ECCV 2018 Accepted Papers

The full list of 776 papers accepted at ECCV 2018 (European Conference on Computer Vision). Click any title for details, similar papers, and links to the original source. You can also search these papers by meaning, not just keywords.

1. CBAM: Convolutional Block Attention ModulePoster27,863 citations
2. Encoder-Decoder with Atrous Separable Convolution for Semantic Image SegmentationPoster19,794 citations
3. ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture DesignPoster7,574 citations
4. Image Super-Resolution Using Very Deep Residual Channel Attention NetworksPoster6,094 citations
5. CornerNet: Detecting Objects as Paired KeypointsPoster5,272 citations
6. Group NormalizationPoster4,921 citations
7. Deep Clustering for Unsupervised Learning of Visual FeaturesPoster3,639 citations
8. BiSeNet: Bilateral Segmentation Network for Real-time Semantic SegmentationPoster3,213 citations
9. Multimodal Unsupervised Image-to-image TranslationPoster3,174 citations
10. Beyond Part Models: Person Retrieval with Refined Part Pooling (and A Strong Convolutional Baseline)Poster3,028 citations
11. Image Inpainting for Irregular Holes Using Partial ConvolutionsPoster2,727 citations
12. Progressive Neural Architecture SearchPoster2,549 citations
13. Simple Baselines for Human Pose Estimation and TrackingPoster2,531 citations
14. Unified Perceptual Parsing for Scene UnderstandingPoster2,392 citations
15. Memory Aware Synapses: Learning what (not) to forgetPoster2,053 citations
16. Receptive Field Block Net for Accurate and Fast Object DetectionPoster2,042 citations
17. ICNet for Real-Time Semantic Segmentation on High-Resolution ImagesPoster2,006 citations
18. Diverse Image-to-Image Translation via Disentangled RepresentationsPoster1,994 citations
19. Unsupervised Domain Adaptation for Semantic Segmentation via Class-Balanced Self-TrainingPoster1,784 citations
20. AMC: AutoML for Model Compression and Acceleration on Mobile DevicesPoster1,783 citations
21. Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video ClassificationPoster1,765 citations
22. Exploring the Limits of Weakly Supervised PretrainingPoster1,746 citations
23. Distractor-aware Siamese Networks for Visual Object TrackingPoster1,726 citations
24. Pixel2Mesh: Generating 3D Mesh Models from Single RGB ImagesPoster1,707 citations
25. Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual NetworkPoster1,650 citations
26. MVSNet: Depth Inference for Unstructured Multi-view StereoPoster1,625 citations
27. Stacked Cross Attention for Image-Text MatchingPoster1,536 citations
28. End-to-End Incremental LearningPoster1,533 citations
29. Riemannian Walk for Incremental Learning: Understanding Forgetting and IntransigencePoster1,482 citations
30. Temporal Relational Reasoning in VideosPoster1,356 citations
31. PSANet: Point-wise Spatial Attention Network for Scene ParsingPoster1,348 citations
32. Scaling Egocentric Vision: The EPIC-KITCHENS DatasetPoster1,329 citations
33. Recovering Accurate 3D Human Pose in The Wild Using IMUs and a Moving CameraPoster1,257 citations
34. Acquisition of Localization Confidence for Accurate Object DetectionPoster1,191 citations
35. TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the WildPoster1,191 citations
36. Deep Continuous Fusion for Multi-Sensor 3D Object DetectionPoster1,168 citations
37. ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic SegmentationPoster1,130 citations
38. Exploring Visual Relationship for Image CaptioningPoster1,123 citations
39. Recognition in Terra IncognitaPoster1,117 citations
40. HiDDeN: Hiding Data with Deep NetworksPoster1,092 citations
41. Graph R-CNN for Scene Graph GenerationPoster1,072 citations
42. Integral Human Pose RegressionPoster1,071 citations
43. Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image DerainingPoster1,039 citations
44. SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional FiltersPoster1,022 citations
45. Multi-scale Residual Network for Image Super-ResolutionPoster1,011 citations
46. Two at Once: Enhancing Learning and Generalization Capacities via IBN-NetPoster1,008 citations
47. The Unmanned Aerial Vehicle Benchmark: Object Detection and TrackingPoster974 citations
48. LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural NetworksPoster936 citations
49. Composition Loss for Counting, Density Map Estimation and Localization in Dense CrowdsPoster932 citations
50. Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression NetworkPoster930 citations
51. Videos as Space-Time Region GraphsPoster930 citations
52. Audio-Visual Scene Analysis with Self-Supervised Multisensory FeaturesPoster915 citations
53. Deep Domain Generalization via Conditional Invariant Adversarial NetworksPoster890 citations
54. DeepIM: Deep Iterative Matching for 6D Pose EstimationPoster889 citations
55. BSN: Boundary Sensitive Network for Temporal Action Proposal GenerationPoster866 citations
56. SkipNet: Learning Dynamic Routing in Convolutional NetworksPoster837 citations
57. Scale Aggregation Network for Accurate and Efficient Crowd CountingPoster835 citations
58. Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask WeightsPoster831 citations
59. PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding ModelPoster821 citations
60. Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary ShapesPoster782 citations
61. GANimation: Anatomically-aware Facial Animation from a Single ImagePoster773 citations
62. Triplet Loss in Siamese Network for Object TrackingPoster768 citations
63. Reverse Attention for Salient Object DetectionPoster767 citations
64. Data-Driven Sparse Structure Selection for Deep Neural NetworksPoster757 citations
65. NetAdapt: Platform-Aware Neural Network Adaptation for Mobile ApplicationsPoster746 citations
66. Generating 3D Faces using Convolutional Mesh AutoencodersPoster736 citations
67. Bi-Real Net: Enhancing the Performance of 1-bit CNNs with Improved Representational Capability and Advanced Training AlgorithmPoster713 citations
68. Learning Category-Specific Mesh Reconstruction from Image CollectionsPoster710 citations
69. TextSnake: A Flexible Representation for Detecting Text of Arbitrary ShapesPoster707 citations
70. Implicit 3D Orientation Learning for 6D Object Detection from RGB ImagesPoster699 citations
71. Learning Human-Object Interactions by Graph Parsing Neural NetworksPoster693 citations
72. DeepPhys: Video-Based Physiological Measurement Using Convolutional Attention NetworksPoster686 citations
73. Learning to Navigate for Fine-grained ClassificationPoster686 citations
74. Open Set Domain Adaptation by BackpropagationPoster686 citations
75. ECO: Efficient Convolutional Network for Online Video UnderstandingPoster680 citations
76. Part-Aligned Bilinear Representations for Person Re-IdentificationPoster671 citations
77. ExFuse: Enhancing Feature Fusion for Semantic SegmentationPoster665 citations
78. Objects that SoundPoster656 citations
79. The Sound of PixelsPoster638 citations
80. Shift-Net: Image Inpainting via Deep Feature RearrangementPoster628 citations
81. Learning SO(3) Equivariant Representations with Spherical CNNsPoster617 citations
82. Deep Co-Training for Semi-Supervised Image RecognitionPoster612 citations
83. Unveiling the Power of Deep TrackingPoster605 citations
84. Learning Deep Representations with Probabilistic Knowledge TransferPoster597 citations
85. YouTube-VOS: Sequence-to-Sequence Video Object SegmentationPoster594 citations
86. Open Set Learning with Counterfactual ImagesPoster593 citations
87. Pyramid Dilated Deeper ConvLSTM for Video Salient Object DetectionPoster593 citations
88. A Systematic DNN Weight Pruning Framework using Alternating Direction Method of MultipliersPoster588 citations
89. DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task ConsistencyPoster585 citations
90. DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain AdaptationPoster579 citations
91. Audio-Visual Event Localization in Unconstrained VideosPoster575 citations
92. Partial Adversarial Domain AdaptationPoster573 citations
93. Pose-Normalized Image Generation for Person Re-identificationPoster566 citations
94. Generalizing A Person Retrieval Model Hetero- and HomogeneouslyPoster561 citations
95. Towards Robust Neural Networks via Random Self-ensemblePoster560 citations
96. SOD-MTGAN: Small Object Detection via Multi-Task Generative Adversarial NetworkPoster559 citations
97. Fighting Fake News: Image Splice Detection via Learned Self-ConsistencyPoster550 citations
98. Occlusion-aware R-CNN: Detecting Pedestrians in a CrowdPoster544 citations
