Computer Vision – ECCV 2012: 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, Proceedings, Part I

Description

The seven-volume set comprising LNCS volumes 7572-7578 constitutes the refereed proceedings of the 12th European Conference on Computer Vision, ECCV 2012, held in Florence, Italy, in October 2012. The 408 revised papers presented were carefully reviewed and selected from 1437 submissions. The papers are organized in topical sections on geometry, 2D and 3D shape, 3D reconstruction, visual recognition and classification, visual features and image matching, visual monitoring: action and activities, models, optimisation, learning, visual tracking and image registration, photometry: lighting and colour, and image segmentation. Front Matter....Pages - Lie Bodies: A Manifold Representation of 3D Human Shape....Pages 1-14 Worldwide Pose Estimation Using 3D Point Clouds....Pages 15-29 Improved Reconstruction of Deforming Surfaces by Cancelling Ambient Occlusion....Pages 30-43 On the Statistical Determination of Optimal Camera Configurations in Large Scale Surveillance Networks....Pages 44-57 The Scale of Geometric Texture....Pages 58-71 Efficient Articulated Trajectory Reconstruction Using Dynamic Programming and Filters....Pages 72-85 Object Co-detection....Pages 86-101 Morphable Displacement Field Based Image Matching for Face Recognition across Pose....Pages 102-115 Combining Per-frame and Per-track Cues for Multi-person Action Recognition....Pages 116-129 Joint Image and Word Sense Discrimination for Image Retrieval....Pages 130-143 Script Data for Attribute-Based Recognition of Composite Activities....Pages 144-157 Undoing the Damage of Dataset Bias....Pages 158-171 Dog Breed Classification Using Part Localization....Pages 172-185 A Dictionary Learning Approach for Classification: Separating the Particularity and the Commonality....Pages 186-199 Learning to Efficiently Detect Repeatable Interest Points in Depth Data....Pages 200-213 Effective Use of Frequent Itemset Mining for Image Classification....Pages 214-227 Efficient Discriminative Projections for Compact Binary Descriptors....Pages 228-242 Descriptor Learning Using Convex Optimisation....Pages 243-256 Bottom-Up Perceptual Organization of Images into Object Part Hypotheses....Pages 257-271 Match Graph Construction for Large Image Databases....Pages 272-285 Modeling Complex Temporal Composition of Actionlets for Activity Prediction....Pages 286-299 Learning Human Interaction by Interactive Phrases....Pages 300-313 Learning to Recognize Daily Actions Using Gaze....Pages 314-327 Gait Recognition by Ranking....Pages 328-341 Semi-intrinsic Mean Shift on Riemannian Manifolds....Pages 342-355 Efficient Nonlocal Regularization for Optical Flow....Pages 356-369 Fast Fusion Moves for Multi-model Estimation....Pages 370-384 Approximate MRF Inference Using Bounded Treewidth Subgraphs....Pages 385-398 Recursive Bilateral Filtering....Pages 399-413 Accelerated Large Scale Optimization by Concomitant Hashing....Pages 414-427 Graph Degree Linkage: Agglomerative Clustering on a Directed Graph....Pages 428-441 Supervised Earth Mover’s Distance Learning and Its Computer Vision Applications....Pages 442-455 Global Optimization of Object Pose and Motion from a Single Rolling Shutter Image with Automatic 2D-3D Matching....Pages 456-469 Online Learning of Linear Predictors for Real-Time Tracking....Pages 470-483 Online Learned Discriminative Part-Based Appearance Models for Multi-human Tracking....Pages 484-498 Exposure Stacks of Live Scenes with Hand-Held Cameras....Pages 499-512 Dual-Force Metric Learning for Robust Distracter-Resistant Tracker....Pages 513-527 Shape and Reflectance from Natural Illumination....Pages 528-541 Frequency Analysis of Transient Light Transport with Applications in Bare Sensor Imaging....Pages 542-555 Nonuniform Lattice Regression for Modeling the Camera Imaging Pipeline....Pages 556-568 Context-Based Automatic Local Image Enhancement....Pages 569-582 Segmentation with Non-linear Regional Constraints via Line-Search Cuts....Pages 583-597 Hausdorff Distance Constraint for Multi-surface Segmentation....Pages 598-611 Background Subtraction Using Low Rank and Group Sparsity Constraints....Pages 612-625 Free Hand-Drawn Sketch Segmentation....Pages 626-639 Auto-Grouped Sparse Representation for Visual Analysis....Pages 640-653 A QCQP Approach to Triangulation....Pages 654-667 Reconstructing the World’s Museums....Pages 668-681 Background Inpainting for Videos with Dynamic Objects and a Free-Moving Camera....Pages 682-695 Optimal Templates for Nonrigid Surface Reconstruction....Pages 696-709 Learning Domain Knowledge for Façade Labelling....Pages 710-723 Simultaneous Shape and Pose Adaption of Articulated Models Using Linear Optimization....Pages 724-737 Robust Fitting for Multiple View Geometry....Pages 738-751 Improving Image-Based Localization by Active Correspondence Search....Pages 752-765 From Meaningful Contours to Discriminative Object Shape....Pages 766-779 A Particle Filter Framework for Contour Detection....Pages 780-793 TriCoS: A Tri-level Class-Discriminative Co-segmentation Method for Image Classification....Pages 794-807 Multi-view Discriminant Analysis....Pages 808-821 Multi-scale Patch Based Collaborative Representation for Face Recognition with Margin Distribution Optimization....Pages 822-835 Object Detection Using Strongly-Supervised Deformable Part Models....Pages 836-849 Efficient Misalignment-Robust Representation for Real-Time Face Recognition....Pages 850-863 Monocular Object Detection Using 3D Geometric Primitives....Pages 864-878 Back Matter....Pages -