Latent mixture vocabularies for object categorization and segmentation - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Article Dans Une Revue Image and Vision Computing Année : 2009

Latent mixture vocabularies for object categorization and segmentation

Résumé

The visual vocabulary is an intermediate level representation which has been proved to be very powerful for addressing object categorization problems. It is generally built by vector quantizing a set of local image descriptors, independently of the object model used for categorizing images. We propose here to embed the visual vocabulary creation within the object model construction, allowing to make it more suited for object class discrimination and therefore for object categorization. We also show that the model can be adapted to perform object level segmentation task, without needing any shape model, making the approach very adapted to high intra-class varying objects.
Fichier principal
Vignette du fichier
ivcj.pdf (1.43 Mo) Télécharger le fichier
Vignette du fichier
vocabulary.png (630.56 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Format : Figure, Image
Loading...

Dates et versions

inria-00548649 , version 1 (27-04-2011)

Identifiants

Citer

Diane Larlus, Frédéric Jurie. Latent mixture vocabularies for object categorization and segmentation. Image and Vision Computing, 2009, The 17th British Machine Vision Conference (BMVC 2006), 27 (5), pp.523-534. ⟨10.1016/j.imavis.2008.04.022⟩. ⟨inria-00548649⟩
447 Consultations
580 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More