Copy the page URI to the clipboard
Choudhury, Smitashree and Breslin, John
(2008).
URL: http://www.johnbreslin.org/files/publications/2008...
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.