Multi-modal dialog scene detection using hidden Markov models for content-based multimedia indexing


Alatan A. A., AKANSU A. N., WOLF W.

MULTIMEDIA TOOLS AND APPLICATIONS, vol.14, no.2, pp.137-151, 2001 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 14 Issue: 2
  • Publication Date: 2001
  • Doi Number: 10.1023/a:1011395131992
  • Journal Name: MULTIMEDIA TOOLS AND APPLICATIONS
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.137-151
  • Middle East Technical University Affiliated: Yes

Abstract

A class of audio-visual data (fiction entertainment: movies, TV series) is segmented into scenes, which contain dialogs, using a novel hidden Markov model-based (HMM) method. Each shot is classified using both audio track (via classification of speech, silence and music) and visual content (face and location information). The result of this shot-based classification is an audio-visual token to be used by the HMM state diagram to achieve scene analysis. After simulations with circular and left-to-right HMM topologies, it is observed that both are performing very good with multi-modal inputs. Moreover, for circular topology, the comparisons between different training and observation sets show that audio and face information together gives the most consistent results among different observation sets.