Learning Object Representations for Visual Object Class Recognition

Marcin Marszałek 1 Cordelia Schmid 1 Hedi Harzallah 1 Joost Van de Weijer 1
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : This talk discussed our object-class recognition method that won the classification contest of the Pascal VOC Challenge 2007. We submitted two recognition methods sharing the same underlying image representations defined by a choice of image sampler, local descriptor and global spatial grid. The submitted methods also share the classifier, which is a one-against-rest non-linear Support Vector Machine with chi-square kernel. The methods differ in the way they combine multiple representations (channels). The first method is based on the approach of Zhang et al., where the final similarity measure is the sum of per-channel similarities. The second method employs a genetic algorithm, which is used to determine (on per-class basis) the parameters of the generalized RBF kernel incorporating all the channels, i.e., to estimate the importance of each sampling/description/spatial method for the recognition and to optimize the required level of generalization. Both methods showed superior performance compared to other state-of-the-art submissions.
Keywords : LEAR
Type de document :
Document associé à des manifestations scientifiques
Visual Recognition Challange workshop, in conjunction with ICCV, Oct 2007, Rio de Janeiro, Brazil. 2007
Liste complète des métadonnées

https://hal.inria.fr/inria-00548669
Contributeur : Thoth Team <>
Soumis le : lundi 20 décembre 2010 - 10:26:16
Dernière modification le : mercredi 11 avril 2018 - 01:57:55
Document(s) archivé(s) le : lundi 21 mars 2011 - 03:30:35

Fichier

MarszalekSchmid-VOC07-Learning...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00548669, version 1

Collections

Citation

Marcin Marszałek, Cordelia Schmid, Hedi Harzallah, Joost Van de Weijer. Learning Object Representations for Visual Object Class Recognition. Visual Recognition Challange workshop, in conjunction with ICCV, Oct 2007, Rio de Janeiro, Brazil. 2007. 〈inria-00548669〉

Partager

Métriques

Consultations de la notice

980

Téléchargements de fichiers

805