Abstract | ||
---|---|---|
Supporting semantic queries is a challenging problem in video retrieval. We propose the use of a lexicon of semantic concepts for handling the queries. We also propose automatic modeling of lexicon items using probabilistic techniques. We use Gaussian mixture models to build computational representations for a variety of semantic concepts including rocket-launch, outdoor greenery, sky etc. Training requires a large amount of annotated (labeled) data. Using the TREC Video test bed we compare the performance of this system supporting query by keywords with the conventional approach of query by example. Results demonstrate significant gains in performance using the automatically learnt models of semantic concepts. |
Year | DOI | Venue |
---|---|---|
2002 | 10.1109/ICIP.2002.1037980 | Image Processing. 2002. Proceedings. 2002 International Conference |
Keywords | Field | DocType |
Gaussian processes,image retrieval,probability,video databases,video signal processing,video signals,Gaussian mixture models,TREC Video test bed,automatic modeling,automatically learnt models,computational representations,feature extraction,greenery,multimedia analysis,outdoor,performance,probabilistic techniques,query by example,query by keywords,rocket-launch,semantic concepts lexicon,semantic concepts modeling,sky,training,video retrieval | Computer vision,Semantic Web Stack,Information retrieval,Computer science,Image retrieval,Feature extraction,Query by Example,Lexicon,Artificial intelligence,Probabilistic logic,Mixture model,Semantic computing | Conference |
Volume | ISSN | Citations |
1 | 1522-4880 | 19 |
PageRank | References | Authors |
2.90 | 3 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Milind R. Naphade | 1 | 1860 | 162.17 |
Sankar Basu | 2 | 168 | 32.17 |
John R. Smith | 3 | 4939 | 487.88 |
Ching-yung Lin | 4 | 1963 | 175.16 |
Belle L. Tseng | 5 | 1539 | 143.03 |