Computer Vision -- ECCV 2010

The 2010 edition of the European Conference on Computer Vision was held in Heraklion, Crete. The call for papers attracted an absolute record of 1,174 submissions. We describe here the selection of the accepted papers: Thirty-eight area chairs were selected coming from Europe (18), USA and Canada (16), and Asia (4). Their selection was based on the following criteria: (1) Researchers who had served at least two times as Area Chairs within the past two years at major vision conferences were excluded; (2) Researchers who served as Area Chairs at the 2010 Computer Vision and Pattern Recognition were also excluded (exception: ECCV 2012 Program Chairs); (3) Minimization of overlap introduced by Area Chairs being former student and advisors; (4) 20% of the Area Chairs had never served before in a major conference; (5) The Area Chair selection process made all possible efforts to achieve a reasonable geographic distribution between countries, thematic areas and trends in computer vision. Each Area Chair was assigned by the Program Chairs between 28–32 papers. Based on paper content, the Area Chair recommended up to seven potential reviewers per paper. Such assignment was made using all reviewers in the database including the conflicting ones. The Program Chairs manually entered the missing conflict domains of approximately 300 reviewers. Based on the recommendation of the Area Chairs, three reviewers were selected per paper (with at least one being of the top three suggestions), with 99.

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.