Computer Vision - ECCV 2008: 10th European Conference on Computer Vision, Marseille, France, October 12-18, 2008, ProceedingsDavid Forsyth, Philip Torr, Andrew Zisserman 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. |
Contents
Something Old Something New Something Borrowed Something Blue | 1 |
Learning to Localize Objects with Structured Output Regression | 2 |
Exploiting Prepositions and Comparative Adjectives for Learning Visual Classifiers | 16 |
Using Stuff to Find Things | 30 |
Segmentation and Recognition Using Structure from Motion Point Clouds | 44 |
Keypoint Signatures for Fast Learning and Recognition | 58 |
Active Matching | 72 |
An Active Learning Approach | 86 |
Surface Visibility Probabilities in 3D Cluttered Scenes | 401 |
A Generative Shape Regularization Model for Robust Face Alignment | 413 |
Modeling and Recognition of Landmark Image Collections Using Iconic Scene Graphs | 427 |
Removing Irrelevant Frames by Discovering the Object of Interest | 441 |
Image Keypoint Detection from Adaptive Shape Neighborhood | 454 |
Online Sparse Matrix Gaussian Process Regression and Vision Applications | 468 |
Multistage Contour Based Detection of Deformable Objects | 483 |
Brain Hallucination | 497 |
Geodesic Image Segmentation | 99 |
Simultaneous Motion Detection and Background Reconstruction with a MixedState Conditional Markov Random Field | 113 |
Semidefinite Programming Heuristics for Surface Reconstruction Ambiguities | 127 |
Robust Optimal Pose Estimation | 141 |
Learning to Recognize Activities from the Wrong View Point | 154 |
Joint Parametric and Nonparametric Curve Evolution for Medical Image Segmentation | 167 |
Localizing Objects with Smart Dictionaries | 179 |
Weakly Supervised Object Localization withStable Segmentations | 193 |
A Perceptual Comparison of Distance Measures for Color Constancy Algorithms | 208 |
Scale Invariant Action Recognition Using Compound Features Mined from Dense Spatiotemporal Corners | 222 |
Semisupervised OnLine Boosting for Robust Tracking | 234 |
Reformulating and Optimizing the MumfordShah Functional on a Graph A Faster Lower Energy Solution | 248 |
Viewpoint Invariant Pedestrian Recognition with an Ensemble of Localized Features | 262 |
Perspective Nonrigid Shape and Motion Recovery | 276 |
Shadows in ThreeSource Photometric Stereo | 290 |
Hamming Embedding and Weak Geometric Consistency for Large Scale Image Search | 304 |
Estimating Geotemporal Location of Stationary Cameras Using Shadow Trajectories | 318 |
An Experimental Comparison of Discrete and Continuous Shape Optimization Methods | 332 |
Image Feature Extraction Using Gradient Local AutoCorrelations | 346 |
Analysis of Building Textures for Reconstructing Partially Occluded Facades | 359 |
Nonrigid Image Registration Using Dynamic HigherOrder MRF Model | 373 |
Tracking of Abrupt Motion Using WangLandau Monte Carlo Estimation | 387 |
Range Flow for Varying Illumination | 509 |
Measuring and Predicting Importance | 523 |
Robust Multiple Structures Estimation with JLinkage | 537 |
Human Activity Recognition with Metric Learning | 548 |
Shape Matching by Segmentation Averaging | 562 |
Search Space Reduction for MRF Stereo | 576 |
Estimating 3D Face Model and Facial Deformation from a Single Image Based on Expression Manifold Optimization | 589 |
3D Face Recognition by Local Shape Difference Boosting | 603 |
Efficiently Learning Random Fields for Stereo Vision with Sparse Message Passing | 617 |
Recovering Light Directions and Camera Poses from a Single Sphere | 631 |
Tracking with Dynamic HiddenState Shape Models | 643 |
Interactive Tracking of 2D Generic Objects with Spacetime Optimization | 657 |
A Segmentation Based Variational Model for Accurate Optical Flow Estimation | 671 |
Similarity Features for Facial Event Analysis | 685 |
Building a Compact Relevant Sample Coverage for Relevance Feedback in ContentBased Image Retrieval | 697 |
A Comparative Study | 711 |
Discriminative Locality Alignment | 725 |
Efficient Dense Scene Flow from Sparse or Dense Stereo Data | 739 |
Integration of Multiview Stereo and Silhouettes Via Convex Functionals on Convex Domains | 752 |
Using Multiple Hypotheses to Improve DepthMaps for MultiView Stereo | 766 |
Sparse Structures in LInfinity Norm Minimization for Structure and Motion Reconstruction | 780 |
Author Index | 795 |
Other editions - View all
Common terms and phrases
3D face accuracy algorithm approach belief propagation binary boosting camera classifier cluster color color constancy Computer Vision conditional random fields Conference on Computer constraints contour corresponding curve CVPR database dataset defined deformation descriptors detection disparity distance ECCV efficient energy equation error estimation evaluate facial frame function Gaussian global gradient graph cuts ground truth Heidelberg histogram ICCV IEEE image gradients image segmentation iteration keypoints L2-norm labeled learning level set linear LNCS Markov random field matching matrix measure method minimization motion multiple object obtained occlusion optical flow optimization outliers parameters patch Pattern Recognition performance pixels points problem Proc proposed random RANSAC reconstruction regions robust samples scale scene segmentation sequence shape shows similar solution space sparse spatial stereo structure surface techniques term texture tion tracking update vector Vision and Pattern visual voxel weight Zisserman