conference paper

Conference/Proceedings2008 IEEE International Conference on Semantic Computing
Start date04.08.2008
End date07.08.2008
AddressSanta Clara/ USA
Pages120 - 127
Author(s)Ronald Glasberg, Sebastian Schmiedeke, Martin Mocigemba, Thomas Sikora
TitleReal-Time Approaches for Video-Genre-Classification using new High-Level Descriptors and a Set of Classifiers
AbstractIn this paper we describe in detail the recent publications related to video-genre-classification and present our improved approaches for classifying video sequences in real-time as ‘cartoon’, ‘commercial’, ‘music’, ‘news’ or ‘sport’ by analyzing the content with high-level audio-visual descriptors and classification methods. Such applications have also been discussed in the context of MPEG-7 [1]. The results demonstrate identification rates of more than 90% based on a large representative collection of 100 videos gathered from free digital TV and Internet.
Key wordsGenre-Detection, Classifier Combination
Noteoral presentation; eingereicht; ISBN 978-0-7695-3279-0