A Unified, Modular and Multimodal Approach to Search and Hyperlinking Video
A Unified, Modular and Multimodal Approach to Search and Hyperlinking Video
This paper describes a modular architecture for searching and hyperlinking clips of TV programmes. The architecture aimed to unify the combination of features from different modalities through a common representation based on a set of probability density functions over the timeline of a programme. The core component of the system consisted of analysis of sections of transcripts based on a textual query. Results show that search is made worse by the addition of other components, whereas in hyperlinking precision is increased by the addition of visual features.
Preston, John
b0d0c588-e023-47dc-bc4a-30bc6bd6a412
Hare, Jonathon
65ba2cda-eaaf-4767-a325-cd845504e5a9
Samangooei, Sina
c380fb26-55d4-4b34-94e7-c92bbb26a40d
Davies, Jamie
e5eff020-453a-4812-9f3c-fbbed7dd3531
Jain, Neha
3f334678-726a-4db8-98c3-a11ee0d30b24
Dupplaw, David
c563ca2b-756a-4d3f-bf99-4f60bb2be1ce
Lewis, Paul H.
7aa6c6d9-bc69-4e19-b2ac-a6e20558c020
Preston, John
b0d0c588-e023-47dc-bc4a-30bc6bd6a412
Hare, Jonathon
65ba2cda-eaaf-4767-a325-cd845504e5a9
Samangooei, Sina
c380fb26-55d4-4b34-94e7-c92bbb26a40d
Davies, Jamie
e5eff020-453a-4812-9f3c-fbbed7dd3531
Jain, Neha
3f334678-726a-4db8-98c3-a11ee0d30b24
Dupplaw, David
c563ca2b-756a-4d3f-bf99-4f60bb2be1ce
Lewis, Paul H.
7aa6c6d9-bc69-4e19-b2ac-a6e20558c020
Preston, John, Hare, Jonathon, Samangooei, Sina, Davies, Jamie, Jain, Neha, Dupplaw, David and Lewis, Paul H.
(2013)
A Unified, Modular and Multimodal Approach to Search and Hyperlinking Video.
MediaEval 2013 / Search and Hyperlinking of Television Content, Barcelona, Spain.
(In Press)
Record type:
Conference or Workshop Item
(Paper)
Abstract
This paper describes a modular architecture for searching and hyperlinking clips of TV programmes. The architecture aimed to unify the combination of features from different modalities through a common representation based on a set of probability density functions over the timeline of a programme. The core component of the system consisted of analysis of sections of transcripts based on a textual query. Results show that search is made worse by the addition of other components, whereas in hyperlinking precision is increased by the addition of visual features.
Text
searchhyper.pdf
- Version of Record
Text
Mediaeval-Search.pdf
- Other
Text
searchhyper-1slide.pdf
- Other
More information
Accepted/In Press date: 18 October 2013
Venue - Dates:
MediaEval 2013 / Search and Hyperlinking of Television Content, Barcelona, Spain, 2013-10-18
Organisations:
Web & Internet Science
Identifiers
Local EPrints ID: 358838
URI: http://eprints.soton.ac.uk/id/eprint/358838
PURE UUID: 0181b9c7-9c97-40a1-9938-b7a6c89a54af
Catalogue record
Date deposited: 21 Oct 2013 09:11
Last modified: 15 Mar 2024 03:25
Export record
Contributors
Author:
John Preston
Author:
Jonathon Hare
Author:
Sina Samangooei
Author:
Jamie Davies
Author:
Neha Jain
Author:
David Dupplaw
Author:
Paul H. Lewis
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