-Based Face Detector With Higher AccuracyPoster40 citations
834. Modulated Convolutional NetworksPoster40 citations
835. Separating Self-Expression and Visual Content in Hashtag SupervisionPoster40 citations
836. Show Me a Story: Towards Coherent Neural Story IllustrationPoster40 citations
837. Camera Pose Estimation With Unknown Principal PointPoster39 citations
838. Geometric Multi-Model Fitting With a Convex Relaxation AlgorithmPoster39 citations
839. Guide Me: Interacting With Deep NetworksPoster39 citations
840. Reconstructing Thin Structures of Manifold Surfaces by Integrating Spatial CurvesPoster39 citations
841. Depth-Aware Stereo Video RetargetingPoster38 citations
842. DiverseNet: When One Right Answer Is Not EnoughPoster38 citations
843. Dynamic Graph Generation Network: Generating Relational Knowledge From DiagramsPoster38 citations
844. Egocentric Basketball Motion Planning From a Single First-Person ImagePoster38 citations
845. Latent RANSACPoster38 citations
846. GraphBit: Bitwise Interaction Mining via Deep Reinforcement LearningPoster37 citations
847. KIPPI: KInetic Polygonal Partitioning of ImagesPoster37 citations
848. Matching Adversarial NetworksPoster37 citations
849. Memory Based Online Learning of Deep Representations From Video StreamsPoster37 citations
850. Nonlocal Low-Rank Tensor Factor Analysis for Image RestorationPoster37 citations
851. A Causal And-Or Graph Model for Visibility Fluent Reasoning in Tracking Interacting ObjectsPoster36 citations
852. Analytic Expressions for Probabilistic Moments of PL-DNN With Gaussian InputPoster36 citations
853. Deep Cost-Sensitive and Order-Preserving Feature Learning for Cross-Population Age EstimationPoster36 citations
854. Mix and Match Networks: Encoder-Decoder Alignment for Zero-Pair Image TranslationPoster36 citations
855. A Weighted Sparse Sampling and Smoothing Frame Transition Approach for Semantic Fast-Forward First-Person VideosPoster35 citations
856. Beyond Holistic Object Recognition: Enriching Image Understanding With Part StatesPoster35 citations
857. Feature Quantization for Defending Against Distortion of ImagesPoster35 citations
858. Regularizing Deep Networks by Modeling and Predicting Label StructurePoster35 citations
859. Generating Synthetic X-Ray Images of a Person From the Surface GeometryPoster34 citations
860. Guided Proofreading of Automatic Segmentations for ConnectomicsPoster34 citations
861. Learning From Noisy Web Data With Category-Level SupervisionPoster34 citations
862. Textbook Question Answering Under Instructor Guidance With Memory NetworksPoster34 citations
863. A Common Framework for Interactive Texture TransferPoster33 citations
864. Shape From Shading Through Shape EvolutionPoster33 citations
865. A Prior-Less Method for Multi-Face Tracking in Unconstrained VideosPoster32 citations
866. Efficient Diverse Ensemble for Discriminative Co-TrackingPoster32 citations
867. Depth and Transient Imaging With Compressive SPAD Array CamerasPoster31 citations
868. Image Collection Pop-Up: 3D Reconstruction and Clustering of Rigid and Non-Rigid CategoriesPoster31 citations
869. Learning Pose Specific Representations by Predicting Different ViewsPoster31 citations
870. Pulling Actions out of Context: Explicit Separation for Effective CombinationPoster31 citations
871. SurfConv: Bridging 3D and 2D Convolution for RGBD ImagesPoster31 citations
872. 3D Object Detection With Latent Support SurfacesPoster30 citations
873. Deep Sparse Coding for Invariant Multimodal Halle Berry NeuronsPoster30 citations
874. Fusing Crowd Density Maps and Visual Object Trackers for People Tracking in Crowd ScenesPoster30 citations
875. Learning Compressible 360° Video IsomersPoster29 citations
876. Learning Globally Optimized Object Detector via Policy GradientPoster29 citations
877. Alternating-Stereo VINS: Observability Analysis and Performance EvaluationPoster28 citations
878. BPGrad: Towards Global Optimality in Deep Learning via Branch and PruningPoster28 citations
879. Large-Scale Distance Metric Learning With UncertaintyPoster28 citations
880. A Face-to-Face Neural Conversation ModelPoster27 citations
881. Distributable Consistent Multi-Object MatchingPoster27 citations
882. Feature Selective Networks for Object DetectionPoster27 citations
