loading...
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'04) - Volume 1
Video Data Mining Using Configurations of Viewpoint Invariant Regions
Washington, D.C., USA
June 27-July 02
ISBN: 0-7695-2158-4
ASCII Text
x 
 
Josef Sivic, Andrew Zisserman, "Video Data Mining Using Configurations of Viewpoint Invariant Regions," Computer Vision and Pattern Recognition, IEEE Computer Society Conference on, vol. 1, pp. 488-495, 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'04) - Volume 1, 2004.
 
 
BibTex
x
 
@article{ 10.1109/CVPR.2004.261,
author = {Josef Sivic and Andrew Zisserman},
title = {Video Data Mining Using Configurations of Viewpoint Invariant Regions},
journal ={Computer Vision and Pattern Recognition, IEEE Computer Society Conference on},
volume = {1},
year = {2004},
issn = {1063-6919},
pages = {488-495},
doi = {http://doi.ieeecomputersociety.org/10.1109/CVPR.2004.261},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - CONF
JO - Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
TI - Video Data Mining Using Configurations of Viewpoint Invariant Regions
SN - 1063-6919
SP488
EP495
A1 - Josef Sivic,
A1 - Andrew Zisserman,
PY - 2004
KW - null
VL - 1
JA - Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
ER -
 
Josef Sivic, University of Oxford
Andrew Zisserman, University of Oxford

We describe a method for obtaining the principal objects, characters and scenes in a video by measuring the reoccurrence of spatial configurations of viewpoint invariant features. We investigate two aspects of the problem: the scale of the configurations, and the similarity requirements for clustering configurations.

The problem is challenging firstly because an object can undergo substantial changes in imaged appearance throughout a video (due to viewpoint and illumination change, and partial occlusion), and secondly because configurations are detected imperfectly, so that inexact patterns must be matched.

The novelty of the method is that viewpoint invariant features are used to form the configurations, and that efficient methods from the text analysis literature are employed to reduce the matching complexity.

Examples of ?mined? objects are shown for a feature length film and a sitcom.

Citation:
Josef Sivic, Andrew Zisserman, "Video Data Mining Using Configurations of Viewpoint Invariant Regions," cvpr, vol. 1, pp.488-495, 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'04) - Volume 1, 2004
Usage of this product signifies your acceptance of the Terms of Use.