Using a lightweight multimedia content model for semantic annotation

Choudhury, Smitashree and Breslin, John (2008). Using a lightweight multimedia content model for semantic annotation. In: The 8th International Conference on Information Technology and Telecommunication (IT&T 2008), 23-24 Oct 2008, Galway, Ireland.

Full text available as:

Preview

PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Download (994kB)

URL:	http://www.johnbreslin.org/files/publications/2008...
Google Scholar:	Look up in Google Scholar

Abstract

In this paper we discuss the use of a multimedia content model for automatic extraction of semantic metadata from multimedia content. We developed a modular and extensible framework to model the content feature of multimedia data and also describe the way it can be integrated with other existing vocabularies. The goal of this model is to generate sufficient understanding of media content, its context and its relation to domain knowledge in order to perform multimedia reasoning. We implemented a tool that analyzes and links low-level descriptions to higher-level domain specific semantic concepts by means of statistical learning and clustering analysis. Experimental result shows the approach performs well in visual concept prediction in the image which can be further augmented with other information sources such as context text and or audio source.

Item Type:	Conference or Workshop Item
Copyright Holders:	2008 The Authors
Keywords:	ontology; multimedia annotation; semantic web; image annotation; concept learning
Academic Unit/School:	Faculty of Science, Technology, Engineering and Mathematics (STEM) > Knowledge Media Institute (KMi) Faculty of Science, Technology, Engineering and Mathematics (STEM)
Related URLs:	http://ittconference.ie/uploads/conferen...(Other)
Item ID:	32450
Depositing User:	Smitashree Choudhury
Date Deposited:	06 Feb 2012 14:01
Last Modified:	07 Dec 2018 18:16
URI:	http://oro.open.ac.uk/id/eprint/32450
Share this page:

Download history for this item

These details should be considered as only a guide to the number of downloads performed manually. Algorithmic methods have been applied in an attempt to remove automated downloads from the displayed statistics but no guarantee can be made as to the accuracy of the figures.

Actions (login may be required)

CORE (COnnecting REpositories)

Policies | Disclaimer