Synopsis Alignment: Importing External Text Information for Multi-model Movie Analysis

Authors:
Ming Li;Yang Liu;Yong-Dong Zhang;Shou-Xun Lin
Affiliations:
Institute of Computing Technology, CAS, Beijing, China 100190 and Graduate School of the Chinese Academy of Sciences, Beijing, China 100039;Institute of Computing Technology, CAS, Beijing, China 100190;Institute of Computing Technology, CAS, Beijing, China 100190;Institute of Computing Technology, CAS, Beijing, China 100190
Venue:
PCM '08 Proceedings of the 9th Pacific Rim Conference on Multimedia: Advances in Multimedia Information Processing
Year:
2008

Citing 5
Cited 0

A Measure of Similarity between Graph Vertices: Applications to Synonym Extraction and Web Searching

SIAM Review
RoleNet: treat a movie as a small society

Proceedings of the international workshop on Workshop on multimedia information retrieval
An Innovative Model of Tempo and Its Application in Action Scene Detection for Movie Analysis

WACV '08 Proceedings of the 2008 IEEE Workshop on Applications of Computer Vision
Content-based movie analysis and indexing based on audiovisual cues

IEEE Transactions on Circuits and Systems for Video Technology
Affective understanding in film

IEEE Transactions on Circuits and Systems for Video Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

Text information, which plays important role in news video concept detection, has been ignored in state-of-the-art movie analysis technology. It is so because movie subtitles are speech of roles which do not directly describe content of movie and contributes little to movie analysis. In this paper, we import collaborative-editing synopsis from professional movie sites for movie analysis, which gives detailed descriptive text of movie. Two aligning methods, subtitle alignment and RoleNet alignment, are proposed complementarily to align synopsis to movie to get scene-level text information of movie. The experiment show that proposed methods can effectively align synopsis to movie scene and the imported text information can give a more user-preferred summarization than merely using audiovisual feature.