Computer Vision - ECCV 2008 10th European Conference on Computer Vision, Marseille, France, October 12-18, 2008, Proceedings, Part III / [electronic resource] :
edited by David Forsyth, Philip Torr, Andrew Zisserman.
- 1st ed. 2008.
- XIX, 826 p. online resource.
- Image Processing, Computer Vision, Pattern Recognition, and Graphics, 5304 3004-9954 ; .
- Image Processing, Computer Vision, Pattern Recognition, and Graphics, 5304 .
Matching -- 3D Non-rigid Surface Matching and Registration Based on Holomorphic Differentials -- Learning Two-View Stereo Matching -- SIFT Flow: Dense Correspondence across Different Scenes -- Learning+Features -- Discriminative Sparse Image Models for Class-Specific Edge Detection and Image Interpretation -- Non-local Regularization of Inverse Problems -- Training Hierarchical Feed-Forward Visual Recognition Models Using Transfer Learning from Pseudo-Tasks -- Learning Optical Flow -- Poster Session III -- Optimizing Binary MRFs with Higher Order Cliques -- Multi-camera Tracking and Atypical Motion Detection with Behavioral Maps -- Automatic Image Colorization Via Multimodal Predictions -- CSDD Features: Center-Surround Distribution Distance for Feature Extraction and Matching -- Detecting Carried Objects in Short Video Sequences -- Constrained Maximum Likelihood Learning of Bayesian Networks for Facial Action Recognition -- Robust Scale Estimation from Ensemble Inlier Sets for Random Sample ConsensusMethods -- Efficient Camera Smoothing in Sequential Structure-from-Motion Using Approximate Cross-Validation -- Semi-automatic Motion Segmentation with Motion Layer Mosaics -- Unified Frequency Domain Analysis of Lightfield Cameras -- Segmenting Fiber Bundles in Diffusion Tensor Images -- View Point Tracking of Rigid Objects Based on Shape Sub-manifolds -- Generative Image Segmentation Using Random Walks with Restart -- Background Subtraction on Distributions -- A Statistical Confidence Measure for Optical Flows -- Automatic Generator of Minimal Problem Solvers -- A New Baseline for Image Annotation -- Behind the Depth Uncertainty: Resolving Ordinal Depth in SFM -- Sparse Long-Range Random Field and Its Application to Image Denoising -- Output Regularized Metric Learning with Side Information -- Student-t Mixture Filter for Robust, Real-Time Visual Tracking -- Photo and Video Quality Evaluation: Focusing on the Subject -- The Bi-directional Framework for Unifying Parametric Image Alignment Approaches -- Direct Bundle Estimation for Recovery of Shape, Reflectance Property and Light Position -- A Probabilistic Cascade of Detectors for Individual Object Recognition -- Scale-Dependent/Invariant Local 3D Shape Descriptors for Fully Automatic Registration of Multiple Sets of Range Images -- Star Shape Prior for Graph-Cut Image Segmentation -- Efficient NCC-Based Image Matching in Walsh-Hadamard Domain -- Object Recognition by Integrating Multiple Image Segmentations -- A Linear Time Histogram Metric for Improved SIFT Matching -- An Extended Phase Field Higher-Order Active Contour Model for Networks and Its Application to Road Network Extraction from VHR Satellite Images -- A Generic Neighbourhood Filtering Framework for Matrix Fields -- Multi-scale Improves Boundary Detection in Natural Images -- Estimating 3D Trajectories of Periodic Motions from Stationary Monocular Views -- Unsupervised Learning of Skeletons from Motion -- Multi-layered Decomposition of Recurrent Scenes -- SERBoost: Semi-supervised Boosting with Expectation Regularization -- View Synthesis for Recognizing Unseen Poses of Object Classes -- Projected Texture for Object Classification -- Prior-Based Piecewise-Smooth Segmentation by Template Competitive Deformation Using Partitions of Unity -- Vision-Based Multiple Interacting Targets Tracking via On-Line Supervised Learning -- An Incremental Learning Method for Unconstrained Gaze Estimation -- Partial Difference Equations over Graphs: Morphological Processing of Arbitrary Discrete Data -- Real-Time Shape Analysis of a Human Body in Clothing Using Time-Series Part-Labeled Volumes -- Kernel Codebooks for Scene Categorization -- Multiple Tree Models for Occlusion and Spatial Constraints in Human Pose Estimation -- Structuring Visual Words in 3D for Arbitrary-View Object Localization -- Multi-thread Parsing for Recognizing Complex Events in Videos -- Signature-Based Document Image Retrieval -- An Effective Approach to 3D Deformable Surface Tracking -- MRFs -- Belief Propagation withDirectional Statistics for Solving the Shape-from-Shading Problem -- A Convex Formulation of Continuous Multi-label Problems -- Beyond Loose LP-Relaxations: Optimizing MRFs by Repairing Cycles.
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. .
9783540886907
10.1007/978-3-540-88690-7 doi
Data mining.
Computer vision.
Image processing--Digital techniques.
Computer graphics.
Pattern recognition systems.
Digital humanities.
