Get 20M+ Full-Text Papers For Less Than $1.50/day. Subscribe now for You or Your Team.

Learn More →

Tagging over time: real-world image annotation by lightweight meta-learning

Tagging over time: real-world image annotation by lightweight meta-learning Tagging over Time: Real-world Image Annotation by Lightweight Meta-learning Ritendra Datta, Dhiraj Joshi, Jia Li, and James Z. Wang The Pennsylvania State University, University Park, PA 16802, USA {datta, djoshi, jiali, jwang}@psu.edu ABSTRACT Automatic image annotation has been a hot-pursuit among multimedia researchers of late. Modest performance guarantees and limited adaptability often restrict its applicability to real-world settings. We propose tagging over time (T/T) to push the technology toward real-world applicability. Of particular interest are online systems that receive user-provided images and feedback over time, with user focus possibly changing and evolving. The T/T framework consists of a principled probabilistic approach to metalearning, which acts as a go-between for a ˜black-box ™ annotation system and the users. Inspired by inductive transfer, the approach attempts to harness available information, including the black-box model ™s performance, the image representations, and the WordNet ontology. Being computationally ˜lightweight ™, this meta-learner e ƒciently re-trains over time, to improve and/or adapt to changes. The black-box annotation model is not required to be re-trained, allowing computationally intensive algorithms to be used. We experiment with standard image datasets and real-world data streams, using two existing annotation systems as blackboxes. Both batch and online annotation settings http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png

Tagging over time: real-world image annotation by lightweight meta-learning

Association for Computing Machinery — Sep 29, 2007

Loading next page...
/lp/association-for-computing-machinery/tagging-over-time-real-world-image-annotation-by-lightweight-meta-WLKTAlD00r

References (25)

Datasource
Association for Computing Machinery
Copyright
Copyright © 2007 by ACM Inc.
ISBN
978-1-59593-702-5
doi
10.1145/1291233.1291328
Publisher site
See Article on Publisher Site

Abstract

Tagging over Time: Real-world Image Annotation by Lightweight Meta-learning Ritendra Datta, Dhiraj Joshi, Jia Li, and James Z. Wang The Pennsylvania State University, University Park, PA 16802, USA {datta, djoshi, jiali, jwang}@psu.edu ABSTRACT Automatic image annotation has been a hot-pursuit among multimedia researchers of late. Modest performance guarantees and limited adaptability often restrict its applicability to real-world settings. We propose tagging over time (T/T) to push the technology toward real-world applicability. Of particular interest are online systems that receive user-provided images and feedback over time, with user focus possibly changing and evolving. The T/T framework consists of a principled probabilistic approach to metalearning, which acts as a go-between for a ˜black-box ™ annotation system and the users. Inspired by inductive transfer, the approach attempts to harness available information, including the black-box model ™s performance, the image representations, and the WordNet ontology. Being computationally ˜lightweight ™, this meta-learner e ƒciently re-trains over time, to improve and/or adapt to changes. The black-box annotation model is not required to be re-trained, allowing computationally intensive algorithms to be used. We experiment with standard image datasets and real-world data streams, using two existing annotation systems as blackboxes. Both batch and online annotation settings

There are no references for this article.