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.

Inhalt

Accelerating the Distribution Estimation for the Weighted Median/Mode Filters.- Saliency Aggregation: Does Unity Make Strength.- Spontaneous Subtle Expression Recognition: Imbalanced Databases and Solutions.- EPML: Expanded Parts Based Metric Learning for Occlusion Robust Face Verification.- Pixel-Level Hand Detection with Shape-Aware Structured Forests.- Beyond Procedural Facade Parsing: Bidirectional Alignment via Linear Programming.- Shape Matching Using Point Context and Contour Segments.- A+: Adjusted Anchored Neighborhood Regression for Fast Super-Resolution.- Multiple Ocular Diseases Classification with Graph Regularized Probabilistic Multi-label Learning.- Deeply Learning Deformable Facial Action Parts Model for Dynamic Expression Analysis.- A Novel Context-Aware Topic Model for Category Discovery in Natural Scenes.- Robust Sharpness Metrics Using Reorganized DCT Coefficients for Auto-Focus Application.-Dislocation: Scalable Descriptor Distinctiveness for Location Recognition.- Discriminative Collaborative Representation for Classification.- Thread-Safe: Towards Recognizing Human Actions Across Shot Boundaries.- Consistent Foreground Co-segmentation.-On Multiple Image Group Co segmentation.- Reconstructive Sparse Code Transfer for Contour Detection and Semantic Labeling.- A Message Passing Algorithm for MRF Inference with Unknown Graphs and Its Applications.- Joint Estimation of Pose and Face Landmark.- Probabilistic Sub pixel Temporal Registration for Facial Expression Analysis.- Depth Recovery with Face Priors.- Inlier Estimation for Moving Camera Motion Segmentation.- Real-Time Tracking of Multiple Objects by Linear Motion and Repulsive Motion.- 6-DOF Model Based Tracking via Object Coordinate Regression.- Probabilistic State Space Decomposition for Human Motion Capture.- Spectral Graph Skeletons for 3D Action Recognition.- Robust Point Matching Using Mixture of Asymmetric Gaussians for Nonrigid Transformation.- Multiple Object Tracking by Efficient Graph Partitioning.- Fast Approximate Nearest-Neighbor Field by Cascaded Spherical Hashing.- Coupling Semi-supervised Learning and Example Selection for Online Object Tracking.- Reconstructing Shape and Appearance of Thin Film Objects with Hyper Spectral Sensor.- A Two-Stage Approach for Bag Detection in Pedestrian Images.- Recognizing Daily Activities from First-Person Videos with Multi-task Clustering.- Multi-view Recognition Using Weighted View Selection.- Graph Transduction Learning of Object Proposals for Video Object Segmentation.-Forecasting Events Using an Augmented Hidden Conditional Random Field.- Camera Motion and Surrounding Scene Appearance as Context for Action Recognition.- Semi-Supervised Ranking for Re-identification with Few Labeled Image Pairs.- Robust Visual Tracking with Dual Group Structure.- 3D Reconstruction of Specular Objects with Occlusion: A Shape-from-Scattering Approach.- 2D or Not 2D: Bridging the Gap Between Tracking and Structure from Motion.- Clouds in the Cloud.- Fast Segmentation of Sparse 3D Point Trajectories Using Group Theoretical Invariants.- Super pixels for Video Content Using a Contour-Based EM Optimization.-Transformed Principal Gradient Orientation for Robust and Precise Batch Face Alignment.