{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T16:59:35Z","timestamp":1743008375017,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":16,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540325499"},{"type":"electronic","value":"9783540325505"}],"license":[{"start":{"date-parts":[[2006,1,1]],"date-time":"2006-01-01T00:00:00Z","timestamp":1136073600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2006]]},"DOI":"10.1007\/11677482_5","type":"book-chapter","created":{"date-parts":[[2006,2,14]],"date-time":"2006-02-14T15:25:18Z","timestamp":1139930718000},"page":"52-63","source":"Crossref","is-referenced-by-count":10,"title":["Multimodal Integration for Meeting Group Action Segmentation and Recognition"],"prefix":"10.1007","author":[{"given":"Marc","family":"Al-Hames","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alfred","family":"Dielmann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Gatica-Perez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stephan","family":"Reiter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Steve","family":"Renals","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gerhard","family":"Rigoll","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Al-Hames, M., Rigoll, G.: A multi-modal graphical model for robust recognition of group actions in meetings from disturbed videos. In: Proc. IEEE ICIP, Italy (2005)","DOI":"10.1109\/ICIP.2005.1530418"},{"key":"5_CR2","doi-asserted-by":"crossref","unstructured":"Al-Hames, M., Rigoll, G.: A multi-modal mixed-state dynamic Bayesian network for robust meeting event recognition from disturbed data. In: Proc. IEEE ICME (2005)","DOI":"10.1109\/ICME.2005.1521356"},{"key":"5_CR3","volume-title":"Advances in NIPS 15","author":"S. Bengio","year":"2003","unstructured":"Bengio, S.: An asynchronous hidden markov model for audio-visual speech recognition. In: Becker, S., Thrun, S., Obermayer, K. (eds.) Advances in NIPS 15. MIT Press, Cambridge (2003)"},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Bilmes, J.: Graphical models and automatic speech recognition. Mathematical Foundations of Speech and Language Processing (2003)","DOI":"10.1007\/978-1-4419-9017-4_10"},{"key":"5_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1007\/978-3-540-30568-2_7","volume-title":"Machine Learning for Multimodal Interaction","author":"A. Dielmann","year":"2005","unstructured":"Dielmann, A., Renals, S.: Multistream dynamic Bayesian network for meeting segmentation. In: Bengio, S., Bourlard, H. (eds.) MLMI 2004. LNCS, vol.\u00a03361, pp. 76\u201386. Springer, Heidelberg (2005)"},{"issue":"3","key":"5_CR6","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1109\/6046.865479","volume":"2","author":"S. Dupont","year":"2000","unstructured":"Dupont, S., Luettin, J.: Audio-visual speech modeling for continuous speech recognition. IEEE Transactions on Multimedia\u00a02(3), 141\u2013151 (September 2000)","journal-title":"IEEE Transactions on Multimedia"},{"key":"5_CR7","unstructured":"Lathoud, G., McCowan, I.A., Odobez, J.-M.: Unsupervised Location-Based Segmentation of Multi-Party Speech. In: Proc. 2004 ICASSP-NIST Meeting Recognition Workshop (2004)"},{"issue":"3","key":"5_CR8","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1109\/TPAMI.2005.49","volume":"27","author":"I. McCowan","year":"2005","unstructured":"McCowan, I., Gatica-Perez, D., Bengio, S., Lathoud, G., Barnard, M., Zhang, D.: Automatic analysis of multimodal group actions in meetings. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI)\u00a027(3), 305\u2013317 (2005)","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI)"},{"key":"5_CR9","unstructured":"Oliver, N., Horvitz, E., Garg, A.: Layered representations for learning and inferring office activity from multiple sensory channels. In: Proc. ICMI, Pittsburgh (October 2002)"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Pavlovic, V., Frey, B., Huang, T.S.: Time series classification using mixed-state dynamic Bayesian networks. In: Proc. IEEE CVPR (1999)","DOI":"10.1109\/CVPR.1999.784983"},{"issue":"77","key":"5_CR11","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/5.18626","volume":"2","author":"L.R. Rabiner","year":"1989","unstructured":"Rabiner, L.R.: A tutorial on hidden markov models and selected applications in speech recognition. Proc. of the IEEE\u00a02(77), 257\u2013286 (1989)","journal-title":"Proc. of the IEEE"},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"Reiter, S., Rigoll, G.: Segmentation and classification of meeting events using multiple classifier fusion and dynamic programming. In: Proc. IEEE ICPR, pp. 434\u2013437 (2004)","DOI":"10.1109\/ICPR.2004.1334559"},{"key":"5_CR13","doi-asserted-by":"crossref","unstructured":"Reiter, S., Rigoll, G.: Multimodal meeting analysis by segmentation and classification of meeting events based on a higher level semantic approach. In: Proc. IEEE ICASSP (2005)","DOI":"10.1109\/ICASSP.2005.1415366"},{"key":"5_CR14","doi-asserted-by":"crossref","unstructured":"Tritschler, A., Gopinath, R.A.: Improved speaker segmentation and segments clustering using the bayesian information criterion. In: Proc. EUROSPEECH 1999 (1999)","DOI":"10.21437\/Eurospeech.1999-174x"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Zhang, D., Gatica-Perez, D., Bengio, S., McCowan, I., Lathoud, G.: Modeling individual and group actions in meetings: a two-layer hmm framework. In: IEEE Workshop on Event Mining at the Conference on Computer Vision and Pattern Recognition (CVPR) (2004)","DOI":"10.1109\/CVPR.2004.399"},{"key":"5_CR16","unstructured":"Zobl, M., Wallhoff, F., Rigoll, G.: Action recognition in meeting scenarios using global motion features. In: Ferryman, J. (ed.) Proc. PETS-ICVS, pp. 32\u201336 (2003)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning for Multimodal Interaction"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11677482_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,7]],"date-time":"2025-01-07T18:57:34Z","timestamp":1736276254000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11677482_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006]]},"ISBN":["9783540325499","9783540325505"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/11677482_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2006]]}}}