99. PyramidBox: A Context-assisted Single Shot Face DetectorPoster536 citations
100. BOP: Benchmark for 6D Object Pose EstimationPoster532 citations
101. BodyNet: Volumetric Inference of 3D Human Body ShapesPoster530 citations
102. Women also Snowboard: Overcoming Bias in Captioning ModelsPoster526 citations
103. How good is my GAN?Poster511 citations
104. X2Face: A network for controlling face generation using images, audio, and pose codesPoster511 citations
105. To learn image super-resolution, use a GAN to learn how to do image degradation firstPoster510 citations
106. Deep Metric Learning with Hierarchical Triplet LossPoster509 citations
107. Mancs: A Multi-task Attentional Network with Curriculum Sampling for Person Re-identificationPoster501 citations
108. Multi-Attention Multi-Class Constraint for Fine-grained Image RecognitionPoster501 citations
109. Toward Characteristic-Preserving Image-based Virtual Try-On NetworkPoster501 citations
110. Tracking Emerges by Colorizing VideosPoster497 citations
111. Exploiting temporal information for 3D human pose estimationPoster493 citations
112. A Closed-form Solution to Photorealistic Image StylizationPoster492 citations
113. Multi-modal Cycle-consistent Generalized Zero-Shot LearningPoster491 citations
114. Convolutional Networks with Adaptive Inference GraphsPoster487 citations
115. Deep Cross-Modal Projection Learning for Image-Text MatchingPoster485 citations
116. Is Robustness the Cost of Accuracy? -- A Comprehensive Study on the Robustness of 18 Deep Image Classification ModelsPoster484 citations
117. PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local DescriptorsPoster476 citations
118. The Contextual Loss for Image Transformation with Non-Aligned DataPoster474 citations
119. Dynamic Task Prioritization for Multitask LearningPoster470 citations
120. StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth PredictionPoster461 citations
121. Zero-Shot Object DetectionPoster457 citations
122. Local Spectral Graph Convolution for Point Set Feature LearningPoster456 citations
123. Online Multi-Object Tracking with Dual Matching Attention NetworksPoster455 citations
124. SphereNet: Learning Spherical Representations for Detection and Classification in Omnidirectional ImagesPoster453 citations
125. Learning Blind Video Temporal ConsistencyPoster452 citations
126. 3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud RegistrationPoster439 citations
127. Skeleton-Based Action Recognition with Spatial Reasoning and Temporal Stack LearningPoster439 citations
128. Recycle-GAN: Unsupervised Video RetargetingPoster437 citations
129. A Joint Sequence Fusion Model for Video Question Answering and RetrievalPoster435 citations
130. Textual Explanations for Self-Driving VehiclesPoster431 citations
131. RESOUND: Towards Action Recognition without Representation BiasPoster429 citations
132. SegStereo: Exploiting Semantic Information for Disparity EstimationPoster429 citations
133. Deep Virtual Stereo Odometry: Leveraging Deep Depth Prediction for Monocular Direct Sparse OdometryPoster427 citations
134. Video Compression through Image InterpolationPoster424 citations
135. RT-GENE: Real-Time Eye Gaze Estimation in Natural EnvironmentsPoster423 citations
136. Instance-level Human Parsing via Part Grouping NetworkPoster421 citations
137. License Plate Detection and Recognition in Unconstrained ScenariosPoster420 citations
138. CurriculumNet: Weakly Supervised Learning from Large-Scale Web ImagesPoster418 citations
139. Hierarchical Bilinear Pooling for Fine-Grained Visual RecognitionPoster417 citations
140. 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene SegmentationPoster416 citations
141. In the Eye of Beholder: Joint Learning of Gaze and Actions in First Person VideoPoster411 citations
142. Towards End-to-End License Plate Detection and Recognition: A Large Dataset and BaselinePoster410 citations
143. Learning Dynamic Memory Networks for Object TrackingPoster405 citations
144. 3D-CODED: 3D Correspondences by Deep DeformationPoster400 citations
145. Depth Estimation via Affinity Learned with Convolutional Spatial Propagation NetworkPoster399 citations
146. W-TALC: Weakly-supervised Temporal Activity Localization and ClassificationPoster397 citations
147. MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual NetworkPoster394 citations
148. Hand Pose Estimation via Latent 2.5D Heatmap RegressionPoster393 citations
149. Transferring GANs: generating images from limited dataPoster393 citations
150. Facial Expression Recognition with Inconsistently Annotated DatasetsPoster389 citations
151. Interpretable Basis Decomposition for Visual ExplanationPoster383 citations
152. On Regularized Losses for Weakly-supervised CNN SegmentationPoster383 citations
153. Person Re-identification with Deep Similarity-Guided Graph Neural NetworkPoster383 citations
154. Multi-Scale Structure-Aware Network for Human Pose EstimationPoster382 citations
155. Salient Objects in Clutter: Bringing Salient Object Detection to the ForegroundPoster380 citations
156. BusterNet: Detecting Copy-Move Image Forgery with Source/Target LocalizationPoster378 citations
157. Factorizable Net: An Efficient Subgraph-based Framework for Scene Graph GenerationPoster365 citations
158. Parallel Feature Pyramid Network for Object DetectionPoster365 citations
159. Weakly-supervised 3D Hand Pose Estimation from Monocular RGB ImagesPoster365 citations
160. 3D Recurrent Neural Networks with Context Fusion for Point Cloud Semantic SegmentationPoster362 citations
161. Real-Time MDNetPoster361 citations
162. Iterative Crowd CountingPoster358 citations
163. VideoMatch: Matching based Video Object SegmentationPoster358 citations
164. CIRL: Controllable Imitative Reinforcement Learning for Vision-based Self-drivingPoster357 citations
165. Recurrent Fusion Network for Image captioningPoster354 citations
166. Depth-aware CNN for RGB-D SegmentationPoster353 citations
167. AugGAN: Cross Domain Adaptation with GAN-based Data AugmentationPoster350 citations
168. Contextual-based Image Inpainting: Infer, Match, and TranslatePoster346 citations
169. AutoLoc: Weakly-supervised Temporal Action Localization in Untrimmed VideosPoster343 citations
170. Verisimilar Image Synthesis for Accurate Detection and Recognition of Texts in ScenesPoster341 citations
171. EC-Net: an Edge-aware Point set Consolidation NetworkPoster340 citations
172. Face De-Spoofing: Anti-Spoofing via Noise ModelingPoster340 citations
173. Learning to Predict Crisp BoundariesPoster337 citations
174. Proximal Dehaze-Net: A Prior Learning-Based Deep Network for Single Image DehazingPoster337 citations
175. Contour Knowledge Transfer for Salient Object DetectionPoster336 citations
176. Video Summarization Using Fully Convolutional Sequence NetworksPoster335 citations
177. Multiresolution Tree Networks for 3D Point Cloud ProcessingPoster334 citations
178. Deep High Dynamic Range Imaging with Large Foreground MotionsPoster330 citations
179. Practical Black-box Attacks on Deep Neural Networks using Efficient Query MechanismsPoster325 citations
180. Structured Siamese Network for Real-Time Visual TrackingPoster325 citations
181. Superpixel Sampling NetworksPoster325 citations
182. Learning to Separate Object Sounds by Watching Unlabeled VideoPoster324 citations
183. Learning Efficient Single-stage Pedestrian Detectors by Asymptotic Localization FittingPoster319 citations
184. Adversarial Geometry-Aware Human Motion PredictionPoster317 citations
185. DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene AdaptationPoster317 citations
186. Modeling Visual Context is Key to Augmenting Object Detection DatasetsPoster314 citations
187. Unsupervised Geometry-Aware Representation for 3D Human Pose EstimationPoster313 citations
188. Bidirectional Feature Pyramid Network with Recurrent Attention Residual Modules for Shadow DetectionPoster312 citations
189. A Trilateral Weighted Sparse Coding Scheme for Real-World Image DenoisingPoster308 citations
190. Deeply Learned Compositional Models for Human Pose EstimationPoster308 citations
191. Lip Movements Generation at a GlancePoster307 citations
192. Transferable Adversarial PerturbationsPoster307 citations
193. Revisiting RCNN: On Awakening the Classification Power of Faster RCNNPoster306 citations
194. Out-of-Distribution Detection Using an Ensemble of Self Supervised Leave-out ClassifiersPoster305 citations
195. Transductive Semi-Supervised Deep Learning using Min-Max FeaturesPoster301 citations
196. Learning Type-Aware Embeddings for Fashion CompatibilityPoster300 citations
