Vector quantizing feature space with a regular lattice

Tinne Tuytelaars 1 Cordelia Schmid 2
2 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : Most recent class-level object recognition systems work with visual words, i.e., vector quantized local descriptors. In this paper we examine the feasibility of a data- independent approach to construct such a visual vocabulary, where the feature space is discretized using a regular lattice. Using hashing techniques, only non-empty bins are stored, and fine-grained grids become possible in spite of the high dimensionality of typical feature spaces. Based on this representation, we can explore the structure of the feature space, and obtain state-of-the-art pixelwise classification results. In the case of image classification, we introduce a class-specific feature selection step, which takes the spatial structure of SIFT-like descriptors into account. Results are reported on the Graz02 dataset.
Type de document :
Communication dans un congrès
ICCV - 11th IEEE International Conference on Computer Vision, Oct 2007, Rio de Janeiro, Brazil. IEEE Computer Society, pp.1-8, 2007, 〈http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4408924〉. 〈10.1109/ICCV.2007.4408924〉
Liste complète des métadonnées

Littérature citée [26 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00548675
Contributeur : Thoth Team <>
Soumis le : lundi 20 décembre 2010 - 10:27:13
Dernière modification le : mercredi 11 avril 2018 - 01:57:54
Document(s) archivé(s) le : lundi 5 novembre 2012 - 14:40:56

Fichier

Tuytelaars_Schmid-lattice-iccv...
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Tinne Tuytelaars, Cordelia Schmid. Vector quantizing feature space with a regular lattice. ICCV - 11th IEEE International Conference on Computer Vision, Oct 2007, Rio de Janeiro, Brazil. IEEE Computer Society, pp.1-8, 2007, 〈http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4408924〉. 〈10.1109/ICCV.2007.4408924〉. 〈inria-00548675〉

Partager

Métriques

Consultations de la notice

392

Téléchargements de fichiers

360