Trans Media Relevance Feedback for Image Autoannotation

Thomas Mensink 1, 2 Jakob Verbeek 2 Gabriela Csurka 1
2 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : Automatic image annotation is an important tool for keyword-based image retrieval, providing a textual index for non-annotated images. Many image auto annotation methods are based on visual similarity between images to be annotated and images in a training corpus. The annotations of the most similar training images are transferred to the image to be annotated. In this paper we consider using also similarities among the training images, both visual and textual, to derive pseudo relevance models, as well as crossmedia relevance models. We extend a recent state-of-the-art image annotation model to incorporate this information. On two widely used datasets (COREL and IAPR) we show experimentally that the pseudo-relevance models improve the annotation accuracy.
Type de document :
Communication dans un congrès
Frédéric Labrosse and Reyer Zwiggelaar and Yonghuai Liu and Bernie Tiddeman. BMVC 2010 - British Machine Vision Conference, Aug 2010, Aberystwyth, United Kingdom. The British Machine Vision Association (BMVA), pp.20.1-20.12, 2010, <http://www.bmva.org/bmvc/2010/conference/paper20/index.html>. <10.5244/C.24.20>
Liste complète des métadonnées



https://hal.inria.fr/inria-00548632
Contributeur : Thoth Team <>
Soumis le : lundi 20 décembre 2010 - 10:22:16
Dernière modification le : mardi 29 juillet 2014 - 00:17:28
Document(s) archivé(s) le : lundi 5 novembre 2012 - 14:36:37

Fichiers

MVC10.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Thomas Mensink, Jakob Verbeek, Gabriela Csurka. Trans Media Relevance Feedback for Image Autoannotation. Frédéric Labrosse and Reyer Zwiggelaar and Yonghuai Liu and Bernie Tiddeman. BMVC 2010 - British Machine Vision Conference, Aug 2010, Aberystwyth, United Kingdom. The British Machine Vision Association (BMVA), pp.20.1-20.12, 2010, <http://www.bmva.org/bmvc/2010/conference/paper20/index.html>. <10.5244/C.24.20>. <inria-00548632>

Partager

Métriques

Consultations de
la notice

465

Téléchargements du document

359