197. Unsupervised Person Re-identification by Deep Learning Tracklet AssociationPoster298 citations
198. Self-produced Guidance for Weakly-supervised Object LocalizationPoster297 citations
199. Domain Adaptation through Synthesis for Unsupervised Person Re-identificationPoster295 citations
200. Making Deep Heatmaps Robust to Partial Occlusions for 3D Object Pose EstimationPoster295 citations
201. Multi-object Tracking with Neural Gating Using Bilinear LSTMPoster295 citations
202. R2P2: A ReparameteRized Pushforward Policy for Diverse, Precise Generative Path ForecastingPoster295 citations
203. Object Detection in Video with Spatiotemporal Sampling NetworksPoster291 citations
204. DeepTAM: Deep Tracking and MappingPoster285 citations
205. Model Adaptation with Synthetic and Real Data for Semantic Dense Foggy Scene UnderstandingPoster285 citations
206. Propagating LSTM: 3D Pose Estimation based on Joint InterdependencyPoster285 citations
207. RIDI: Robust IMU Double IntegrationPoster285 citations
208. A Style-Aware Content Loss for Real-time HD Style TransferPoster283 citations
209. Compound Memory Networks for Few-shot Video ClassificationPoster282 citations
210. Pairwise Confusion for Fine-Grained Visual ClassificationPoster282 citations
211. Actor-centric Relation NetworkPoster280 citations
212. OmniDepth: Dense Depth Estimation for Indoors Spherical PanoramasPoster280 citations
213. Multi-Fiber Networks for Video RecognitionPoster278 citations
214. Deep Regression Tracking with Shrinkage LossPoster277 citations
215. Attention-based Ensemble for Deep Metric LearningPoster276 citations
216. RelocNet: Continuous Metric Learning Relocalisation using Neural NetsPoster276 citations
217. Deep Feature Pyramid Reconfiguration for Object DetectionPoster275 citations
218. Repeatability Is Not Enough: Learning Affine Regions via DiscriminabilityPoster275 citations
219. Deep Imbalanced Attribute Classification using Visual Attention AggregationPoster274 citations
220. DPP-Net: Device-aware Progressive Search for Pareto-optimal Neural ArchitecturesPoster272 citations
221. Less is More: Picking Informative Frames for Video CaptioningPoster272 citations
222. Learning to Anonymize Faces for Privacy Preserving Action DetectionPoster271 citations
223. CrossNet: An End-to-end Reference-based Super Resolution Network using Cross-scale WarpingPoster270 citations
224. Uncertainty Estimates and Multi-Hypotheses Networks for Optical FlowPoster270 citations
225. Deep Fundamental Matrix EstimationPoster269 citations
226. Dense Pose TransferPoster269 citations
227. Improving DNN Robustness to Adversarial Attacks using Jacobian RegularizationPoster269 citations
228. Face Super-resolution Guided by Facial Component HeatmapsPoster267 citations
229. Graininess-Aware Deep Feature Learning for Pedestrian DetectionPoster267 citations
230. Learning 3D Human Pose from Structure and MotionPoster264 citations
231. The Devil of Face Recognition is in the NoisePoster263 citations
232. Joint Task-Recursive Learning for Semantic Segmentation and Depth EstimationPoster261 citations
233. Look Before You Leap: Bridging Model-Free and Model-Based Reinforcement Learning for Planned-Ahead Vision-and-Language NavigationPoster259 citations
234. Fully Motion-Aware Network for Video Object DetectionPoster258 citations
235. Video Object Segmentation with Joint Re-identification and Attention-Aware Mask PropagationPoster257 citations
236. Lifelong Learning via Progressive Distillation and RetrospectionPoster256 citations
237. Look Deeper into Depth: Monocular Depth Estimation with Semantic Booster and Attention-Driven LossPoster256 citations
238. Jointly Discovering Visual Objects and Spoken Words from Raw Sensory InputPoster254 citations
239. Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow EstimationPoster254 citations
240. Wasserstein Divergence for GANsPoster254 citations
241. Where are the blobs: Counting by Localization with Point SupervisionPoster254 citations
242. Bi-box Regression for Pedestrian Detection and Occlusion EstimationPoster252 citations
243. Attribute-Guided Face Generation Using Conditional CycleGANPoster250 citations
244. Grounding Visual ExplanationsPoster250 citations
245. Deforming Autoencoders: Unsupervised Disentangling of Shape and AppearancePoster249 citations
246. Fully-Convolutional Point Networks for Large-Scale Point CloudsPoster247 citations
247. ReenactGAN: Learning to Reenact Faces via Boundary TransferPoster247 citations
248. Weakly Supervised Region Proposal Network and Object DetectionPoster247 citations
249. Adaptive Affinity Fields for Semantic SegmentationPoster246 citations
250. DetNet: Design Backbone for Object DetectionPoster246 citations
251. Video Object Detection with an Aligned Spatial-Temporal MemoryPoster246 citations
252. Learning with Biased Complementary LabelsPoster245 citations
253. Person Search via A Mask-guided Two-stream CNN ModelPoster245 citations
254. Explainable Neural Computation via Stack Neural Module NetworksPoster243 citations
255. ELEGANT: Exchanging Latent Encodings with GAN for Transferring Multiple Face AttributesPoster240 citations
256. Spatio-Temporal Channel Correlation Networks for Action ClassificationPoster239 citations
257. DeepWrinkles: Accurate and Realistic Clothing ModelingPoster237 citations
258. Learning Monocular Depth by Distilling Cross-domain Stereo NetworksPoster237 citations
259. Deep Pictorial Gaze EstimationPoster234 citations
260. Modality Distillation with Multiple Stream Networks for Action RecognitionPoster234 citations
261. Learning Shape Priors for Single-View 3D Completion and ReconstructionPoster232 citations
262. Unsupervised Learning of Multi-Frame Optical Flow with OcclusionsPoster232 citations
263. SRFeat: Single Image Super-Resolution with Feature DiscriminationPoster231 citations
264. Attention-GAN for Object Transfiguration in Wild ImagesPoster229 citations
265. Attributes as Operators: Factorizing Unseen Attribute-Object CompositionsPoster227 citations
266. Dynamic Multimodal Instance Segmentation Guided by Natural Language QueriesPoster227 citations
267. Value-aware Quantization for Training and Inference of Neural NetworksPoster227 citations
268. Learning to Detect and Track Visible and Occluded Body Joints in a Virtual WorldPoster226 citations
269. T2Net: Synthetic-to-Realistic Translation for Solving Single-Image Depth Estimation TasksPoster225 citations
270. ConvNets and ImageNet Beyond Accuracy: Understanding Mistakes and Uncovering BiasesPoster224 citations
271. Visual Coreference Resolution in Visual Dialog using Neural Module NetworksPoster224 citations
272. Deep Adaptive Attention for Joint Facial Action Unit Detection and Face AlignmentPoster223 citations
273. DeepVS: A Deep Learning Based Video Saliency Prediction ApproachPoster223 citations
274. Weakly- and Semi-Supervised Panoptic SegmentationPoster223 citations
275. Distortion-Aware Convolutional Filters for Dense Prediction in Panoramic ImagesPoster221 citations
276. A Zero-Shot Framework for Sketch based Image RetrievalPoster220 citations
277. Learning-based Video Motion MagnificationPoster220 citations
278. Quaternion Convolutional Neural NetworksPoster220 citations
279. CTAP: Complementary Temporal Action Proposal GenerationPoster219 citations
280. Meta-Tracker: Fast and Robust Online Adaptation for Visual Object TrackersPoster219 citations
281. Point-to-Point Regression PointNet for 3D Hand Pose EstimationPoster219 citations
282. WildDash - Creating Hazard-Aware BenchmarksPoster217 citations
283. GeoDesc: Learning Local Descriptors by Integrating Geometry ConstraintsPoster216 citations
284. Key-Word-Aware Network for Referring Expression Image SegmentationPoster214 citations
285. End-to-End Learning of Driving Models with Surround-View Cameras and Route PlannersPoster213 citations
286. Deep Model-Based 6D Pose Refinement in RGBPoster211 citations
287. Multi-Scale Context Intertwining for Semantic SegmentationPoster211 citations
288. A Unified Framework for Multi-View Multi-Class Object Pose EstimationPoster208 citations
289. Object Level Visual Reasoning in VideosPoster207 citations
290. Long-term Tracking in the Wild: a BenchmarkPoster206 citations
291. Effective Use of Synthetic Data for Urban Scene Semantic SegmentationPoster205 citations
292. Self-supervised Knowledge Distillation Using Singular Value DecompositionPoster205 citations
293. Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot StudyPoster205 citations
294. Spatio-temporal Transformer Network for Video RestorationPoster203 citations
295. Seeing Deeply and Bidirectionally: A Deep Learning Approach for Single Image Reflection RemovalPoster201 citations
