DocumentCode
2336912
Title
A new framework for high-level feature extraction
Author
Gao, Zan ; Nan, Xiaoming ; Liu, Tao ; Zhao, Zhicheng ; Cai, Anni
Author_Institution
Sch. of Inf. & Telecommun. Eng., BUPT, Beijing
fYear
2009
fDate
25-27 May 2009
Firstpage
2118
Lastpage
2122
Abstract
A new framework for high-level feature extraction (or semantic concept detection) is proposed. In this system, features at different granularities are extracted, and four classifiers with complementary features for each concept are employed, and then the results are fused. We have evaluated 18 fusion schemes, and choose the best one for each concept to form the final results. The experiments on the auto-test corpus and TRECVID-2008 corpus show that the proposed system is effective and stable.
Keywords
feature extraction; video signal processing; TRECVID-2008 corpus; high-level feature extraction; semantic concept detection; video analysis; Data mining; Face detection; Feature extraction; Fuses; High definition video; Histograms; Performance analysis; Stability; Testing; Vocabulary; TRECVID; high-level feature extraction; semantic concept detection; video analysis;
fLanguage
English
Publisher
ieee
Conference_Titel
Industrial Electronics and Applications, 2009. ICIEA 2009. 4th IEEE Conference on
Conference_Location
Xi´an
Print_ISBN
978-1-4244-2799-4
Electronic_ISBN
978-1-4244-2800-7
Type
conf
DOI
10.1109/ICIEA.2009.5138523
Filename
5138523
Link To Document