Region based image annotation through multiple-instance learning

Abstract

In an annotated image database, keywords are usually associated with images instead of individual regions, which poses a major challenge for any region based image annotation algorithm. In this paper, we propose to learn the correspondence between image regions and keywords through Multiple-Instance Learning (MIL). After a representative image region has been learned for a given keyword, we consider image annotation as a problem of image classification, in which each keyword is treated as a distinct class label. The classification problem is then addressed using the Bayesian framework. The proposed image annotation method is evaluated on an image database with 5,000 images.

DOI: 10.1145/1101149.1101245

Extracted Key Phrases

3 Figures and Tables

Statistics

051015'06'07'08'09'10'11'12'13'14'15'16'17
Citations per Year

92 Citations

Semantic Scholar estimates that this publication has 92 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@inproceedings{Yang2005RegionBI, title={Region based image annotation through multiple-instance learning}, author={Changbo Yang and Ming Dong and Farshad Fotouhi}, booktitle={ACM Multimedia}, year={2005} }