883. Salience Guided Depth Calibration for Perceptually Optimized Compressive Light Field 3D DisplayPoster27 citations
884. Sketch-a-Classifier: Sketch-Based Photo Classifier GenerationPoster27 citations
885. Tags2Parts: Discovering Semantic Regions From Shape TagsPoster27 citations
886. Coupled End-to-End Transfer Learning With Generalized Fisher InformationPoster26 citations
887. Now You Shake Me: Towards Automatic 4D CinemaPoster26 citations
888. OATM: Occlusion Aware Template Matching by Consensus Set MaximizationPoster26 citations
889. Generative Adversarial Image Synthesis With Decision Tree Latent ControllerPoster25 citations
890. Multiple Granularity Group Interaction PredictionPoster25 citations
891. Photometric Stereo in Participating Media Considering Shape-Dependent Forward ScatterPoster25 citations
892. Reflection Removal for Large-Scale 3D Point CloudsPoster25 citations
893. Temporal Hallucinating for Action Recognition With Few Still ImagesPoster25 citations
894. Inverse Composition Discriminative Optimization for Point Cloud RegistrationPoster24 citations
895. Lean Multiclass CrowdsourcingPoster24 citations
896. A Neural Multi-Sequence Alignment TeCHnique (NeuMATCH)Poster23 citations
897. Label Denoising Adversarial Network (LDAN) for Inverse Lighting of FacesPoster23 citations
898. Representing and Learning High Dimensional Data With the Optimal Transport Map From a Probabilistic ViewpointPoster23 citations
899. Spline Error Weighting for Robust Visual-Inertial FusionPoster23 citations
900. Exploiting Transitivity for Learning Person Re-Identification Models on a BudgetPoster22 citations
901. Globally Optimal Inlier Set Maximization for Atlanta Frame EstimationPoster22 citations
902. Easy Identification From Better Constraints: Multi-Shot Person Re-Identification From Reference ConstraintsPoster21 citations
903. Learning Multi-Instance Enriched Image Representations via Non-Greedy Ratio Maximization of the l1-Norm DistancesPoster21 citations
904. Manifold Learning in Quotient SpacesPoster21 citations
905. Probabilistic Joint Face-Skull Modelling for Facial ReconstructionPoster21 citations
906. Deformation Aware Image CompressionPoster19 citations
907. Joint Cuts and Matching of Partitions in One GraphPoster19 citations
908. Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional NetworksPoster19 citations
909. 3D Registration of Curves and Surfaces Using Local Differential InformationPoster18 citations
910. Adversarial Data Programming: Using GANs to Relax the Bottleneck of Curated Labeled DataPoster18 citations
911. Discovering Point Lights With Intensity Distance FieldsPoster18 citations
912. Fast Monte-Carlo Localization on Aerial Vehicles Using Approximate Continuous Belief RepresentationsPoster18 citations
913. Indoor RGB-D Compass From a Single Line and PlanePoster18 citations
914. pOSE: Pseudo Object Space Error for Initialization-Free Bundle AdjustmentPoster18 citations
915. Boundary Flow: A Siamese Network That Predicts Boundary Motion Without Training on MotionPoster17 citations
916. CNN Driven Sparse Multi-Level B-Spline Image RegistrationPoster17 citations
917. Learning Compositional Visual Concepts With Mutual ConsistencyPoster17 citations
918. Divide and Conquer for Full-Resolution Light Field DeblurringPoster16 citations
919. Illuminant Spectra-Based Source Separation Using Flash PhotographyPoster16 citations
920. Learning a Complete Image Indexing PipelinePoster16 citations
921. Multi-Task Learning by Maximizing Statistical DependencePoster16 citations
922. Robust Hough Transform Based 3D Reconstruction From Circular Light FieldsPoster16 citations
923. A Minimalist Approach to Type-Agnostic Detection of Quadrics in Point CloudsPoster15 citations
924. Analyzing Filters Toward Efficient ConvNetPoster15 citations
925. ClcNet: Improving the Efficiency of Convolutional Neural Network Using Channel Local ConvolutionsPoster15 citations
926. Dimensionality's Blessing: Clustering Images by Underlying DistributionPoster15 citations
927. Disentangling Structure and Aesthetics for Style-Aware Image CompletionPoster15 citations
928. Feedback-Prop: Convolutional Neural Network Inference Under Partial EvidencePoster15 citations
929. Focus Manipulation Detection via Photometric Histogram AnalysisPoster15 citations
