1Guide lines for the TRECVID 2004 evaluation[EB/OL].(2005-02-17). http ://www-nlpir.nist.gov/proj ects/tv2004/tv2004.html#2.2.
2Hoashi K,Sugano M,Naito M,et al.Shot boundary determination on MPEG compressed domain and story segmentation experiments for TRECVID 2004[C]//TREC Video Retrieval Evaluation Foruin,2004.
3Hsu W,Chang S F.Generative,discriminative,and ensemble learning on multi-model perceptual fusion toward news video story segmentation[C]//International Conference on Multimedia and Expo,2004.
4Chaisorn L,Chua T S,Lee C H.The segmentation of news video into story units[C]//International Conference on Multimedia and Expo, 2002.
5Zhai Y,Yillnaz A,Shah M.Story segmentation in news videos using visual and text cues[C]//Leow W K.LNCS 3568:CIVR 2005,2005: 92-102.
6Rabiner L, Juang B H.Fundamentals of speech recognition[M].Englewood Cliffs, NJ: Prentice Hall, 1993.
7Reynolds D A,Rose R C.Robust text-independent speaker identification using Gaussian mixture speaker models[J].IEEE Trans Speech and Audio ProceSsing, 1995,3 ( 1 ) : 72-83.
8Reynolds D A.Speaker identification and verification using Gaussian mixture speaker models[J],Speech Communication, 1995,17 (1/2) : 91-108.
9Cover T M,Tomas J A.Elements of information theory[M],USA: John Wiley & Sons, 1991:18-19.
