Latent mixture vocabularies for object categorization

D. Larlus (1) , Frédéric Jurie (1)

1 LEAR - Learning and recognition in vision

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.

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]

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⟩