Computer Vision -- ECCV 2010

Spotlights and Posters T1.- Learning a Fine Vocabulary.- Video Synchronization Using Temporal Signals from Epipolar Lines.- The Generalized PatchMatch Correspondence Algorithm.- Automated 3D Reconstruction and Segmentation from Optical Coherence Tomography.- Combining Geometric and Appearance Priors for Robust Homography Estimation.- Real-Time Spherical Mosaicing Using Whole Image Alignment.- Geometry.- Adaptive Metric Registration of 3D Models to Non-rigid Image Trajectories.- Local Occlusion Detection under Deformations Using Topological Invariants.- 2.5D Dual Contouring: A Robust Approach to Creating Building Models from Aerial LiDAR Point Clouds.- Analytical Forward Projection for Axial Non-central Dioptric and Catadioptric Cameras.- 5D Motion Subspaces for Planar Motions.- 3D Reconstruction of a Moving Point from a Series of 2D Projections.- Spotlights and Posters T2.- Manifold Learning for Object Tracking with Multiple Motion Dynamics.- Detection and Tracking of Large Number of Targets in Wide Area Surveillance.- Discriminative Tracking by Metric Learning.- Memory-Based Particle Filter for Tracking Objects with Large Variation in Pose and Appearance.- 3D Deformable Face Tracking with a Commodity Depth Camera.- Human Attributes from 3D Pose Tracking.- Discriminative Nonorthogonal Binary Subspace Tracking.- TriangleFlow: Optical Flow with Triangulation-Based Higher-Order Likelihoods.- Articulation-Invariant Representation of Non-planar Shapes.- Inferring 3D Shapes and Deformations from Single Views.- Efficient Inference with Multiple Heterogeneous Part Detectors for Human Pose Estimation.- Co-transduction for Shape Retrieval.- Learning Shape Detector by Quantizing Curve Segments with Multiple Distance Metrics.- Unique Signatures of Histograms for Local Surface Description.- Exploring Ambiguities for Monocular Non-rigid Shape Estimation.- Efficient Computation of Scale-Space Features for Deformable Shape Correspondences.- Intrinsic Regularity Detection in 3D Geometry.- Balancing Deformability and Discriminability for Shape Matching.- 2D Action Recognition Serves 3D Human Pose Estimation.- A Streakline Representation of Flow in Crowded Scenes.- Fast Multi-aspect 2D Human Detection.- Deterministic 3D Human Pose Estimation Using Rigid Structure.- Robust Fusion: Extreme Value Theory for Recognition Score Normalization.- Recognizing Partially Occluded Faces from a Single Sample Per Class Using String-Based Matching.- Real-Time Spatiotemporal Stereo Matching Using the Dual-Cross-Bilateral Grid.- Fast Multi-labelling for Stereo Matching.- Anisotropic Minimal Surfaces Integrating Photoconsistency and Normal Information for Multiview Stereo.- An Efficient Graph Cut Algorithm for Computer Vision Problems.- Non-Local Kernel Regression for Image and Video Restoration.- A Spherical Harmonics Shape Model for Level Set Segmentation.- A Model of Volumetric Shape for the Analysis of Longitudinal Alzheimer's Disease Data.- Fast Optimization for Mixture Prior Models.- 3D Point Correspondence by Minimum Description Length in Feature Space.- Making Action Recognition Robust to Occlusions and Viewpoint Changes.- Structured Output Ordinal Regression for Dynamic Facial Emotion Intensity Prediction.- Image Features and Motion.- Critical Nets and Beta-Stable Features for Image Matching.- Descriptor Learning for Efficient Retrieval.- Texture Regimes for Entropy-Based Multiscale Image Analysis.- A High-Quality Video Denoising Algorithm Based on Reliable Motion Estimation.- An Oriented Flux Symmetry Based Active Contour Model for Three Dimensional Vessel Segmentation.- Spotlights and Posters W1.- MRF Inference by k-Fan Decomposition and Tight Lagrangian Relaxation.- Randomized Locality Sensitive Vocabularies for Bag-of-Features Model.- Image Categorization Using Directed Graphs.- Robust Multi-View Boosting with Priors.- Optimum Subspace Learning and Error Correction for Tensors.