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 Image Quality Assessment Using Similar Scene as Reference....Pages 3-18 MOON: A Mixed Objective Optimization Network for the Recognition of Facial Attributes....Pages 19-35 Degeneracies in Rolling Shutter SfM....Pages 36-51 Deep Deformation Network for Object Landmark Localization....Pages 52-70 Learning Visual Storylines with Skipping Recurrent Neural Networks....Pages 71-88 Towards Large-Scale City Reconstruction from Satellites....Pages 89-104 Weakly Supervised Object Localization Using Size Estimates....Pages 105-121 Supervised Transformer Network for Efficient Face Detection....Pages 122-138 A Geometric Approach to Image Labeling....Pages 139-154 ActionSnapping: Motion-Based Video Synchronization....Pages 155-169 A Minimal Solution for Non-perspective Pose Estimation from Line Correspondences....Pages 170-185 Natural Image Stitching with the Global Similarity Prior....Pages 186-201 Minimal Solvers for Generalized Pose and Scale Estimation from Two Rays and One Point....Pages 202-218 Learning to Hash with Binary Deep Neural Network....Pages 219-234 Automatically Selecting Inference Algorithms for Discrete Energy Minimisation....Pages 235-252 Ego2Top: Matching Viewers in Egocentric and Top-View Videos....Pages 253-268 Online Action Detection....Pages 269-284 Cross-Modal Supervision for Learning Active Speaker Detection in Video....Pages 285-301 Recurrent Temporal Deep Field for Semantic Video Labeling....Pages 302-317 Ultra-Resolving Face Images by Discriminative Generative Networks....Pages 318-333 Front Matter....Pages 1-1 A Discriminative Framework for Anomaly Detection in Large Videos....Pages 334-349 ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localization....Pages 350-365 Network Flow Formulations for Learning Binary Hashing....Pages 366-381 SPICE: Semantic Propositional Image Caption Evaluation....Pages 382-398 Transfer Neural Trees for Heterogeneous Domain Adaptation....Pages 399-414 Tracking Persons-of-Interest via Adaptive Discriminative Features....Pages 415-433 Front Matter....Pages 435-435 Spot On: Action Localization from Pointly-Supervised Proposals....Pages 437-453 Detecting Engagement in Egocentric Video....Pages 454-471 Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking....Pages 472-488 Look-Ahead Before You Leap: End-to-End Active Recognition by Forecasting the Effect of Motion....Pages 489-505 Front Matter....Pages 507-507 General Automatic Human Shape and Motion Capture Using Volumetric Contour Cues....Pages 509-526 Globally Continuous and Non-Markovian Crowd Activity Analysis from Videos....Pages 527-544 Joint Face Alignment and 3D Face Reconstruction....Pages 545-560 Keep It SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image....Pages 561-578 Do We Really Need to Collect Millions of Faces for Effective Face Recognition?....Pages 579-596 Generative Visual Manipulation on the Natural Image Manifold....Pages 597-613 Deep Cascaded Bi-Network for Face Hallucination....Pages 614-630 Cluster Sparsity Field for Hyperspectral Imagery Denoising....Pages 631-647 Zoom Better to See Clearer: Human and Object Parsing with Hierarchical Auto-Zoom Net....Pages 648-663 Learning Common and Specific Features for RGB-D Semantic Segmentation with Deconvolutional Networks....Pages 664-679 Front Matter....Pages 507-507 MADMM: A Generic Algorithm for Non-smooth Optimization on Manifolds....Pages 680-696 Interpreting the Ratio Criterion for Matching SIFT Descriptors....Pages 697-712 Semi-supervised Learning Based on Joint Diffusion of Graph Functions and Laplacians....Pages 713-729 Improving Semantic Embedding Consistency by Metric Learning for Zero-Shot Classiffication....Pages 730-746 A Sequential Approach to 3D Human Pose Estimation: Separation of Localization and Identification of Body Joints....Pages 747-761 A Novel Tiny Object Recognition Algorithm Based on Unit Statistical Curvature Feature....Pages 762-777 Fine-Grained Material Classification Using Micro-geometry and Reflectance....Pages 778-792 The Conditional Lucas & Kanade Algorithm....Pages 793-808 Where Should Saliency Models Look Next?....Pages 809-824 Robust Face Alignment Using a Mixture of Invariant Experts....Pages 825-841 Partial Linearization Based Optimization for Multi-class SVM....Pages 842-857 Search-Based Depth Estimation via Coupled Dictionary Learning with Large-Margin Structure Inference....Pages 858-874 Scalable Metric Learning via Weighted Approximate Rank Component Analysis....Pages 875-890 Back Matter....Pages 891-893