Computer Vision – ACCV 2016: 13th Asian Conference on Computer Vision, Taipei, Taiwan, November 20-24, 2016, Revised Selected Papers, Part II

Front Matter....Pages I-XIII
Front Matter....Pages 1-1
Sparse Code Filtering for Action Pattern Mining....Pages 3-18
Learning Action Concept Trees and Semantic Alignment Networks from Image-Description Data....Pages 19-34
Pedestrian Color Naming via Convolutional Neural Network....Pages 35-51
Speed Invariance vs. Stability: Cross-Speed Gait Recognition Using Single-Support Gait Energy Image....Pages 52-67
Parametric Image Segmentation of Humans with Structural Shape Priors....Pages 68-83
Front Matter....Pages 85-85
Lip Reading in the Wild....Pages 87-103
Recurrent Convolutional Face Alignment....Pages 104-120
Continuous Supervised Descent Method for Facial Landmark Localisation....Pages 121-135
Modeling Stylized Character Expressions via Deep Learning....Pages 136-153
Variational Gaussian Process Auto-Encoder for Ordinal Prediction of Facial Action Units....Pages 154-170
Multi-Instance Dynamic Ordinal Random Fields for Weakly-Supervised Pain Intensity Estimation....Pages 171-186
Front Matter....Pages 187-187
Analysis on the Dropout Effect in Convolutional Neural Networks....Pages 189-204
Efficient Model Averaging for Deep Neural Networks....Pages 205-220
Joint Training of Generic CNN-CRF Models with Stochastic Optimization....Pages 221-236
Object-Aware Dictionary Learning with Deep Features....Pages 237-253
Front Matter....Pages 255-255
Gait Energy Response Function for Clothing-Invariant Gait Recognition....Pages 257-272
Action Recognition Based on Optimal Joint Selection and Discriminative Depth Descriptor....Pages 273-287
Model-Free Multiple Object Tracking with Shared Proposals....Pages 288-304
Learning to Integrate Occlusion-Specific Detectors for Heavily Occluded Pedestrian Detection....Pages 305-320
Deep Second-Order Siamese Network for Pedestrian Re-identification....Pages 321-337
Front Matter....Pages 255-255
Cost-Sensitive Two-Stage Depression Prediction Using Dynamic Visual Clues....Pages 338-351
Human Interaction Recognition by Mining Discriminative Patches on Key Frames....Pages 352-367
Stacked Overcomplete Independent Component Analysis for Action Recognition....Pages 368-383
Searching Action Proposals via Spatial Actionness Estimation and Temporal Path Inference and Tracking....Pages 384-399
Markov Chain Monte Carlo Cascade for Camera Network Calibration Based on Unconstrained Pedestrian Tracklets....Pages 400-415
Scale-Adaptive Deconvolutional Regression Network for Pedestrian Detection....Pages 416-430
Back Matter....Pages 431-436