Combining efficient object localization and image classification

Hedi Harzallah 1 Frédéric Jurie 1 Cordelia Schmid 1
1 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 a combined approach for object localization and classification. Our contribution is two-fold. (a) A contextual combination of localization and classification which shows that classification can improve detection and vice versa. (b) An efficient two stage sliding window object localization method that combines the efficiency of a linear classifier with the robustness of a sophisticated non-linear one. Experimental results evaluate the parameters of our two stage sliding window approach and show that our combined object localization and classification methods outperform the state-of-the-art on the PASCAL VOC 2007 and 2008 datasets.
Keywords : LEAR Computer vision Object localization Object detection
Type de document :
Communication dans un congrès
ICCV 2009 - 12th International Conference on Computer Vision, Sep 2009, Kyoto, Japan. IEEE, pp.237-244, 2009, <10.1109/ICCV.2009.5459257>
Liste complète des métadonnées

https://hal.inria.fr/inria-00439516
Contributeur : Hedi Harzallah <>
Soumis le : lundi 7 décembre 2009 - 16:59:52
Dernière modification le : mercredi 29 juillet 2015 - 01:22:12
Document(s) archivé(s) le : jeudi 18 octobre 2012 - 10:10:37

Fichiers

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

Identifiants

Collections

INRIA | GRID5000 | LJK_GI | LJK | LJK_GI_LEAR | UGA

Citation

Hedi Harzallah, Frédéric Jurie, Cordelia Schmid. Combining efficient object localization and image classification. ICCV 2009 - 12th International Conference on Computer Vision, Sep 2009, Kyoto, Japan. IEEE, pp.237-244, 2009, <10.1109/ICCV.2009.5459257>. <inria-00439516>

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de
la notice

667

Téléchargements du document

657

Contact


archive-ouverte@inria.fr