Learning Distance Functions for Automatic Annotation of Images

Josip Krapac 1 Frédéric Jurie 1
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : This paper gives an overview of recent approaches towards image representation and image similarity computation for content-based image retrieval and automatic image annotation (category tagging). Additionaly, a new similarity function between an image and an object class is proposed. This similarity function combines various aspects of object class appearance through use of representative images of the class. Similarity to a representative image is determined by weighting local image similarities, where weights are learned from training image pairs, labeled "same" and "different", using linear SVM. The proposed approach is validated on a challenging dataset where it performed favorably.
Type de document :
Communication dans un congrès
Nozha Boujemaa and Marcin Detyniecki and Andreas Nürnberger. AMR - 5th International Workshop on Adaptive Multimedia Retrieval, Jul 2007, Paris, France. Springer-Verlag, 4918, pp.1-16, 2008, 〈http://www.springerlink.com/content/fq31244055h2w73g/〉. 〈10.1007/978-3-540-79860-6_1〉
Liste complète des métadonnées

Littérature citée [32 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00548684
Contributeur : Thoth Team <>
Soumis le : mardi 25 janvier 2011 - 12:52:49
Dernière modification le : mardi 5 juin 2018 - 18:00:02
Document(s) archivé(s) le : mardi 26 avril 2011 - 02:37:12

Fichier

kj07amr.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Josip Krapac, Frédéric Jurie. Learning Distance Functions for Automatic Annotation of Images. Nozha Boujemaa and Marcin Detyniecki and Andreas Nürnberger. AMR - 5th International Workshop on Adaptive Multimedia Retrieval, Jul 2007, Paris, France. Springer-Verlag, 4918, pp.1-16, 2008, 〈http://www.springerlink.com/content/fq31244055h2w73g/〉. 〈10.1007/978-3-540-79860-6_1〉. 〈inria-00548684〉

Partager

Métriques

Consultations de la notice

659

Téléchargements de fichiers

245