File Download
 
Links for fulltext
(May Require Subscription)
 
Supplementary

Article: Automated Video Segmentation for Lecture Videos: A Linguistics-based Approach
  • Basic View
  • Metadata View
  • XML View
TitleAutomated Video Segmentation for Lecture Videos: A Linguistics-based Approach
 
AuthorsLin, M
Chau, M
Cao, J
Nunamaker, JF
 
KeywordsComputational linguistics
Lecture video
Multimedia application
Video segmentation
 
Issue Date2005
 
PublisherIdea Group Publishing. The Journal's web site is located at http://www.idea-group.com/journals/details.asp?id=4290
 
CitationInternational Journal of Technology and Human Interaction, 2005, v. 1 n. 2, p. 27-45 [How to Cite?]
DOI: http://dx.doi.org/10.4018/jthi.2005040102
 
AbstractVideo, a rich information source, is commonly used for capturing and sharing knowledge in learning systems. However, the unstructured and linear features of video introduce difficulties for end users in accessing the knowledge captured in videos. To extract the knowledge structures hidden in a lengthy, multi-topic lecture video and thus make it easily accessible, we need to first segment the video into shorter clips by topic. Because of the high cost of manual segmentation, automated segmentation is highly desired. However, current automated video segmentation methods mainly rely on scene and shot change detection, which are not suitable for lecture videos with few scene/shot changes and unclear topic boundaries. In this article we investigate a new video segmentation approach with high performance on this special type of video: lecture videos. This approach uses natural language processing techniques such as noun phrases extraction, and utilizes lexical knowledge sources such as WordNet. Multiple linguisticbased segmentation features are used, including content-based features such as noun phrases and discourse-based features such as cue phrases. Our evaluation results indicate that the noun phrases feature is salient.
 
ISSN1548-3908
 
DOIhttp://dx.doi.org/10.4018/jthi.2005040102
 
DC FieldValue
dc.contributor.authorLin, M
 
dc.contributor.authorChau, M
 
dc.contributor.authorCao, J
 
dc.contributor.authorNunamaker, JF
 
dc.date.accessioned2010-09-06T09:11:21Z
 
dc.date.available2010-09-06T09:11:21Z
 
dc.date.issued2005
 
dc.description.abstractVideo, a rich information source, is commonly used for capturing and sharing knowledge in learning systems. However, the unstructured and linear features of video introduce difficulties for end users in accessing the knowledge captured in videos. To extract the knowledge structures hidden in a lengthy, multi-topic lecture video and thus make it easily accessible, we need to first segment the video into shorter clips by topic. Because of the high cost of manual segmentation, automated segmentation is highly desired. However, current automated video segmentation methods mainly rely on scene and shot change detection, which are not suitable for lecture videos with few scene/shot changes and unclear topic boundaries. In this article we investigate a new video segmentation approach with high performance on this special type of video: lecture videos. This approach uses natural language processing techniques such as noun phrases extraction, and utilizes lexical knowledge sources such as WordNet. Multiple linguisticbased segmentation features are used, including content-based features such as noun phrases and discourse-based features such as cue phrases. Our evaluation results indicate that the noun phrases feature is salient.
 
dc.identifier.citationInternational Journal of Technology and Human Interaction, 2005, v. 1 n. 2, p. 27-45 [How to Cite?]
DOI: http://dx.doi.org/10.4018/jthi.2005040102
 
dc.identifier.doihttp://dx.doi.org/10.4018/jthi.2005040102
 
dc.identifier.epage45
 
dc.identifier.hkuros105276
 
dc.identifier.issn1548-3908
 
dc.identifier.issue2
 
dc.identifier.spage27
 
dc.identifier.urihttp://hdl.handle.net/10722/85972
 
dc.identifier.volume1
 
dc.languageeng
 
dc.publisherIdea Group Publishing. The Journal's web site is located at http://www.idea-group.com/journals/details.asp?id=4290
 
dc.publisher.placeUnited States
 
dc.relation.ispartofInternational Journal of Technology and Human Interaction
 
dc.subjectComputational linguistics
 
dc.subjectLecture video
 
dc.subjectMultimedia application
 
dc.subjectVideo segmentation
 
dc.titleAutomated Video Segmentation for Lecture Videos: A Linguistics-based Approach
 
dc.typeArticle
 
<?xml encoding="utf-8" version="1.0"?>
<item><contributor.author>Lin, M</contributor.author>
<contributor.author>Chau, M</contributor.author>
<contributor.author>Cao, J</contributor.author>
<contributor.author>Nunamaker, JF</contributor.author>
<date.accessioned>2010-09-06T09:11:21Z</date.accessioned>
<date.available>2010-09-06T09:11:21Z</date.available>
<date.issued>2005</date.issued>
<identifier.citation>International Journal of Technology and Human Interaction, 2005, v. 1 n. 2, p. 27-45</identifier.citation>
<identifier.issn>1548-3908</identifier.issn>
<identifier.uri>http://hdl.handle.net/10722/85972</identifier.uri>
<description.abstract>Video, a rich information source, is commonly used for capturing and sharing knowledge in
learning systems. However, the unstructured and linear features of video introduce difficulties
for end users in accessing the knowledge captured in videos. To extract the knowledge structures
hidden in a lengthy, multi-topic lecture video and thus make it easily accessible, we need to first
segment the video into shorter clips by topic. Because of the high cost of manual segmentation,
automated segmentation is highly desired. However, current automated video segmentation
methods mainly rely on scene and shot change detection, which are not suitable for lecture
videos with few scene/shot changes and unclear topic boundaries. In this article we investigate
a new video segmentation approach with high performance on this special type of video:
lecture videos. This approach uses natural language processing techniques such as noun
phrases extraction, and utilizes lexical knowledge sources such as WordNet. Multiple linguisticbased
segmentation features are used, including content-based features such as noun phrases
and discourse-based features such as cue phrases. Our evaluation results indicate that the
noun phrases feature is salient.</description.abstract>
<language>eng</language>
<publisher>Idea Group Publishing. The Journal&apos;s web site is located at http://www.idea-group.com/journals/details.asp?id=4290</publisher>
<relation.ispartof>International Journal of Technology and Human Interaction</relation.ispartof>
<subject>Computational linguistics</subject>
<subject>Lecture video</subject>
<subject>Multimedia application</subject>
<subject>Video segmentation</subject>
<title>Automated Video Segmentation for Lecture Videos: A Linguistics-based Approach</title>
<type>Article</type>
<identifier.doi>10.4018/jthi.2005040102</identifier.doi>
<identifier.hkuros>105276</identifier.hkuros>
<identifier.volume>1</identifier.volume>
<identifier.issue>2</identifier.issue>
<identifier.spage>27</identifier.spage>
<identifier.epage>45</identifier.epage>
<publisher.place>United States</publisher.place>
</item>