Computer Vision – ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part IV (Lecture Notes in Computer Science Book 9908)

The Eight-volume Set Comprising Lncs Volumes 9905-9912 Constitutes The Refereed Proceedings Of The 14th European Conference On Computer Vision, Eccv 2016, Held In Amsterdam, The Netherlands, In October 2016. The 415 Revised Papers Presented Were Carefully Reviewed And Selected From 1480 Submissions. The Papers Cover All Aspects Of Computer Vision And Pattern Recognition Such As 3d Computer Vision; Computational Photography, Sensing And Display; Face And Gesture; Low-level Vision And Image Processing; Motion And Tracking; Optimization Methods; Physics-based Vision, Photometry And Shape-from-x; Recognition: Detection, Categorization, Indexing, Matching; Segmentation, Grouping And Shape Representation; Statistical Methods And Learning; Video: Events, Activities And Surveillance; Applications. They Are Organized In Topical Sections On Detection, Recognition And Retrieval; Scene Understanding; Optimization; Image And Video Processing; Learning; Action Activity And Tracking; 3d; And 9 Poster Sessions. Detection, Recognition And Retrieval -- Scene Understanding -- Optimization -- Image And Video Processing -- Learning -- Action Activity And Tracking -- 3d -- Poster Sessions. Edited By Bastian Leibe, Jiri Matas, Nicu Sebe, Max Welling. Front Matter....Pages I-XXIX Front Matter....Pages 1-1 Generating Visual Explanations....Pages 3-19 Marker-Less 3D Human Motion Capture with Monocular Image Sequence and Height-Maps....Pages 20-36 Tensor Representations via Kernel Linearization for Action Recognition from 3D Skeletons....Pages 37-53 Manhattan-World Urban Reconstruction from Point Clouds....Pages 54-69 From Multiview Image Curves to 3D Drawings....Pages 70-87 Shape from Selfies: Human Body Shape Estimation Using CCA Regression Forests....Pages 88-104 Can We Jointly Register and Reconstruct Creased Surfaces by Shape-from-Template Accurately?....Pages 105-120 Distractor-Supported Single Target Tracking in Extremely Cluttered Scenes....Pages 121-136 Connectionist Temporal Modeling for Weakly Supervised Action Labeling....Pages 137-153 Deep Joint Image Filtering....Pages 154-169 Efficient Multi-frequency Phase Unwrapping Using Kernel Density Estimation....Pages 170-185 A Multi-scale CNN for Affordance Segmentation in RGB Images....Pages 186-201 Hierarchical Dynamic Parsing and Encoding for Action Recognition....Pages 202-217 Distinct Class-Specific Saliency Maps for Weakly Supervised Semantic Segmentation....Pages 218-234 A Diagram is Worth a Dozen Images....Pages 235-251 Automatic Attribute Discovery with Neural Activations....Pages 252-268 “What Happens If...” Learning to Predict the Effect of Forces in Images....Pages 269-285 View Synthesis by Appearance Flow....Pages 286-301 Top-Down Learning for Structured Labeling with Convolutional Pseudoprior....Pages 302-317 Generative Image Modeling Using Style and Structure Adversarial Networks....Pages 318-335 Front Matter....Pages 1-1 Joint Learning of Semantic and Latent Attributes....Pages 336-353 A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection....Pages 354-370 Deep Specialized Network for Illuminant Estimation....Pages 371-387 Weakly-Supervised Semantic Segmentation Using Motion Cues....Pages 388-404 Human-in-the-Loop Person Re-identification....Pages 405-422 Real-Time Monocular Segmentation and Pose Tracking of Multiple Objects....Pages 423-438 Estimation of Human Body Shape in Motion with Wide Clothing....Pages 439-454 A Shape-Based Approach for Salient Object Detection Using Deep Learning....Pages 455-470 Fast Optical Flow Using Dense Inverse Search....Pages 471-488 Global Registration of 3D Point Sets via LRS Decomposition....Pages 489-504 Recognition from Hand Cameras: A Revisit with Deep Learning....Pages 505-521 Front Matter....Pages 523-523 XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks....Pages 525-542 Top-Down Neural Attention by Excitation Backprop....Pages 543-559 Learning Recursive Filters for Low-Level Vision via a Hybrid Neural Network....Pages 560-576 Learning Representations for Automatic Colorization....Pages 577-593 Front Matter....Pages 595-595 Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation....Pages 597-613 Learning Without Forgetting....Pages 614-629 Identity Mappings in Deep Residual Networks....Pages 630-645 Deep Networks with Stochastic Depth....Pages 646-661 Less Is More: Towards Compact CNNs....Pages 662-677 Front Matter....Pages 595-595 Unsupervised Visual Representation Learning by Graph-Based Consistent Constraints....Pages 678-694 Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation....Pages 695-711 Patch-Based Low-Rank Matrix Completion for Learning of Shape and Motion Models from Few Training Samples....Pages 712-727 Chained Predictions Using Convolutional Neural Networks....Pages 728-743 Multi-region Two-Stream R-CNN for Action Detection....Pages 744-759 Semantic Co-segmentation in Videos....Pages 760-775 Attribute2Image: Conditional Image Generation from Visual Attributes....Pages 776-791 Modeling Context Between Objects for Referring Expression Understanding....Pages 792-807 Friction from Reflectance: Deep Reflectance Codes for Predicting Physical Surface Properties from One-Shot In-Field Reflectance....Pages 808-824 Saliency Detection with Recurrent Fully Convolutional Networks....Pages 825-841 Deep3D: Fully Automatic 2D-to-3D Video Conversion with Deep Convolutional Neural Networks....Pages 842-857 Temporal Model Adaptation for Person Re-identification....Pages 858-877 Back Matter....Pages 879-881