Abstract | ||
---|---|---|
The exploitation of semantic information in videos is difficult because of the large difference in representations, levels of knowledge and abstract episodes. Traditional image/video understanding and indexing is formulated in terms of low-level features describing image/video structure and intensity, while high-level knowledge such as common sense and human perceptual knowledge are encoded. This paper attempts to bridge this gap through the integration of image/video analysis algorithms with multi-level semantic network to interpret the baseball video. |
Year | DOI | Venue |
---|---|---|
2003 | 10.1109/ICASSP.2003.1200097 | ICASSP (5) |
Keywords | Field | DocType |
video signal processing,video intensity,semantic networks,visual databases,common sense,high-level knowledge,indexing,database indexing,semantic network modeling,sport,multi-level semantic network,feature extraction,low-level features,image/video analysis algorithms,human perceptual knowledge,image/video structure,baseball video understanding,content-based retrieval,information analysis,data mining,indexation,semantic network,engines,bayesian methods,hidden markov models | Computer science,Search engine indexing,Artificial intelligence,Database index,Object detection,Information retrieval,Pattern recognition,Feature extraction,Semantic network,Video tracking,Hidden Markov model,Multimedia,Perception | Conference |
Volume | ISSN | ISBN |
5 | 1520-6149 | 0-7803-7663-3 |
Citations | PageRank | References |
7 | 0.73 | 6 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Huang-Chia Shih | 1 | 187 | 21.98 |
Chung-Lin Huang | 2 | 540 | 37.61 |