Titre du document / Document title
To mine capture intention of camcorder users
Auteur(s) / Author(s)
TAO MEI
(1) ;
HUA Xian-Sheng
(2) ;
ZHOU He-Qin
(1) ;
SHIPENG LI
(2) ;
Affiliation(s) du ou des auteurs / Author(s) Affiliation(s)
(1) Department of Automation, University of Science and Technology of China, Hefei, 230027, CHINE
(2) Microsoft Research Asia, 3F Sigma Center, 49 Zhichun Road, Beijing, 100080, CHINE
Résumé / Abstract
In this paper, we present a learning-based approach to mining the capture intention of camcorder users, aiming at providing a novel viewpoint in terms of home video content analysis. In contrast to existing approaches to video analysis designed from the viewers' standpoint, this approach models the capture intention from a camcorder user's point of view, by investigating a set of effective intention oriented features. With this approach, not only the capture intention is effectively mined, but also a set of intention probability curves are produced for efficient browsing of home video content. The experimental evaluations indicate that the intention based approach is an effective complement to existing home video content analysis schemes.
Revue / Journal Title
SPIE proceedings series
Source / Source
Congrès
Visual communications and image processing 2005 : 12-15 July 2005, Beijing, Chine
Visual communications and image processing. Conference, Beijing
, CHINE
(12/07/2005)
, vol. 5960, p.1 (14 ref.)
ISBN 0-8194-5976-3 ;
Langue / Language
Anglais
Editeur / Publisher
Society of Photo-Optical Instrumentation Engineers, Bellingham, WA, INTERNATIONAL
(1988)
(Revue)
Mots-clés anglais / English Keywords
Home video ;
Information browsing ;
Observer ;
Content analysis ;
Image analysis ;
Learning ;
Mine ;
Mots-clés français / French Keywords
Vidéo domestique ;
Navigation information ;
Observateur ;
Analyse contenu ;
Analyse image ;
Apprentissage ;
Mine ;
Mots-clés espagnols / Spanish Keywords
Navegacíon informacíon ;
Observador ;
Análisis contenido ;
Análisis imagen ;
Aprendizaje ;
Mina ;
Localisation / Location
INIST-CNRS, Cote INIST : 21760, 35400013870747.0290
Nº notice refdoc (ud4) : 17527731
