Integrated graph-based semi-supervised multiple/single instance learning framework for image annotation

Jinhui Tang, Haojie Li, Guo-Jun Qi, Tat-Seng Chua

Abstract

Recently, many learning methods based on multiple-instance (local) or single-instance (global) representations of images have been proposed for image annotation. Their performances on image annotation, however, are mixed as for certain concepts the single-instance representations of images are more suitable, while for some other concepts the multiple-instance representations are better. Thus in this paper, we explore an unified learning framework that combines the multiple-instance and single-instance representations for image annotation. More specifically, we propose an integrated graph-based semi-supervised learning framework to utilize these two types of representations simultaneously, and explore an effective and computationally efficient strategy to convert the multiple-instance representation into a single-instance one. Experiments conducted on the Coral image dataset show the effectiveness and efficiency of the proposed integrated framework.
BibTeX
@inproceedings{tang2008integrated,
  author = {Jinhui Tang and Haojie Li and Guo-Jun Qi and Tat-Seng Chua},
  title = {{Integrated graph-based semi-supervised multiple/single instance learning framework for image annotation}},
  booktitle = {ACM Multimedia},
  year = {2008},
  doi = {10.1145/1459359.1459446},
}

Loading related content...

Figure