Sciweavers

Share
CVPR
2005
IEEE

A Bayesian Hierarchical Model for Learning Natural Scene Categories

11 years 18 days ago
A Bayesian Hierarchical Model for Learning Natural Scene Categories
We propose a novel approach to learn and recognize natural scene categories. Unlike previous work [9, 17], it does not require experts to annotate the training set. We represent the image of a scene by a collection of local regions, denoted as codewords obtained by unsupervised learning. Each region is represented as part of a "theme". In previous work, such themes were learnt from hand-annotations of experts, while our method learns the theme distributions as well as the codewords distribution over the themes without supervision. We report satisfactory categorization performances on a large set of 13 categories of complex scenes.
Fei-Fei Li 0002, Pietro Perona, California Institu
Added 12 Oct 2009
Updated 12 Oct 2009
Type Conference
Year 2005
Where CVPR
Authors Fei-Fei Li 0002, Pietro Perona, California Institute of Technology
Comments (0)
books