出版社:Know-Center, Graz in cooperation with IICM, Graz University of Technology
摘要:In this paper we present first results of the implementation work on the
exploitation of MPEG-7 descriptors within the MISTRAL system, which aims at
enhanced procedures for semantic annotation and enrichment of meeting-related
multi-modal data. As the system consists of several specialised units, the focus
is set on its Semantic Applications Unit (SemAU). First, we give a short
overview on the MISTRAL system as well as explain the overall architecture and
some functional modules of SemAU. Then, emphasis is placed on the role of MPEG-7
metadata within the MISTRAL system as standardised bridge between its units and
as basic standardised input for SemAU. Finally, some insights are given into the
current development stage of two user-centred applications of SemAU. These
applications manage semantically enriched multi-modal data in order to enhance
its retrieval and visualisation.