Effective and efficient sports highlights extraction using the minimum description length criterion in selecting GMM structures

In fitting the training data with Guassian Mixture Models(GMMs) of appropriate structures using the MDL criterion, we are able to improve audio classification accuracy with a large margin. With the MDL-GMMs, we are also able to greatly improve the accuracy in extracting sports highlights. Since we have focused on audio domain processing, it enables us to extract highlights very fast. In this paper, we have demonstrated the importance of a better understanding of model structures in such a pattern recognition task.

[1]  J. Rissanen.  A UNIVERSAL PRIOR FOR INTEGERS AND ESTIMATION BY MINIMUM DESCRIPTION LENGTH , 1983 .

[2]  Anoop Gupta,et al.  Automatically extracting highlights for TV Baseball programs , 2000, ACM Multimedia.

[3]  Shih-Fu Chang,et al.  Structure analysis of soccer video with hidden Markov models , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[4]  Regunathan Radhakrishnan,et al.  Audio events detection based highlights extraction from baseball, golf and soccer games in a unified framework , 2003, 2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698).

[5]  Ziyou Xiong,et al.  Audio–visual sports highlights extraction using Coupled Hidden Markov Models , 2005, Pattern Analysis and Applications.