Please use this identifier to cite or link to this item: https://scholarbank.nus.edu.sg/handle/10635/41100
DC FieldValue
dc.titleStory boundary detection in large broadcast news video archives - Techniques, experience and trends
dc.contributor.authorChua, T.-S.
dc.contributor.authorChang, S.-F.
dc.contributor.authorChaisorn, L.
dc.contributor.authorHsu, W.
dc.date.accessioned2013-07-04T08:19:37Z
dc.date.available2013-07-04T08:19:37Z
dc.date.issued2004
dc.identifier.citationChua, T.-S.,Chang, S.-F.,Chaisorn, L.,Hsu, W. (2004). Story boundary detection in large broadcast news video archives - Techniques, experience and trends. ACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia : 656-659. ScholarBank@NUS Repository.
dc.identifier.isbn1581138938
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/41100
dc.description.abstractThe segmentation of news video into story units is an important step towards effective processing and management of large news video archives. In the story segmentation task in TRECVID 2003, a wide variety of techniques were employed by many research groups to segment over 120-hour of news video. The techniques employed range from simple anchor person detector to sophisticated machine learning models based on HMM and Maximum Entropy (ME) approaches. The general results indicate that the judicious use of multi-modality features coupled with rigorous machine learning models could produce effective solutions. This paper presents the algorithms and experience learned in TRECVID evaluations. It also points the way towards the development of scalable technology to process large news video corpuses.
dc.sourceScopus
dc.subjectMachine learning techniques
dc.subjectNews video
dc.subjectStory segmentation
dc.typeConference Paper
dc.contributor.departmentCOMPUTER SCIENCE
dc.description.sourcetitleACM Multimedia 2004 - proceedings of the 12th ACM International Conference on Multimedia
dc.description.page656-659
dc.identifier.isiutNOT_IN_WOS
Appears in Collections:Staff Publications

Show simple item record
Files in This Item:
There are no files associated with this item.

Page view(s)

132
checked on May 5, 2021

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.