Abstract | ||
---|---|---|
In this paper, we proposed a novel decision fusion scheme based on the psychological observations on human beings' visual and aural attention characteristics, which combines a set of decisions obtained from different data sources or features to generate better decision result. Based on studying of the “heterogeneity” and “monotonicity” properties of certain types of decision fusion issues, a set of so-called Attention Fusion Functions are devised, which are able to obtain more reasonable fusion results than typical fusion schemes. Preliminary experiment on image retrieval shows the effectiveness of the proposed fusion scheme. |
Year | DOI | Venue |
---|---|---|
2004 | 10.1007/978-3-540-30542-2_123 | PCM (2) |
Keywords | Field | DocType |
decision fusion issue,reasonable fusion result,typical fusion scheme,different data source,aural attention characteristic,novel decision fusion scheme,human being,better decision result,certain type,multimedia information retrieval,proposed fusion scheme,attention-based decision fusion scheme,image retrieval | Computer vision,Decision fusion,Information retrieval,Computer science,Fusion,Multimedia information retrieval,Image retrieval,Artificial intelligence,Fusion scheme | Conference |
Volume | ISSN | ISBN |
3332 | 0302-9743 | 3-540-23977-4 |
Citations | PageRank | References |
16 | 1.36 | 9 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xian-Sheng Hua | 1 | 6566 | 328.17 |
Hong-Jiang ZHANG | 2 | 17378 | 1393.22 |