Weakly supervised learning of visual models and its application to content-based retrieval

Cordelia Schmid 1, *
* Auteur correspondant
1 LEAR - Learning and recognition in vision
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : This paper presents a method for weakly supervised learning of visual models. The visual model is based on a two-layer image description: a set of "generic" descriptors and their distribution over neighbourhoods. "Generic" descriptors represent sets of similar rotational invariant feature vectors. Statistical spatial constraints describe the neighborhood structure and make our description more discriminant. The joint probability of the frequencies of "generic" descriptors over a neighbourhood is multi-modal and is represented by a set of "neighbourhood-frequency" clusters. Our image description is rotationally invariant, robust to model deformations and characterizes efficiently "appearance-based" visual structure. The selection of distinctive clusters determines model features (common to the positive and rare in the negative examples). Visual models are retrieved and localized using a probabilistic score. Experimental results for "textured" animals and faces show a very good performance for retrieval as well as localization.
Type de document :
Article dans une revue
International Journal of Computer Vision, Springer Verlag, 2004, Special Issue on Content-Based Image Retrieval, 56 (1), pp.7--16. 〈http://springerlink.metapress.com/content/w2r28045h5164556/〉. 〈10.1023/B:VISI.0000004829.38247.b0〉
Liste complète des métadonnées

https://hal.inria.fr/inria-00548553
Contributeur : Thoth Team <>
Soumis le : lundi 20 décembre 2010 - 09:09:43
Dernière modification le : mercredi 11 avril 2018 - 01:57:01
Document(s) archivé(s) le : lundi 21 mars 2011 - 03:17:07

Fichier

schmid_ijcv2004.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Cordelia Schmid. Weakly supervised learning of visual models and its application to content-based retrieval. International Journal of Computer Vision, Springer Verlag, 2004, Special Issue on Content-Based Image Retrieval, 56 (1), pp.7--16. 〈http://springerlink.metapress.com/content/w2r28045h5164556/〉. 〈10.1023/B:VISI.0000004829.38247.b0〉. 〈inria-00548553〉

Partager

Métriques

Consultations de la notice

273

Téléchargements de fichiers

368