Automatic social network construction from movies using film-editing cues

Mei Chen Yeh, Ming Chi Tseng, Wen Po Wu

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

6 Citations (Scopus)

Abstract

In this paper, we investigate the problem of automatically constructing characters' social network from movies. Unlike existing approaches that use co-appearance information to measure the relationship between two characters, we argue that a method that describes the characters' interaction, rather than the co-appearance, makes more sense. We propose a new scheme that quantifies the interaction of characters by the use of film-editing cues, based on which we construct the characters' social network. Experiments on real-world data validate the effectiveness of the proposed method. In addition, we show an application of discovering characters' social clusters enabled by the automatically constructed social network.

Original languageEnglish
Title of host publicationProceedings of the 2012 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2012
Pages242-247
Number of pages6
DOIs
Publication statusPublished - 2012 Oct 4
Event2012 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2012 - Melbourne, VIC, Australia
Duration: 2012 Jul 92012 Jul 13

Publication series

NameProceedings of the 2012 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2012

Other

Other2012 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2012
CountryAustralia
CityMelbourne, VIC
Period12/7/912/7/13

Fingerprint

Experiments

Keywords

  • Social network
  • face clustering
  • social cluster discovery

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Human-Computer Interaction

Cite this

Yeh, M. C., Tseng, M. C., & Wu, W. P. (2012). Automatic social network construction from movies using film-editing cues. In Proceedings of the 2012 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2012 (pp. 242-247). [6266262] (Proceedings of the 2012 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2012). https://doi.org/10.1109/ICMEW.2012.48

Automatic social network construction from movies using film-editing cues. / Yeh, Mei Chen; Tseng, Ming Chi; Wu, Wen Po.

Proceedings of the 2012 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2012. 2012. p. 242-247 6266262 (Proceedings of the 2012 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2012).

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

Yeh, MC, Tseng, MC & Wu, WP 2012, Automatic social network construction from movies using film-editing cues. in Proceedings of the 2012 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2012., 6266262, Proceedings of the 2012 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2012, pp. 242-247, 2012 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2012, Melbourne, VIC, Australia, 12/7/9. https://doi.org/10.1109/ICMEW.2012.48
Yeh MC, Tseng MC, Wu WP. Automatic social network construction from movies using film-editing cues. In Proceedings of the 2012 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2012. 2012. p. 242-247. 6266262. (Proceedings of the 2012 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2012). https://doi.org/10.1109/ICMEW.2012.48
Yeh, Mei Chen ; Tseng, Ming Chi ; Wu, Wen Po. / Automatic social network construction from movies using film-editing cues. Proceedings of the 2012 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2012. 2012. pp. 242-247 (Proceedings of the 2012 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2012).
@inproceedings{4d8a5746307143e195909d132e1231c5,
title = "Automatic social network construction from movies using film-editing cues",
abstract = "In this paper, we investigate the problem of automatically constructing characters' social network from movies. Unlike existing approaches that use co-appearance information to measure the relationship between two characters, we argue that a method that describes the characters' interaction, rather than the co-appearance, makes more sense. We propose a new scheme that quantifies the interaction of characters by the use of film-editing cues, based on which we construct the characters' social network. Experiments on real-world data validate the effectiveness of the proposed method. In addition, we show an application of discovering characters' social clusters enabled by the automatically constructed social network.",
keywords = "Social network, face clustering, social cluster discovery",
author = "Yeh, {Mei Chen} and Tseng, {Ming Chi} and Wu, {Wen Po}",
year = "2012",
month = "10",
day = "4",
doi = "10.1109/ICMEW.2012.48",
language = "English",
isbn = "9780769547299",
series = "Proceedings of the 2012 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2012",
pages = "242--247",
booktitle = "Proceedings of the 2012 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2012",

}

TY - GEN

T1 - Automatic social network construction from movies using film-editing cues

AU - Yeh, Mei Chen

AU - Tseng, Ming Chi

AU - Wu, Wen Po

PY - 2012/10/4

Y1 - 2012/10/4

N2 - In this paper, we investigate the problem of automatically constructing characters' social network from movies. Unlike existing approaches that use co-appearance information to measure the relationship between two characters, we argue that a method that describes the characters' interaction, rather than the co-appearance, makes more sense. We propose a new scheme that quantifies the interaction of characters by the use of film-editing cues, based on which we construct the characters' social network. Experiments on real-world data validate the effectiveness of the proposed method. In addition, we show an application of discovering characters' social clusters enabled by the automatically constructed social network.

AB - In this paper, we investigate the problem of automatically constructing characters' social network from movies. Unlike existing approaches that use co-appearance information to measure the relationship between two characters, we argue that a method that describes the characters' interaction, rather than the co-appearance, makes more sense. We propose a new scheme that quantifies the interaction of characters by the use of film-editing cues, based on which we construct the characters' social network. Experiments on real-world data validate the effectiveness of the proposed method. In addition, we show an application of discovering characters' social clusters enabled by the automatically constructed social network.

KW - Social network

KW - face clustering

KW - social cluster discovery

UR - http://www.scopus.com/inward/record.url?scp=84866874733&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84866874733&partnerID=8YFLogxK

U2 - 10.1109/ICMEW.2012.48

DO - 10.1109/ICMEW.2012.48

M3 - Conference contribution

AN - SCOPUS:84866874733

SN - 9780769547299

T3 - Proceedings of the 2012 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2012

SP - 242

EP - 247

BT - Proceedings of the 2012 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2012

ER -