Semantic Hierarchies for Visual Object Recognition

Marcin Marszałek 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 propose to use lexical semantic networks to extend the state-of-the-art object recognition techniques. We use the semantics of image labels to integrate prior knowledge about inter-class relationships into the visual appearance learning. We show how to build and train a semantic hierarchy of discriminative classifiers and how to use it to perform object detection. We evaluate how our approach influences the classification accuracy and speed on the PASCAL VOC challenge 2006 dataset, a set of challenging real-world images. We also demonstrate additional features that become available to object recognition due to the extension with semantic inference tools - we can classify high-level categories, such as animals, and we can train part detectors, for example a window detector, by pure inference in the semantic network.
Type de document :
Communication dans un congrès
CVPR - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2007, Minneapolis, United States. IEEE Computer Society, pp.1-7, 2007, 〈http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4270297〉. 〈10.1109/CVPR.2007.383272〉
Liste complète des métadonnées


https://hal.inria.fr/inria-00548680
Contributeur : Thoth Team <>
Soumis le : lundi 20 décembre 2010 - 10:28:33
Dernière modification le : jeudi 11 janvier 2018 - 01:48:43
Document(s) archivé(s) le : lundi 21 mars 2011 - 03:31:57

Identifiants

Collections

Citation

Marcin Marszałek, Cordelia Schmid. Semantic Hierarchies for Visual Object Recognition. CVPR - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2007, Minneapolis, United States. IEEE Computer Society, pp.1-7, 2007, 〈http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4270297〉. 〈10.1109/CVPR.2007.383272〉. 〈inria-00548680〉

Partager

Métriques

Consultations de la notice

2096

Téléchargements de fichiers

3118