Latent mixture vocabularies for object categorization and segmentation

Diane Larlus 1 Frédéric Jurie 1, 2
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
2 Equipe Image - Laboratoire GREYC - UMR6072
GREYC - Groupe de Recherche en Informatique, Image, Automatique et Instrumentation de Caen
Abstract : 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.
Document type :
Journal articles
Complete list of metadatas

Cited literature [23 references]  Display  Hide  Download


https://hal.inria.fr/inria-00548649
Contributor : Thoth Team <>
Submitted on : Wednesday, April 27, 2011 - 1:26:45 PM
Last modification on : Thursday, February 7, 2019 - 5:47:17 PM
Long-term archiving on : Thursday, July 28, 2011 - 2:26:31 AM

Files

ivcj.pdf
Files produced by the author(s)

Identifiers

Citation

Diane Larlus, Frédéric Jurie. Latent mixture vocabularies for object categorization and segmentation. Image and Vision Computing, Elsevier, 2009, The 17th British Machine Vision Conference (BMVC 2006), 27 (5), pp.523-534. ⟨http://resolver.scholarsportal.info/resolve/doi/10.1016/j.imavis.2008.04.022⟩. ⟨10.1016/j.imavis.2008.04.022⟩. ⟨inria-00548649⟩

Share

Metrics

Record views

734

Files downloads

955