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.
Deep Networks for Audio Event Classification in Soccer Videos / Lamberto Ballan;Alessio Bazzica;Marco Bertini; Alberto Del Bimbo;Giuseppe Serra. - ELETTRONICO. - (2009), pp. 474-477. (Intervento presentato al convegno IEEE International Conference on Multimedia & Expo (ICME) tenutosi a New York, USA nel June 28-July 3) [10.1109/ICME.2009.5202537].
Deep Networks for Audio Event Classification in Soccer Videos
BALLAN, LAMBERTO;BERTINI, MARCO;DEL BIMBO, ALBERTO;SERRA, GIUSEPPE
2009
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.I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.