Creating audio keywords for event detection in soccer video

Xu, M, Maddage, N, Xu, C, Kankanhalli, M and Tian, Q 2003, 'Creating audio keywords for event detection in soccer video', in B. S. Manjunath, Yao Wang (ed.) Proceedings of the 2003 International Conference on Multimedia and Expo (ICME): Volume II, Maryland, United States, 6-9 July 2003, pp. 281-284.


Document type: Conference Paper
Collection: Conference Papers

Title Creating audio keywords for event detection in soccer video
Author(s) Xu, M
Maddage, N
Xu, C
Kankanhalli, M
Tian, Q
Year 2003
Conference name International Conference on Multimedia & Expo (ICME)
Conference location Maryland, United States
Conference dates 6-9 July 2003
Proceedings title Proceedings of the 2003 International Conference on Multimedia and Expo (ICME): Volume II
Editor(s) B. S. Manjunath, Yao Wang
Publisher IEEE
Place of publication United states
Start page 281
End page 284
Total pages 4
Abstract This paper presents a novel framework called audio keywords to assist event detection in soccer video. Audio keyword is a middle-level representation that can bridge the gap between low-level features and high-level semantics. Audio keywords are created from low-level audio features by using support vector machine learning. The created audio keywords can be used to detect semantic events in soccer video by applying a heuristic mapping. Experiments of audio keywords creation and event detection based on audio keywords have illustrated promising results. According to the experimental results, we believe that audio keyword is an effective representation that is able to achieve more intuitionistic result for event detection in sports video compared with the method of event detection directly based on low-level features.
Subjects Artificial Intelligence and Image Processing not elsewhere classified
Keyword(s) Bridges
Event detection
Information analysis
Machine learning
Memory
Speech
Standards development
Support vector machines
Transform coding
Video compression
DOI - identifier 10.1109/ICME.2003.1221608
Copyright notice © 2003 IEEE
ISBN 0780379659
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 44 times in Thomson Reuters Web of Science Article | Citations
Altmetric details:
Access Statistics: 109 Abstract Views  -  Detailed Statistics
Created: Mon, 26 Nov 2012, 09:22:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us