Computer Vision – ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part VII (Lecture Notes in Computer Science Book 9911)

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. Front Matter....Pages I-XXIX Front Matter....Pages 1-1 Angry Crowds: Detecting Violent Events in Videos....Pages 3-18 Sparse Recovery of Hyperspectral Signal from Natural RGB Images....Pages 19-34 Light Field Segmentation Using a Ray-Based Graph Structure....Pages 35-50 Design of Kernels in Convolutional Neural Networks for Image Classification....Pages 51-66 Learning Visual Features from Large Weakly Supervised Data....Pages 67-84 3D Mask Face Anti-spoofing with Remote Photoplethysmography....Pages 85-100 Guided Matching Based on Statistical Optical Flow for Fast and Robust Correspondence Analysis....Pages 101-117 Pose Estimation Errors, the Ultimate Diagnosis....Pages 118-134 A Siamese Long Short-Term Memory Architecture for Human Re-identification....Pages 135-153 Integration of Probabilistic Pose Estimates from Multiple Views....Pages 154-170 SurfCut: Free-Boundary Surface Extraction....Pages 171-186 CATS: Co-saliency Activated Tracklet Selection for Video Co-localization....Pages 187-202 Online Human Action Detection Using Joint Classification-Regression Recurrent Neural Networks....Pages 203-220 Jensen Bregman LogDet Divergence Optimal Filtering in the Manifold of Positive Definite Matrices....Pages 221-235 SyB3R: A Realistic Synthetic Benchmark for 3D Reconstruction from Images....Pages 236-251 Front Matter....Pages 253-253 When is Rotations Averaging Hard?....Pages 255-270 Capturing Dynamic Textured Surfaces of Moving Targets....Pages 271-288 ShapeFit and ShapeKick for Robust, Scalable Structure from Motion....Pages 289-304 Heat Diffusion Long-Short Term Memory Learning for 3D Shape Analysis....Pages 305-321 Multi-view 3D Models from Single Images with a Convolutional Network....Pages 322-337 Front Matter....Pages 253-253 Extending Long Short-Term Memory for Multi-View Structured Learning....Pages 338-353 Gated Bi-directional CNN for Object Detection....Pages 354-369 Graph Based Skeleton Motion Representation and Similarity Measurement for Action Recognition....Pages 370-385 Reliable Fusion of ToF and Stereo Depth Driven by Confidence Measures....Pages 386-401 Fast, Exact and Multi-scale Inference for Semantic Image Segmentation with Deep Gaussian CRFs....Pages 402-418 Kernel-Based Supervised Discrete Hashing for Image Retrieval....Pages 419-433 Iterative Reference Driven Metric Learning for Signer Independent Isolated Sign Language Recognition....Pages 434-450 Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering....Pages 451-466 Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networks....Pages 467-482 Counting in the Wild....Pages 483-498 A Discriminative Feature Learning Approach for Deep Face Recognition....Pages 499-515 Network of Experts for Large-Scale Image Categorization....Pages 516-532 Zero-Shot Recognition via Structured Prediction....Pages 533-548 What’s the Point: Semantic Segmentation with Point Supervision....Pages 549-565 A Generalized Successive Shortest Paths Solver for Tracking Dividing Targets....Pages 566-582 Accurate and Linear Time Pose Estimation from Points and Lines....Pages 583-599 Pseudo-geometric Formulation for Fitting Equidistant Parallel Lines....Pages 600-614 Towards Perspective-Free Object Counting with Deep Learning....Pages 615-629 Information Bottleneck Domain Adaptation with Privileged Information for Visual Recognition....Pages 630-647 Template-Free 3D Reconstruction of Poorly-Textured Nonrigid Surfaces....Pages 648-663 Front Matter....Pages 253-253 FigureSeer: Parsing Result-Figures in Research Papers....Pages 664-680 Approximate Search with Quantized Sparse Representations....Pages 681-696 Sympathy for the Details: Dense Trajectories and Hybrid Classification Architectures for Action Recognition....Pages 697-716 Human Pose Estimation via Convolutional Part Heatmap Regression....Pages 717-732 Collaborative Layer-Wise Discriminative Learning in Deep Neural Networks....Pages 733-749 Deep Decoupling of Defocus and Motion Blur for Dynamic Segmentation....Pages 750-765 Video Summarization with Long Short-Term Memory....Pages 766-782 Leaving Some Stones Unturned: Dynamic Feature Prioritization for Activity Detection in Streaming Video....Pages 783-800 Robust and Accurate Line- and/or Point-Based Pose Estimation without Manhattan Assumptions....Pages 801-818 MARLow: A Joint Multiplanar Autoregressive and Low-Rank Approach for Image Completion....Pages 819-834 An Uncertain Future: Forecasting from Static Images Using Variational Autoencoders....Pages 835-851 Carried Object Detection Based on an Ensemble of Contour Exemplars....Pages 852-866 Back Matter....Pages 867-869