{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T11:27:02Z","timestamp":1763551622740,"version":"3.38.0"},"publisher-location":"Berlin, Heidelberg","reference-count":47,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540204183"},{"type":"electronic","value":"9783540398639"}],"license":[{"start":{"date-parts":[[2003,1,1]],"date-time":"2003-01-01T00:00:00Z","timestamp":1041379200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2003]]},"DOI":"10.1007\/978-3-540-39863-9_18","type":"book-chapter","created":{"date-parts":[[2011,1,8]],"date-time":"2011-01-08T20:43:56Z","timestamp":1294519436000},"page":"235-251","source":"Crossref","is-referenced-by-count":10,"title":["Towards Computer Understanding of Human Interactions"],"prefix":"10.1007","author":[{"given":"Iain","family":"McCowan","sequence":"first","affiliation":[]},{"given":"Daniel","family":"Gatica-Perez","sequence":"additional","affiliation":[]},{"given":"Samy","family":"Bengio","sequence":"additional","affiliation":[]},{"given":"Darren","family":"Moore","sequence":"additional","affiliation":[]},{"given":"Herv\u00e9","family":"Bourlard","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"unstructured":"Waibel, A., Schultz, T., Bett, M., Malkin, R., Rogina, I., Stiefelhagen, R., Yang, J.: SMaRT:the Smart Meeting Room Task at ISL. In: Proc. IEEE ICASSP 2003 (2003)","key":"18_CR1"},{"doi-asserted-by":"crossref","unstructured":"Bobick, A., Intille, S., Davis, J., Baird, F., Pinhanez, C., Campbell, L., Ivanov, Y., Schutte, A., Wilson, A.: The KidsRoom: A Perceptually-Based Interactive and Immersive Story Environment. PRESENCE: Teleoperators and Virtual Environments 8 (August 1999)","key":"18_CR2","DOI":"10.1162\/105474699566297"},{"unstructured":"Johnson, N., Galata, A., Hogg, D.: The acquisition and use of interaction behaviour models. In: Proc. IEEE Int. Conference on Computer Vision and Pattern Recognition (June 1998)","key":"18_CR3"},{"doi-asserted-by":"crossref","unstructured":"Jebara, T., Pentland, A.: Action reaction learning: Automatic visual analysis and synthesis of interactive behaviour. In: Proc. International Conference on Vision Systems (January 1999)","key":"18_CR4","DOI":"10.1007\/3-540-49256-9_17"},{"doi-asserted-by":"crossref","unstructured":"Oliver, N., Rosario, B., Pentland, A.: A bayesian computer vision system for modeling human interactions. IEEE Transactions on Pattern Analysis and Machine Intelligence 22 (August 2000)","key":"18_CR5","DOI":"10.1109\/34.868684"},{"unstructured":"Hongeng, S., Nevatia, R.: Multi-agent event recognition. In: Proc. IEEE Int. Conference on Computer Vision (Vancouver) (July 2001)","key":"18_CR6"},{"unstructured":"Carletta, J., Isard, A., Isard, S., Kowtko, J., Doherty-Sneddon, G., Anderson, A.: The coding of dialogue structure in a corpus. In: Andernach, J., van de Burgt, S., van der Hoeven, G. (eds.) Proceedings of the Twente Workshop on Language Technology: Corpus-based approaches to dialogue modelling, Universiteit Twente (1995)","key":"18_CR7"},{"doi-asserted-by":"crossref","unstructured":"Morgan, N., Baron, D., Edwards, J., Ellis, D., Gelbart, D., Janin, A., Pfau, T., Shriberg, E., Stolcke, A.: The meeting project at ICSI. In: Proc. of the Human Language Technology Conference, San Diego, CA (March 2001)","key":"18_CR8","DOI":"10.3115\/1072133.1072203"},{"key":"18_CR9","volume-title":"Interaction Process Analysis: A method for the study of small groups","author":"R.F. Bales","year":"1951","unstructured":"Bales, R.F.: Interaction Process Analysis: A method for the study of small groups. Addison-Wesley, Reading (1951)"},{"key":"18_CR10","volume-title":"Groups: Interaction and Performance","author":"J.E. McGrath","year":"1984","unstructured":"McGrath, J.E.: Groups: Interaction and Performance. Prentice-Hall, Englewood Cliffs (1984)"},{"key":"18_CR11","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1146\/annurev.ps.33.020182.001211","volume":"33","author":"J. McGrath","year":"1982","unstructured":"McGrath, J., Kravitz, D.: Group research. Annual Review of Psychology\u00a033, 195\u2013230 (1982)","journal-title":"Annual Review of Psychology"},{"unstructured":"Padilha, E., Carletta, J.C.: A simulation of small group discussion. In: EDILOG (2002)","key":"18_CR12"},{"issue":"6","key":"18_CR13","doi-asserted-by":"publisher","first-page":"965","DOI":"10.1037\/0022-3514.54.6.965","volume":"54","author":"K.C.H. Parker","year":"1988","unstructured":"Parker, K.C.H.: Speaking turns in small group interaction: A context-sensitive event sequence model. Journal of Personality and Social Psychology\u00a054(6), 965\u2013971 (1988)","journal-title":"Journal of Personality and Social