Please use this identifier to cite or link to this item:
|Title:||Integrated graph-based semi-supervised multiple/single instance learning framework for image annotation|
|Authors:||Tang, J. |
Multiple/single instance learning
|Source:||Tang, J.,Li, H.,Qi, G.-J.,Chua, T.-S. (2008). Integrated graph-based semi-supervised multiple/single instance learning framework for image annotation. MM'08 - Proceedings of the 2008 ACM International Conference on Multimedia, with co-located Symposium and Workshops : 631-634. ScholarBank@NUS Repository. https://doi.org/10.1145/1459359.1459446|
|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. Copyright 2008 ACM.|
|Source Title:||MM'08 - Proceedings of the 2008 ACM International Conference on Multimedia, with co-located Symposium and Workshops|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
checked on Jan 17, 2018
checked on Jan 21, 2018
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.