Segmenting lecture videos by topic: From manual to automated methods

Ming Lin, Christopher B R Diller, Nicole Forsgren, Yunchu Huang, Jay F Nunamaker

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

More and more universities and corporations are starting to provide videotaped lectures online for knowledge sharing and learning. Segmenting lecture videos into short clips by topic can extract the hidden information structure of the videos and facilitate information searching and learning. Manual segmentation has high accuracy rates but is very labor intensive. In order to develop a high performance automated segmentation method for lecture videos, we conducted a case study to learn the segmentation process of humans and the effective segmentation features used in the process. Based on the findings from the case study, we designed an automated segmentation approach with two phases: initial segmentation and segmentation refinement. The approach combines segmentation features from three information sources of video (speech text transcript, audio and video) and makes use of various knowledge sources such as world knowledge and domain knowledge. Our preliminary results show that the proposed two-phase approach is promising.

Original languageEnglish (US)
Title of host publicationAssociation for Information Systems - 11th Americas Conference on Information Systems, AMCIS 2005: A Conference on a Human Scale
Pages1891-1898
Number of pages8
Volume4
StatePublished - 2005
Event11th Americas Conference on Information Systems, AMCIS 2005 - Omaha, NE, United States
Duration: Aug 11 2005Aug 15 2005

Other

Other11th Americas Conference on Information Systems, AMCIS 2005
CountryUnited States
CityOmaha, NE
Period8/11/058/15/05

Fingerprint

video
Personnel
Industry
knowledge
segmentation
source of information
learning
corporation
labor
university
performance

Keywords

  • Knowledge bases
  • Lecture video
  • Segmentation features
  • Video segmentation

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Networks and Communications
  • Information Systems
  • Library and Information Sciences

Cite this

Lin, M., Diller, C. B. R., Forsgren, N., Huang, Y., & Nunamaker, J. F. (2005). Segmenting lecture videos by topic: From manual to automated methods. In Association for Information Systems - 11th Americas Conference on Information Systems, AMCIS 2005: A Conference on a Human Scale (Vol. 4, pp. 1891-1898)

Segmenting lecture videos by topic : From manual to automated methods. / Lin, Ming; Diller, Christopher B R; Forsgren, Nicole; Huang, Yunchu; Nunamaker, Jay F.

Association for Information Systems - 11th Americas Conference on Information Systems, AMCIS 2005: A Conference on a Human Scale. Vol. 4 2005. p. 1891-1898.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Lin, M, Diller, CBR, Forsgren, N, Huang, Y & Nunamaker, JF 2005, Segmenting lecture videos by topic: From manual to automated methods. in Association for Information Systems - 11th Americas Conference on Information Systems, AMCIS 2005: A Conference on a Human Scale. vol. 4, pp. 1891-1898, 11th Americas Conference on Information Systems, AMCIS 2005, Omaha, NE, United States, 8/11/05.
Lin M, Diller CBR, Forsgren N, Huang Y, Nunamaker JF. Segmenting lecture videos by topic: From manual to automated methods. In Association for Information Systems - 11th Americas Conference on Information Systems, AMCIS 2005: A Conference on a Human Scale. Vol. 4. 2005. p. 1891-1898
Lin, Ming ; Diller, Christopher B R ; Forsgren, Nicole ; Huang, Yunchu ; Nunamaker, Jay F. / Segmenting lecture videos by topic : From manual to automated methods. Association for Information Systems - 11th Americas Conference on Information Systems, AMCIS 2005: A Conference on a Human Scale. Vol. 4 2005. pp. 1891-1898
@inproceedings{58dfe9661a3e44ed9845db6efc63c8cf,
title = "Segmenting lecture videos by topic: From manual to automated methods",
abstract = "More and more universities and corporations are starting to provide videotaped lectures online for knowledge sharing and learning. Segmenting lecture videos into short clips by topic can extract the hidden information structure of the videos and facilitate information searching and learning. Manual segmentation has high accuracy rates but is very labor intensive. In order to develop a high performance automated segmentation method for lecture videos, we conducted a case study to learn the segmentation process of humans and the effective segmentation features used in the process. Based on the findings from the case study, we designed an automated segmentation approach with two phases: initial segmentation and segmentation refinement. The approach combines segmentation features from three information sources of video (speech text transcript, audio and video) and makes use of various knowledge sources such as world knowledge and domain knowledge. Our preliminary results show that the proposed two-phase approach is promising.",
keywords = "Knowledge bases, Lecture video, Segmentation features, Video segmentation",
author = "Ming Lin and Diller, {Christopher B R} and Nicole Forsgren and Yunchu Huang and Nunamaker, {Jay F}",
year = "2005",
language = "English (US)",
isbn = "9781604235531",
volume = "4",
pages = "1891--1898",
booktitle = "Association for Information Systems - 11th Americas Conference on Information Systems, AMCIS 2005: A Conference on a Human Scale",

}

TY - GEN

T1 - Segmenting lecture videos by topic

T2 - From manual to automated methods

AU - Lin, Ming

AU - Diller, Christopher B R

AU - Forsgren, Nicole

AU - Huang, Yunchu

AU - Nunamaker, Jay F

PY - 2005

Y1 - 2005

N2 - More and more universities and corporations are starting to provide videotaped lectures online for knowledge sharing and learning. Segmenting lecture videos into short clips by topic can extract the hidden information structure of the videos and facilitate information searching and learning. Manual segmentation has high accuracy rates but is very labor intensive. In order to develop a high performance automated segmentation method for lecture videos, we conducted a case study to learn the segmentation process of humans and the effective segmentation features used in the process. Based on the findings from the case study, we designed an automated segmentation approach with two phases: initial segmentation and segmentation refinement. The approach combines segmentation features from three information sources of video (speech text transcript, audio and video) and makes use of various knowledge sources such as world knowledge and domain knowledge. Our preliminary results show that the proposed two-phase approach is promising.

AB - More and more universities and corporations are starting to provide videotaped lectures online for knowledge sharing and learning. Segmenting lecture videos into short clips by topic can extract the hidden information structure of the videos and facilitate information searching and learning. Manual segmentation has high accuracy rates but is very labor intensive. In order to develop a high performance automated segmentation method for lecture videos, we conducted a case study to learn the segmentation process of humans and the effective segmentation features used in the process. Based on the findings from the case study, we designed an automated segmentation approach with two phases: initial segmentation and segmentation refinement. The approach combines segmentation features from three information sources of video (speech text transcript, audio and video) and makes use of various knowledge sources such as world knowledge and domain knowledge. Our preliminary results show that the proposed two-phase approach is promising.

KW - Knowledge bases

KW - Lecture video

KW - Segmentation features

KW - Video segmentation

UR - http://www.scopus.com/inward/record.url?scp=84869807184&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84869807184&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84869807184

SN - 9781604235531

VL - 4

SP - 1891

EP - 1898

BT - Association for Information Systems - 11th Americas Conference on Information Systems, AMCIS 2005: A Conference on a Human Scale

ER -