Face Detection and Recognition -- Robust Multi-view Face Detection Using Error Correcting Output Codes -- Inter-modality Face Recognition -- Face Recognition from Video Using the Generic Shape-Illumination Manifold -- Illumination and Reflectance Modelling -- A Theory of Spherical Harmonic Identities for BRDF/Lighting Transfer and Image Consistency -- Covariant Derivatives and Vision -- Retexturing Single Views Using Texture and Shading -- Poster Session IV Tracking and Motion -- Feature Points Tracking: Robustness to Specular Highlights and Lighting Changes -- A General Framework for Motion Segmentation: Independent, Articulated, Rigid, Non-rigid, Degenerate and Non-degenerate -- Robust Visual Tracking for Multiple Targets -- Multivalued Default Logic for Identity Maintenance in Visual Surveillance -- A Multiview Approach to Tracking People in Crowded Scenes Using a Planar Homography Constraint -- Multiview Geometry and 3D Methods -- Uncalibrated Factorization Using a Variable Symmetric Affine Camera -- Dense Photometric Stereo by Expectation Maximization -- Space-Time-Scale Registration of Dynamic Scene Reconstructions -- Self-calibration of a General Radially Symmetric Distortion Model -- A Simple Solution to the Six-Point Two-View Focal-Length Problem -- Iterative Extensions of the Sturm/Triggs Algorithm: Convergence and Nonconvergence -- Low-Level Vision, Image Features -- An Efficient Method for Tensor Voting Using Steerable Filters -- Interpolating Orientation Fields: An Axiomatic Approach -- Alias-Free Interpolation -- An Intensity Similarity Measure in Low-Light Conditions -- Direct Energy Minimization for Super-Resolution on Nonlinear Manifolds -- Wavelet-Based Super-Resolution Reconstruction: Theory and Algorithm -- Face/Gesture/Action Detection and Recognition -- Extending Kernel Fisher Discriminant Analysis with the Weighted Pairwise Chernoff Criterion -- Face Authentication Using Adapted Local Binary Pattern Histograms -- An Integrated Model for Accurate Shape Alignment -- Robust Player Gesture Spotting and Recognition in Low-Resolution Sports Video -- Recognition and Segmentation of 3-D Human Action Using HMM and Multi-class AdaBoost -- Segmenting Highly Articulated Video Objects with Weak-Prior Random Forests -- Segmentation and Grouping -- SpatialBoost: Adding Spatial Reasoning to AdaBoost -- Database-Guided Simultaneous Multi-slice 3D Segmentation for Volumetric Data -- Density Estimation Using Mixtures of Mixtures of Gaussians -- Example Based Non-rigid Shape Detection -- Towards Safer, Faster Prenatal Genetic Tests: Novel Unsupervised, Automatic and Robust Methods of Segmentation of Nuclei and Probes -- Object Recognition, Retrieval and Indexing -- Fast Memory-Efficient Generalized Belief Propagation -- Adapted Vocabularies for Generic Visual Categorization -- Identification of Highly Similar 3D Objects Using Model Saliency -- Sampling Strategies for Bag-of-Features Image Classification -- Maximally Stable Local Description for Scale Selection -- Scene Classification Via pLSA -- Probabilistic Linear Discriminant Analysis -- A New 3-D Model Retrieval System Based on Aspect-Transition Descriptor -- Low-Level Vision, Segmentation and Grouping -- Unsupervised Patch-Based Image Regularization and Representation -- A Fast Approximation of the Bilateral Filter Using a Signal Processing Approach -- Learning to Combine Bottom-Up and Top-Down Segmentation -- Multi-way Clustering Using Super-Symmetric Non-negative Tensor Factorization.