A Context-Based Audiovisual Representation Model for Audiovisual Information Systems
In this paper we present a contextual representation model of audiovisual (AV) documents for AV information systems. In the first part, we study AV medium, and show that AV intra-document context is always related to a user task seen as a general description task. We then present the AI-Strata model for AV description: audiovisual units (pieces of AV documents) are annotated with annotation elements described in a knowledge base. The annotation elements are connected at the document level. The whole system being considered as a single graph, we define a context of one element as end points of graph-paths starting with this element. In order to control contextual paths, we define the notion of potential graphs as graph-patterns instantiated in the general graph. Finally, we show how these graphs are used in the main task of AV information system: navigation, indexing and retrieval.
KeywordsSemantic Context User Task Symbolic Annotation Document Level Annotation Element
Unable to display preview. Download preview PDF.
- 1.T. G. Aguierre Smith and G. Davenport. The stratification system, a design environment for random access video. In Proc. Network and Operating System Support for Digital Audio and Video — 3th International Workshop, La Jolla, 1992.Google Scholar
- 2.G. Auffret, J. Carrive, O. Chevet, T. Dechilly, R. Ronfard, and B. Bachimont. Audiovisual-based hypermedia authoring: using structured representations for efficient access to AV documents. In ACM Hypertext’99, Darmstadt, Germany, Feb. 1999.Google Scholar
- 3.F. Brémond and M. Thonnat. Issues in representing context illustrated by scene interpretation applications. In Proc. of the first Int. and Interdisciplinary Conf. on Modeling and Using Context, Rio de Janeiro, 1997.Google Scholar
- 4.P. Brézillon and M. Cavalcanti. Modeling and using context: Report on the first international and interdisciplinary conference context-97. The Knowledge Engineering Review, 12(4):1–10, 1997.Google Scholar
- 5.P. Brézillon and I. Saker. Modeling context in information seeking. In International Conference on Information needs, Seeking and Use in Different Contexts, ISIC’98, Sheffeld,UK, 1998.Google Scholar
- 7.J.P. Desclés, E. Cartier, A. Jackiewicz, and J.L. Minel. Textual processing and contextual exploration method. In Proc. of the first Int. and Interdisciplinary Conf. on Modeling and Using Context, Rio de Janeiro, 1997.Google Scholar
- 8.B. Edmonds. A simple-minded network model with context-like objects. In European Conference on Cognitive Science (ECCS’97), Manchester, 1997.Google Scholar
- 10.F. Pereira. Mpeg-7: A standard for content-based audiovisual description. In 2nd Int. Conf. on Visual Information Systems, pages 1–4, San Diego, Dec. 1997.Google Scholar
- 11.D. Ponceleon, S. Srinivasan, A. Amir, and D. Petkovic. Key to effective video retrieval: Effective cataloging and browsing. In ACM Multimedia 98 Proc., Sept. 1998.Google Scholar
- 12.Y. Prié, A. Mille, and J.-M. Pinon. Ai-strata: A user-centered model for content-based description and retrieval of audiovisual sequences. In Springer Verlag, editor, First Int. Advanced Multimedia Content Processing Conf., number 1554 in LNCS, pages 143–152, Osaka, Nov. 1998.Google Scholar
- 13.S.W. Smoliar and L.D. Wilcox. Indexing the content of multimedia documents. In 2nd Int. Conf. on Visual Information Systems, pages 53–60, San Diego, Dec. 1997.Google Scholar
- 14.E. Walther, H. Eriksson, and M.A. Musen. Plug and play: Construction of task specific expert-system shells using sharable context ontologies. In Proc. of the AAAI workshop on Knowledge Representation Aspects of Knowledge Acquisition, San Jose, 1992.Google Scholar