Computer Vision - ECCV 2000 [electronic resource] : 6th European Conference on Computer Vision Dublin, Ireland, June 26 - July 1, 2000 Proceedings, Part I /

Recognition & Modelling I -- Non-linear Bayesian Image Modelling -- Unsupervised Learning of Models for Recognition -- Learning over Multiple Temporal Scales in Image Databases -- Colour Image Retrieval and Object Recognition Using the Multimodal Neighbourhood Signature -- Stereoscopic Vision -- Approximate N-View Stereo -- A Minimal Set of Constraints for the Trifocal Tensor -- Intrinsic Images for Dense Stereo Matching with Occlusions -- Recognition & Modelling / Stereoscopic Vision / Texture, Shading, & Colour -- Local Scale Selection for Gaussian Based Description Techniques -- Anti-Faces for Detection -- Combining Elastic and Statistical Models of Appearance Variation -- Object Recognition Using Coloured Receptive Fields -- Learning Similarity for Texture Image Retrieval -- Parametric View-Synthesis -- Least Committment Graph Matching by Evolutionary Optimisation -- Predicting Disparity Windows for Real-Time Stereo -- On the Estimation of the Fundamental Matrix: A Convex Approach to Constrained Least-Squares -- Velocity-Guided Tracking of Deformable Contours in Three Dimensional Space -- Model Based Pose Estimator Using Linear-Programming -- Measuring the Self-Consistency of Stereo Algorithms -- Log-Polar Stereo for Anthropomorphic Robots -- Contour-Based Correspondence for Stereo -- Color and Scale: The Spatial Structure of Color Images -- Constrained Dichromatic Colour Constancy -- Objective Colour from Multispectral Imaging -- Colour by Correlation in a Three-Dimensional Colour Space -- Improvements to Gamut Mapping Colour Constancy Algorithms -- Gray Scale and Rotation Invariant Texture Classification with Local Binary Patterns -- Adapting Spectral Scale for Shape from Texture -- Recognition & Modelling II -- Learning to Recognize 3D Objects with SNoW -- Region-Based Object Recognition Using Shape-from-Shading -- Recognizing Walking People -- A Probabilistic Sensor for the Perception and the Recognition of Activities -- Structure from Motion I -- Homography Tensors: On Algebraic Entities ThatRepresent Three Views of Static or Moving Planar Points -- Plane + Parallax, Tensors and Factorization -- Factorization with Uncertainty -- Estimating the Jacobian of the Singular Value Decomposition: Theory and Applications -- Shape -- Diffeomorphic Matching Problems in One Dimension: Designing and Minimizing Matching Functionals -- Level Sets and Distance Functions -- Divergence-Based Medial Surfaces -- Structure from Motion / Shape / Image Features -- 3D Reconstruction from Tangent-of-Sight Measurements of a Moving Object Seen from a Moving Camera -- A Six Point Solution for Structure and Motion -- Reconstruction from Uncalibrated Sequences with a Hierarchy of Trifocal Tensors -- Characterizing Depth Distortion Due to Calibration Uncertainty -- On Calibration and Reconstruction from Planar Curves -- How Does CONDENSATION Behave with a Finite Number of Samples? -- On the Structure and Properties of the Quadrifocal Tensor -- Geotensity Constraint for 3D Surface Reconstruction under Multiple Light Sources -- Noise-Resistant Affine Skeletons of Planar Curves -- Shape and Radiance Estimation from the Information Divergence of Blurred Images -- Surface Matching with Large Deformations and Arbitrary Topology: A Geodesic Distance Evolution Scheme on a 3-Manifold -- Duals, Invariants, and the Recognition of Smooth Objects from Their Occluding Contour -- On Utilising Template and Feature-based Correspondence in Multi-view Appearance Models -- Wide Baseline Point Matching Using Affine Invariants Computed from Intensity Profiles -- Determining Correspondences for Statistical Models of Appearance -- Approximation and Processing of Intensity Images with Discontinuity-Preserving Adaptive Triangular Meshes -- Scale Dependent Differential Geometry for the Measurement of Center Line and Diameter in 3D Curvilinear Structures -- Fast Selective Detection of Rotational Symmetries Using Normalized Inhibition -- Structure from Motion II -- Multibody Structure and Motion: 3-D Reconstruction of Independently MovingObjects -- Integrating Local Affine into Global Projective Images in the Joint Image Space -- Ambiguous Configurations for 3-View Projective Reconstruction -- On the Reprojection of 3D and 2D Scenes without Explicit Model Selection.

Ten years ago, the inaugural European Conference on Computer Vision was held in Antibes, France. Since then, ECCV has been held biennially under the auspices of the European Vision Society at venues around Europe. This year, the privilege of organizing ECCV 2000 falls to Ireland and it is a signal honour for us to host what has become one of the most important events in the calendar of the computer vision community. ECCV is a single-track conference comprising the highest quality, previously unpublished, contributed papers on new and original research in computer vision. This year, 266 papers were submitted and, following a rigorous double-blind review process, with each paper being reviewed by three referees, 116 papers were selected by the Programme Committee for presentation at the conference. The venue for ECCV 2000 is the University of Dublin, Trinity College. - unded in 1592, it is Ireland’s oldest university and has a proud tradition of scholarship in the Arts, Humanities, and Sciences, alike. The Trinity campus, set in the heart of Dublin, is an oasis of tranquility and its beautiful squares, elegant buildings, and tree-lined playing- elds provide the perfect setting for any conference.