Representing and playing user selected video narrative domains

ABSTRACT

This paper presents a new framework for representing and playing user selected video narrative domains. Hypermedia graphs, generated from complex video narratives provide users with links to selected sequences of the whole video. These graphs have three main structures, representing three different domains: story time domain, space domain and character domain. Complex narratives are often enriched by different parallel lines of narrative or stories within the story, only intersected in one or two of the above mentioned domains. This can be difficult to understand and analyze. The proposed graphs can make these lines visible. More than that, an automatic procedure can search these stories within the story. Then, using suitable signal time alignment procedures, a set of kernel films can be built, each one showing one perspective or even just one of the stories within the story of the whole film.

REFERENCES

• 1: Buszard, L. A. 2003. Constructional Polysemy and Mental Spaces in Potawatomi Discourse, PhD Thesis, University of California, Berkley.
• 2: Kobus Barnard , Pinar Duygulu , David Forsyth , Nando de Freitas , David M. Blei , Michael I. Jordan, Matching words and pictures, The Journal of Machine Learning Research, 3, 3/1/2003
• 3: Enis Cetin, A. 2005. "Report on progress with respect to partial solutions on human detection algorithms, human activity analysis methods, and multimedia databases". Deliverable 11--4, http://www.cs.bilkent.edu.tr/~ismaila/MUSCLE/DeliverableWP11_4.doc.
• 4: Riad Hammoud , Roger Mohr, Interactive tools for constructing and browsing structures for movie films, Proceedings of the eighth ACM international conference on Multimedia, p.497-498, October 2000, Marina del Rey, California, United States [doi>10.1145/354384.376418]
• 5: Hitchcock A. Rope, 1948. http://www.imdb.com/title/tt0040746/.
• 6: Jahn, M. 2005. Narratology: A Guide to the Theory of Narrative. English Department, University of Cologne.Version: 1.8., 28 May.
• 7: Dawn J. Lawrie , W. Bruce Croft, Generating hierarchical summaries for web searches, Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval, July 28-August 01, 2003, Toronto, Canada [doi>10.1145/860435.860549]
• 8: Rainer Lienhart , Silvia Pfeiffer , Wolfgang Effelsberg, Video abstracting, Communications of the ACM, v.40 n.12, p.54-62, Dec. 1997 [doi>10.1145/265563.265572]
• 9: Pavel, T. G. 1980. Narrative Domains, Poetics Today, Vol. 1, No. 4, Narratology II: The Fictional Text and the Reader, 105--114, Duke University Press.
• 10: Teixeira, C. and Respício, A. 2007. See, Hear or Read the Film. in Ma L., Rauterberg M. and Nakatsu R. (eds.): Entertainment Computing - ICEC2007, Proceedings of the 6th International Conference on Entertainment Computing, Lecture Notes in Computer Science, 4740, Springer, 271--281.
• 11: Thomas Anderson, P. Magnolia, 1999. http://www.imdb.com/title/tt0175880/.
• 12: Tsvetomira Tsoneva , Mauro Barbieri , Hans Weda, Automated summarization of narrative video on a semantic level, Proceedings of the International Conference on Semantic Computing, p.169-176, September 17-19, 2007 [doi>10.1109/ICSC.2007.16]
• 13: Turesky, R. and Dimitrova, N. 2004. Screenplay Alignment for Closed-System Speaker Identification and Analysis of Feature Films, IEEE International Conference on Multimedia and Expo, 1659--1662.
• 14: Chung-Yi Weng , Wei-Ta Chu , Ja-Ling Wu, RoleNet: treat a movie as a small society, Proceedings of the international workshop on Workshop on multimedia information retrieval, September 24-29, 2007, Augsburg, Bavaria, Germany [doi>10.1145/1290082.1290092]

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.1 Content Analysis and Indexing
          Subjects: Indexing methods

Additional Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.3 Information Search and Retrieval
          Subjects: Information filtering; Search process

General Terms:
Algorithms, Design, Documentation

Keywords:
multimedia time alignment, narrative analysis, narrative representation