TR2009-001

Discriminative Genre-Independent Audio-Visual Scene Change Detection

    •  Wilson, K.W., Divakaran, A., "Discriminative Genre-Independent Audio-Visual Scene Change Detection", SPIE Conference on Multimedia Content Access: Algorithms and Systems, January 2009, vol. 7255,.
      BibTeX TR2009-001 PDF
      • @inproceedings{Wilson2009jan,
      • author = {Wilson, K.W. and Divakaran, A.},
      • title = {Discriminative Genre-Independent Audio-Visual Scene Change Detection},
      • booktitle = {SPIE Conference on Multimedia Content Access: Algorithms and Systems},
      • year = 2009,
      • volume = {7255,},
      • month = jan,
      • url = {https://www.merl.com/publications/TR2009-001}
      • }
  • Research Areas:

    Artificial Intelligence, Data Analytics

TR Image
SVM Classifier Framework
Abstract:

We present a technique for genre-independent scene-change detection using audio and video features in a discriminative support vector machines (SVM) framework. This work builds on our previous work by adding a video feature based on the MPEG-7 "scalable color" descriptor. Adding this feature imporoves our detection rate over all genres by 5% to 15% for a fixed false positive rate of 10%. We also find that the genres that benefit the most are those with which the previous audio-only was least effective.

 

  • Related News & Events