Computer Vision – ACCV 2016: 13th Asian Conference on Computer Vision, Taipei, Taiwan, November 20-24, 2016, Revised Selected Papers, Part IV (Lecture Notes in Computer Science (10114))

The five-volume set LNCS 10111-10115 constitutes the thoroughly refereed post-conference proceedings of the 13th Asian Conference on Computer Vision, ACCV 2016, held in Taipei, Taiwan, in November 2016. The total of 143 contributions presented in these volumes was carefully reviewed and selected from 479 submissions. The papers are organized in topical sections on Segmentation and Classification; Segmentation and Semantic Segmentation; Dictionary Learning, Retrieval, and Clustering; Deep Learning; People Tracking and Action Recognition; People and Actions; Faces; Computational Photography; Face and Gestures; Image Alignment; Computational Photography and Image Processing; Language and Video; 3D Computer Vision; Image Attributes, Language, and Recognition; Video Understanding; and 3D Vision. Front Matter....Pages I-XIII Front Matter....Pages 1-1 Blind Image Quality Assessment Based on Natural Redundancy Statistics....Pages 3-18 Sparse Coding on Cascaded Residuals....Pages 19-34 End-to-End Learning for Image Burst Deblurring....Pages 35-51 Spectral Reflectance Recovery with Interreflection Using a Hyperspectral Image....Pages 52-67 Learning Contextual Dependencies for Optical Flow with Recurrent Neural Networks....Pages 68-83 Front Matter....Pages 85-85 Auto-Illustrating Poems and Songs with Style....Pages 87-103 Spatio-Temporal Attention Models for Grounded Video Captioning....Pages 104-119 Variational Convolutional Networks for Human-Centric Annotations....Pages 120-135 Anticipating Accidents in Dashcam Videos....Pages 136-153 PicMarker: Data-Driven Image Categorization Based on Iterative Clustering....Pages 154-171 Front Matter....Pages 172-187 Adaptive Direct RGB-D Registration and Mapping for Large Motions....Pages 189-189 Deep Discrete Flow....Pages 191-206 Dense Motion Estimation for Smoke....Pages 207-224 Data Association Based Multi-target Tracking Using a Joint Formulation....Pages 225-239 Combining Texture and Shape Cues for Object Recognition with Minimal Supervision....Pages 240-255 Video Temporal Alignment for Object Viewpoint....Pages 256-272 Front Matter....Pages 273-288 Recovering Pose and 3D Deformable Shape from Multi-instance Image Ensembles....Pages 289-289 Robust Multi-Model Fitting Using Density and Preference Analysis....Pages 291-307 Photometric Bundle Adjustment for Vision-Based SLAM....Pages 308-323 Front Matter....Pages 324-341 Can Computer Vision Techniques be Applied to Automated Forensic Examinations? A Study on Sex Identification from Human Skulls Using Head CT Scans....Pages 289-289 Deep Depth Super-Resolution: Learning Depth Super-Resolution Using Deep Convolutional Neural Network....Pages 342-359 3D Watertight Mesh Generation with Uncertainties from Ubiquitous Data....Pages 360-376 Color Correction for Image-Based Modeling in the Large....Pages 377-391 Bringing 3D Models Together: Mining Video Liaisons in Crowdsourced Reconstructions....Pages 392-407 Planar Markerless Augmented Reality Using Online Orientation Estimation....Pages 408-423 Simultaneous Independent Image Display Technique on Multiple 3D Objects....Pages 424-439 ZigzagNet: Efficient Deep Learning for Real Object Recognition Based on 3D Models....Pages 440-455 Precise Measurement of Cargo Boxes for Gantry Robot Palletization in Large Scale Workspaces Using Low-Cost RGB-D Sensors....Pages 456-471 Visual Place Recognition Using Landmark Distribution Descriptors....Pages 472-486 Real Time Direct Visual Odometry for Flexible Multi-camera Rigs....Pages 487-502 Analysis and Practical Minimization of Registration Error in a Spherical Fish Tank Virtual Reality System....Pages 503-518 Enhancing Direct Camera Tracking with Dense Feature Descriptors....Pages 519-534 Back Matter....Pages 535-551 ....Pages 553-558