Dynamic social network for narrative video analysis

Tsung Hung Tsai*, Wen-Huang Cheng, Yung Huan Hsieh

*Corresponding author for this work

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

4 Scopus citations

Abstract

Narrative video analysis has attracted much research attention, for narrative scenes can provide meaningful representations of multimedia contents. To go beyond the limitations of content based appraoches, social network techniques was introduced in the literature to explore the high-level narrative structures by mining the relations between video characters. Taking into account the fact that such a social network is not static but changes over time as the video narrative evolves, in this work, we develop a novel social network model, namely dynamic social network, for capturing the spatiotemporal dynamics in the social network of video characters so as to enable the automatic segmentation of a video into a sequence of narrative scenes. The proposed approach is experimented with various genres of movies and the results demonstrate our effectiveness.

Original languageEnglish
Title of host publicationMM'11 - Proceedings of the 2011 ACM Multimedia Conference and Co-Located Workshops
Pages663-666
Number of pages4
DOIs
StatePublished - 29 Dec 2011
Event19th ACM International Conference on Multimedia ACM Multimedia 2011, MM'11 - Scottsdale, AZ, United States
Duration: 28 Nov 20111 Dec 2011

Publication series

NameMM'11 - Proceedings of the 2011 ACM Multimedia Conference and Co-Located Workshops

Conference

Conference19th ACM International Conference on Multimedia ACM Multimedia 2011, MM'11
CountryUnited States
CityScottsdale, AZ
Period28/11/111/12/11

Keywords

  • Narrative analysis
  • Social network
  • Video segmentation

Fingerprint Dive into the research topics of 'Dynamic social network for narrative video analysis'. Together they form a unique fingerprint.

  • Cite this

    Tsai, T. H., Cheng, W-H., & Hsieh, Y. H. (2011). Dynamic social network for narrative video analysis. In MM'11 - Proceedings of the 2011 ACM Multimedia Conference and Co-Located Workshops (pp. 663-666). (MM'11 - Proceedings of the 2011 ACM Multimedia Conference and Co-Located Workshops). https://doi.org/10.1145/2072298.2072413