296. Appearance-Based Gaze Estimation via Evaluation-Guided Asymmetric RegressionPoster196 citations
297. Semi-Dense 3D Reconstruction with a Stereo Event CameraPoster196 citations
298. ContextVP: Fully Context-Aware Video PredictionPoster194 citations
299. Stereo Vision-based Semantic 3D Object and Ego-motion Tracking for Autonomous DrivingPoster194 citations
300. Supervising the new with the old: learning SFM from SFMPoster191 citations
301. TS2C: Tight Box Mining with Surrounding Segmentation Context for Weakly Supervised Object DetectionPoster190 citations
302. Generative Adversarial Network with Spatial Attention for Face Attribute EditingPoster189 citations
303. CGIntrinsics: Better Intrinsic Image Decomposition through Physically-Based RenderingPoster188 citations
304. Deep Video Generation, Prediction and Completion of Human Action SequencesPoster186 citations
305. PS-FCN: A Flexible Learning Framework for Photometric StereoPoster186 citations
306. Person Search by Multi-Scale MatchingPoster186 citations
307. Real-time 'Actor-Critic' TrackingPoster186 citations
308. SDC-Net: Video prediction using spatially-displaced convolutionPoster185 citations
309. Learning to Zoom: a Saliency-Based Sampling Layer for Neural NetworksPoster184 citations
310. Materials for Masses: SVBRDF Acquisition with a Single Mobile Phone ImagePoster184 citations
311. MT-VAE: Learning Motion Transformations to Generate Multimodal Human DynamicsPoster183 citations
312. CNN-PS: CNN-based Photometric Stereo for General Non-Convex SurfacesPoster181 citations
313. Asynchronous, Photometric Feature Tracking using Events and FramesPoster180 citations
314. Hard-Aware Point-to-Set Deep Metric for Person Re-identificationPoster180 citations
315. stagNet: An Attentive Semantic RNN for Group Activity RecognitionPoster180 citations
316. Compositional Learning for Human Object InteractionPoster179 citations
317. Layer-structured 3D Scene Inference via View SynthesisPoster179 citations
318. Macro-Micro Adversarial Network for Human ParsingPoster179 citations
319. Saliency Detection in 360° VideosPoster178 citations
320. CAR-Net: Clairvoyant Attentive Recurrent NetworkPoster177 citations
321. Learning Warped Guidance for Blind Face RestorationPoster177 citations
322. Zoom-Net: Mining Deep Feature Interactions for Visual Relationship RecognitionPoster177 citations
323. CubeNet: Equivariance to 3D Rotation and TranslationPoster176 citations
324. Learnable PINs: Cross-Modal Embeddings for Person IdentityPoster176 citations
325. Cross-Modal and Hierarchical Modeling of Video and TextPoster175 citations
326. Image Generation from Sketch Constraint Using Contextual GANPoster174 citations
327. Mutual Learning to Adapt for Joint Human Parsing and Pose EstimationPoster174 citations
328. Fast Light Field Reconstruction With Deep Coarse-To-Fine Modeling of Spatial-Angular CluesPoster173 citations
329. FloorNet: A Unified Framework for Floorplan Reconstruction from 3D ScansPoster173 citations
330. Small-scale Pedestrian Detection Based on Topological Line Localization and Temporal Feature AggregationPoster172 citations
331. Holistic 3D Scene Parsing and Reconstruction from a Single RGB ImagePoster171 citations
332. Improving Deep Visual Representation for Person Re-identification by Global and Local Image-language AssociationPoster169 citations
333. Pairwise Body-Part Attention for Recognizing Human-Object InteractionsPoster169 citations
334. Predicting Gaze in Egocentric Video by Learning Task-dependent Attention TransitionPoster168 citations
335. Multi-view to Novel view: Synthesizing novel views with Self-Learned ConfidencePoster166 citations
336. Pose Guided Human Video GenerationPoster166 citations
337. Quantized Densely Connected U-Nets for Efficient Landmark LocalizationPoster166 citations
338. Semantic Match Consistency for Long-Term Visual LocalizationPoster166 citations
339. Show, Tell and Discriminate: Image Captioning by Self-retrieval with Partially Labeled DataPoster166 citations
340. A Modulation Module for Multi-task Learning with Applications in Image RetrievalPoster165 citations
341. Orthogonal Deep Features Decomposition for Age-Invariant Face RecognitionPoster165 citations
342. Deep Structure Inference Network for Facial Action Unit RecognitionPoster164 citations
343. Cross-Modal Ranking with Soft Consistency and Noisy Labels for Robust RGB-T TrackingPoster163 citations
344. Disentangling Factors of Variation with Cycle-Consistent Variational Auto-EncodersPoster163 citations
345. FishEyeRecNet: A Multi-Context Collaborative Deep Network for Fisheye Image RectificationPoster163 citations
346. Deep Adversarial Attention Alignment for Unsupervised Domain Adaptation: the Benefit of Target Expectation MaximizationPoster162 citations
347. Learning Class Prototypes via Structure Alignment for Zero-Shot RecognitionPoster162 citations
348. Retrospective Encoders for Video SummarizationPoster162 citations
349. Super-Identity Convolutional Neural Network for Face HallucinationPoster162 citations
350. VSO: Visual Semantic OdometryPoster162 citations
351. Connecting Gaze, Scene, and Attention: Generalized Attention Estimation via Joint Modeling of Gaze and Scene SaliencyPoster161 citations
352. Flow-Grounded Spatial-Temporal Video Prediction from Still ImagesPoster159 citations
353. Motion Feature Network: Fixed Motion Filter for Action RecognitionPoster159 citations
354. Localization Recall Precision (LRP): A New Performance Metric for Object DetectionPoster158 citations
355. Attention-aware Deep Adversarial Hashing for Cross-Modal RetrievalPoster157 citations
356. Folded Recurrent Neural Networks for Future Video PredictionPoster157 citations
357. Hierarchical Relational Networks for Group Activity Recognition and RetrievalPoster157 citations
358. Unsupervised Video Object Segmentation with Motion-based Bilateral NetworksPoster157 citations
359. Few-Shot Human Motion Prediction via Meta-LearningPoster155 citations
360. Graph Adaptive Knowledge Transfer for Unsupervised Domain AdaptationPoster154 citations
361. Improving Generalization via Scalable Neighborhood Component AnalysisPoster154 citations
362. Deep Burst DenoisingPoster153 citations
363. GAL: Geometric Adversarial Loss for Single-View 3D-Object ReconstructionPoster153 citations
364. Remote Photoplethysmography Correspondence Feature for 3D Mask Face Presentation Attack DetectionPoster153 citations
365. Deep Video Quality Assessor: From Spatio-temporal Visual Sensitivity to A Convolutional Neural Aggregation NetworkPoster151 citations
366. Burst Image Deblurring Using Permutation Invariant Convolutional Neural NetworksPoster150 citations
367. Deep Bilevel LearningPoster150 citations
368. Deep Recursive HDRI: Inverse Tone Mapping using Generative Adversarial NetworksPoster150 citations
369. Deep Image Demosaicking using a Cascade of Convolutional Residual Denoising NetworksPoster149 citations
370. Accurate Scene Text Detection through Border Semantics Awareness and BootstrappingPoster148 citations
371. Monocular Depth Estimation with Affinity, Vertical Pooling, and Label EnhancementPoster148 citations
372. Start, Follow, Read: End-to-End Full-Page Handwriting RecognitionPoster148 citations
373. Stroke Controllable Fast Style Transfer with Adaptive Receptive FieldsPoster148 citations
374. Context Refinement for Object DetectionPoster147 citations
375. Recurrent Tubelet Proposal and Recognition Networks for Action DetectionPoster146 citations
376. Deep Volumetric Video From Very Sparse Multi-View Performance CapturePoster144 citations
377. Domain transfer through deep activation matchingPoster144 citations
378. Move Forward and Tell: A Progressive Generator of Video DescriptionsPoster144 citations
379. A Hybrid Model for Identity Obfuscation by Face ReplacementPoster143 citations
380. A+D Net: Training a Shadow Detector with Adversarial Shadow AttenuationPoster142 citations
381. Conditional Image-Text Embedding NetworksPoster141 citations
382. Cross-Modal Hamming HashingPoster141 citations
383. Quantization Mimic: Towards Very Tiny CNN for Object DetectionPoster141 citations
384. Dist-GAN: An Improved GAN using Distance ConstraintsPoster140 citations
385. Estimating Depth from RGB and Sparse SensingPoster140 citations
386. Graph Distillation for Action Detection with Privileged ModalitiesPoster140 citations
387. ActiveStereoNet: End-to-End Self-Supervised Learning for Active Stereo SystemsPoster139 citations
388. End-to-end View Synthesis for Light Field Imaging with Pseudo 4DCNNPoster139 citations
