Computer Vision - ECCV 2008 : 10th European Conference on Computer Vision, Marseille, France, October 12-18, 2008, Proceedings, Part I / edited by David Forsyth, Philip Torr, Andrew Zisserman.

Format:

Book

Contributor:

Forsyth, David, editor.

Torr, Philip, editor.

Zisserman, Andrew, editor.

SpringerLink (Online service)

Series:

Computer Science (Springer-11645)

LNCS sublibrary. Image processing, computer vision, pattern recognition, and graphics ; SL 6, 5302.

Image Processing, Computer Vision, Pattern Recognition, and Graphics ; 5302

Language:

English

Subjects (All):

Data mining.

Optical data processing.

Computer graphics.

Pattern perception.

Application software.

Data Mining and Knowledge Discovery.

Image Processing and Computer Vision.

Computer Imaging, Vision, Pattern Recognition and Graphics.

Computer Graphics.

Pattern Recognition.

Computer Appl. in Arts and Humanities.

Local Subjects:

Data Mining and Knowledge Discovery.

Image Processing and Computer Vision.

Computer Imaging, Vision, Pattern Recognition and Graphics.

Computer Graphics.

Pattern Recognition.

Computer Appl. in Arts and Humanities.

Physical Description:

1 online resource (XXXVII, 801 pages).

Edition:

First edition 2008.

Contained In:

Springer eBooks

Place of Publication:

Berlin, Heidelberg : Springer Berlin Heidelberg : Imprint: Springer, 2008.

System Details:

text file PDF

Summary:

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. .

Contents:

Lecture by Prof. Jan Koenderink

Something Old, Something New, Something Borrowed, Something Blue

Recognition

Learning to Localize Objects with Structured Output Regression

Beyond Nouns: Exploiting Prepositions and Comparative Adjectives for Learning Visual Classifiers

Learning Spatial Context: Using Stuff to Find Things

Segmentation and Recognition Using Structure from Motion Point Clouds

Poster Session I

Keypoint Signatures for Fast Learning and Recognition

Active Matching

Towards Scalable Dataset Construction: An Active Learning Approach

GeoS: Geodesic Image Segmentation

Simultaneous Motion Detection and Background Reconstruction with a Mixed-State Conditional Markov Random Field

Semidefinite Programming Heuristics for Surface Reconstruction Ambiguities

Robust Optimal Pose Estimation

Learning to Recognize Activities from the Wrong View Point

Joint Parametric and Non-parametric Curve Evolution for Medical Image Segmentation

Localizing Objects with Smart Dictionaries

Weakly Supervised Object Localization with Stable Segmentations

A Perceptual Comparison of Distance Measures for Color Constancy Algorithms

Scale Invariant Action Recognition Using Compound Features Mined from Dense Spatio-temporal Corners

Semi-supervised On-Line Boosting for Robust Tracking

Reformulating and Optimizing the Mumford-Shah Functional on a Graph - A Faster, Lower Energy Solution

Viewpoint Invariant Pedestrian Recognition with an Ensemble of Localized Features

Perspective Nonrigid Shape and Motion Recovery

Shadows in Three-Source Photometric Stereo

Hamming Embedding and Weak Geometric Consistency for Large Scale Image Search

Estimating Geo-temporal Location of Stationary Cameras Using Shadow Trajectories

An Experimental Comparison of Discrete and Continuous Shape Optimization Methods

Image Feature Extraction Using Gradient Local Auto-Correlations

Analysis of Building Textures for Reconstructing Partially Occluded Facades

Nonrigid Image Registration Using Dynamic Higher-Order MRF Model

Tracking of Abrupt Motion Using Wang-Landau Monte Carlo Estimation

Surface Visibility Probabilities in 3D Cluttered Scenes

A Generative Shape Regularization Model for Robust Face Alignment

Modeling and Recognition of Landmark Image Collections Using Iconic Scene Graphs

VideoCut: Removing Irrelevant Frames by Discovering the Object of Interest

ASN: Image Keypoint Detection from Adaptive Shape Neighborhood

Online Sparse Matrix Gaussian Process Regression and Vision Applications

Multi-stage Contour Based Detection of Deformable Objects

Brain Hallucination

Range Flow for Varying Illumination

Some Objects Are More Equal Than Others: Measuring and Predicting Importance

Robust Multiple Structures Estimation with J-Linkage

Human Activity Recognition with Metric Learning

Shape Matching by Segmentation Averaging

Search Space Reduction for MRF Stereo

Estimating 3D Face Model and Facial Deformation from a Single Image Based on Expression Manifold Optimization

3D Face Recognition by Local Shape Difference Boosting

Efficiently Learning Random Fields for Stereo Vision with Sparse Message Passing

Recovering Light Directions and Camera Poses from a Single Sphere

Tracking with Dynamic Hidden-State Shape Models

Interactive Tracking of 2D Generic Objects with Spacetime Optimization

A Segmentation Based Variational Model for Accurate Optical Flow Estimation

Similarity Features for Facial Event Analysis

Building a Compact Relevant Sample Coverage for Relevance Feedback in Content-Based Image Retrieval

Discriminative Learning for Deformable Shape Segmentation: A Comparative Study

Discriminative Locality Alignment

Stereo

Efficient Dense Scene Flow from Sparse or Dense Stereo Data

Integration of Multiview Stereo and Silhouettes Via Convex Functionals on Convex Domains

Using Multiple Hypotheses to Improve Depth-Maps for Multi-View Stereo

Sparse Structures in L-Infinity Norm Minimization for Structure and Motion Reconstruction.

Other Format:

Printed edition:

ISBN:

978-3-540-88682-2

9783540886822

Access Restriction:

Restricted for use by site license.