DocumentCode
2930683
Title
Deep networks for audio event classification in soccer videos
Author
Ballan, Lamberto ; Bazzica, Alessio ; Bertini, Marco ; Del Bimbo, Alberto ; Serra, Giuseppe
Author_Institution
Media Integration & Commun. Center, Univ. of Florence, Florence, Italy
fYear
2009
fDate
June 28 2009-July 3 2009
Firstpage
474
Lastpage
477
Abstract
In this work is presented a novel approach for the classification of audio concepts in broadcast soccer videos using deep belief network (DBN), a probabilistic neural network with several hidden layers. Comparison with support vector machine (SVM) classifiers has been carried on, showing that our preliminary results are promisingly comparable to the state-of-the-art.
Keywords
belief networks; neural nets; sport; support vector machines; video signal processing; audio event classification; broadcast soccer videos; deep belief network; probabilistic neural network; support vector machine classifiers; Broadcasting; Cepstral analysis; Event detection; Information retrieval; Intelligent networks; Neural networks; Real time systems; Support vector machine classification; Support vector machines; Videos; Deep belief networks; SVM; audio event classification; sports videos;
fLanguage
English
Publisher
ieee
Conference_Titel
Multimedia and Expo, 2009. ICME 2009. IEEE International Conference on
Conference_Location
New York, NY
ISSN
1945-7871
Print_ISBN
978-1-4244-4290-4
Electronic_ISBN
1945-7871
Type
conf
DOI
10.1109/ICME.2009.5202537
Filename
5202537
Link To Document