Graph commute times for image representation

Abstract : We introduce a new image representation that encompasses both the general layout of groups of quantized local invariant descriptors as well as their relative frequency. A graph of interest points clusters is constructed and we use the matrix of commute times between the different nodes of the graph to obtain a description of their relative arrangement that is robust to large intra class variation. The obtained high dimensional representation is then embedded in a space of lower dimension by exploiting the spectral properties of the graph made of the different images. Classification tasks can be performed in this embedding space. We expose classification and labelling results obtained on three different datasets, including the challenging PASCAL VOC2007 dataset. The performances of our approach compare favorably with the standard bag of features, which is a particular case of our representation.
Type de document :
Communication dans un congrès
CVPR 2008 - Computer Vision and Pattern Recognition, Jun 2008, Anchorage, AK, United States. IEEE, pp.1-8, 2008, 〈10.1109/CVPR.2008.4587840〉
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-00918707
Contributeur : Enzo Ferrante <>
Soumis le : samedi 14 décembre 2013 - 11:49:34
Dernière modification le : mardi 5 février 2019 - 13:52:14

Lien texte intégral

Identifiants

Collections

Citation

Régis Behmo, Nikos Paragios, Veronique Prinet. Graph commute times for image representation. CVPR 2008 - Computer Vision and Pattern Recognition, Jun 2008, Anchorage, AK, United States. IEEE, pp.1-8, 2008, 〈10.1109/CVPR.2008.4587840〉. 〈hal-00918707〉

Partager

Métriques

Consultations de la notice

369