Computer Vision – ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part VIII

Front Matter....Pages I-XXVIII
Front Matter....Pages 1-1
Query-Focused Extractive Video Summarization....Pages 3-19
Temporal Segment Networks: Towards Good Practices for Deep Action Recognition....Pages 20-36
PlaNet - Photo Geolocation with Convolutional Neural Networks....Pages 37-55
Detecting Text in Natural Image with Connectionist Text Proposal Network....Pages 56-72
Face Recognition Using a Unified 3D Morphable Model....Pages 73-89
Augmented Feedback in Semantic Segmentation Under Image Level Supervision....Pages 90-105
Front Matter....Pages 107-107
Linear Depth Estimation from an Uncalibrated, Monocular Polarisation Image....Pages 109-125
Online Variational Bayesian Motion Averaging....Pages 126-142
Unified Depth Prediction and Intrinsic Image Decomposition from a Single Image via Joint Convolutional Neural Fields....Pages 143-159
ObjectNet3D: A Large Scale Database for 3D Object Recognition....Pages 160-176
Branching Gaussian Processes with Applications to Spatiotemporal Reconstruction of 3D Trees....Pages 177-193
Tracking Completion....Pages 194-209
Inter-battery Topic Representation Learning....Pages 210-226
Online Adaptation for Joint Scene and Object Classification....Pages 227-243
Real-Time Facial Segmentation and Performance Capture from RGB Input....Pages 244-261
Learning Temporal Transformations from Time-Lapse Videos....Pages 262-277
Interactive Image Segmentation Using Constrained Dominant Sets....Pages 278-294
Deep Markov Random Field for Image Modeling....Pages 295-312
A Symmetry Prior for Convex Variational 3D Reconstruction....Pages 313-328
SPLeaP: Soft Pooling of Learned Parts for Image Classification....Pages 329-345
Front Matter....Pages 107-107
Spatial Attention Deep Net with Partial PSO for Hierarchical Hybrid Hand Pose Estimation....Pages 346-361
VolumeDeform: Real-Time Volumetric Non-rigid Reconstruction....Pages 362-379
Peripheral Expansion of Depth Information via Layout Estimation with Fisheye Camera....Pages 380-395
Built-in Foreground/Background Prior for Weakly-Supervised Semantic Segmentation....Pages 396-412
It’s Moving! A Probabilistic Model for Causal Motion Segmentation in Moving Camera Videos....Pages 413-432
Kernelized Subspace Ranking for Saliency Detection....Pages 433-449
Depth-Aware Motion Magnification....Pages 450-466
Stacked Hourglass Networks for Human Pose Estimation....Pages 467-482
Real-Time Large-Scale Dense 3D Reconstruction with Loop Closure....Pages 483-499
Pixel-Level Domain Transfer....Pages 500-516
Accelerating Convolutional Neural Networks with Dominant Convolutional Kernel and Knowledge Pre-regression....Pages 517-532
Learning Social Etiquette: Human Trajectory Understanding In Crowded Scenes....Pages 533-548
Bayesian Image Based 3D Pose Estimation....Pages 549-565
Efficient and Robust Semi-supervised Learning Over a Sparse-Regularized Graph....Pages 566-582
Novel Coplanar Line-Points Invariants for Robust Line Matching Across Views....Pages 583-598
Sparse Representation Based Complete Kernel Marginal Fisher Analysis Framework for Computational Art Painting Categorization....Pages 599-611
3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction....Pages 612-627
Cascaded Continuous Regression for Real-Time Incremental Face Tracking....Pages 628-644
Real-Time Visual Tracking: Promoting the Robustness of Correlation Filter Learning....Pages 645-661
Front Matter....Pages 662-678
Deep Self-correlation Descriptor for Dense Cross-Modal Correspondence....Pages 107-107
Structured Matching for Phrase Localization....Pages 679-695
Crossing-Line Crowd Counting with Two-Phase Deep Neural Networks....Pages 696-711
Revisiting Visual Question Answering Baselines....Pages 712-726
Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue....Pages 727-739
A Continuous Optimization Approach for Efficient and Accurate Scene Flow....Pages 740-756
Improving Multi-frame Data Association with Sparse Representations for Robust Near-online Multi-object Tracking....Pages 757-773
Gated Siamese Convolutional Neural Network Architecture for Human Re-identification....Pages 774-790
Saliency Detection via Combining Region-Level and Pixel-Level Predictions with CNNs....Pages 791-808
Back Matter....Pages 809-825
....Pages 827-829