389. Improving Spatiotemporal Self-Supervision by Deep Reinforcement LearningPoster138 citations
390. Saliency Benchmarking Made Easy: Separating Models, Maps and MetricsPoster138 citations
391. VQA-E: Explaining, Elaborating, and Enhancing Your Answers for Visual QuestionsPoster138 citations
392. Diagnosing Error in Temporal Action DetectorsPoster137 citations
393. Lambda Twist: An Accurate Fast Robust Perspective Three Point (P3P) SolverPoster137 citations
394. Deep Variational Metric LearningPoster136 citations
395. On Offline Evaluation of Vision-based Driving ModelsPoster135 citations
396. Penalizing Top Performers: Conservative Loss for Semantic Segmentation AdaptationPoster135 citations
397. Coloring with Words: Guiding Image Colorization Through Text-based Palette GenerationPoster134 citations
398. Efficient Uncertainty Estimation for Semantic Segmentation in VideosPoster134 citations
399. Fine-Grained Visual Categorization using Meta-Learning Optimization with Sample Selection of Auxiliary DataPoster134 citations
400. HGMR: Hierarchical Gaussian Mixtures for Adaptive 3D RegistrationPoster134 citations
401. TBN: Convolutional Neural Network with Ternary Inputs and Binary WeightsPoster134 citations
402. Correcting the Triplet Selection Bias for Triplet LossPoster132 citations
403. Learning Visual Question Answering by Bootstrapping Hard AttentionPoster132 citations
404. Neural Graph Matching Networks for Fewshot 3D Action RecognitionPoster132 citations
405. RCAA: Relational Context-Aware Agents for Person SearchPoster129 citations
406. Straight to the Facts: Learning Knowledge Base Retrieval for Factual Visual Question AnsweringPoster129 citations
407. Efficient Semantic Scene Completion Network with Spatial Group ConvolutionPoster127 citations
408. Recovering 3D Planes from a Single Image via Convolutional Neural NetworksPoster127 citations
409. Robust Anchor Embedding for Unsupervised Video Person Re-Identification in the WildPoster127 citations
410. Affinity Derivation and Graph Merge for Instance SegmentationPoster126 citations
411. Deep Randomized Ensembles for Metric LearningPoster125 citations
412. Unsupervised Video Object Segmentation using Motion Saliency-Guided Spatio-Temporal PropagationPoster125 citations
413. A Deeply-initialized Coarse-to-fine Ensemble of Regression Trees for Face AlignmentPoster124 citations
414. Learning to Segment via Cut-and-PastePoster124 citations
415. Unsupervised Image-to-Image Translation with Stacked Cycle-Consistent Adversarial NetworksPoster124 citations
416. ADVIO: An Authentic Dataset for Visual-Inertial OdometryPoster123 citations
417. An Adversarial Approach to Hard Triplet GenerationPoster121 citations
418. Characterizing Adversarial Examples Based on Spatial Consistency Information for Semantic SegmentationPoster121 citations
419. Deep Boosting for Image DenoisingPoster121 citations
420. Deep Directional Statistics: Pose Estimation with Uncertainty QuantificationPoster121 citations
421. Grassmann Pooling as Compact Homogeneous Bilinear Pooling for Fine-Grained Visual ClassificationPoster121 citations
422. Associating Inter-Image Salient Instances for Weakly Supervised Semantic SegmentationPoster120 citations
423. Deep Kalman Filtering Network for Video Compression Artifact ReductionPoster120 citations
424. Learning to Forecast and Refine Residual Motion for Image-to-Video GenerationPoster119 citations
425. Deep Feature Factorization For Concept DiscoveryPoster118 citations
426. Interaction-aware Spatio-temporal Pyramid Attention Networks for Action ClassificationPoster118 citations
427. Collaborative Deep Reinforcement Learning for Multi-Object TrackingPoster116 citations
428. Deep Bilinear Learning for RGB-D Action RecognitionPoster116 citations
429. C-WSL: Count-guided Weakly Supervised LocalizationPoster115 citations
430. ShapeStacks: Learning Vision-Based Physical Intuition for Generalised Object StackingPoster115 citations
431. Clustering Convolutional Kernels to Compress Deep Neural NetworksPoster114 citations
432. Predicting Future Instance Segmentation by Forecasting Convolutional FeaturesPoster114 citations
433. Ask, Acquire, and Attack: Data-free UAP Generation using Class ImpressionsPoster113 citations
434. Revisiting the Inverted Indices for Billion-Scale Approximate Nearest NeighborsPoster113 citations
435. HybridFusion: Real-Time Performance Capture Using a Single Depth Sensor and Sparse IMUsPoster112 citations
436. Learning Rigidity in Dynamic Scenes with a Moving Camera for 3D Motion Field EstimationPoster112 citations
437. Semi-convolutional Operators for Instance SegmentationPoster110 citations
438. Simultaneous Edge Alignment and LearningPoster109 citations
439. Synthetically Supervised Feature Learning for Scene Text RecognitionPoster109 citations
440. Double JPEG Detection in Mixed JPEG Quality Factors using Deep Convolutional Neural NetworkPoster108 citations
441. Geolocation Estimation of Photos using a Hierarchical Model and Scene ClassificationPoster108 citations
442. Task-Aware Image DownscalingPoster108 citations
443. Action Search: Spotting Actions in Videos and Its Application to Temporal Action LocalizationPoster107 citations
444. Generative Domain-Migration Hashing for Sketch-to-Image RetrievalPoster107 citations
445. Zero-Shot Deep Domain AdaptationPoster107 citations
446. Contemplating Visual Emotions: Understanding and Overcoming Dataset BiasPoster106 citations
447. Adding Attentiveness to the Neurons in Recurrent Neural NetworksPoster105 citations
448. Imagine This! Scripts to Compositions to VideosPoster104 citations
449. MVTec D2S: Densely Segmented Supermarket DatasetPoster104 citations
450. Self-Supervised Relative Depth Learning for Urban Scene UnderstandingPoster104 citations
451. Weakly-supervised Video Summarization using Variational Encoder-Decoder and Web PriorPoster104 citations
452. Coreset-Based Neural Network CompressionPoster103 citations
453. Learning Region Features for Object DetectionPoster103 citations
454. Unpaired Image Captioning by Language PivotingPoster103 citations
455. Eliminating the Blind Spot: Adapting 3D Object Detection and Monocular Depth Estimation to 360° Panoramic ImageryPoster102 citations
456. Pose Partition Networks for Multi-Person Pose EstimationPoster102 citations
457. Realtime Time Synchronized Event-based StereoPoster102 citations
458. StarMap for Category-Agnostic Keypoint and Viewpoint EstimationPoster102 citations
459. Consensus-Driven Propagation in Massive Unlabeled Data for Face RecognitionPoster101 citations
460. Constrained Optimization Based Low-Rank Approximation of Deep Neural NetworksPoster101 citations
461. Learning to Solve Nonlinear Least Squares for Monocular StereoPoster100 citations
462. Action Anticipation with RBF Kernelized Feature Mapping RNNPoster99 citations
463. Product Quantization Network for Fast Image RetrievalPoster99 citations
464. Scalable Exemplar-based Subspace Clustering on Class-Imbalanced DataPoster99 citations
465. Linear RGB-D SLAM for Planar EnvironmentsPoster98 citations
466. Multimodal Dual Attention Memory for Video Story Question AnsweringPoster97 citations
467. Comparator NetworksPoster96 citations
468. Improving Shape Deformation in Unsupervised Image-to-Image TranslationPoster96 citations
469. The Mutex Watershed: Efficient, Parameter-Free Image PartitioningPoster96 citations
470. Learning to Look around Objects for Top-View Representations of Outdoor ScenesPoster95 citations
471. ``Factual'' or ``Emotional'': Stylized Image Captioning with Adaptive Learning and AttentionPoster95 citations
472. Open-World Stereo Video Matching with Deep RNNPoster94 citations
473. Temporal Modular Networks for Retrieving Complex Compositional Activities in VideosPoster94 citations
474. Unsupervised Class-Specific DeblurringPoster94 citations
475. Where Will They Go? Predicting Fine-Grained Adversarial Multi-Agent Motion using Conditional Variational AutoencodersPoster94 citations
476. AGIL: Learning Attention from Human for Visuomotor TasksPoster93 citations
477. CPlaNet: Enhancing Image Geolocalization by Combinatorial Partitioning of MapsPoster93 citations
478. Question-Guided Hybrid Convolution for Visual Question AnsweringPoster93 citations
479. Attentive Semantic Alignment with Offset-Aware Correlation KernelsPoster92 citations
480. Deep Expander Networks: Efficient Deep Networks from Graph TheoryPoster92 citations
481. Deep Shape MatchingPoster92 citations
482. Dividing and Aggregating Network for Multi-view Action RecognitionPoster92 citations
483. Constraint-Aware Deep Neural Network CompressionPoster91 citations
