Computer Vision – ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part V (Lecture Notes in Computer Science Book 9909)

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 CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples....Pages 3-20 SSD: Single Shot MultiBox Detector....Pages 21-37 A Recurrent Encoder-Decoder Network for Sequential Face Alignment....Pages 38-56 Robust Facial Landmark Detection via Recurrent Attentive-Refinement Networks....Pages 57-72 Front Matter....Pages 73-73 Learning to Refine Object Segments....Pages 75-91 Deep Automatic Portrait Matting....Pages 92-107 Segmentation from Natural Language Expressions....Pages 108-124 Semantic Object Parsing with Graph LSTM....Pages 125-143 SSHMT: Semi-supervised Hierarchical Merge Tree for Electron Microscopy Image Segmentation....Pages 144-159 Towards Viewpoint Invariant 3D Human Pose Estimation....Pages 160-177 Deep Learning the City: Quantifying Urban Perception at a Global Scale....Pages 178-195 4D Match Trees for Non-rigid Surface Alignment....Pages 196-212 Eigen Appearance Maps of Dynamic Shapes....Pages 213-229 Learnable Histogram: Statistical Context Features for Deep Neural Networks....Pages 230-245 Pedestrian Behavior Understanding and Prediction with Deep Neural Networks....Pages 246-262 Real-Time RGB-D Activity Prediction by Soft Regression....Pages 263-279 A 3D Morphable Eye Region Model for Gaze Estimation....Pages 280-296 Foreground Segmentation via Dynamic Tree-Structured Sparse RPCA....Pages 297-313 Contextual Priming and Feedback for Faster R-CNN....Pages 314-329 Front Matter....Pages 330-348 Efficient Multi-view Surface Refinement with Adaptive Resolution Control....Pages 73-73 Gaussian Process Density Counting from Weak Supervision....Pages 349-364 Region-Based Semantic Segmentation with End-to-End Training....Pages 365-380 Fast 6D Pose Estimation from a Monocular Image Using Hierarchical Pose Trees....Pages 381-397 Learning Models for Actions and Person-Object Interactions with Transfer to Question Answering....Pages 398-413 A Software Platform for Manipulating the Camera Imaging Pipeline....Pages 414-428 A Benchmark and Simulator for UAV Tracking....Pages 429-444 Scene Depth Profiling Using Helmholtz Stereopsis....Pages 445-461 Projective Bundle Adjustment from Arbitrary Initialization Using the Variable Projection Method....Pages 462-476 Localizing and Orienting Street Views Using Overhead Imagery....Pages 477-493 Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding....Pages 494-509 Shuffle and Learn: Unsupervised Learning Using Temporal Order Verification....Pages 510-526 DOC: Deep OCclusion Estimation from a Single Image....Pages 527-544 RepMatch: Robust Feature Matching and Pose for Reconstructing Modern Cities....Pages 545-561 Convolutional Oriented Boundaries....Pages 562-579 Superpixel Convolutional Networks Using Bilateral Inceptions....Pages 580-596 Sublabel-Accurate Convex Relaxation of Vectorial Multilabel Energies....Pages 597-613 Building Dual-Domain Representations for Compression Artifacts Reduction....Pages 614-627 Geometric Neural Phrase Pooling: Modeling the Spatial Co-occurrence of Neurons....Pages 628-644 Photo Aesthetics Ranking Network with Attributes and Content Adaptation....Pages 645-661 Front Matter....Pages 662-679 SDF-2-SDF: Highly Accurate 3D Object Reconstruction....Pages 73-73 Knowledge Transfer for Scene-Specific Motion Prediction....Pages 680-696 Weakly Supervised Localization Using Deep Feature Maps....Pages 697-713 Embedding Deep Metric for Person Re-identification: A Study Against Large Variations....Pages 714-731 Learning to Track at 100 FPS with Deep Regression Networks....Pages 732-748 Matching Handwritten Document Images....Pages 749-765 Semantic Clustering for Robust Fine-Grained Scene Recognition....Pages 766-782 Front Matter....Pages 783-798 Ambient Sound Provides Supervision for Visual Learning....Pages 799-799 Grounding of Textual Phrases in Images by Reconstruction....Pages 801-816 Improving Multi-label Learning with Missing Labels by Structured Semantic Correlations....Pages 817-834 Visual Relationship Detection with Language Priors....Pages 835-851 Back Matter....Pages 852-869 ....Pages 871-873