Data Mining and Knowledge Discovery.
Computer Vision.
Computer Imaging, Vision, Pattern Recognition and Graphics.
Computer Graphics.
Automated Pattern Recognition.
Digital Humanities.
QA76.9.D343
006.312
Matching -- 3D Non-rigid Surface Matching and Registration Based on Holomorphic Differentials -- Learning Two-View Stereo Matching -- SIFT Flow: Dense Correspondence across Different Scenes -- Learning+Features -- Discriminative Sparse Image Models for Class-Specific Edge Detection and Image Interpretation -- Non-local Regularization of Inverse Problems -- Training Hierarchical Feed-Forward Visual Recognition Models Using Transfer Learning from Pseudo-Tasks -- Learning Optical Flow -- Poster Session III -- Optimizing Binary MRFs with Higher Order Cliques -- Multi-camera Tracking and Atypical Motion Detection with Behavioral Maps -- Automatic Image Colorization Via Multimodal Predictions -- CSDD Features: Center-Surround Distribution Distance for Feature Extraction and Matching -- Detecting Carried Objects in Short Video Sequences -- Constrained Maximum Likelihood Learning of Bayesian Networks for Facial Action Recognition -- Robust Scale Estimation from Ensemble Inlier Sets for Random Sample ConsensusMethods -- Efficient Camera Smoothing in Sequential Structure-from-Motion Using Approximate Cross-Validation -- Semi-automatic Motion Segmentation with Motion Layer Mosaics -- Unified Frequency Domain Analysis of Lightfield Cameras -- Segmenting Fiber Bundles in Diffusion Tensor Images -- View Point Tracking of Rigid Objects Based on Shape Sub-manifolds -- Generative Image Segmentation Using Random Walks with Restart -- Background Subtraction on Distributions -- A Statistical Confidence Measure for Optical Flows -- Automatic Generator of Minimal Problem Solvers -- A New Baseline for Image Annotation -- Behind the Depth Uncertainty: Resolving Ordinal Depth in SFM -- Sparse Long-Range Random Field and Its Application to Image Denoising -- Output Regularized Metric Learning with Side Information -- Student-t Mixture Filter for Robust, Real-Time Visual Tracking -- Photo and Video Quality Evaluation: Focusing on the Subject -- The Bi-directional Framework for Unifying Parametric Image Alignment Approaches -- Direct Bundle Estimation for Recovery of Shape, Reflectance Property and Light Position -- A Probabilistic Cascade of Detectors for Individual Object Recognition -- Scale-Dependent/Invariant Local 3D Shape Descriptors for Fully Automatic Registration of Multiple Sets of Range Images -- Star Shape Prior for Graph-Cut Image Segmentation -- Efficient NCC-Based Image Matching in Walsh-Hadamard Domain -- Object Recognition by Integrating Multiple Image Segmentations -- A Linear Time Histogram Metric for Improved SIFT Matching -- An Extended Phase Field Higher-Order Active Contour Model for Networks and Its Application to Road Network Extraction from VHR Satellite Images -- A Generic Neighbourhood Filtering Framework for Matrix Fields -- Multi-scale Improves Boundary Detection in Natural Images -- Estimating 3D Trajectories of Periodic Motions from Stationary Monocular Views -- Unsupervised Learning of Skeletons from Motion -- Multi-layered Decomposition of Recurrent Scenes -- SERBoost: Semi-supervised Boosting with Expectation Regularization -- View Synthesis for Recognizing Unseen Poses of Object Classes -- Projected Texture for Object Classification -- Prior-Based Piecewise-Smooth Segmentation by Template Competitive Deformation Using Partitions of Unity -- Vision-Based Multiple Interacting Targets Tracking via On-Line Supervised Learning -- An Incremental Learning Method for Unconstrained Gaze Estimation -- Partial Difference Equations over Graphs: Morphological Processing of Arbitrary Discrete Data -- Real-Time Shape Analysis of a Human Body in Clothing Using Time-Series Part-Labeled Volumes -- Kernel Codebooks for Scene Categorization -- Multiple Tree Models for Occlusion and Spatial Constraints in Human Pose Estimation -- Structuring Visual Words in 3D for Arbitrary-View Object Localization -- Multi-thread Parsing for Recognizing Complex Events in Videos -- Signature-Based Document Image Retrieval -- An Effective Approach to 3D Deformable Surface Tracking -- MRFs -- Belief Propagation withDirectional Statistics for Solving the Shape-from-Shading Problem -- A Convex Formulation of Continuous Multi-label Problems -- Beyond Loose LP-Relaxations: Optimizing MRFs by Repairing Cycles.
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. .
9783540886907
10.1007/978-3-540-88690-7 doi
Data mining.
Computer vision.
Image processing--Digital techniques.
Computer graphics.
Pattern recognition systems.
Digital humanities.
Data Mining and Knowledge Discovery.
Computer Vision.
Computer Imaging, Vision, Pattern Recognition and Graphics.
Computer Graphics.
Automated Pattern Recognition.
Digital Humanities.
QA76.9.D343
006.312