Spatial Weighting for Bag-of-Features

Marcin Marszałek 1 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 an extension to category classification with bag-of-features, which represents an image as an orderless distribution of features. We propose a method to exploit spatial relations between features by utilizing object boundaries provided during supervised training. We boost the weights of features that agree on the position and shape of the object and suppress the weights of background features, hence the name of our method - "spatial weighting". The proposed representation is thus richer and more robust to background clutter. Experimental results show that our approach improves the results of one of the best current image classification techniques. Furthermore, we propose to apply the spatial model to object localization. Initial results are promising.
Type de document :
Communication dans un congrès
IEEE Conference on Computer Vision & Pattern Recognition (CPRV '06), Jun 2006, New York, United States. IEEE Computer Society, 2, pp.2118--2125, 2006, 〈http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1641013〉. 〈10.1109/CVPR.2006.288〉
Liste complète des métadonnées


https://hal.inria.fr/inria-00548584
Contributeur : Thoth Team <>
Soumis le : lundi 20 décembre 2010 - 09:49:25
Dernière modification le : jeudi 11 janvier 2018 - 06:20:04
Document(s) archivé(s) le : lundi 21 mars 2011 - 03:20:35

Identifiants

Collections

IMAG | INRIA | UGA

Citation

Marcin Marszałek, Cordelia Schmid. Spatial Weighting for Bag-of-Features. IEEE Conference on Computer Vision & Pattern Recognition (CPRV '06), Jun 2006, New York, United States. IEEE Computer Society, 2, pp.2118--2125, 2006, 〈http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1641013〉. 〈10.1109/CVPR.2006.288〉. 〈inria-00548584〉

Partager

Métriques

Consultations de la notice

236

Téléchargements de fichiers

441