Computer vision -- ACCV 2014 : 12th Asian Conference on Computer Vision, Singapore, Singapore, November 1-5, 2014, Revised selected papers. by Asian Conference on Computer Vision Singapore, Singapore, SpringerLink (Online service)

Table of Contents: “….- 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.…”
Get full text

Computer vision -- ACCV 2014 : 12th Asian Conference on Computer Vision, Singapore, Singapore, November 1-5, 2014, Revised selected papers. by Asian Conference on Computer Vision Singapore, Singapore, SpringerLink (Online service)

Table of Contents: “…-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.…”
Get full text

Computer vision-- ACCV 2014 : 12th Asian Conference on Computer Vision, Singapore, Singapore, November 1-5, 2014, Revised selected papers. by Asian Conference on Computer Vision Singapore, Singapore, SpringerLink (Online service)

Table of Contents: “…Jointly Learning Dictionaries and Subspace Structure for Video-Based Face Recognition1 Introduction; 1.1 Related Work; 2 Preliminaries; 2.1 Subspace Learning via Low-Rank Minimization; 2.2 Dictionary Learning for Sparse Representation; 3 Joint Discriminative Dictionary Learning and Subspace Structure Recovery for Videos; 3.1 Problem Formulation; 3.2 Optimization; 3.3 Recognition; 4 Experiments; 4.1 Comparison Methods; 4.2 Experimental Set-Up; 4.3 Analysis and Discussions; 5 Conclusion and Future Work; References; Visual Salience Learning via Low Rank Matrix Recovery; 1 Introduction…”
Get full text

Computer vision -- ACCV 2014 : 12th Asian Conference on Computer Vision, Singapore, Singapore, November 1-5, 2014, Revised selected papers. by Asian Conference on Computer Vision Singapore, Singapore, SpringerLink (Online service)

Table of Contents: “…1 Introduction2 Background; 2.1 Linear Discriminant Analysis with Stationarity; 2.2 Correlation Filters; 2.3 Related Work; 3 Fast Estimation of the Toeplitz Covariance; 4 From Toeplitz to Circulant; 5 Multi-channel, Two-Dimensional Signals; 5.1 Toeplitz Covariance Matrix; 5.2 Circulant Covariance Matrix; 5.3 From Toeplitz to Circulant; 6 Solving Toeplitz Systems; 6.1 Direct Methods; 6.2 Iterative Methods; 6.3 An Effective Heuristic; 7 Empirical Study; 7.1 Detection Performance; 7.2 Time and Memory; 8 Conclusion; References; Age Estimation Based on Complexity-Aware Features; 1 Introduction…”
Get full text