930. Deep Face Detector Adaptation Without Negative Transfer or Catastrophic ForgettingPoster14 citations
931. Spatially-Adaptive Filter Units for Deep Neural NetworksPoster14 citations
932. 3D Semantic Trajectory Reconstruction From 3D Pixel ContinuumPoster13 citations
933. Multimodal Visual Concept Learning With Weakly Supervised TechniquesPoster13 citations
934. Multispectral Image Intrinsic Decomposition via Subspace ConstraintPoster13 citations
935. Objects as Context for Detecting Their Semantic PartsPoster13 citations
936. Statistical Tomography of Microscopic LifePoster13 citations
937. Content-Sensitive Supervoxels via Uniform Tessellations on Video ManifoldsPoster12 citations
938. Estimation of Camera Locations in Highly Corrupted Scenarios: All About That Base, No Shape TroublePoster12 citations
939. SoS-RSC: A Sum-of-Squares Polynomial Approach to Robustifying Subspace Clustering AlgorithmsPoster12 citations
940. A Fast Resection-Intersection Method for the Known Rotation ProblemPoster11 citations
941. Dual Skipping NetworksPoster11 citations
942. Modifying Non-Local Variations Across Multiple ViewsPoster11 citations
943. Rolling Shutter and Radial Distortion Are Features for High Frame Rate Multi-Camera TrackingPoster11 citations
944. Context Embedding NetworksPoster10 citations
945. Customized Image Narrative Generation via Interactive Visual Question Generation and AnsweringPoster10 citations
946. Discrete-Continuous ADMM for Transductive Inference in Higher-Order MRFsPoster10 citations
947. Fast and Robust Estimation for Unit-Norm Constrained Linear Fitting ProblemsPoster10 citations
948. Learned Shape-Tailored Descriptors for SegmentationPoster10 citations
949. Analytical Modeling of Vanishing Points and Curves in Catadioptric CamerasPoster9 citations
950. Augmenting Crowd-Sourced 3D Reconstructions Using Semantic DetectionsPoster9 citations
951. Compare and Contrast: Learning Prominent Visual DifferencesPoster9 citations
952. Learning Patch Reconstructability for Accelerating Multi-View StereoPoster9 citations
953. Multi-Cell Detection and Classification Using a Generative Convolutional ModelPoster9 citations
954. Consensus Maximization for Semantic Region CorrespondencesPoster8 citations
955. Environment Upgrade Reinforcement Learning for Non-Differentiable Multi-Stage PipelinesPoster8 citations
956. Local and Global Optimization Techniques in Graph-Based ClusteringPoster8 citations
957. Time-Resolved Light Transport Decomposition for Thermal Photometric StereoPoster8 citations
958. Trapping Light for Time of FlightPoster8 citations
959. Unsupervised Correlation AnalysisPoster8 citations
960. 4D Human Body Correspondences From Panoramic Depth MapsPoster7 citations
961. Categorizing Concepts With Basic Level for Vision-to-LanguagePoster7 citations
962. Inference in Higher Order MRF-MAP Problems With Small and Large CliquesPoster7 citations
963. Robust Depth Estimation From Auto Bracketed ImagesPoster7 citations
964. Self-Calibrating Polarising Radiometric CalibrationPoster7 citations
965. Continuous Relaxation of MAP Inference: A Nonconvex PerspectivePoster5 citations
966. Compassionately Conservative Balanced Cuts for Image SegmentationPoster4 citations
967. On the Convergence of PatchMatch and Its VariantsPoster4 citations
968. A Biresolution Spectral Framework for Product QuantizationPoster3 citations
969. Efficient, Sparse Representation of Manifold Distance Matrices for Classical ScalingPoster3 citations
970. Seeing Temporal Modulation of Lights From Standard CamerasPoster3 citations
971. Stochastic Variational Inference With Gradient LinearizationPoster3 citations
972. Curve Reconstruction via the Global Statistics of Natural CurvesPoster2 citations
973. Efficient Subpixel Refinement With Symbolic Linear PredictorsPoster1 citations
974. High-Order Tensor Regularization With Application to Attribute RankingPoster1 citations
975. CSGNet: Neural Shape Parser for Constructive Solid GeometryPoster
976. Independently Recurrent Neural Network (IndRNN): Building a Longer and Deeper RNNPoster
977. Solving the Perspective-2-Point Problem for Flying-Camera Photo CompositionPoster
978. Viewpoint-Aware Attentive Multi-View Inference for Vehicle Re-IdentificationPoster
979. Viewpoint-Aware Video SummarizationPoster

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