Recognition II -- Blind Vision -- Object Detection by Contour Segment Networks -- Sparse Flexible Models of Local Features -- Shape from X -- Differential Geometric Consistency Extends Stereo to Curved Surfaces -- Resolution-Enhanced Photometric Stereo -- The 4-Source Photometric Stereo Under General Unknown Lighting -- Poster Session III -- Incorporating Non-motion Cues into 3D Motion Segmentation -- Multi-camera Tracking and Segmentation of Occluded People on Ground Plane Using Search-Guided Particle Filtering -- Learning Semantic Scene Models by Trajectory Analysis -- Multivariate Relevance Vector Machines for Tracking -- Real-Time Upper Body Detection and 3D Pose Estimation in Monoscopic Images -- Gait Recognition Using a View Transformation Model in the Frequency Domain -- Multiview Geometry and 3D Methods -- Video Mensuration Using a Stationary Camera -- Revisiting the Brightness Constraint: Probabilistic Formulation and Algorithms -- Triangulation for Points on Lines -- A Fast Line Segment Based Dense Stereo Algorithm Using Tree Dynamic Programming -- Describing and Matching 2D Shapes by Their Points of Mutual Symmetry -- Oriented Visibility for Multiview Reconstruction -- Integrating Surface Normal Vectors Using Fast Marching Method -- Statistical Models and Visual Learning -- Learning Discriminative Canonical Correlations for Object Recognition with Image Sets -- Statistical Priors for Efficient Combinatorial Optimization Via Graph Cuts -- Sampling Representative Examples for Dimensionality Reduction and Recognition - Bootstrap Bumping LDA -- Studying Aesthetics in Photographic Images Using a Computational Approach -- Located Hidden Random Fields: Learning Discriminative Parts for Object Detection -- Learning Compositional Categorization Models -- EMD-L 1: An Efficient and Robust Algorithm for Comparing Histogram-Based Descriptors -- Face/Gesture/Action Detection and Recognition -- 2D and 3D Multimodal Hybrid Face Recognition -- Robust Attentive Behavior Detection by Non-linear Head Pose Embedding and Estimation -- Human Pose Tracking Using Multi-level Structured Models -- Context-Aided Human Recognition - Clustering -- Robust Expression-Invariant Face Recognition from Partially Missing Data -- Segmentation and Grouping -- An Integral Solution to Surface Evolution PDEs Via Geo-cuts -- Detecting Doctored JPEG Images Via DCT Coefficient Analysis -- A Learning Based Approach for 3D Segmentation and Colon Detagging -- Fast, Quality, Segmentation of Large Volumes - Isoperimetric Distance Trees -- Segmentation of High Angular Resolution Diffusion MRI Modeled as a Field of von Mises-Fisher Mixtures -- Globally Optimal Active Contours, Sequential Monte Carlo and On-Line Learning for Vessel Segmentation -- Matching -- Optimal Multi-frame Correspondence with Assignment Tensors -- Kernel-Predictability: A New Information Measure and Its Application to Image Registration -- Algebraic Methods for Direct and Feature Based Registration of Diffusion Tensor Images -- Rethinking the Prior Model for Stereo -- Aligning Sequences and Actions by Maximizing Space-Time Correlations -- Simultaneous Nonrigid Registration of Multiple Point Sets and Atlas Construction -- Enforcing Temporal Consistency in Real-Time Stereo Estimation -- The Alignment Between 3-D Data and Articulated Shapes with Bending Surfaces -- Visual Tracking -- Feature Harvesting for Tracking-by-Detection -- Effective Appearance Model and Similarity Measure for Particle Filtering and Visual Tracking -- Tracking and Labelling of Interacting Multiple Targets -- Level-Set Curve Particles.