Abstract | ||
---|---|---|
This paper proposes a novel semantics-based content analysis system for reliable media highlight extraction using dynamic Bayesian network (DBN). It extracts the low-level evidences and then converts the input video to high-level semantic meaning. Specific domains contain rich spatial and temporal transitional structures that help the transformation process. We introduce a robust audio-visual low-level evidence extraction scheme, and develop the so-called temporal intervening network to improve the performance of our system. In experiments, we show that our system can detect soccer events such as goal event, corner kick event, penalty kick event, and card event effectively. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1109/ICASSP.2005.1415590 | ICASSP (2) |
Keywords | Field | DocType |
spatial transitional structures,soccer event detection,video signal processing,belief networks,goal event,semantics-based content analysis,penalty kick event,sports video,temporal intervening network,dbn,dynamic bayesian network,card event,corner kick event,sport,audio-visual low-level evidence extraction scheme,feature extraction,temporal transitional structures,high-level semantic meaning,media highlight extraction,semantics-based soccer highlight extraction,content analysis,bayesian methods,face detection,hidden markov models,broadcasting,data mining | Broadcasting,Computer science,Feature extraction,Artificial intelligence,Face detection,Hidden Markov model,Machine learning,Semantics,Dynamic Bayesian network,Bayesian probability | Conference |
Volume | ISSN | ISBN |
2 | 1520-6149 | 0-7803-8874-7 |
Citations | PageRank | References |
10 | 0.58 | 3 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chung-Yuan Chao | 1 | 85 | 2.91 |
Huang-Chia Shih | 2 | 187 | 21.98 |
Chung-Lin Huang | 3 | 540 | 37.61 |