Learning Tree-structured Descriptor Quantizers for Image Categorization - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2011

Learning Tree-structured Descriptor Quantizers for Image Categorization

Abstract

Current state-of-the-art image categorization systems rely on bag-of-words representations that model image content as a histogram of quantization indices that code local image appearance. In this context, randomized tree-structured quantizers have been shown to be both computationally efficient and yielding discriminative visual words for a given categorization task. This paper presents a new algorithm that builds tree-structured quantizers not to optimize patch classification but to directly optimize the image classification performance. This approach is experimentally validated on several challenging data sets for which it outperforms other patch quantizers such as standard decision trees or k-means.
Fichier principal
Vignette du fichier
paper.pdf (116.97 Ko) Télécharger le fichier
Vignette du fichier
Screenshot.png (46.52 Ko) Télécharger le fichier
Origin : Publisher files allowed on an open archive
Format : Figure, Image
Loading...

Dates and versions

inria-00613118 , version 1 (02-08-2011)

Identifiers

Cite

Josip Krapac, Jakob Verbeek, Frédéric Jurie. Learning Tree-structured Descriptor Quantizers for Image Categorization. BMVC 2011 - British Machine Vision Conference, Aug 2011, Dundee, United Kingdom. pp.47.1-47.11, ⟨10.5244/C.25.47⟩. ⟨inria-00613118⟩
509 View
533 Download

Altmetric

Share

Gmail Facebook X LinkedIn More