Computer Vision -- ECCV 2006: 9th European Conference on Computer Vision, Graz, Austria, May 7-13, 2006, Proceedings, Part II(3952 Lecture Notes in Computer Science)

These are the proceedings of the 9th European Conference on Computer Vision (ECCV 2006), the premium European conference on computer vision, held in Graz, Austria, in May 2006. Inresponsetoourconferencecall,wereceived811papers,thelargestnumber of submissions so far. Finally, 41 papers were selected for podium presentation and 151 for presentation in poster sessions (a 23. 67% acceptance rate). The double-blind reviewing process started by assigning each paper to one of the 22 area chairs, who then selected 3 reviewers for each paper. After the reviewswerereceived,theauthorswereo?eredthepossibilitytoprovidefeedback on the reviews. On the basis of the reviews and the rebuttal of the authors, the area chairs wrote the initial consolidation report for each paper. Finally, all the area chairs attended a two-day meeting in Graz, where all decisions on acceptance/rejectionweremade. At that meeting,the areachairsresponsiblefor similar sub-?elds thoroughly evaluated the assigned papers and discussed them in great depth. Again, all decisions were reached without the knowledge of the authors' identity. We are fully aware of the fact that reviewing is always also subjective, and that somegood papers might havebeen overlooked;however,we tried our best to apply a fair selection process. The conference preparation went smoothly thanks to several people. We ?rst wish to thank the ECCV Steering Committee for entrusting us with the orga- zationoftheconference. Wearegratefultotheareachairs,whodidatremendous job in selecting the papers, and to more than 340 ProgramCommittee members and 220 additional reviewers for all their professional e?orts.

Table of Contents:
Energy Minimization.- Comparison of Energy Minimization Algorithms for Highly Connected Graphs.- A Comparative Study of Energy Minimization Methods for Markov Random Fields.- Measuring Uncertainty in Graph Cut Solutions – Efficiently Computing Min-marginal Energies Using Dynamic Graph Cuts.- Tracking and Motion.- Tracking Dynamic Near-Regular Texture Under Occlusion and Rapid Movements.- Simultaneous Object Pose and Velocity Computation Using a Single View from a Rolling Shutter Camera.- A Theory of Multiple Orientation Estimation.- Poster Session II.- Resolution-Aware Fitting of Active Appearance Models to Low Resolution Images.- High Accuracy Optical Flow Serves 3-D Pose Tracking: Exploiting Contour and Flow Based Constraints.- Enhancing the Point Feature Tracker by Adaptive Modelling of the Feature Support.- Tracking Objects Across Cameras by Incrementally Learning Inter-camera Colour Calibration and Patterns of Activity.- Monocular Tracking of 3D Human Motion with a Coordinated Mixture of Factor Analyzers.- Multiview Geometry and 3D Reconstruction.- Balanced Exploration and Exploitation Model Search for Efficient Epipolar Geometry Estimation.- Shape-from-Silhouette with Two Mirrors and an Uncalibrated Camera.- Robust and Efficient Photo-Consistency Estimation for Volumetric 3D Reconstruction.- An Affine Invariant of Parallelograms and Its Application to Camera Calibration and 3D Reconstruction.- Nonrigid Shape and Motion from Multiple Perspective Views.- 3D Surface Reconstruction Using Graph Cuts with Surface Constraints.- Statistical Models and Visual Learning.- Trace Quotient Problems Revisited.- Learning Nonlinear Manifolds from Time Series.- Accelerated Convergence Using Dynamic Mean Shift.- Efficient Belief Propagation with Learned Higher-Order Markov Random Fields.- Non Linear Temporal Textures Synthesis: A Monte Carlo Approach.- Low-Level Vision, Image Features.- Curvature-Preserving Regularization of Multi-valued Images Using PDE’s.- Higher Order Image Pyramids.- Image Specific Feature Similarities.- Coloring Local Feature Extraction.- Defocus Inpainting.- Viewpoint Induced Deformation Statistics and the Design of Viewpoint Invariant Features: Singularities and Occlusions.- Face/Gesture/Action Detection and Recognition.- Spatio-temporal Embedding for Statistical Face Recognition from Video.- Super-Resolution of 3D Face.- Estimating Gaze Direction from Low-Resolution Faces in Video.- Learning Effective Intrinsic Features to Boost 3D-Based Face Recognition.- Human Detection Using Oriented Histograms of Flow and Appearance.- Cyclostationary Processes on Shape Spaces for Gait-Based Recognition.- Segmentation and Grouping.- Multiclass Image Labeling with Semidefinite Programming.- Automatic Image Segmentation by Positioning a Seed.- Patch-Based Texture Edges and Segmentation.- Unsupervised Texture Segmentation with Nonparametric Neighborhood Statistics.- Detecting Symmetry and Symmetric Constellations of Features.- Discovering Texture Regularity as a Higher-Order Correspondence Problem.- Object Recognition, Retrieval and Indexing.- Exploiting Model Similarity for Indexing and Matching to a Large Model Database.- Shift-Invariant Dynamic Texture Recognition.- Modeling 3D Objects from Stereo Views and Recognizing Them in Photographs.- A Boundary-Fragment-Model for Object Detection.- Region Covariance: A Fast Descriptor for Detection and Classification.- Segmentation.- Affine-Invariant Multi-reference Shape Priors for Active Contours.- Figure/Ground Assignment in Natural Images.- Background Cut.- PoseCut: Simultaneous Segmentation and 3D Pose Estimation of Humans Using Dynamic Graph-Cuts.