Computer Vision -- ECCV 2010: 11th European Conference on Computer Vision, Heraklion, Crete, Greece, September 5-11, 2010, Proceedings, Part VI (Lecture Notes in Computer Science, 6316)

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. Front Matter....Pages - Learning a Fine Vocabulary....Pages 1-14 Video Synchronization Using Temporal Signals from Epipolar Lines....Pages 15-28 The Generalized PatchMatch Correspondence Algorithm....Pages 29-43 Automated 3D Reconstruction and Segmentation from Optical Coherence Tomography....Pages 44-57 Combining Geometric and Appearance Priors for Robust Homography Estimation....Pages 58-72 Real-Time Spherical Mosaicing Using Whole Image Alignment....Pages 73-86 Adaptive Metric Registration of 3D Models to Non-rigid Image Trajectories....Pages 87-100 Local Occlusion Detection under Deformations Using Topological Invariants....Pages 101-114 2.5D Dual Contouring: A Robust Approach to Creating Building Models from Aerial LiDAR Point Clouds....Pages 115-128 Analytical Forward Projection for Axial Non-central Dioptric and Catadioptric Cameras....Pages 129-143 5D Motion Subspaces for Planar Motions....Pages 144-157 3D Reconstruction of a Moving Point from a Series of 2D Projections....Pages 158-171 Manifold Learning for Object Tracking with Multiple Motion Dynamics....Pages 172-185 Detection and Tracking of Large Number of Targets in Wide Area Surveillance....Pages 186-199 Discriminative Tracking by Metric Learning....Pages 200-214 Memory-Based Particle Filter for Tracking Objects with Large Variation in Pose and Appearance....Pages 215-228 3D Deformable Face Tracking with a Commodity Depth Camera....Pages 229-242 Human Attributes from 3D Pose Tracking....Pages 243-257 Discriminative Nonorthogonal Binary Subspace Tracking....Pages 258-271 TriangleFlow: Optical Flow with Triangulation-Based Higher-Order Likelihoods....Pages 272-285 Articulation-Invariant Representation of Non-planar Shapes....Pages 286-299 Inferring 3D Shapes and Deformations from Single Views....Pages 300-313 Efficient Inference with Multiple Heterogeneous Part Detectors for Human Pose Estimation....Pages 314-327 Co-transduction for Shape Retrieval....Pages 328-341 Learning Shape Detector by Quantizing Curve Segments with Multiple Distance Metrics....Pages 342-355 Unique Signatures of Histograms for Local Surface Description....Pages 356-369 Exploring Ambiguities for Monocular Non-rigid Shape Estimation....Pages 370-383 Efficient Computation of Scale-Space Features for Deformable Shape Correspondences....Pages 384-397 Intrinsic Regularity Detection in 3D Geometry....Pages 398-410 Balancing Deformability and Discriminability for Shape Matching....Pages 411-424 2D Action Recognition Serves 3D Human Pose Estimation....Pages 425-438 A Streakline Representation of Flow in Crowded Scenes....Pages 439-452 Fast Multi-aspect 2D Human Detection....Pages 453-466 Deterministic 3D Human Pose Estimation Using Rigid Structure....Pages 467-480 Robust Fusion: Extreme Value Theory for Recognition Score Normalization....Pages 481-495 Recognizing Partially Occluded Faces from a Single Sample Per Class Using String-Based Matching....Pages 496-509 Real-Time Spatiotemporal Stereo Matching Using the Dual-Cross-Bilateral Grid....Pages 510-523 Fast Multi-labelling for Stereo Matching....Pages 524-537 Anisotropic Minimal Surfaces Integrating Photoconsistency and Normal Information for Multiview Stereo....Pages 538-551 An Efficient Graph Cut Algorithm for Computer Vision Problems....Pages 552-565 Non-Local Kernel Regression for Image and Video Restoration....Pages 566-579 A Spherical Harmonics Shape Model for Level Set Segmentation....Pages 580-593 A Model of Volumetric Shape for the Analysis of Longitudinal Alzheimer’s Disease Data....Pages 594-606 Fast Optimization for Mixture Prior Models....Pages 607-620 3D Point Correspondence by Minimum Description Length in Feature Space....Pages 621-634 Making Action Recognition Robust to Occlusions and Viewpoint Changes....Pages 635-648 Structured Output Ordinal Regression for Dynamic Facial Emotion Intensity Prediction....Pages 649-662 Critical Nets and Beta-Stable Features for Image Matching....Pages 663-676 Descriptor Learning for Efficient Retrieval....Pages 677-691 Texture Regimes for Entropy-Based Multiscale Image Analysis....Pages 692-705 A High-Quality Video Denoising Algorithm Based on Reliable Motion Estimation....Pages 706-719 An Oriented Flux Symmetry Based Active Contour Model for Three Dimensional Vessel Segmentation....Pages 720-734 MRF Inference by k -Fan Decomposition and Tight Lagrangian Relaxation....Pages 735-747 Randomized Locality Sensitive Vocabularies for Bag-of-Features Model....Pages 748-761 Image Categorization Using Directed Graphs....Pages 762-775 Robust Multi-View Boosting with Priors....Pages 776-789 Optimum Subspace Learning and Error Correction for Tensors....Pages 790-803 Back Matter....Pages - Annotation The six-volume set comprising LNCS volumes 6311 until 6313 constitutes the refereed proceedings of the 11th European Conference on Computer Vision, ECCV 2010, held in Heraklion, Crete, Greece, in September 2010. The 325 revised papers presented were carefully reviewed and selected from 1174 submissions. The papers are organized in topical sections on object and scene recognition; segmentation and grouping; face, gesture, biometrics; motion and tracking; statistical models and visual learning; matching, registration, alignment; computational imaging; multi-view geometry; image features; video and event characterization; shape representation and recognition; stereo; reflectance, illumination, color; medical image analysis The six-volume set comprising LNCS volumes 6311 -- 6316 constitutes the refereed proceedings of the 11th European Conference on Computer Vision, ECCV 2010, held in Heraklion, Crete, Greece, in September 2010. The 325 revised papers presented were carefully reviewed and selected from 1174 submissions. The papers are organized in topical sections on object and scene recognition; segmentation and grouping; face, gesture, biometrics; motion and tracking; statistical models and visual learning; matching, registration, alignment; computational imaging; mutli-view geometry; image features; video and event characterization; shape representation and recognition; stereo; reflectance, illumination, color; medical image analysis