Automated Video Segmentation for Lecture Videos: A Linguistics-Based Approach

Ming Lin, Michael Chau, Jinwei Cao, Jay F Nunamaker

Research output: Contribution to journalArticle

17 Citations (Scopus)

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 linguistic-based 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.

Original languageEnglish (US)
Pages (from-to)27-45
Number of pages19
JournalInternational Journal of Technology and Human Interaction (IJTHI)
Volume1
Issue number2
DOIs
StatePublished - 2005

Fingerprint

Linguistics
Learning systems
Processing
Costs

Keywords

  • computational linguistics
  • lecture video
  • multimedia application
  • video segmentation
  • virtual learning

ASJC Scopus subject areas

  • Information Systems
  • Human-Computer Interaction

Cite this

Automated Video Segmentation for Lecture Videos : A Linguistics-Based Approach. / Lin, Ming; Chau, Michael; Cao, Jinwei; Nunamaker, Jay F.

In: International Journal of Technology and Human Interaction (IJTHI), Vol. 1, No. 2, 2005, p. 27-45.

Research output: Contribution to journalArticle

@article{f7a8117a55fe45a19ab1a301549a30d8,
title = "Automated Video Segmentation for Lecture Videos: A Linguistics-Based Approach",
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 linguistic-based 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.",
keywords = "computational linguistics, lecture video, multimedia application, video segmentation, virtual learning",
author = "Ming Lin and Michael Chau and Jinwei Cao and Nunamaker, {Jay F}",
year = "2005",
doi = "10.4018/jthi.2005040102",
language = "English (US)",
volume = "1",
pages = "27--45",
journal = "International Journal of Technology and Human Interaction",
issn = "1548-3908",
publisher = "IGI Publishing",
number = "2",

}

TY - JOUR

T1 - Automated Video Segmentation for Lecture Videos

T2 - A Linguistics-Based Approach

AU - Lin, Ming

AU - Chau, Michael

AU - Cao, Jinwei

AU - Nunamaker, Jay F

PY - 2005

Y1 - 2005

N2 - 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 linguistic-based 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.

AB - 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 linguistic-based 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.

KW - computational linguistics

KW - lecture video

KW - multimedia application

KW - video segmentation

KW - virtual learning

UR - http://www.scopus.com/inward/record.url?scp=85001817379&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85001817379&partnerID=8YFLogxK

U2 - 10.4018/jthi.2005040102

DO - 10.4018/jthi.2005040102

M3 - Article

AN - SCOPUS:85001817379

VL - 1

SP - 27

EP - 45

JO - International Journal of Technology and Human Interaction

JF - International Journal of Technology and Human Interaction

SN - 1548-3908

IS - 2

ER -