標題: Incorporating frequent pattern analysis into multimodal HMM event classification for baseball videos
作者: Chen, Hsuan-Sheng
Tsai, Wen-Jiin
資訊工程學系
Department of Computer Science
關鍵字: Multimedia system;Video semantic analysis;Baseball event classification;Interval-based multimodal feature;Temporal sequence symbol coding;Co-occurrence symbol coding;HMM;Data mining;Frequent pattern analysis;Frequent-pattern trained HMM;Frequent-pattern tailored HMM;VOGUE
公開日期: May-2016
摘要: Data mining and frequent pattern analysis have recently become a popular way of discovering new knowledge from a data set. However, it is rarely applied to video semantic analysis. Therefore, this paper introduces two methods: frequent-pattern trained HMM and frequent-pattern tailored HMM to incorporate frequent pattern analysis into multimodal HMM event classification for baseball videos. Besides, different symbol coding methods including temporal sequence coding and co-occurrence symbol coding for multimodal HMM classification are compared. The results of our experiments on baseball video event classification demonstrate that integration of frequent pattern analysis could help to improve event classification performances.
URI: http://dx.doi.org/10.1007/s11042-015-2447-2
http://hdl.handle.net/11536/133790
ISSN: 1380-7501
DOI: 10.1007/s11042-015-2447-2
期刊: MULTIMEDIA TOOLS AND APPLICATIONS
Volume: 75
Issue: 9
起始頁: 4913
結束頁: 4932
Appears in Collections:Articles