Name
Abstract | ||
|---|---|---|
In this paper we describe a hybrid approach to improving semantic extraction from news video. Experiments show the value of careful parameter tuning, exploiting multiple feature sets and multilingual linguistic resources, applying text retrieval approaches for image features, and establishing synergy between multiple concepts through undirected graphical models. No single approach provides a consistently better result for every concept detection, which suggests that extracting video semantics should exploit multiple resources and techniques rather than a single approach. |
Year | DOI | Venue |
|---|---|---|
2007 | 10.1109/ICSC.2007.3 | ICSC |
Keywords | Field | DocType |
image features,computational linguistics,feature extraction,graphical model | Data mining,Computer science,Natural language processing,Artificial intelligence,Information retrieval,Video retrieval,Feature (computer vision),Computational linguistics,Exploit,Feature extraction,Graphical model,Semantics,Text retrieval | Conference |
ISBN | Citations | PageRank |
0-7695-2997-6 | 6 | 0.41 |
References | Authors | |
21 | 5 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Alexander G. Hauptmann | 1 | 7472 | 558.23 |
| Ming-yu Chen | 2 | 902 | 79.29 |
| Michael G. Christel | 3 | 1170 | 157.47 |
| Wei-hao Lin | 4 | 679 | 41.81 |
| Jun Yang | 5 | 937 | 37.42 |