Computer Vision - ECCV 2008: 10th European Conference on Computer Vision, Marseille, France, October 12-18, 2008, Proceedings, Part IV (Lecture Notes in Computer Science (5305))

The four-volume set comprising LNCS volumes 5302/5303/5304/5305 constitutes the refereed proceedings of the 10th European Conference on Computer Vision, ECCV 2008, held in Marseille, France, in October 2008. The 243 revised papers presented were carefully reviewed and selected from a total of 871 papers submitted. The four books cover the entire range of current issues in computer vision. The papers are organized in topical sections on recognition, stereo, people and face recognition, object tracking, matching, learning and features, MRFs, segmentation, computational photography and active reconstruction. Front Matter....Pages - Image Segmentation in the Presence of Shadows and Highlights....Pages 1-14 Image Segmentation by Branch-and-Mincut....Pages 15-29 What Is a Good Image Segment? A Unified Approach to Segment Extraction....Pages 30-44 Light-Efficient Photography....Pages 45-59 Flexible Depth of Field Photography....Pages 60-73 Priors for Large Photo Collections and What They Reveal about Cameras....Pages 74-87 Understanding Camera Trade-Offs through a Bayesian Analysis of Light Field Projections....Pages 88-101 CenSurE: Center Surround Extremas for Realtime Feature Detection and Matching....Pages 102-115 Searching the World’s Herbaria: A System for Visual Identification of Plant Species....Pages 116-129 A Column-Pivoting Based Strategy for Monomial Ordering in Numerical Gröbner Basis Calculations....Pages 130-143 Co-recognition of Image Pairs by Data-Driven Monte Carlo Image Exploration....Pages 144-157 Movie/Script: Alignment and Parsing of Video and Text Transcription....Pages 158-171 Using 3D Line Segments for Robust and Efficient Change Detection from Multiple Noisy Images....Pages 172-185 Action Recognition with a Bio–inspired Feedforward Motion Processing Model: The Richness of Center-Surround Interactions....Pages 186-199 Linking Pose and Motion....Pages 200-213 Automated Delineation of Dendritic Networks in Noisy Image Stacks....Pages 214-227 Calibration from Statistical Properties of the Visual World....Pages 228-241 Regular Texture Analysis as Statistical Model Selection....Pages 242-255 Higher Dimensional Affine Registration and Vision Applications....Pages 256-269 Semantic Concept Classification by Joint Semi-supervised Learning of Feature Subspaces and Support Vector Machines....Pages 270-283 Learning from Real Images to Model Lighting Variations for Face Images....Pages 284-297 Toward Global Minimum through Combined Local Minima....Pages 298-311 Differential Spatial Resection - Pose Estimation Using a Single Local Image Feature....Pages 312-325 Riemannian Anisotropic Diffusion for Tensor Valued Images....Pages 326-339 FaceTracer: A Search Engine for Large Collections of Images with Faces....Pages 340-353 What Does the Sky Tell Us about the Camera?....Pages 354-367 Three Dimensional Curvilinear Structure Detection Using Optimally Oriented Flux....Pages 368-382 Scene Segmentation for Behaviour Correlation....Pages 383-395 Robust Visual Tracking Based on an Effective Appearance Model....Pages 396-408 Key Object Driven Multi-category Object Recognition, Localization and Tracking Using Spatio-temporal Context....Pages 409-422 A Pose-Invariant Descriptor for Human Detection and Segmentation....Pages 423-436 Texture-Consistent Shadow Removal....Pages 437-450 Scene Discovery by Matrix Factorization....Pages 451-464 Simultaneous Detection and Registration for Ileo-Cecal Valve Detection in 3D CT Colonography....Pages 465-478 Constructing Category Hierarchies for Visual Recognition....Pages 479-491 Sample Sufficiency and PCA Dimension for Statistical Shape Models....Pages 492-503 Locating Facial Features with an Extended Active Shape Model....Pages 504-513 Dynamic Integration of Generalized Cues for Person Tracking....Pages 514-526 Extracting Moving People from Internet Videos....Pages 527-540 Multiple Instance Boost Using Graph Embedding Based Decision Stump for Pedestrian Detection....Pages 541-552 Object Detection from Large-Scale 3D Datasets Using Bottom-Up and Top-Down Descriptors....Pages 553-566 Making