Exploiting Captions for Multimedia Data Mining / Chapter in Encyclopedia of Multimedia Technology and Networking
Rowe, Neil C.
MetadataShow full item record
Captions are essential accompaniments to multimedia data objects as a way to facilitate their data mining. This article describes the kinds of possible captions and the task of recognizing them. It then discusses the forms of the caption-object relationship and the ways in which components of the two can be matched. Automatic generation of captions is also discussed. While no breakthroughs are expected on this subject, captioned multimedia will become increasingly important in future systems as increases in processing speeds enable it to be more easily used.
This is a chapter in the Encyclopedia of Multimedia Technology and Networking, ed. M. Pagani, Hershey, PA: The Idea Group, 2005.
Showing items related by title, author, creator and subject.
Retrieving Captioned Pictures Using Statistical Correlations and a Theory of Caption-Picture Co-reference Rowe, Neil C. (Monterey, California. Naval Postgraduate School, 1995-04);The MARIE project is investigating new methods for efficient information retrieval of captioned multimedia from multimedia libraries. Captions are essential to understanding multimedia and to finding relevant examples ...
Rowe, Neil C. (Monterey, California. Naval Postgraduate School, 2004-06);The easiest way to index multimedia from ordinary Web pages is to find their captions. However, captions are not used consistently, and retrieval effectiveness for caption-based multimedia browsers is significantly poorer ...
Rowe, Neil C.; Guglielmo, Eugene J. (Monterey, California. Naval Postgraduate School, 1992-07); NPS-CS-92-011Descriptive natural-language captions can help organize multimedia data. We described our MARIE system that interprets English queries directing the fetch of media objects. it is novel in the extent to which it exploits ...