Hierarchical Part-Based Visual Object Categorization

Guillaume Bouchard 1 Bill Triggs 2
2 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 : We propose a generative model that codes the geometry and appearance of generic visual object categories as a loose hierarchy of parts, with probabilistic spatial relations linking parts to subparts, soft assignment of subparts to parts, and scale invariant keypoint based local features at the lowest level of the hierarchy. The method is designed to efficiently handle categories containing hundreds of redundant local features, such as those returned by current key-point detectors. This robustness allows it to outperform constellation style models, despite their stronger spatial models. The model is initialized by robust bottom-up voting over location-scale pyramids, and optimized by expectation-maximization. Training is rapid, and objects do not need to be marked in the training images. Experiments on several popular datasets show the method's ability to capture complex natural object classes.
Type de document :
Communication dans un congrès
Cordelia Schmid and Stefano Soatto and Carlo Tomasi. IEEE Conference on Computer Vision & Pattern Recognition (CPRV '05), Jun 2005, San Diego, United States. IEEE Computer Society, 1, pp.710--715, 2005, 〈http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1467338〉. 〈10.1109/CVPR.2005.174〉
Liste complète des métadonnées

Littérature citée [12 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00548513
Contributeur : Thoth Team <>
Soumis le : lundi 20 décembre 2010 - 09:08:38
Dernière modification le : mercredi 11 avril 2018 - 01:53:37
Document(s) archivé(s) le : lundi 21 mars 2011 - 03:07:51

Fichier

Bouchard-cvpr05.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

IMAG | INRIA | UGA

Citation

Guillaume Bouchard, Bill Triggs. Hierarchical Part-Based Visual Object Categorization. Cordelia Schmid and Stefano Soatto and Carlo Tomasi. IEEE Conference on Computer Vision & Pattern Recognition (CPRV '05), Jun 2005, San Diego, United States. IEEE Computer Society, 1, pp.710--715, 2005, 〈http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1467338〉. 〈10.1109/CVPR.2005.174〉. 〈inria-00548513〉

Partager

Métriques

Consultations de la notice

300

Téléchargements de fichiers

426