484. Efficient Global Point Cloud Registration by Matching Rotation Invariant Features Through Translation SearchPoster91 citations
485. Find and Focus: Retrieve and Localize Video Events with Natural Language QueriesPoster90 citations
486. Modular Generative Adversarial NetworksPoster90 citations
487. Unsupervised Hard Example Mining from Videos for Improved Object DetectionPoster90 citations
488. DDRNet: Depth Map Denoising and Refinement for Consumer Depth Cameras Using Cascaded CNNsPoster89 citations
489. Does Haze Removal Help CNN-based Image Classification?Poster89 citations
490. SketchyScene: Richly-Annotated Scene SketchesPoster89 citations
491. Online Detection of Action Start in Untrimmed, Streaming VideosPoster88 citations
492. Probabilistic Video Generation using Holistic Attribute ControlPoster88 citations
493. 3D Ego-Pose Estimation via Imitation LearningPoster87 citations
494. Deep Regionlets for Object DetectionPoster87 citations
495. Deformable Pose Traversal Convolution for 3D Action and Gesture RecognitionPoster87 citations
496. HairNet: Single-View Hair Reconstruction using Convolutional Neural NetworksPoster86 citations
497. Semi-Supervised Deep Learning with MemoryPoster86 citations
498. Shuffle-Then-Assemble: Learning Object-Agnostic Visual Relationship FeaturesPoster86 citations
499. Diverse and Coherent Paragraph Generation from ImagesPoster84 citations
500. Deep Attention Neural Tensor Network for Visual Question AnsweringPoster83 citations
501. Dynamic Conditional Networks for Few-Shot LearningPoster82 citations
502. Extreme Network Compression via Filter Group ApproximationPoster82 citations
503. Robust fitting in computer vision: easy or hard?Poster82 citations
504. Video Re-localizationPoster82 citations
505. Single Image Intrinsic Decomposition without a Single Intrinsic ImagePoster81 citations
506. Separating Reflection and Transmission Images in the WildPoster80 citations
507. Single Image Highlight Removal with a Sparse and Low-Rank Reflection ModelPoster80 citations
508. Deep Reinforcement Learning with Iterative Shift for Visual TrackingPoster79 citations
509. Person Search in Videos with One Portrait Through Visual and Temporal LinksPoster79 citations
510. Sparsely Aggregated Convolutional NetworksPoster78 citations
511. Discriminative Region Proposal Adversarial Networks for High-Quality Image-to-Image TranslationPoster77 citations
512. MaskConnect: Connectivity Learning by Gradient DescentPoster77 citations
513. Robust image stitching with multiple registrationsPoster77 citations
514. Semi-supervised Adversarial Learning to Generate Photorealistic Face Images of New Identities from 3D Morphable ModelPoster77 citations
515. Analyzing Clothing Layer Deformation Statistics of 3D Human MotionsPoster76 citations
516. SAN: Learning Relationship between Convolutional Features for Multi-Scale Object DetectionPoster76 citations
517. Semi-supervised FusedGAN for Conditional Image GenerationPoster76 citations
518. Deep Autoencoder for Combined Human Pose Estimation and Body Model UpscalingPoster75 citations
519. DeepKSPD: Learning Kernel-matrix-based SPD Representation for Fine-grained Image RecognitionPoster74 citations
520. LAPRAN: A Scalable Laplacian Pyramid Reconstructive Adversarial Network for Flexible Compressive Sensing ReconstructionPoster74 citations
521. Beyond local reasoning for stereo confidence estimation with deep learningPoster73 citations
522. Real-to-Virtual Domain Unification for End-to-End Autonomous DrivingPoster73 citations
523. Towards Human-Level License Plate RecognitionPoster73 citations
524. Joint Learning of Intrinsic Images and Semantic SegmentationPoster72 citations
525. Learning to Fuse Proposals from Multiple Scanline Optimizations in Semi-Global MatchingPoster72 citations
526. Occlusion-aware Hand Pose Estimation Using Hierarchical Mixture Density NetworkPoster72 citations
527. Learning to Capture Light Fields through a Coded Aperture CameraPoster71 citations
528. Deep Cross-modality Adaptation via Semantics Preserving Adversarial Learning for Sketch-based 3D Shape RetrievalPoster70 citations
529. Geometric Constrained Joint Lane Segmentation and Lane Boundary DetectionPoster70 citations
530. Joint Camera Spectral Sensitivity Selection and Hyperspectral Image RecoveryPoster70 citations
531. Decouple Learning for Parameterized Image OperatorsPoster69 citations
532. PARN: Pyramidal Affine Regression Networks for Dense Semantic CorrespondencePoster69 citations
533. Focus, Segment and Erase: An Efficient Network for Multi-Label Brain Tumor SegmentationPoster68 citations
534. Human Motion Analysis with Deep Metric LearningPoster68 citations
535. Unsupervised CNN-based Co-Saliency Detection with Graphical OptimizationPoster68 citations
536. Video Object Segmentation by Learning Location-Sensitive EmbeddingsPoster68 citations
537. Visual Tracking via Spatially Aligned Correlation Filters NetworkPoster68 citations
538. Volumetric performance capture from minimal camera viewpointsPoster68 citations
539. Learning Single-View 3D Reconstruction with Limited Pose SupervisionPoster67 citations
540. Generative Semantic Manipulation with Mask-Contrasting GANPoster66 citations
541. Neural Network EncapsulationPoster66 citations
542. Part-Activated Deep Reinforcement Learning for Action PredictionPoster66 citations
543. Tackling 3D ToF Artifacts Through Learning and the FLAT DatasetPoster66 citations
544. ExplainGAN: Model Explanation via Decision Boundary Crossing TransformationsPoster65 citations
545. Interactive Boundary Prediction for Object SelectionPoster65 citations
546. Interpretable Intuitive Physics ModelPoster65 citations
547. Joint Representation and Truncated Inference Learning for Correlation Filter based TrackingPoster64 citations
548. Massively Parallel Video NetworksPoster64 citations
549. ADVISE: Symbolism and External Knowledge for Decoding AdvertisementsPoster63 citations
550. Boosted Attention: Leveraging Human Attention for Image CaptioningPoster63 citations
551. Shape Reconstruction Using Volume Sweeping and Learned PhotoconsistencyPoster63 citations
552. Learn-to-Score: Efficient 3D Scene Exploration by Predicting View UtilityPoster62 citations
553. Question Type Guided Attention in Visual Question AnsweringPoster62 citations
554. Single Shot Scene Text RetrievalPoster62 citations
555. SwapNet: Garment Transfer in Single View ImagesPoster61 citations
556. Adversarial Open-World Person Re-IdentificationPoster60 citations
557. Face Recognition with Contrastive ConvolutionPoster60 citations
558. Fine-grained Video Categorization with Redundancy Reduction AttentionPoster60 citations
559. Improving Sequential Determinantal Point Processes for Supervised Video SummarizationPoster60 citations
560. Egocentric Activity Prediction via Event Modulated AttentionPoster59 citations
561. Robust Optical Flow in Rainy ScenesPoster59 citations
562. Learning and Matching Multi-View Descriptors for Registration of Point CloudsPoster58 citations
563. Pose Proposal NetworksPoster58 citations
564. Statistically-motivated Second-order PoolingPoster58 citations
565. Universal Sketch Perceptual GroupingPoster58 citations
566. HybridNet: Classification and Reconstruction Cooperation for Semi-Supervised LearningPoster57 citations
567. Normalized Blind DeconvolutionPoster57 citations
568. Choose Your Neuron: Incorporating Domain Knowledge through Neuron-ImportancePoster56 citations
569. Direct Sparse Odometry With Rolling ShutterPoster56 citations
570. HBE: Hand Branch Ensemble Network for Real-time 3D Hand Pose EstimationPoster56 citations
571. Hierarchical Metric Learning and Matching for 2D and 3D Geometric CorrespondencesPoster56 citations
572. How Local is the Local Diversity? Reinforcing Sequential Determinantal Point Processes with Dynamic Ground Sets for Supervised Video SummarizationPoster56 citations
573. Learning Priors for Semantic 3D ReconstructionPoster56 citations
574. A Dataset and Architecture for Visual Reasoning with a Working MemoryPoster55 citations
575. Deep Multi-Task Learning to Recognise Subtle Facial Expressions of Mental StatesPoster55 citations
576. Highly-Economized Multi-View Binary Compression for Scalable Image ClusteringPoster55 citations
577. Selfie Video StabilizationPoster55 citations
578. Structural Consistency and Controllability for Diverse ColorizationPoster55 citations
579. Attend and Rectify: a gated attention mechanism for fine-grained recoveryPoster54 citations
580. DFT-based Transformation Invariant Pooling Layer for Visual ClassificationPoster54 citations
581. Eigendecomposition-free Training of Deep Networks with Zero Eigenvalue-based LossesPoster54 citations
