UNIGE document Chapitre d'actes
previous document  unige:47730  next document
add to browser collection
Title

Asymmetric Learning and Dissimilarity Spaces for Content-based Retrieval

Authors
Published in Image and Video Retrieval : 5th International Conference, CIVR 2006. Proceedings. Tempe (AZ) - July 13-15 - Springer. 2006, p. 330-339
Collection Lecture Notes in Computer Science; 4071
Abstract This paper presents novel dissimilarity space specially designed for interactive multimedia retrieval. By providing queries made of positive and negative examples, the goal consists in learning the positive class distribution. This classification problem is known to be asymmetric, i.e. the negative class does not cluster in the original feature spaces. We introduce here the idea of Query-based Dissimilarity Space (QDS) which enables to cope with the asymmetrical setup by converting it in a more classical 2-class problem. The proposed approach is evaluated on both artificial data and real image database, and compared with state-of-the-art algorithms.
Keywords Computer GraphicsInformation Storage and RetrievalDatabase ManagementInformation Systems Applications (incl. Internet)Multimedia Information SystemsImage Processing and Computer Vision
Identifiers
Full text
Structures
Research groups Computer Vision and Multimedia Laboratory
Viper group
Citation
(ISO format)
BRUNO, Eric, MOENNE-LOCCOZ, Nicolas, MARCHAND-MAILLET, Stéphane. Asymmetric Learning and Dissimilarity Spaces for Content-based Retrieval. In: Image and Video Retrieval : 5th International Conference, CIVR 2006. Proceedings. Tempe (AZ). [s.l.] : Springer, 2006. p. 330-339. (Lecture Notes in Computer Science; 4071) https://archive-ouverte.unige.ch/unige:47730

140 hits

21 downloads

Update

Deposited on : 2015-03-06

Export document
Format :
Citation style :