Computer Vision -- ACCV 2014

The five-volume set LNCS 9003--9007 constitutes the thoroughly refereed post-conference proceedings of the 12th Asian Conference on Computer Vision, ACCV 2014, held in Singapore, Singapore, in November 2014.

The total of 227 contributions presented in these volumes was carefully reviewed and selected from 814 submissions. The papers are organized in topical sections on recognition; 3D vision; low-level vision and features; segmentation; face and gesture, tracking; stereo, physics, video and events; and poster sessions 1-3.

Accurate Vessel Segmentation with Progressive Contrast Enhancement and Canny Refinement.- Eigen-PEP for Video Face Recognition.- Local Generic Representation for Face Recognition with Single Sample per Person.- Unsupervised Image Co-segmentation Based on Cooperative Game.- A High Performance CRF Model for Clothes Parsing.- Real-Time Head Orientation from a Monocular Camera Using Deep Neural Network.- Jointly Learning Dictionaries and Subspace Structure for Video-Based Face Recognition.- Visual Salience Learning via Low Rank Matrix Recovery.- A New Framework for Multiclass Classification Using Multiview Assisted Adaptive Boosting.- Age Estimation by Multi-scale Convolutional Network.- Photorealistic Face De-Identification by Aggregating Donors’ Face Components.- Which Image Pairs Will Cosegment Well? Predicting Partners for Cosegmentation.- Image Restoration via Multi-prior Collaboration.- Modeling the Temporality of Saliency.- Salient Object Detection Using Window Mask Transferring with Multi-layer Background Contrast.- A Patch Aware Multiple Dictionary Framework for Demosaicing.- Large Margin Multi-metric Learning for Face and Kinship Verification in the Wild.- A Three-Color Coupled Level-Set Algorithm for Simultaneous Multiple Cell Segmentation and Tracking.- OR-PCA with MRF for Robust Foreground Detection in Highly Dynamic Backgrounds.- Segmentation of Cells from Spinning Disk Confocal Images Using a Multi-stage Approach.- Head Motion Signatures from Egocentric Videos.- Improving Saliency Models by Predicting Human Fixation Patches.- Fast Super-Resolution via Dense Local Training and Inverse Regressor Search.- PSPGC: Part-Based Seeds for Parametric Graph-Cuts.- Multi-cue Mid-level Grouping.- Simple-to-Complex Discriminative Clustering for Hierarchical Image Segmentation.- Learning One-Shot Exemplar SVM from the Web for Face Verification.- Unsupervised Segmentation of RGB-D Images.- Class-Driven Color Transformation for Semantic Labeling.- Discovering Harmony: A Hierarchical Colour Harmony Model for Aesthetics Assessment.- Deconstructing Binary Classifiers in Computer Vision.- Effective Drusen Segmentation from Fundus Images for Age-Related Macular Degeneration Screening.- Recognizing People by Their Personal Aesthetics: A Statistical Multi-level Approach.- FASA: Fast, Accurate, and Size-Aware Salient Object Detection.- Gesture Modeling by Hanklet-Based Hidden Markov Model.- A Novel Face Spoofing Detection Method Based on Gaze Estimation.- Hybrid Euclidean-and-Riemannian Metric Learning for Image Set Classification.- Size and Location Matter: A New Baseline for Salient Object Detection.- Learning Hierarchical Feature Representation in Depth Image.- Automatic Wrinkle Detection Using Hybrid Hessian Filter.- Transductive Transfer Machine.- Fully Automatic Segmentation of Hip CT Images via Random Forest Regression-Based Atlas Selection and Optimal Graph Search-Based Surface Detection.- Optimal Transportation for Example-Guided Color Transfer.- Evaluation of Discriminative Models for the Reconstruction of Hand-Torn Documents.- Hand Segmentation with Structured Convolutional Learning.- Topic-Aware Deep Auto-Encoders (TDA) for Face Alignment.