Psychology"},{"issue":"6","key":"18_CR14","doi-asserted-by":"publisher","first-page":"487","DOI":"10.1111\/1467-9280.00292","volume":"11","author":"N. Fay","year":"2000","unstructured":"Fay, N., Garrod, S., Carletta, J.: Group discussion as interactive dialogue or serial monologue: The influence of group size. Psychological Science\u00a011(6), 487\u2013492 (2000)","journal-title":"Psychological Science"},{"doi-asserted-by":"crossref","unstructured":"Novick, D., Hansen, B., Ward, K.: Coordinating turn-taking with gaze. In: Proceedings of the 1996 International Conference on Spoken Language Processing, ICSLP 1996 (1996)","key":"18_CR15","DOI":"10.21437\/ICSLP.1996-485"},{"issue":"7","key":"18_CR16","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1037\/0022-3514.35.7.523","volume":"35","author":"R. Krauss","year":"1977","unstructured":"Krauss, R., Garlock, C., Bricker, P., McMahon, L.: The role of audible and visible back-channel responses in interpersonal communication. Journal of Personality and Social Psychology\u00a035(7), 523\u2013529 (1977)","journal-title":"Journal of Personality and Social Psychology"},{"issue":"3","key":"18_CR17","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1037\/0022-3514.36.3.313","volume":"36","author":"B. DePaulo","year":"1978","unstructured":"DePaulo, B., Rosenthal, R., Eisenstat, R., Rogers, P., Finkelstein, S.: Decoding discrepant nonverbal cues. Journal of Personality and Social Psychology\u00a036(3), 313\u2013323 (1978)","journal-title":"Journal of Personality and Social Psychology"},{"doi-asserted-by":"crossref","unstructured":"Kubala, F.: Rough\u2019n\u2019ready: a meeting recorder and browser. ACM Computing Surveys\u00a031 (1999)","key":"18_CR18","DOI":"10.1145\/323216.323354"},{"unstructured":"Waibel, A., Bett, M., Metze, F., Ries, K., Schaaf, T., Schultz, T., Soltau, H., Yu, H., Zechner, K.: Advances in automatic meeting record creation and access. In: Proc. IEEE ICASSP, Salt Lake City, UT (May 2001)","key":"18_CR19"},{"unstructured":"Renals, S., Ellis, D.: Audio information access from meeting rooms. In: Proc. IEEE ICASSP 2003 (2003)","key":"18_CR20"},{"doi-asserted-by":"crossref","unstructured":"Cutler, R., Rui, Y., Gupta, A., Cadiz, J., Tashev, I., He, L., Colburn, A., Zhang, Z., Liu, Z., Silverberg, S.: Distributed meetings: A meeting capture and broadcasting system. In: Proc. ACM Multimedia Conference (2002)","key":"18_CR21","DOI":"10.1145\/641007.641112"},{"unstructured":"Gatica-Perez, D., Lathoud, G., McCowan, I., Odobez, J.-M.: A mixed-state i-particle filter for multi-camera speaker tracking. In: Proceedings of WOMTEC (September 2003)","key":"18_CR22"},{"key":"18_CR23","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-3437-9","volume-title":"Sequential Monte Carlo Methods in Practice","author":"A. Doucet","year":"2001","unstructured":"Doucet, A., de Freitas, N., Gordon, N.: Sequential Monte Carlo Methods in Practice. Springer, Heidelberg (2001)"},{"unstructured":"Cutler, R.: The distributed meetings system. In: Proceedings of IEEE ICASSP 2003 (2003)","key":"18_CR24"},{"unstructured":"Stanford, V., Garofolo, J., Michel, M.: The nist smart space and meeting room projects: Signals, acquisition, annotation, and metrics. In: Proceedings of IEEE ICASSP 2003 (2003)","key":"18_CR25"},{"unstructured":"Silverman, H., Patterson, W., Flanagan, J., Rabinkin, D.: A digital processing system for source location and sound capture by large microphone arrays. In: Proceedings of ICASSP 1997 (April 1997)","key":"18_CR26"},{"doi-asserted-by":"crossref","unstructured":"Shriberg, E., Stolcke, A., Baron, D.: Observations on overlap: findings and implications for automatic processing of multi-party conversation. In: Proceedings of Eurospeech 2001, vol.\u00a02, pp. 1359\u20131362 (2001)","key":"18_CR27","DOI":"10.21437\/Eurospeech.2001-352"},{"unstructured":"Pfau, T., Ellis, D., Stolcke, A.: Multispeaker speech activity detection for the ICSI meeting recorder. In: Proceedings of ASRU 2001 (2001)","key":"18_CR28"},{"unstructured":"Kemp, T., Schmidt, M., Westphal, M., Waibel, A.: Strategies for automatic segmentation of audio data. In: Proceedings of ICASSP 2000 (2000)","key":"18_CR29"},{"doi-asserted-by":"crossref","unstructured":"Lathoud, G., McCowan, I.: Location based speaker segmentation. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing (April 2003)","key":"18_CR30","DOI":"10.1109\/ICME.2003.1221388"},{"doi-asserted-by":"crossref","unstructured":"Lathoud, G., McCowan, I., Moore, D.: Segmenting multiple concurrent speakers using microphone arrays. In: Proceedings of Eurospeech 2003 (September 2003)","key":"18_CR31","DOI":"10.21437\/Eurospeech.2003-47"},{"key":"18_CR32","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1007\/978-3-662-04619-7_2","volume-title":"Microphone Arrays","author":"J. Bitzer","year":"2001","unstructured":"Bitzer, J., Simmer, K.U.: Superdirective microphone arrays. In: Brandstein, M., Ward, D. (eds.) Microphone Arrays, ch. 2, pp. 19\u201338. Springer, Heidelberg (2001)"},{"doi-asserted-by":"crossref","unstructured":"McCowan, I., Bourlard, H.: Microphone array post-filter based on noise field coherence. To appear in IEEE Transactions on Speech and Audio Processing (November 2003)","key":"18_CR33","DOI":"10.1109\/ICASSP.2002.5743886"},{"unstructured":"Moore, D., McCowan, I.: Microphone array speech recognition: Experiments on overlapping speech in meetings. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing (April 2003)","key":"18_CR34"},{"key":"18_CR35","doi-asserted-by":"crossref","DOI":"10.1007\/b117227","volume-title":"Biometrics: Person Identification in Networked Society","author":"A. Jain","year":"1999","unstructured":"Jain, A., Bolle, R., Pankanti, S.: Biometrics: Person Identification in Networked Society. Kluwer, Dordrecht (1999)"},{"doi-asserted-by":"crossref","unstructured":"Mari\u00e9thoz, J., Bengio, S.: A comparative study of adaptation methods for speaker verification. In: Proceedings of the International Conference on Spoken Language Processing, ICSLP (2002)","key":"18_CR36","DOI":"10.21437\/ICSLP.2002-197"},{"key":"18_CR37","volume-title":"Proceedings of the 16th International Conference on Pattern Recognition, ICPR","author":"S. Marcel","year":"2002","unstructured":"Marcel, S., Bengio, S.: Improving face verification using skin color information. In: Proceedings of the 16th International Conference on Pattern Recognition, ICPR, IEEE Computer Society Press, Los Alamitos (2002)"},{"doi-asserted-by":"crossref","unstructured":"Sanderson, C., Paliwal, K.: Polynomial Features for Robust Face Authentication. In: Proceedings of International Conference on Image Processing, vol.\u00a03, pp. 997\u20131000 (2002)","key":"18_CR38","DOI":"10.1109\/ICIP.2002.1039143"},{"issue":"4","key":"18_CR39","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1016\/S1566-2535(02)00089-1","volume":"3","author":"S. Bengio","year":"2002","unstructured":"Bengio, S., Marcel, C., Marcel, S., Mari\u00e9thoz, J.: Confidence measures for multimodal identity verification. Information Fusion\u00a03(4), 267\u2013276 (2002)","journal-title":"Information Fusion"},{"key":"18_CR40","volume-title":"Fundamentals of Speech Recognition","author":"L.R. Rabiner","year":"1993","unstructured":"Rabiner, L.R., Juang, B.-H.: Fundamentals of Speech Recognition. Prentice-Hall, Englewood Cliffs (1993)"},{"unstructured":"Starner, T., Pentland, A.: Visual recognition of american sign language using HMMs. In: Proc. Int. Work. on Auto. Face and Gesture Recognition, Zurich (1995)","key":"18_CR41"},{"key":"18_CR42","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, 141\u2013151 (2000)","journal-title":"IEEE Transactions on Multimedia"},{"key":"18_CR43","volume-title":"Advances in Neural Information Processing Systems, 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 Neural Information Processing Systems, NIPS 15, MIT Press, Cambridge (2003)"},{"doi-asserted-by":"crossref","unstructured":"McCowan, I., Gatica-Perez, D., Bengio, S., Lathoud, G.: Automatic analysis of multimodal group actions in meetings. Tech. Rep. RR 03\u201327, IDIAP (2003)","key":"18_CR44","DOI":"10.1109\/TPAMI.2005.49"},{"key":"18_CR45","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1080\/026999300378824","volume":"14","author":"B. Gelder De","year":"2002","unstructured":"De Gelder, B., Vroomen, J.: The perception of emotions by ear and by eye. Cognition and Emotion\u00a014, 289\u2013311 (2002)","journal-title":"Cognition and Emotion"},{"unstructured":"Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proc. IEEE Int. Conf. on Computer Vision (CVPR) (December 2001)","key":"18_CR46"},{"unstructured":"Basu, S., Choudhury, T., Clarkson, B., Pentland, A.: Learning human interactions with the influence model. Tech. Rep. 539, MIT Media Laboratory (June 2001)","key":"18_CR47"}],"container-title":["Lecture Notes in Computer Science","Ambient Intelligence"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-39863-9_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T15:12:33Z","timestamp":1740841953000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-39863-9_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2003]]},"ISBN":["9783540204183","9783540398639"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-39863-9_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2003]]}}}