582. Joint 3D tracking of a deformable object in interaction with a handPoster54 citations
583. Multi-Class Model Fitting by Energy Minimization and Mode-SeekingPoster54 citations
584. Museum Exhibit Identification Challenge for the Supervised Domain Adaptation and BeyondPoster54 citations
585. Pairwise Relational Networks for Face RecognitionPoster54 citations
586. Dependency-aware Attention Control for Unconstrained Face Recognition with Image SetsPoster53 citations
587. Single Image Water Hazard Detection using FCN with Reflection Attention UnitsPoster53 citations
588. End-to-End Joint Semantic Segmentation of Actors and Actions in VideoPoster52 citations
589. Faces as Lighting Probes via Unsupervised Deep Highlight ExtractionPoster52 citations
590. LSQ++: Lower running time and higher recall in multi-codebook quantizationPoster52 citations
591. Reinforced Temporal Attention and Split-Rate Transfer for Depth-Based Person Re-IdentificationPoster52 citations
592. Variational Wasserstein ClusteringPoster52 citations
593. Zero-shot keyword spotting for visual speech recognition in-the-wildPoster52 citations
594. Gray-box Adversarial TrainingPoster51 citations
595. Multimodal image alignment through a multiscale chain of neural networks with application to remote sensingPoster51 citations
596. Programmable Triangulation Light CurtainsPoster51 citations
597. What do I Annotate Next? An Empirical Study of Active Learning for Action LocalizationPoster51 citations
598. 3D Face Reconstruction from Light Field Images: A Model-free ApproachPoster50 citations
599. Deep Texture and Structure Aware Filtering Network for Image SmoothingPoster50 citations
600. Dynamic Filtering with Large Sampling Field for ConvNetsPoster50 citations
601. PSDF Fusion: Probabilistic Signed Distance Function for On-the-fly 3D Data Fusion and Scene ReconstructionPoster50 citations
602. A Dataset of Flash and Ambient Illumination Pairs from the CrowdPoster49 citations
603. Efficient Dense Point Cloud Object Reconstruction using Deformation Vector FieldsPoster49 citations
604. Learning 3D Keypoint Descriptors for Non-Rigid Shape MatchingPoster49 citations
605. Switchable Temporal Propagation NetworkPoster49 citations
606. Task-driven Webpage SaliencyPoster49 citations
607. Visual Psychophysics for Making Face Recognition Algorithms More ExplainablePoster49 citations
608. Deep Generative Models for Weakly-Supervised Multi-Label ClassificationPoster48 citations
609. Conditional Prior Networks for Optical FlowPoster47 citations
610. Goal-Oriented Visual Question Generation via Intermediate RewardsPoster47 citations
611. Learning Data Terms for Non-blind DeblurringPoster47 citations
612. Visual Question Answering as a Meta Learning TaskPoster47 citations
613. Joint Person Segmentation and Identification in Synchronized First- and Third-person VideosPoster46 citations
614. Extending Layered Models to 3D MotionPoster45 citations
615. GridFace: Face Rectification via Learning Local Homography TransformationsPoster45 citations
616. Linear Span Network for Object Skeleton DetectionPoster45 citations
617. Monocular Depth Estimation Using Whole Strip Masking and Reliability-Based RefinementPoster45 citations
618. Object-centered image stitchingPoster45 citations
619. Bayesian Semantic Instance Segmentation in Open Set WorldPoster44 citations
620. Relaxation-Free Deep Hashing via Policy GradientPoster44 citations
621. Reconstruction-based Pairwise Depth Dataset for Depth Image Enhancement Using CNNPoster43 citations
622. Simultaneous 3D Reconstruction for Water Surface and Underwater ScenePoster43 citations
623. A Framework for Evaluating 6-DOF Object TrackersPoster42 citations
624. Compressing the Input for CNNs with the First-Order Scattering TransformPoster42 citations
625. DOCK: Detecting Objects by transferring Common-sense KnowledgePoster42 citations
626. HandMap: Robust Hand Pose Estimation via Intermediate Dense Guidance Map SupervisionPoster42 citations
627. Image Reassembly Combining Deep Learning and Shortest Path ProblemPoster42 citations
628. Semi-Supervised Generative Adversarial Hashing for Image RetrievalPoster42 citations
629. Summarizing First-Person Videos from Third Persons' Points of ViewPoster42 citations
630. Joint optimization for compressive video sensing and reconstruction under hardware constraintsPoster41 citations
631. PlaneMatch: Patch Coplanarity Prediction for Robust RGB-D ReconstructionPoster41 citations
632. Unsupervised Domain Adaptation for 3D Keypoint Estimation via View ConsistencyPoster41 citations
633. Evaluating Capability of Deep Neural Networks for Image Classification via Information PlanePoster40 citations
634. Learning 3D Shapes as Multi-Layered Height-maps using 2D Convolutional NetworksPoster40 citations
635. Towards Realistic PredictorsPoster40 citations
636. Transductive Centroid Projection for Semi-supervised Large-scale RecognitionPoster40 citations
637. A New Large Scale Dynamic Texture Dataset with Application to ConvNet UnderstandingPoster39 citations
638. Coded Two-Bucket Cameras for Computer VisionPoster39 citations
639. DYAN: A Dynamical Atoms-Based Network For Video PredictionPoster39 citations
640. Joint & Progressive Learning from High-Dimensional Data for Multi-Label ClassificationPoster39 citations
641. A-Contrario Horizon-First Vanishing Point Detection Using Second-Order Grouping LawsPoster38 citations
642. Improved Structure from Motion Using Fiducial Marker MatchingPoster38 citations
643. Learning to Reconstruct High-quality 3D Shapes with Cascaded Fully Convolutional NetworksPoster38 citations
644. Real-Time Hair Rendering using Sequential Adversarial NetworksPoster38 citations
645. Scenes-Objects-Actions: A Multi-Task, Multi-Label Video DatasetPoster38 citations
646. DeepGUM: Learning Deep Robust Regression with a Gaussian-Uniform Mixture ModelPoster37 citations
647. Large Scale Urban Scene Modeling from MVS MeshesPoster37 citations
648. Second-order Democratic AggregationPoster37 citations
649. Selective Zero-Shot Classification with Augmented AttributesPoster37 citations
650. Efficient Relative Attribute Learning using Graph Neural NetworksPoster36 citations
651. Super-Resolution and Sparse View CT ReconstructionPoster36 citations
652. A Minimal Closed-Form Solution for Multi-Perspective Pose Estimation using Points and LinesPoster35 citations
653. Deterministic Consensus Maximization with Biconvex ProgrammingPoster35 citations
654. Dual-Agent Deep Reinforcement Learning for Deformable Face TrackingPoster35 citations
655. Fictitious GAN: Training GANs with Historical ModelsPoster35 citations
656. Learning Compression from Limited Unlabeled DataPoster35 citations
657. Neural Procedural Reconstruction for Residential BuildingsPoster35 citations
658. Revisiting Autofocus for Smartphone CamerasPoster35 citations
659. Saliency Preservation in Low-Resolution Grayscale ImagesPoster35 citations
660. Sidekick Policy Learning for Active Visual ExplorationPoster35 citations
661. A Geometric Perspective on Structured Light CodingPoster34 citations
662. A Segmentation-aware Deep Fusion Network for Compressed Sensing MRIPoster34 citations
663. Deblurring Natural Image Using Super-Gaussian FieldsPoster34 citations
664. Neural Stereoscopic Image Style TransferPoster34 citations
665. Physical Primitive DecompositionPoster34 citations
666. Polarimetric Three-View GeometryPoster34 citations
667. Diverse feature visualizations reveal invariances in early layers of deep neural networksPoster33 citations
668. Maximum Margin Metric Learning Over Discriminative Nullspace for Person Re-identificationPoster33 citations
669. Joint Blind Motion Deblurring and Depth Estimation of Light FieldPoster32 citations
670. PM-GANs: Discriminative Representation Learning for Action Recognition Using Partial-modalitiesPoster32 citations
671. Rendering Portraitures from Monocular Camera and BeyondPoster32 citations
672. Semantically Aware Urban 3D Reconstruction with Plane-Based RegularizationPoster32 citations
673. Descending, lifting or smoothing: Secrets of robust cost optimizationPoster31 citations
674. ISNN: Impact Sound Neural Network for Audio-Visual Object ClassificationPoster31 citations
675. Learning Discriminative Video Representations Using Adversarial PerturbationsPoster31 citations
676. Hashing with Binary Matrix PursuitPoster30 citations
677. Image Manipulation with Perceptual DiscriminatorsPoster30 citations
678. Exploiting Vector Fields for Geometric Rectification of Distorted Document ImagesPoster29 citations
