| Conference/Proceedings | 2008 IEEE International Conference on Semantic Computing |
| Start date | 04.08.2008 |
| End date | 07.08.2008 |
| Address | Santa Clara/ USA |
| Organisation | IEEE |
| Publisher | IEEE |
| Volume | 2008 |
| Pages | 120 - 127 |
| Author(s) | Ronald Glasberg, Sebastian Schmiedeke, Martin Mocigemba, Thomas Sikora |
| Title | Real-Time Approaches for Video-Genre-Classification using new High-Level Descriptors and a Set of Classifiers |
| Abstract | In 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 words | Genre-Detection, Classifier Combination |
| Note | oral presentation; eingereicht; ISBN 978-0-7695-3279-0 |
| File | 1181Glasberg2008.pdf |
| DOI | 10.1109/ICSC.2008.92 |