{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T13:20:13Z","timestamp":1789996813755,"version":"4.0.1"},"reference-count":16,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2001,6,1]],"date-time":"2001-06-01T00:00:00Z","timestamp":991353600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2001,6,1]],"date-time":"2001-06-01T00:00:00Z","timestamp":991353600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Multimedia Tools and Applications"],"published-print":{"date-parts":[[2001,6]]},"DOI":"10.1023\/a:1011395131992","type":"journal-article","created":{"date-parts":[[2002,12,23]],"date-time":"2002-12-23T09:44:13Z","timestamp":1040636653000},"page":"137-151","source":"Crossref","is-referenced-by-count":41,"title":["Multi-Modal Dialog Scene Detection Using Hidden Markov Models for Content-Based Multimedia Indexing"],"prefix":"10.1007","volume":"14","author":[{"given":"A. Aydin","family":"Alatan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali N.","family":"Akansu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wayne","family":"Wolf","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"334057_CR1","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1147\/rd.422.0233","volume":"42","author":"R.M. Bolle","year":"1998","unstructured":"R.M. Bolle, B.-L. Yeo, and M.M. Yeung, \u201cVideo query: research directions,\u201d IBM Journal of Research and Development, Vol. 42, pp. 233\u2013252, 1998. (also avaiable at http:\/\/www.almaden.ibm.com\/journal\/ rd\/422\/bolle.txt).","journal-title":"IBM Journal of Research and Development"},{"key":"334057_CR2","doi-asserted-by":"crossref","unstructured":"J.S. Boreczky and L.D. Wilcox, \u201cA hidden Markov model framework for video segmentation audio and image features,\u201d in Proceedings of ICASSP'98, 1998, pp. 3741\u20133744.","DOI":"10.1109\/ICASSP.1998.679697"},{"key":"334057_CR3","doi-asserted-by":"crossref","unstructured":"S. Eickler and G. Rigoll, \u201cContinuous online gesture recognition based on hidden Markov models,\u201d in Proceedings of ICPR'98, 1998, pp. 1206\u20131208.","DOI":"10.1109\/ICPR.1998.711914"},{"key":"334057_CR4","unstructured":"M. Ferman and A.M. Tekalp, \u201cProbabilistic analysis and extraction of video content,\u201d in Proceedings of ICIP'99, 1999."},{"key":"334057_CR5","unstructured":"J. Huang, Z. Liu, and Y. Wang, \u201cIntegration of audio and visual information for content-based video segmentation,\u201d in Proceedings of ICIP'98, 1998."},{"key":"334057_CR6","doi-asserted-by":"crossref","unstructured":"Q. Huang, Z. Liu, A. Rosenberg, D. Gibbon, and B. Shahraray, \u201cAutomated generation of new content hierarchy by integrating audio, video and text information,\u201d in Proceedings of ICASSP'99, 1999, pp. 3025\u20133028.","DOI":"10.1109\/ICASSP.1999.757478"},{"issue":"12","key":"334057_CR7","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1145\/265563.265572","volume":"40","author":"R. Lienhart","year":"1997","unstructured":"R. Lienhart, S. Pfeiffer, and W. Effelsberg, \u201cVideo abstracting,\u201d Communications of ACM, Vol. 40, No. 12, pp. 55\u201362, 1997.","journal-title":"Communications of ACM"},{"key":"334057_CR8","unstructured":"J. Nam, A.E. Cetin, and A.H. Tewfik, \u201cSpeaker identification and video shot analysis for hierarchical video shot classification,\u201d in Proceedings of ICIP'97, 1997."},{"key":"334057_CR9","doi-asserted-by":"crossref","unstructured":"J. Nam, M. Alghoneiemy, and A.H. Tewfik, \u201cAudio-visual content-based violent scene characterization,\u201d in Proceedings of ICIP'98, 1998, pp. 353\u2013357.","DOI":"10.1109\/ICIP.1998.723496"},{"key":"334057_CR10","doi-asserted-by":"crossref","unstructured":"A.V. Nefian and M.H. Hayes III, \u201cAn embedded HMM-based approach for face detection and recognition,\u201d in Proceedings of ICASSP'99, 1999, pp. 3553\u20133556.","DOI":"10.1109\/ICASSP.1999.757610"},{"key":"334057_CR11","doi-asserted-by":"crossref","unstructured":"H. Pan, Z.-P. Liang, T.J. Anastasio, and T.S. Huang, \u201cA hybrid NN-bayesian architecture for information fusion,\u201d in Proceedings of ICIP'98, 1998, pp. 368\u2013371.","DOI":"10.1109\/ICIP.1998.723502"},{"key":"334057_CR12","volume-title":"Fundementals of Speech Recognition","author":"L.R. Rabiner","year":"1993","unstructured":"L.R. Rabiner and B-H. Juang, Fundementals of Speech Recognition. Prentice Hall. Englewood Cliffs, NJ, USA, 1993."},{"key":"334057_CR13","doi-asserted-by":"crossref","unstructured":"C. Saraceno and R. Leonardi, \u201cIdentification of story units in audio-visual sequences by joint audio and video processing,\u201d in Proceedings of ICIP'98, 1998, pp. 363\u2013367.","DOI":"10.1109\/ICIP.1998.723500"},{"key":"334057_CR14","doi-asserted-by":"crossref","unstructured":"S. Tsekeridou and I. Pitas, \u201cSpeaker dependent video indexing based on audio-visual interaction,\u201d in Proceedings of ICIP'98, 1998, pp. 358\u2013362.","DOI":"10.1109\/ICIP.1998.723498"},{"key":"334057_CR15","unstructured":"N. Vasconcelos and A. Lippman, \u201cTowards semantically meaningful feature spaces for the characterization of video content,\u201d in Proceedings of ICIP'97, 1997."},{"key":"334057_CR16","doi-asserted-by":"crossref","unstructured":"W. Wolf, \u201cHidden Markov model parsing of video programs,\u201d in Proceedings of ICASSP'97, 1997, pp. 2609\u20132611.","DOI":"10.1109\/ICASSP.1997.595323"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1011395131992.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1023\/A:1011395131992\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1011395131992.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T06:34:11Z","timestamp":1748241251000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1023\/A:1011395131992"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2001,6]]},"references-count":16,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2001,6]]}},"alternative-id":["334057"],"URL":"https:\/\/doi.org\/10.1023\/a:1011395131992","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2001,6]]}}}