Background Subtraction Robust to Sudden Illumination Changes....Pages 567-580 Closed-Form Solution to Non-rigid 3D Surface Registration....Pages 581-594 Implementing Decision Trees and Forests on a GPU....Pages 595-608 General Imaging Geometry for Central Catadioptric Cameras....Pages 609-622 Estimating Radiometric Response Functions from Image Noise Variance....Pages 623-637 Solving Image Registration Problems Using Interior Point Methods....Pages 638-651 3D Face Model Fitting for Recognition....Pages 652-664 A Multi-scale Vector Spline Method for Estimating the Fluids Motion on Satellite Images....Pages 665-676 Continuous Energy Minimization Via Repeated Binary Fusion....Pages 677-690 Unified Crowd Segmentation....Pages 691-704 Quick Shift and Kernel Methods for Mode Seeking....Pages 705-718 A Fast Algorithm for Creating a Compact and Discriminative Visual Codebook....Pages 719-732 A Dynamic Conditional Random Field Model for Joint Labeling of Object and Scene Classes....Pages 733-747 Local Regularization for Multiclass Classification Facing Significant Intraclass Variations....Pages 748-759 Saliency Based Opportunistic Search for Object Part Extraction and Labeling....Pages 760-774 Stereo Matching: An Outlier Confidence Approach....Pages 775-787 Improving Shape Retrieval by Learning Graph Transduction....Pages 788-801 Cat Head Detection - How to Effectively Exploit Shape and Texture Features....Pages 802-816 Motion Context: A New Representation for Human Action Recognition....Pages 817-829 Temporal Dithering of Illumination for Fast Active Vision....Pages 830-844 Compressive Structured Light for Recovering Inhomogeneous Participating Media....Pages 845-858 Passive Reflectometry....Pages 859-872 Fusion of Feature- and Area-Based Information for Urban Buildings Modeling from Aerial Imagery....Pages 873-886 Back Matter....Pages - Welcome To The 2008europeanconference Oncomputer Vision. These Proce- Ings Are The Result Of A Great Deal Of Hard Work By Many People. To Produce Them, A Total Of 871 Papers Were Reviewed. Forty Were Selected For Oral Pres- Tation And 203 Were Selected For Poster Presentation, Yielding Acceptance Rates Of 4.6% For Oral, 23.3% For Poster, And 27.9% In Total. Weappliedthreeprinciples.first,sincewehadastronggroupofareachairs, The ?nal Decisions To Accept Or Reject A Paper Rested With The Area Chair, Who Wouldbeinformedbyreviewsandcouldactonlyinconsensuswithanotherarea Chair. Second, We Felt That Authors Were Entitled To A Summary That Explained How The Area Chair Reached A Decision For A Paper. Third, We Were Very Careful To Avoid Con?icts Of Interest. Each Paper Was Assigned To An Area Chair By The Program Chairs, And Each Area Chair Received A Pool Of About 25 Papers. The Area Chairs Then Identi?ed And Rankedappropriatereviewersfor Eachpaper In Their Pool, And A Constrained Optimization Allocated Three Reviewers To Each Paper. We Are Very Proud That Every Paper Received At Least Three Reviews. At This Point, Authors Were Able To Respond To Reviews. The Area Chairs Then Needed To Reach A Decision. We Used A Series Of Procedures To Ensure Careful Review And To Avoid Con?icts Of Interest. Programchairs Did Not Submit Papers. The Area Chairs Were Divided Into Three Groups So That No Area Chair In The Group Was In Con?ict With Any Paper Assigned To Any Area Chair In The Group. Annotation The four-volume set comprising LNCS volumes 5302/5303/5304/5305 constitutes the refereed proceedings of the 10th European Conference on Computer Vision, ECCV 2008, held in Marseille, France, in October 2008. The 243 revised papers presented were carefully reviewed and selected from a total of 871 papers submitted. The four books cover the entire range of current issues in computer vision. The papers are organized in topical sections on recognition, stereo, people and face recognition, object tracking, matching, learning and features, MRFs, segmentation, computational photography and active reconstruction Comprising of "LNCS" volumes 5302/5303/5304/5305, this set constitutes the refereed proceedings of the 10th European Conference on Computer Vision, ECCV 2008, held in Marseille, France, in October 2008. Organized in topical sections, it covers the entire range of issues in computer vision.