Computer Vision - ECCV 2008

People.- Floor Fields for Tracking in High Density Crowd Scenes.- The Naked Truth: Estimating Body Shape Under Clothing.- Temporal Surface Tracking Using Mesh Evolution.- Faces.- Grassmann Registration Manifolds for Face Recognition.- Facial Expression Recognition Based on 3D Dynamic Range Model Sequences.- Face Alignment Via Component-Based Discriminative Search.- Improving People Search Using Query Expansions.- Poster Session II.- Fast Automatic Single-View 3-d Reconstruction of Urban Scenes.- Fourier Analysis of the 2D Screened Poisson Equation for Gradient Domain Problems.- Anisotropic Geodesics for Perceptual Grouping and Domain Meshing.- Regularized Partial Matching of Rigid Shapes.- Compressive Sensing for Background Subtraction.- Robust 3D Pose Estimation and Efficient 2D Region-Based Segmentation from a 3D Shape Prior.- Linear Time Maximally Stable Extremal Regions.- Efficient Edge-Based Methods for Estimating Manhattan Frames in Urban Imagery.- Multiple Component Learning forObject Detection.- A Probabilistic Approach to Integrating Multiple Cues in Visual Tracking.- Fast and Accurate Rotation Estimation on the 2-Sphere without Correspondences.- A Lattice-Preserving Multigrid Method for Solving the Inhomogeneous Poisson Equations Used in Image Analysis.- SMD: A Locally Stable Monotonic Change Invariant Feature Descriptor.- Finding Actions Using Shape Flows.- Cross-View Action Recognition from Temporal Self-similarities.- Window Annealing over Square Lattice Markov Random Field.- Unsupervised Classification and Part Localization by Consistency Amplification.- Simultaneous Visual Recognition of Manipulation Actions and Manipulated Objects.- Active Contour Based Segmentation of 3D Surfaces.- What Is a Good Nearest Neighbors Algorithm for Finding Similar Patches in Images?.- Learning for Optical Flow Using Stochastic Optimization.- Region-Based 2D Deformable Generalized Cylinder for Narrow Structures Segmentation.- Pose Priors for Simultaneously Solving Alignment and Correspondence.- Latent Pose Estimator for Continuous Action Recognition.- Relevant Feature Selection for Human Pose Estimation and Localization in Cluttered Images.- Determining Patch Saliency Using Low-Level Context.- Edge-Preserving Smoothing and Mean-Shift Segmentation of Video Streams.- Deformed Lattice Discovery Via Efficient Mean-Shift Belief Propagation.- Local Statistic Based Region Segmentation with Automatic Scale Selection.- A Comparative Analysis of RANSAC Techniques Leading to Adaptive Real-Time Random Sample Consensus.- Video Registration Using Dynamic Textures.- Hierarchical Support Vector Random Fields: Joint Training to Combine Local and Global Features.- Scene Segmentation Using the Wisdom of Crowds.- Optimization of Symmetric Transfer Error for Sub-frame Video Synchronization.- Shape-Based Retrieval of Heart Sounds for Disease Similarity Detection.- Learning CRFs Using Graph Cuts.- Feature Correspondence Via Graph Matching: Models and Global Optimization.-Event Modeling and Recognition Using Markov Logic Networks.- Illumination and Person-Insensitive Head Pose Estimation Using Distance Metric Learning.- 2D Image Analysis by Generalized Hilbert Transforms in Conformal Space.- An Efficient Dense and Scale-Invariant Spatio-Temporal Interest Point Detector.- A Graph Based Subspace Semi-supervised Learning Framework for Dimensionality Reduction.- Online Tracking and Reacquisition Using Co-trained Generative and Discriminative Trackers.- Statistical Analysis of Global Motion Chains.- Active Image Labeling and Its Application to Facial Action Labeling.- Real Time Feature Based 3-D Deformable Face Tracking.- Rank Classification of Linear Line Structure in Determining Trifocal Tensor.- Learning Visual Shape Lexicon for Document Image Content Recognition.- Unsupervised Structure Learning: Hierarchical Recursive Composition, Suspicious Coincidence and Competitive Exclusion.- Contour Context Selection for Object Detection: A Set-to-Set Contour Matching Approach.- Tracking.- Robust Object Tracking by Hierarchical Association of Detection Responses.- Improving the Agility of Keyframe-Based SLAM.- Articulated Multi-body Tracking under Egomotion.- Robust Real-Time Visual Tracking Using Pixel-Wise Posteriors.