Incorporating Audio Cues into Dialog and Action Scene Extraction

Abstract

In this paper, we present an approach to extract scenes in video. The approach is top-down and uses video editing rules and audio cues to extract simple dialog and action scenes. The underlying model is a finite state machine coupled with audio cues that are determined using an audio classifier.

DOI: 10.1117/12.476317

Extracted Key Phrases

10 Figures and Tables

Cite this paper

@inproceedings{Chen2003IncorporatingAC, title={Incorporating Audio Cues into Dialog and Action Scene Extraction}, author={Lei Chen and Shariq J. Rizvi and M. Tamer {\"{O}zsu}, booktitle={Storage and Retrieval for Media Databases}, year={2003} }