Share Email Print
cover

Proceedings Paper

Audio-visual event detection based on mining of semantic audio-visual labels
Author(s): King-Shy Goh; Koji Miyahara; Regunathan Radhakrishnan; Ziyou Xiong; Ajay Divakaran
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Removing commercials from television programs is a much sought-after feature for a personal video recorder. In this paper, we employ an unsupervised clustering scheme (CM_Detect) to detect commercials in television programs. Each program is first divided into W8-minute chunks, and we extract audio and visual features from each of these chunks. Next, we apply k-means clustering to assign each chunk with a commercial/program label. In contrast to other methods, we do not make any assumptions regarding the program content. Thus, our method is highly content-adaptive and computationally inexpensive. Through empirical studies on various content, including American news, Japanese news, and sports programs, we demonstrate that our method is able to filter out most of the commercials without falsely removing the regular program.

Paper Details

Date Published: 18 December 2003
PDF: 8 pages
Proc. SPIE 5307, Storage and Retrieval Methods and Applications for Multimedia 2004, (18 December 2003); doi: 10.1117/12.524572
Show Author Affiliations
King-Shy Goh, Mitsubishi Electric Research Labs. (United States)
Koji Miyahara, Mitsubishi Electric Research Labs. (United States)
Regunathan Radhakrishnan, Mitsubishi Electric Research Labs. (United States)
Ziyou Xiong, Mitsubishi Electric Research Labs. (United States)
Ajay Divakaran, Mitsubishi Electric Research Labs. (United States)


Published in SPIE Proceedings Vol. 5307:
Storage and Retrieval Methods and Applications for Multimedia 2004
Minerva M. Yeung; Rainer W. Lienhart; Chung-Sheng Li, Editor(s)

© SPIE. Terms of Use
Back to Top