Object Detection, Tracking and Recognition -- Robust Tracking with and Beyond Visible Spectrum: A Four-Layer Data Fusion Framework -- Scale Space Based Grammar for Hand Detection -- Combined Classifiers for Action Recognition -- Adaptive Sparse Vector Tracking Via Online Bayesian Learning -- Iterative Division and Correlograms for Detection and Tracking of Moving Objects -- Human Pose Estimation from Polluted Silhouettes Using Sub-manifold Voting Strategy -- Kernel Modified Quadratic Discriminant Function for Facial Expression Recognition -- 3D Motion from Image Derivatives Using the Least Trimmed Square Regression -- Motion and Gray Based Automatic Road Segment Method MGARS in Urban Traffic Surveillance -- A Statistically Selected Part-Based Probabilistic Model for Object Recognition -- Approximate Vehicle Waiting Time Estimation Using Adaptive Video-Based Vehicle Tracking -- Mouth Region Localization Method Based on Gaussian Mixture Model -- Traffic Video Segmentation Using Adaptive-K Gaussian Mixture Model -- EM-in-M: Analyze and Synthesize Emotion in Motion -- Pattern Representation and Modeling -- Discriminant Transform Based on Scatter Difference Criterion in Hidden Space -- Looking for Prototypes by Genetic Programming -- Identifying Single Good Clusters in Data Sets -- A New Simplified Gravitational Clustering Method for Multi-prototype Learning Based on Minimum Classification Error Training -- Speaker Identification and Verification Using Support Vector Machines and Sparse Kernel Logistic Regression -- Monitoring Abnormal Patterns with Complex Semantics over ICU Data Streams -- Spatial-temporal Analysis Method of Plane Circuits Based on Two-Layer Cellular Neural Networks -- Feature-Based Synchronization of Video and Background Music -- Visual Pattern Modeling -- An Integration Conceptfor Vision-Based Object Handling: Shape-Capture, Detection and Tracking -- Visual Information Encryption in Frequency Domain: Risk and Enhancement -- Automatic 3D Face Model Reconstruction Using One Image -- Cognitive Approach to Visual Data Interpretation in Medical Information and Recognition Systems -- Modelling the Human Visual Process by Evolving Images from Noise -- A Novel Recovery Algorithm of Incomplete Observation Matrix for Converting 2-D Video to 3-D Content -- Study on the Geolocation Algorithm of Space-Borne SAR Image -- Image Processing -- Perceptual Image Retrieval Using Eye Movements -- A Pseudo-hilbert Scan Algorithm for Arbitrarily-Sized Rectangle Region -- Panoramas from Partially Blurred Video -- Salience-Preserving Image Composition with Luminance Consistency -- Filament Enhancement by Non-linear Volumetric Filtering Using Clustering-Based Connectivity -- Applying Preattentive Visual Guidance in Document Image Analysis -- Efficient and Robust Segmentations Based on Eikonal and Diffusion PDEs -- Local Orientation Estimation in Corrupted Images -- Illumination-Invariant Color Image Correction -- Motion Blur Identification in Noisy Images Using Feed-Forward Back Propagation Neural Network -- Using Shear Invariant for Image Denoising in the Contourlet Domain -- Region-Based Shock-Diffusion Equation for Adaptive Image Enhancement -- A Statistical Level Set Framework for Segmentation of Left Ventricle -- A Bayesian Estimation Approach to Super-Resolution Reconstruction for Face Images -- Hierarchical Markovian Models for Hyperspectral Image Segmentation -- Compression and Coding -- Adaptive Geometry Compression Based on 4-Point Interpolatory Subdivision Schemes -- Parametrization Construction of Integer Wavelet Transforms for Embedded Image Coding -- Reinforcement Learning with Raw Image Pixels as Input State -- New Region of Interest Medical Image Coding for JPEG2000: Compensation-Based Partial Bitplane Alternating Shift -- A New Wavelet Lifting Scheme for Image Compression Applications -- Texture Analysis and Synthesis -- BTF Modelling Using BRDF Texels -- Texture Classification Via Stationary-Wavelet Based Contourlet Transform -- Automatic Color-Texture Image Segmentation by Using Active Contours.