Published 2005
| public
Book Section - Chapter
A Bayesian Hierarchical Model for Learning Natural Scene Categories
- Creators
- Li, Fei-Fei
-
Perona, Pietro
Abstract
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.
Additional Information
© 2005 IEEE. Issue Date: 20-25 June 2005. Date of Current Version: 25 July 2005. We would like to thank Chris Bishop, Tom Minka, Silvio Savarese and Max Welling for helpful discussions. We also thank Aude Oliva and Michael Fink for providing parts of the dataset.Additional details
- Eprint ID
- 24762
- Resolver ID
- CaltechAUTHORS:20110809-110622441
- Created
-
2011-09-12Created from EPrint's datestamp field
- Updated
-
2021-11-09Created from EPrint's last_modified field
- Series Name
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition
- Other Numbering System Name
- INSPEC Accession Number
- Other Numbering System Identifier
- 8624081