Abstract | ||
---|---|---|
Detection of commercials in TV videos is difficult because the diversity of them puts up a high barrier to construct an appropriate model. In this work, we try to deal with this problem through a top-down approach. We take account of the domain knowledge of commercial production and extract features that describe the characteristics of commercials. According to the clues from speech-music discrimination, video scene detection, and caption detection, a multi-modal commercial detection scheme is proposed. Experimental results show good performance of the proposed scheme on detecting commercials in news and talk show programs. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1007/11581772_68 | PCM (1) |
Keywords | Field | DocType |
tv video,appropriate model,multi-modal commercial detection scheme,video scene detection,caption detection,commercial production,commercial boundary detection,proposed scheme,audiovisual feature,domain knowledge,talk show program,top down | Computer vision,Domain knowledge,Computer science,Edge detection,Speech recognition,Boundary detection,Artificial intelligence | Conference |
Volume | ISSN | ISBN |
3767 | 0302-9743 | 3-540-30027-9 |
Citations | PageRank | References |
2 | 0.41 | 6 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jun-cheng Chen | 1 | 274 | 21.35 |
Jen-hao Yeh | 2 | 13 | 1.81 |
Wei-ta Chu | 3 | 611 | 56.68 |
Jin-hau Kuo | 4 | 116 | 10.87 |
Ja-ling Wu | 5 | 1569 | 168.11 |