The automatic segmentation, indexing, and retrieval of audiovisual data has important applications in professional media production, audiovisual archive management, video-on-demand, user agent driven media selection and filtering, semantic multicast backbone video, education, surveillance, and so on. For example, television and film archives store a vast amount of audiovisual material. If these data are properly indexed at the segment level, it will provide a great help for studios in delivering video segments for editing an archive-based video, a documentary, or an advertisement video clip. In audiovisual libraries or the family entertainment applications, it will be convenient to users if they are able to retrieve and watch the video segments of their interest. As the volume of the available material becomes huge, manual segmentation and indexing is impossible. The most proper way to achieve segmentation and indexing is through computer processing based on content analysis of audiovisual data.


Hide Markov Model Audio Signal Environmental Sound Audio Data Audio Feature 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer Science+Business Media New York 2001

Authors and Affiliations

  • Tong Zhang
    • 1
  • C.-C. Jay Kuo
    • 2
  1. 1.Integrated Media Systems CenterUniversity of Southern CaliforniaLos AngelesUSA
  2. 2.Department of Electrical Engineering — SystemsUniversity of Southern CaliforniaLos AngelesUSA

Personalised recommendations