1. ScholarBank@NUS
  2. 1. Staff
  3. Staff Publications
Please use this identifier to cite or link to this item: https://doi.org/10.1109/ICME.2006.262649
DC FieldValue
dc.titleStory boundary detection in news video using global rule induction technique
dc.contributor.authorChaisorn, L.
dc.contributor.authorChua, T.-S.
dc.date.accessioned2013-07-04T08:26:25Z
dc.date.available2013-07-04T08:26:25Z
dc.date.issued2006
dc.identifier.citationChaisorn, L., Chua, T.-S. (2006). Story boundary detection in news video using global rule induction technique. 2006 IEEE International Conference on Multimedia and Expo, ICME 2006 - Proceedings 2006 : 2101-2104. ScholarBank@NUS Repository. https://doi.org/10.1109/ICME.2006.262649
dc.identifier.isbn1424403677
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/41390
dc.description.abstractGlobal rule induction technique has been successfully used in information extraction (IE) from text documents. In this paper, we employ the technique to identify story boundaries in news video. We divide our framework into two levels: shot and story levels. We use a hybrid algorithm to classify each input video shot into one of the predefined genre types and employ the global rule induction technique to extract story boundaries from the sequence of classified shots. We evaluate our rule induction based system on ∼120-hours of news video provided by TRECVID 2003. The results show that we could achieve an F 1 accuracy of over 75%. © 2006 IEEE.
dc.description.urihttp://libproxy1.nus.edu.sg/login?url=http://dx.doi.org/10.1109/ICME.2006.262649
dc.sourceScopus
dc.typeConference Paper
dc.contributor.departmentCOMPUTER SCIENCE
dc.description.doi10.1109/ICME.2006.262649
dc.description.sourcetitle2006 IEEE International Conference on Multimedia and Expo, ICME 2006 - Proceedings
dc.description.volume2006
dc.description.page2101-2104
dc.identifier.isiut000245384804087
Appears in Collections:Staff Publications

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

Google ScholarTM

Check

Altmetric


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