Poster Session 1: Stereo, Motion Analysis, and Tracking -- A Dynamic Programming Approach to Maximizing Tracks for Structure from Motion -- Dense and Accurate Spatio-temporal Multi-view Stereovision -- Semi-supervised Feature Selection for Gender Classification -- Planar Scene Modeling from Quasiconvex Subproblems -- Fast Depth Map Compression and Meshing with Compressed Tritree -- A Three-Phase Approach to Photometric Calibration for Multi-projector Display Using LCD Projectors -- Twisted Cubic: Degeneracy Degree and Relationship with General Degeneracy -- Two-View Geometry and Reconstruction under Quasi-perspective Projection -- Similarity Scores Based on Background Samples -- Human Action Recognition Using Spatio-temporal Classification -- Face Alignment Using Boosting and Evolutionary Search -- Tracking Eye Gaze under Coordinated Head Rotations with an Ordinary Camera -- Orientation and Scale Invariant Kernel-Based Object Tracking with Probabilistic Emphasizing -- Combining Edge and Color Features for Tracking Partially Occluded Humans -- Incremental Multi-view Face Tracking Based on General View Manifold -- Hierarchical Model for Joint Detection and Tracking of Multi-target -- Heavy-Tailed Model for Visual Tracking via Robust Subspace Learning -- Efficient Scale-Space Spatiotemporal Saliency Tracking for Distortion-Free Video Retargeting -- Visual Saliency Based Object Tracking -- People Tracking and Segmentation Using Efficient Shape Sequences Matching -- Monocular Template-Based Tracking of Inextensible Deformable Surfaces under L 2-Norm -- A Graph-Based Feature Combination Approach to Object Tracking -- A Smarter Particle Filter -- Robust Real-Time Multiple Target Tracking -- Dynamic Kernel-Based Progressive Particle Filter for 3D Human Motion Tracking -- Bayesian 3D Human Body Pose Tracking from Depth Image Sequences -- Crowd Flow Characterization with Optimal Control Theory -- Human Action Recognition Using HDP by Integrating Motion and Location Information -- Detecting Spatiotemporal Structure Boundaries: Beyond Motion Discontinuities -- An Accelerated Human Motion Tracking System Based on Voxel Reconstruction under Complex Environments -- Automated Center of Radial Distortion Estimation, Using Active Targets -- Rotation Averaging with Application to Camera-Rig Calibration -- Single-Camera Multi-baseline Stereo Using Fish-Eye Lens and Mirrors -- Generation of an Omnidirectional Video without Invisible Areas Using Image Inpainting -- Accurate and Efficient Cost Aggregation Strategy for Stereo Correspondence Based on Approximated Joint Bilateral Filtering -- Detecting Critical Configurations for Dividing Long Image Sequences for Factorization-Based 3-D Scene Reconstruction -- Scene Gist: A Holistic Generative Model of Natural Image -- A Robust Algorithm for Color Correction between Two Stereo Images -- Efficient Human Action Detection Using a Transferable Distance Function -- Crease Detection on Noisy Meshes via Probabilistic Scale Selection -- Improved Uncalibrated View Synthesis by Extended Positioning of Virtual Cameras and Image Quality Optimization -- Region Based Color Image Retrieval Using Curvelet Transform -- Extracting Spatio-temporal Local Features Considering Consecutiveness of Motions -- Multi-view Texturing of Imprecise Mesh -- Poster Session 2: Segmentation, Detection, Color and Texture -- Semantic Classification in Aerial Imagery by Integrating Appearance and Height Information -- Real-Time Video Matting Based on Bilayer Segmentation -- Transductive Segmentation of Textured Meshes -- Levels of Details for Gaussian Mixture Models -- A Blind Robust Watermarking Scheme Based on ICA and Image Dividing Blocks -- MIFT: A Mirror Reflection Invariant Feature Descriptor -- Detection of Vehicle Manufacture Logos Using Contextual Information -- Part-Based Object Detection Using Cascades of Boosted Classifiers -- A Novel Self-created Tree Structure Based Multi-view Face Detection -- Multilinear Nonparametric Feature Analysis -- A Harris-Like Scale Invariant Feature Detector -- Probabilistic Cascade Random Fields for Man-Made Structure Detection -- A Novel System for Robust Text Location and Recognition of Book Covers -- A Multi-scale Bilateral Structure Tensor Based Corner Detector -- Pedestrian Recognition Using Second-Order HOG Feature -- Fabric Defect Detection and Classification Using Gabor Filters and Gaussian Mixture Model -- Moving Object Segmentation in the H.264 Compressed Domain -- Video Segmentation Using Iterated Graph Cuts Based on Spatio-temporal Volumes -- Spectral Graph Partitioning Based on a Random Walk Diffusion Similarity Measure -- Iterated Graph Cuts for Image Segmentation -- Contour Extraction Based on Surround Inhibition and Contour Grouping -- Confidence-Based Color Modeling for Online Video Segmentation -- Multicue Graph Mincut for Image Segmentation.