Computer Vision – ECCV 2010 [electronic resource] :11th European Conference on Computer Vision, Heraklion, Crete, Greece, September 5-11, 2010, Proceedings, Part V /
Contributor(s): Daniilidis, Kostas [editor.] | Maragos, Petros [editor.] | Paragios, Nikos [editor.] | SpringerLink (Online service).Material type: BookSeries: Lecture Notes in Computer Science: 6315Publisher: Berlin, Heidelberg : Springer Berlin Heidelberg, 2010.Description: XXIII, 807 p. 370 illus. online resource.Content type: text Media type: computer Carrier type: online resourceISBN: 9783642155550.Subject(s): Computer science | Algorithms | Computer graphics | Image processing | Pattern recognition | Biometrics (Biology) | Computer Science | Image Processing and Computer Vision | Pattern Recognition | Computer Imaging, Vision, Pattern Recognition and Graphics | Biometrics | Computer Graphics | Algorithm Analysis and Problem ComplexityOnline resources: Click here to access online
Spotlights and Posters W2 -- Towards Computational Models of the Visual Aesthetic Appeal of Consumer Videos -- Object Recognition Using Junctions -- Using Partial Edge Contour Matches for Efficient Object Category Localization -- Active Mask Hierarchies for Object Detection -- From a Set of Shapes to Object Discovery -- What Does Classifying More Than 10,000 Image Categories Tell Us? -- Modeling and Analysis of Dynamic Behaviors of Web Image Collections -- Non-local Characterization of Scenery Images: Statistics, 3D Reasoning, and a Generative Model -- Efficient Highly Over-Complete Sparse Coding Using a Mixture Model -- Attribute-Based Transfer Learning for Object Categorization with Zero/One Training Example -- Image Classification Using Super-Vector Coding of Local Image Descriptors -- A Discriminative Latent Model of Object Classes and Attributes -- Seeing People in Social Context: Recognizing People and Social Relationships -- Discovering Multipart Appearance Models from Captioned Images -- Voting by Grouping Dependent Parts -- Superpixels and Supervoxels in an Energy Optimization Framework -- Segmentation -- Convex Relaxation for Multilabel Problems with Product Label Spaces -- Graph Cut Based Inference with Co-occurrence Statistics -- Ambrosio-Tortorelli Segmentation of Stochastic Images -- Multiple Hypothesis Video Segmentation from Superpixel Flows -- Object Segmentation by Long Term Analysis of Point Trajectories -- Spotlights and Posters R1 -- Exploiting Repetitive Object Patterns for Model Compression and Completion -- Feature Tracking for Wide-Baseline Image Retrieval -- Crowd Detection with a Multiview Sampler -- A Unified Contour-Pixel Model for Figure-Ground Segmentation -- SuperParsing: Scalable Nonparametric Image Parsing with Superpixels -- Segmenting Salient Objects from Images and Videos -- ClassCut for Unsupervised Class Segmentation -- A Dynamic Programming Approach to Reconstructing Building Interiors -- Discriminative Mixture-of-Templates for Viewpoint Classification -- Efficient Non-consecutive Feature Tracking for Structure-from-Motion -- P2?: A Minimal Solution for Registration of 3D Points to 3D Planes -- Boosting Chamfer Matching by Learning Chamfer Distance Normalization -- Geometry Construction from Caustic Images -- Archive Film Restoration Based on Spatiotemporal Random Walks -- Reweighted Random Walks for Graph Matching -- Rotation Invariant Non-rigid Shape Matching in Cluttered Scenes -- Loosely Distinctive Features for Robust Surface Alignment -- Accelerated Hypothesis Generation for Multi-structure Robust Fitting -- Aligning Spatio-Temporal Signals on a Special Manifold -- Supervised Label Transfer for Semantic Segmentation of Street Scenes -- Category Independent Object Proposals -- Photo-Consistent Planar Patches from Unstructured Cloud of Points -- Contour Grouping and Abstraction Using Simple Part Models -- Dynamic Color Flow: A Motion-Adaptive Color Model for Object Segmentation in Video -- What Is the Chance of Happening: A New Way to Predict Where People Look -- Supervised and Unsupervised Clustering with Probabilistic Shift -- Depth-Encoded Hough Voting for Joint Object Detection and Shape Recovery -- Shape Analysis of Planar Objects with Arbitrary Topologies Using Conformal Geometry -- A Coarse-to-Fine Taxonomy of Constellations for Fast Multi-class Object Detection -- Object Classification Using Heterogeneous Co-occurrence Features -- Converting Level Set Gradients to Shape Gradients -- A Close-Form Iterative Algorithm for Depth Inferring from a Single Image -- Learning Shape Segmentation Using Constrained Spectral Clustering and Probabilistic Label Transfer -- Weakly Supervised Shape Based Object Detection with Particle Filter -- Geodesic Shape Retrieval via Optimal Mass Transport -- Spotlights and Posters R2 -- Image Segmentation with Topic Random Field.
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.