Latent mixture vocabularies for object categorization - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2006

Latent mixture vocabularies for object categorization

D. Larlus
  • Function : Author
Learning and recognition in vision
Frédéric Jurie
Learning and recognition in vision
CV

Abstract

The visual vocabulary is an intermediate level representation which has been proven 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.

Domains

Signal and Image processing Signal and Image Processing
Fichier principal
Vignette du fichier
bmvc06.pdf (593.53 Ko) Télécharger le fichier
Vignette du fichier
modele_ldavoc.png (354.22 Ko) Télécharger le fichier
Origin : Publisher files allowed on an open archive
Format : Figure, Image

HAL System  : Connect in order to contact the contributor

https://hal.science/hal-00203721

Submitted on : Friday, January 18, 2008-10:56:43 AM

Last modification on : Thursday, April 4, 2024-6:25:48 PM

Long-term archiving on: Thursday, September 27, 2012-2:05:22 PM

Download

Dates and versions

hal-00203721 , version 1 (18-01-2008)

Identifiers

  • HAL Id : hal-00203721 , version 1

Cite

D. Larlus, Frédéric Jurie. Latent mixture vocabularies for object categorization. The 17th British Machine Vision Conference (BVMC '06), Sep 2006, Edinburgh, United Kingdom. pp.959-968. ⟨hal-00203721⟩

Export

BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite

Collections

UGA IMAG CNRS INRIA INRIA2
225 View
505 Download

Share

Gmail Facebook X LinkedIn More