Improving Human Action Recognition Using Score Distribution and Ranking.- Context-Aware Activity Forecasting.- DMM-Pyramid Based Deep Architectures for Action Recognition with Depth Cameras.- Discriminative Orderlet Mining for Real-Time Recognition of Human-Object Interaction.- Anomaly Detection via Local Coordinate Factorization and Spatio-Temporal Pyramid.- Intrinsic Image Decomposition from Pair-Wise Shading Ordering.- Never Get Lost Again: Vision Based Navigation Using StreetView Images.- Qualitative and Quantitative Spatio-temporal Relations in Daily Living Activity Recognition.- Blur-Resilient Tracking Using Group Sparsity.- Visual Tracking via Supervised Similarity Matching.- Multi-state Discriminative Video Segment Selection for Complex Event Classification.- Action Recognition in the Presence of One Egocentric and Multiple Static Cameras.- Robust Online Visual Tracking with a Single Convolutional Neural Network.- -Stage Large Point Set Registration Using Gaussian Mixture Models.- Enhanced Sequence Matching for Action Recognition from 3D Skeletal Data.- Multi-label Discriminative Weakly-Supervised Human Activity Recognition and Localization.- Action-Gons: Action Recognition with a Discriminative Dictionary of Structured Elements with Varying Granularity.- Fast Inference of Contaminated Data for Real Time Object Tracking.- Data Mining for Action Recognition.- A Rotation-Invariant Regularization Term for Optical Flow Related Problems.- Landmark-Based Inductive Model for Robust Discriminative Tracking.- Extended Co-occurrence HOG with Dense Trajectories for Fine-Grained.- Motion Based Foreground Detection and Poselet Motion Features for Action Recognition.- Global Motion Estimation from Relative Measurements in the Presence of Outliers -- Clustering Ensemble Tracking.- Query Based Adaptive Re-ranking for Person Re-identification.- Improved Color Patch Similarity Measure Based Weighted Median Filter.- Efficient Pose-Based Action Recognition.- Tracking Multiple People Online and in Real Time.- Optimizing Storage Intensive Vision Applications to Device Capacity.- MTS: A Multiple Temporal Scale Tracker Handling Occlusion and Abrupt Motion Variation.- Video Annotation by Incremental Learning from Grouped Heterogeneous Sources.- A Novel Group-Sparsity-Optimization-Based Feature Selection Model for Complex Interaction Recognition -- Boosting-Based Visual Tracking Using Structural Local Sparse Descriptors.- Coupling Multiple Alignments and Re-ranking for Low-Latency Online Multi-target Tracking.- Determining Interacting Objects in Human-Centric Activities via Qualitative Spatio-Temporal Reasoning -- Enhanced Laplacian Group Sparse Learning with Lifespan Outlier Rejection for Visual Tracking.- Cross-view Action Recognition via Dual-Codebook and Hierarchical Transfer Framework -- Stereo Ground Truth with Error Bars.- Separation of Reflection Components by Sparse Non-negative Matrix Factorization.- Spatiotemporal Derivative Pattern: A Dynamic Texture Descriptor for Video Matching -- Weakly Supervised Action Recognition and Localization Using Web Images -- A Game-Theoretic Probabilistic Approach for Detecting Conversational Groups.

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.