Automating the Linking of Content and Concept
Automating the Linking of Content and Concept
In previous work we have described a multimedia system, MAVIS 2, supporting content and concept based retrieval and navigation. A central component of the system is a multimedia thesaurus in which media content is associated with appropriate concepts in a semantic layer. A major challenge is identifying and constructing these associations in a particular application without requiring a huge amount of manual effort. In this paper we propose a two phase approach to the problem. In the first phase, latent semantic analysis is used to associate metadata available for some media objects with concept class descriptions. This facilitates automatic associations to be made with the concept layer for those media objects. In the second phase, media content matching is used to classify media objects without metadata through their similarity to media objects classified in phase 1.
0-201-48566-4
445-448
Tansley, Robert
56b8abed-e61b-4714-bb64-cdfed08b8b54
Bird, Colin
5880b548-6b24-4ae5-8b56-acced401f3e4
Hall, Wendy
11f7f8db-854c-4481-b1ae-721a51d8790c
Lewis, Paul
7aa6c6d9-bc69-4e19-b2ac-a6e20558c020
Weal, Mark
e8fd30a6-c060-41c5-b388-ca52c81032a4
2000
Tansley, Robert
56b8abed-e61b-4714-bb64-cdfed08b8b54
Bird, Colin
5880b548-6b24-4ae5-8b56-acced401f3e4
Hall, Wendy
11f7f8db-854c-4481-b1ae-721a51d8790c
Lewis, Paul
7aa6c6d9-bc69-4e19-b2ac-a6e20558c020
Weal, Mark
e8fd30a6-c060-41c5-b388-ca52c81032a4
Tansley, Robert, Bird, Colin, Hall, Wendy, Lewis, Paul and Weal, Mark
(2000)
Automating the Linking of Content and Concept.
Proceedings ACM Multimedia 2000.
.
Record type:
Conference or Workshop Item
(Other)
Abstract
In previous work we have described a multimedia system, MAVIS 2, supporting content and concept based retrieval and navigation. A central component of the system is a multimedia thesaurus in which media content is associated with appropriate concepts in a semantic layer. A major challenge is identifying and constructing these associations in a particular application without requiring a huge amount of manual effort. In this paper we propose a two phase approach to the problem. In the first phase, latent semantic analysis is used to associate metadata available for some media objects with concept class descriptions. This facilitates automatic associations to be made with the concept layer for those media objects. In the second phase, media content matching is used to classify media objects without metadata through their similarity to media objects classified in phase 1.
Other
mm2000-poster.vsd
- Other
Image
tansley_fig1.gif
- Other
Text
tansley.html
- Other
Archive
mm2000.ps.gz
- Other
Show all 6 downloads.
More information
Published date: 2000
Additional Information:
Address: New York
Venue - Dates:
Proceedings ACM Multimedia 2000, 2000-01-01
Organisations:
Web & Internet Science
Identifiers
Local EPrints ID: 254205
URI: http://eprints.soton.ac.uk/id/eprint/254205
ISBN: 0-201-48566-4
PURE UUID: 62cd5a0a-5180-4201-9d9c-9784f3ac09c2
Catalogue record
Date deposited: 17 May 2001
Last modified: 15 Mar 2024 02:46
Export record
Contributors
Author:
Robert Tansley
Author:
Colin Bird
Author:
Paul Lewis
Author:
Mark Weal
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
