LEAR and XRCE's participation to Visual Concept Detection Task - ImageCLEF 2010

Thomas Mensink 1, 2 Gabriela Csurka 1 Florent Perronnin 1 Jorge Sánchez 1 Jakob Verbeek 2
2 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : In this paper we present the common effort of Lear and XRCE for the ImageCLEF Visual Concept Detection and Annotation Task. We first sought to combine our individual state-of-the-art approaches: the Fisher vector image representation, with the TagProp method for image auto-annotation. Our second motivation was to investigate the annotation performance by using extra information in the form of provided Flickr-tags. The results show that using the Flickr-tags in combination with visual features improves the results of any method using only visual features. Our winning system, an early-fusion linear-SVM classifier, trained on visual and Flickr-tags features, obtains 45.5% in mean Average Precision (mAP), almost a 5% absolute improvement compared to the best visual-only system. Our best visual-only system obtains 39.0% mAP, and is close to the best visual-only system. It is a late-fusion linear-SVM classifier, trained on two types of visual features (SIFT and colour). The performance of TagProp is close to our SVM classifiers. The methods presented in this paper, are all scalable to large datasets and/or many concepts. This is due to the fast FK framework for image representation, and due to the classifiers. The linear SVM classifier has proven to scale well for large datasets. The k-NN approach of TagProp, is interesting in this respect since it requires only 2 parameters per concept.
Type de document :
Communication dans un congrès
ImageCLEF - Workshop Cross Language Image Retrieval, Sep 2010, Padua, Italy. pp.48, 2010
Liste complète des métadonnées



https://hal.inria.fr/inria-00548633
Contributeur : Thoth Team <>
Soumis le : lundi 20 décembre 2010 - 10:22:23
Dernière modification le : mardi 29 juillet 2014 - 00:18:01
Document(s) archivé(s) le : lundi 5 novembre 2012 - 14:36:44

Fichiers

LEAR.XRCE.ImageClef.2010.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00548633, version 1

Collections

Citation

Thomas Mensink, Gabriela Csurka, Florent Perronnin, Jorge Sánchez, Jakob Verbeek. LEAR and XRCE's participation to Visual Concept Detection Task - ImageCLEF 2010. ImageCLEF - Workshop Cross Language Image Retrieval, Sep 2010, Padua, Italy. pp.48, 2010. <inria-00548633>

Partager

Métriques

Consultations de
la notice

581

Téléchargements du document

308