{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T17:52:41Z","timestamp":1725558761901},"publisher-location":"Berlin, Heidelberg","reference-count":55,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540245094"},{"type":"electronic","value":"9783540305682"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2005]]},"DOI":"10.1007\/978-3-540-30568-2_6","type":"book-chapter","created":{"date-parts":[[2010,7,4]],"date-time":"2010-07-04T18:40:10Z","timestamp":1278268810000},"page":"56-75","source":"Crossref","is-referenced-by-count":1,"title":["Towards Computer Understanding of Human Interactions"],"prefix":"10.1007","author":[{"given":"Iain","family":"McCowan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Gatica-Perez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Samy","family":"Bengio","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Darren","family":"Moore","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Herv\u00e9","family":"Bourlard","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"6_CR1","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":"6_CR2","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\u00a08 (1999)","DOI":"10.1162\/105474699566297"},{"key":"6_CR3","doi-asserted-by":"crossref","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 (1998)","DOI":"10.1109\/CVPR.1998.698706"},{"key":"6_CR4","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 (1999)","DOI":"10.1007\/3-540-49256-9_17"},{"key":"6_CR5","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\u00a022 (2000)","DOI":"10.1109\/34.868684"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Hongeng, S., Nevatia, R.: Multi-agent event recognition. In: Proc. IEEE Int. Conference on Computer Vision, Vancouver (2001)","DOI":"10.1109\/ICCV.2001.937608"},{"key":"6_CR7","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":"6_CR8","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 (2001)","DOI":"10.3115\/1072133.1072203"},{"key":"6_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":"6_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":"6_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"},{"key":"6_CR12","unstructured":"Padilha, E., Carletta, J.C.: A simulation of small group discussion. In: EDILOG (2002)"},{"key":"6_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, 965\u2013971 (1988)","journal-title":"Journal of Personality and Social Psychology"},{"key":"6_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, 487\u2013492 (2000)","journal-title":"Psychological Science"},{"key":"6_CR15","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)","DOI":"10.1109\/ICSLP.1996.608001"},{"key":"6_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, 523\u2013529 (1977)","journal-title":"Journal of Personality and Social Psychology"},{"key":"6_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, 313\u2013323 (1978)","journal-title":"Journal of Personality and Social Psychology"},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"Kubala, F.: Rough\u2019n\u2019ready: a meeting recorder and browser. ACM Computing Surveys\u00a031 (1999)","DOI":"10.1145\/323216.323354"},{"key":"6_CR19","doi-asserted-by":"crossref","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 (2001)","DOI":"10.1109\/ICASSP.2001.940902"},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Renals, S., Ellis, D.: Audio information access from meeting rooms. In: Proc. IEEE ICASSP 2003 (2003)","DOI":"10.1109\/ICASSP.2003.1202750"},{"key":"6_CR21","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)","DOI":"10.1145\/641007.641112"},{"key":"6_CR22","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 (2003)"},{"key":"6_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)"},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Smith, K., Gatica-Perez, D.: Order matters: a distributed sampling method for multi-object tracking. In: IDIAP Research Report IDIAP-RR-04-25, Martigny (2004)","DOI":"10.5244\/C.18.89"},{"key":"6_CR25","doi-asserted-by":"crossref","unstructured":"Ba, S., Odobez, J.M.: A probabilistic framework for joint head tracking and pose estimation. In: Proc. ICPR, Cambridge (2004)","DOI":"10.1109\/ICPR.2004.1333754"},{"key":"6_CR26","doi-asserted-by":"crossref","unstructured":"Cutler, R.: The distributed meetings system. In: Proceedings of IEEE ICASSP 2003 (2003)","DOI":"10.1109\/ICASSP.2003.1202753"},{"key":"6_CR27","doi-asserted-by":"crossref","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)","DOI":"10.1109\/ICASSP.2003.1202748"},{"key":"6_CR28","doi-asserted-by":"crossref","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 (1997)","DOI":"10.1109\/ICASSP.1997.599616"},{"key":"6_CR29","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)","DOI":"10.21437\/Eurospeech.2001-352"},{"key":"6_CR30","doi-asserted-by":"crossref","unstructured":"Pfau, T., Ellis, D., Stolcke, A.: Multispeaker speech activity detection for the ICSI meeting recorder. In: Proceedings of ASRU 2001 (2001)","DOI":"10.1109\/ASRU.2001.1034599"},{"key":"6_CR31","doi-asserted-by":"crossref","unstructured":"Kemp, T., Schmidt, M., Westphal, M., Waibel, A.: Strategies for automatic segmentation of audio data. In: Proceedings of ICASSP 2000 (2000)","DOI":"10.1109\/ICASSP.2000.861862"},{"key":"6_CR32","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 (2003)","DOI":"10.1109\/ICME.2003.1221388"},{"key":"6_CR33","doi-asserted-by":"crossref","unstructured":"Lathoud, G., McCowan, I., Moore, D.: Segmenting multiple concurrent speakers using microphone arrays. In: Proceedings of Eurospeech 2003 (2003)","DOI":"10.21437\/Eurospeech.2003-47"},{"key":"6_CR34","unstructured":"Lathoud, G., Odobez, J.M., McCowan, I.: Unsupervised location-based segmentation of multi-party speech. In: Proceedings of the 2004 ICASSP-NIST Meeting Recognition Workshop (2004)"},{"key":"6_CR35","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, pp. 19\u201338. Springer, Heidelberg (2001)"},{"key":"6_CR36","doi-asserted-by":"crossref","unstructured":"McCowan, I., Bourlard, H.: Microphone array post-filter based on noise field coherence. IEEE Transactions on Speech and Audio Processing (2003) (to appear)","DOI":"10.1109\/TSA.2003.818212"},{"key":"6_CR37","doi-asserted-by":"crossref","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 (2003)","DOI":"10.1109\/ICASSP.2003.1200015"},{"key":"6_CR38","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 Academic Publishers, Dordrecht (1999)"},{"key":"6_CR39","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)","DOI":"10.21437\/ICSLP.2002-197"},{"key":"6_CR40","doi-asserted-by":"crossref","unstructured":"Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proc. IEEE Int. Conf. on Computer Vision (CVPR), Kawaii (2001)","DOI":"10.1109\/CVPR.2001.990517"},{"issue":"1","key":"6_CR41","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1109\/34.655647","volume":"20","author":"H. Rowley","year":"1998","unstructured":"Rowley, H., Baluja, S., Kanade, T.: Neural network-based face detection. IEEE Tran. Pattern Analysis and Machine Intelligence\u00a020(1), 23\u201338 (1998)","journal-title":"IEEE Tran. Pattern Analysis and Machine Intelligence"},{"key":"6_CR42","doi-asserted-by":"publisher","first-page":"2409","DOI":"10.1016\/S0167-8655(03)00070-9","volume":"24","author":"C. Sanderson","year":"2003","unstructured":"Sanderson, C., Paliwal, K.: Fast features for face authentication under illumination direction changes. Pattern Recognition Letters\u00a024, 2409\u20132419 (2003)","journal-title":"Pattern Recognition Letters"},{"key":"6_CR43","doi-asserted-by":"crossref","unstructured":"Cardinaux, F., Sanderson, C., Bengio, S.: Face verification using adapted generative models. In: Proc. Int. Conf. Automatic Face and Gesture Recognition (AFGR), Seoul, Korea (2004)","DOI":"10.1109\/AFGR.2004.1301636"},{"key":"6_CR44","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, 267\u2013276 (2002)","journal-title":"Information Fusion"},{"key":"6_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1007\/3-540-44887-X_74","volume-title":"Audio-and Video-Based Biometrie Person Authentication","author":"E. Bailly-Bailli\u00e8re","year":"2003","unstructured":"Bailly-Bailli\u00e8re, E., Bengio, S., Bimbot, F., Hamouz, M., Kittler, J., Mari\u00e9thoz, J., Matas, J., Messer, K., Popovici, V., Por\u00e9e, F., Ruiz, B., Thiran, J.P.: The BANCA database and evaluation protocol. In: Kittler, J., Nixon, M.S. (eds.) AVBPA 2003. LNCS, vol.\u00a02688, pp. 625\u2013638. Springer, Heidelberg (2003)"},{"key":"6_CR46","doi-asserted-by":"crossref","unstructured":"Messer, K., Kittler, J., Sadeghi, M., Hamouz, M., Kostyn, A., Marcel, S., Bengio, S., Cardinaux, F., Sanderson, C., Poh, N., Rodriguez, Y., Kryszczuk, K., Czyz, J., Vandendorpe, L., Ng, J., Cheung, H., Tang, B.: Face authentication competition on the BANCA database. In: International Conference on Biometric Authentication, ICBA (2004)","DOI":"10.1007\/978-3-540-25948-0_2"},{"key":"6_CR47","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)"},{"key":"6_CR48","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":"6_CR49","doi-asserted-by":"crossref","unstructured":"McCowan, I., Gatica-Perez, D., Bengio, S., Lathoud, G.: Automatic analysis of multimodal group actions in meetings. Technical Report RR 03-27, IDIAP (2003)","DOI":"10.1109\/TPAMI.2005.49"},{"key":"6_CR50","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":"6_CR51","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)"},{"key":"6_CR52","unstructured":"Brand, M.: Coupled hidden markov models for modeling interacting processes. TR 405, MIT Media Lab Vision and Modeling (1996)"},{"key":"6_CR53","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: Proc. IEEE CVPR Workshop on Event Mining, Washington, DC (2004)","DOI":"10.1109\/CVPR.2004.399"},{"key":"6_CR54","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"},{"key":"6_CR55","unstructured":"Basu, S., Choudhury, T., Clarkson, B., Pentland, A.: Learning human interactions with the influence model. Technical Report 539, MIT Media Laboratory (2001)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning for Multimodal Interaction"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-30568-2_6.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T22:33:15Z","timestamp":1685658795000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-30568-2_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2005]]},"ISBN":["9783540245094","9783540305682"],"references-count":55,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-30568-2_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2005]]}}}