679. Generalized Loss-Sensitive Adversarial Learning with Manifold MarginsPoster29 citations
680. ML-LocNet: Improving Object Localization with Multi-view Learning NetworkPoster29 citations
681. Progressive Structure from MotionPoster29 citations
682. Viewpoint Estimation---Insights & ModelPoster29 citations
683. Broadcasting Convolutional Network for Visual Relational ReasoningPoster28 citations
684. Specular-to-Diffuse Translation for Multi-View ReconstructionPoster28 citations
685. End-to-End Deep Structured Models for Drawing CrosswalksPoster27 citations
686. NAM: Non-Adversarial Unsupervised Domain MappingPoster27 citations
687. SRDA: Generating Instance Segmentation Annotation via Scanning, Reasoning and Domain AdaptationPoster27 citations
688. Visual-Inertial Object Detection and MappingPoster27 citations
689. Affine Correspondences between Central Cameras for Rapid Relative Pose EstimationPoster26 citations
690. ArticulatedFusion: Real-time Reconstruction of Motion, Geometry and Segmentation Using a Single Depth CameraPoster26 citations
691. NNEval: Neural Network based Evaluation Metric for Image CaptioningPoster26 citations
692. Modeling Varying Camera-IMU Time Offset in Optimization-Based Visual-Inertial OdometryPoster25 citations
693. Visual Question Generation for Class Acquisition of Unknown ObjectsPoster25 citations
694. Zero-Annotation Object Detection with Web Knowledge TransferPoster25 citations
695. Deep Component Analysis via Alternating Direction Neural NetworksPoster24 citations
696. Hierarchy of Alternating Specialists for Scene RecognitionPoster24 citations
697. Integrating Egocentric Videos in Top-view Surveillance Videos: Joint Identification and Temporal AlignmentPoster24 citations
698. Multiple-gaze geometry: Inferring novel 3D locations from gazes observed in monocular videoPoster24 citations
699. Sequential Clique Optimization for Video Object SegmentationPoster24 citations
700. Sub-GAN: An Unsupervised Generative Model via SubspacesPoster24 citations
701. Using Object Information for Spotting TextPoster24 citations
702. Snap Angle Prediction for 360° PanoramasPoster23 citations
703. Training Binary Weight Networks via Semi-Binary DecompositionPoster23 citations
704. Fast and Accurate Intrinsic Symmetry DetectionPoster22 citations
705. Good Line Cutting: towards Accurate Pose Tracking of Line-assisted VO/VSLAMPoster22 citations
706. Incremental Multi-graph Matching via Diversity and Randomness based Graph ClusteringPoster22 citations
707. MPLP++: Fast, Parallel Dual Block-Coordinate Ascent for Dense Graphical ModelsPoster22 citations
708. Perturbation Robust Representations of Topological Persistence DiagramsPoster22 citations
709. SaaS: Speed as a Supervisor for Semi-supervised LearningPoster22 citations
710. Visual Reasoning with Multi-hop Feature ModulationPoster22 citations
711. Compositing-aware Image SearchPoster21 citations
712. Concept Mask: Large-Scale Segmentation from Semantic ConceptsPoster21 citations
713. Urban Zoning Using Higher-Order Markov Random Fields on Multi-View Imagery DataPoster21 citations
714. X-ray Computed Tomography Through ScatterPoster21 citations
715. Rethinking the Form of Latent States in Image CaptioningPoster20 citations
716. ShapeCodes: Self-Supervised Feature Learning by Lifting Views to ViewgridsPoster20 citations
717. Dense Semantic and Topological Correspondence of 3D Faces without LandmarksPoster19 citations
718. Deep Factorised Inverse-SketchingPoster18 citations
719. Efficient Sliding Window Computation for NN-Based Template MatchingPoster18 citations
720. Escaping from Collapsing Modes in a Constrained SpacePoster18 citations
721. A Dataset for Lane Instance Segmentation in Urban EnvironmentsPoster17 citations
722. Combining 3D Model Contour Energy and Keypoints for Object TrackingPoster17 citations
723. Multi-Scale Spatially-Asymmetric Recalibration for Image ClassificationPoster17 citations
724. On the Solvability of Viewing GraphsPoster17 citations
725. Stereo relative pose from line and point feature tripletsPoster17 citations
726. U-PC: Unsupervised Planogram CompliancePoster17 citations
727. Efficient 6-DoF Tracking of Handheld Objects from an Egocentric ViewpointPoster16 citations
728. Joint Map and Symmetry SynchronizationPoster16 citations
729. Quadtree Convolutional Neural NetworksPoster16 citations
730. Scale-Awareness of Light Field Camera based Visual OdometryPoster16 citations
731. Teaching Machines to Understand Baseball Games: Large-Scale Baseball Video Database for Multiple Video Understanding TasksPoster16 citations
732. Unsupervised holistic image generation from key local patchesPoster16 citations
733. 3D Vehicle Trajectory Reconstruction in Monocular Video Data Using Environment Structure ConstraintsPoster15 citations
734. Fast and Accurate Camera Covariance Computation for Large 3D ReconstructionPoster15 citations
735. Rolling Shutter Pose and Ego-motion Estimation using Shape-from-TemplatePoster15 citations
736. Structure-from-Motion-Aware PatchMatch for Adaptive Optical Flow EstimationPoster15 citations
737. Accelerating Dynamic Programs via Nested Benders Decomposition with Application to Multi-Person Pose EstimationPoster14 citations
738. K-convexity shape priors for segmentationPoster14 citations
739. Online Dictionary Learning for Approximate Archetypal AnalysisPoster14 citations
740. Pivot Correlational Neural Network for Multimodal Video CategorizationPoster14 citations
741. RefocusGAN: Scene Refocusing using a Single ImagePoster14 citations
742. Seeing Tree Structure from VibrationPoster14 citations
743. Understanding Degeneracies and Ambiguities in Attribute TransferPoster14 citations
744. Learning to Dodge A Bullet: Concyclic View Morphing via Deep LearningPoster13 citations
745. Stereo Computation for a Single Mixture ImagePoster13 citations
746. 3D Scene Flow from 4D Light Field GradientsPoster12 citations
747. Estimating the Success of Unsupervised Image to Image TranslationPoster12 citations
748. Visual Text CorrectionPoster12 citations
749. Learning to Blend PhotosPoster11 citations
750. Self-Calibration of Cameras with Euclidean Image Plane in Case of Two Views and Known Relative Rotation AnglePoster11 citations
751. Toward Scale-Invariance and Position-Sensitive Region Proposal NetworksPoster11 citations
752. From Face Recognition to Models of Identity: A Bayesian Approach to Learning about Unknown Identities from Unsupervised DataPoster10 citations
753. Adaptively Transforming Graph MatchingPoster9 citations
754. Deep Discriminative Model for Video ClassificationPoster9 citations
755. Lifting Layers: Analysis and ApplicationsPoster9 citations
756. Liquid Pouring Monitoring via Rich Sensory InputsPoster9 citations
757. View-graph Selection Framework for SfMPoster9 citations
758. ForestHash: Semantic Hashing With Shallow Random Forests and Tiny Convolutional NetworksPoster8 citations
759. Into the Twilight Zone: Depth Estimation using Joint Structure-Stereo OptimizationPoster8 citations
760. Light Structure from Pin Motion: Simple and Accurate Point Light Calibration for Physics-based ModelingPoster8 citations
761. Sampling Algebraic Varieties for Robust Camera AutocalibrationPoster8 citations
762. Variable Ring Light Imaging: Capturing Transient Subsurface Scattering with An Ordinary CameraPoster8 citations
763. Facial Dynamics Interpreter Network: What are the Important Relations between Local Dynamics for Facial Trait Estimation?Poster7 citations
764. Incremental Non-Rigid Structure-from-Motion with Unknown Focal LengthPoster6 citations
765. Inner Space Preserving Generative Pose MachinePoster6 citations
766. Self-Calibrating Isometric Non-Rigid Structure-from-MotionPoster6 citations
767. Diverse Conditional Image Generation by Stochastic Regression with Latent Drop-Out CodesPoster5 citations
768. Interpolating Convolutional Neural Networks Using Batch NormalizationPoster5 citations
769. Coded Illumination and Imaging for Fluorescence Based ClassificationPoster4 citations
770. Local Orthogonal-Group TestingPoster4 citations
771. Using LIP to Gloss Over Faces in Single-Stage Face Detection NetworksPoster4 citations
772. MRF Optimization with Separable Convex Prior on Partially Ordered LabelsPoster3 citations
773. Model-free Consensus Maximization for Non-Rigid ShapesPoster3 citations
774. Understanding Perceptual and Conceptual Fluency at a Large ScalePoster3 citations
775. Proxy Clouds for Live RGB-D Stream Processing and ConsolidationPoster2 citations
776. Leveraging Motion Priors in Videos for Improving Human SegmentationPoster1 citations

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