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

Front Matter....Pages I-XXIX
Front Matter....Pages 1-1
Reflection Symmetry Detection via Appearance of Structure Descriptor....Pages 3-18
Faceless Person Recognition: Privacy Implications in Social Media....Pages 19-35
Segmental Spatiotemporal CNNs for Fine-Grained Action Segmentation....Pages 36-52
Structure from Motion on a Sphere....Pages 53-68
Evaluation of LBP and Deep Texture Descriptors with a New Robustness Benchmark....Pages 69-86
MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition....Pages 87-102
Hierarchical Beta Process with Gaussian Process Prior for Hyperspectral Image Super Resolution....Pages 103-120
A 4D Light-Field Dataset and CNN Architectures for Material Recognition....Pages 121-138
Graph-Based Consistent Matching for Structure-from-Motion....Pages 139-155
All-Around Depth from Small Motion with a Spherical Panoramic Camera....Pages 156-172
On Volumetric Shape Reconstruction from Implicit Forms....Pages 173-188
Multi-attributed Graph Matching with Multi-layer Random Walks....Pages 189-204
Deep Learning of Local RGB-D Patches for 3D Object Detection and 6D Pose Estimation....Pages 205-220
A Neural Approach to Blind Motion Deblurring....Pages 221-235
Joint Face Representation Adaptation and Clustering in Videos....Pages 236-251
Uncovering Symmetries in Polynomial Systems....Pages 252-267
ATGV-Net: Accurate Depth Super-Resolution....Pages 268-284
Indoor-Outdoor 3D Reconstruction Alignment....Pages 285-300
The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition....Pages 301-320
A Simple Hierarchical Pooling Data Structure for Loop Closure....Pages 321-337
Front Matter....Pages 1-1
A Versatile Approach for Solving PnP, PnPf, and PnPfr Problems....Pages 338-352
Depth Map Super-Resolution by Deep Multi-Scale Guidance....Pages 353-369
SEAGULL: Seam-Guided Local Alignment for Parallax-Tolerant Image Stitching....Pages 370-385
Grid Loss: Detecting Occluded Faces....Pages 386-402
Large-Scale R-CNN with Classifier Adaptive Quantization....Pages 403-419
Face Detection with End-to-End Integration of a ConvNet and a 3D Model....Pages 420-436
Large Scale Asset Extraction for Urban Images....Pages 437-452
Multi-label Active Learning Based on Maximum Correntropy Criterion: Towards Robust and Discriminative Labeling....Pages 453-468
Shading-Aware Multi-view Stereo....Pages 469-485
Fine-Scale Surface Normal Estimation Using a Single NIR Image....Pages 486-500
Pixelwise View Selection for Unstructured Multi-View Stereo....Pages 501-518
Laplacian Pyramid Reconstruction and Refinement for Semantic Segmentation....Pages 519-534
Generic 3D Representation via Pose Estimation and Matching....Pages 535-553
Hand Pose Estimation from Local Surface Normals....Pages 554-569
Abundant Inverse Regression Using Sufficient Reduction and Its Applications....Pages 570-584
Learning Diverse Models: The Coulomb Structured Support Vector Machine....Pages 585-599
Pose Hashing with Microlens Arrays....Pages 600-614
Front Matter....Pages 615-615
The Fast Bilateral Solver....Pages 617-632
Phase-Based Modification Transfer for Video....Pages 633-648
Colorful Image Colorization....Pages 649-666
Front Matter....Pages 615-615
Focal Flow: Measuring Distance and Velocity with Defocus and Differential Motion....Pages 667-682
Front Matter....Pages 683-683
An Evaluation of Computational Imaging Techniques for Heterogeneous Inverse Scattering....Pages 685-701
Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks....Pages 702-716
Fast Guided Global Interpolation for Depth and Motion....Pages 717-733
Learning High-Order Filters for Efficient Blind Deconvolution of Document Photographs....Pages 734-749
Multi-view Inverse Rendering Under Arbitrary Illumination and Albedo....Pages 750-767
DAPs: Deep Action Proposals for Action Understanding....Pages 768-784
A Large Contextual Dataset for Classification, Detection and Counting of Cars with Deep Learning....Pages 785-800
Reliable Attribute-Based Object Recognition Using High Predictive Value Classifiers....Pages 801-815
Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition....Pages 816-833
Going Further with Point Pair Features....Pages 834-848
Webly-Supervised Video Recognition by Mutually Voting for Relevant Web Images and Web Video Frames....Pages 849-866
HFS: Hierarchical Feature Selection for Efficient Image Segmentation....Pages 867-882
Back Matter....Pages 883-885