Ranking user-annotated images for multiple query terms

Moray Allan 1 Jakob Verbeek 1
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : We show how web image search can be improved by taking into account the users who provided different images, and that performance when searching for multiple terms can be increased by learning a new combined model and taking account of images which partially match the query. Search queries are answered by using a mixture of kernel density estimators to rank the visual content of web images from the Flickr website whose noisy tag annotations match the given query terms. Experiments show that requiring agreement between images from different users allows a better model of the visual class to be learnt, and that precision can be increased by rejecting images from 'untrustworthy' users. We focus on search queries for multiple terms, and demonstrate enhanced performance by learning a single model for the overall query, treating images which only satisfy a subset of the search terms as negative training examples.
Type de document :
Communication dans un congrès
A. Cavallaro and S. Prince and D. Alexander. BMVC 2009 - British Machine Vision Conference, Sep 2009, London, United Kingdom. BMVA Press, pp.20.1-20.10, 2009, Proceedings of the British Machine Vision Conference. <10.5244/C.23.20>
Liste complète des métadonnées



https://hal.inria.fr/inria-00439278
Contributeur : Jakob Verbeek <>
Soumis le : lundi 11 avril 2011 - 15:11:37
Dernière modification le : mercredi 9 juillet 2014 - 17:54:11
Document(s) archivé(s) le : samedi 3 décembre 2016 - 22:45:24

Fichiers

verbeek09bmvc.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Moray Allan, Jakob Verbeek. Ranking user-annotated images for multiple query terms. A. Cavallaro and S. Prince and D. Alexander. BMVC 2009 - British Machine Vision Conference, Sep 2009, London, United Kingdom. BMVA Press, pp.20.1-20.10, 2009, Proceedings of the British Machine Vision Conference. <10.5244/C.23.20>. <inria-00439278v2>

Partager

Métriques

Consultations de
la notice

290

Téléchargements du document

6624