Issue No. 02 - April-June (2002 vol. 9)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/93.998057
<p>The authors propose two approaches for semantic indexing of audio-visual documents, based on bottom-up and top-down strategies. They base the first approach on a finite-state machine using low-level motion indices extracted from an MPEG compressed bitstream. The second approach innovatively performs semantic indexing through Hidden Markov Models.</p>
R. Leonardi and P. Migliorati, "Semantic Indexing of Multimedia Documents," in IEEE MultiMedia, vol. 9, no. , pp. 44-51, 2002.