{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T06:18:38Z","timestamp":1743056318727,"version":"3.40.3"},"publisher-location":"Boston, MA","reference-count":62,"publisher":"Springer US","isbn-type":[{"type":"print","value":"9780387938073"},{"type":"electronic","value":"9780387938080"}],"license":[{"start":{"date-parts":[[2010,1,1]],"date-time":"2010-01-01T00:00:00Z","timestamp":1262304000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2010,1,1]],"date-time":"2010-01-01T00:00:00Z","timestamp":1262304000000},"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":[],"published-print":{"date-parts":[[2010]]},"DOI":"10.1007\/978-0-387-93808-0_16","type":"book-chapter","created":{"date-parts":[[2009,10,1]],"date-time":"2009-10-01T11:47:11Z","timestamp":1254397631000},"page":"433-461","source":"Crossref","is-referenced-by-count":1,"title":["Visual Attention, Speaking Activity, and Group Conversational Analysis in Multi-Sensor Environments"],"prefix":"10.1007","author":[{"given":"Daniel","family":"Gatica-Perez","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jean-Marc","family":"Odobez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"16_CR1","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1007\/BF01115461","volume":"1","author":"M Argyle","year":"1977","unstructured":"Argyle M, JGraham (1977) The central europe experiment - looking at persons and looking at things. Journal of Environmental Psychology and Nonverbal Behaviour 1:6\u201316","journal-title":"Journal of Environmental Psychology and Nonverbal Behaviour"},{"key":"16_CR2","unstructured":"Ba S, Odobez JM (2008) Multi-person visual focus of attention from head pose and meeting contextual cues. Tech. Rep. 47, Idiap Research Institute"},{"key":"16_CR3","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1109\/TSMCB.2008.927274","volume":"39","author":"S Ba","year":"2008","unstructured":"Ba S, Odobez JM (2008) Recognizing human visual focus of attention from head pose in meetings. IEEE Trans. on System, Man and Cybernetics: part B, Man, Vol. 39. No. 1. pp. 16-34, Feb 2009","journal-title":"IEEE Trans. on System, Man and Cybernetics: part B, Man"},{"key":"16_CR4","unstructured":"Ba SO, Odobez JM (2005) A Rao-Blackwellized mixed state particle filter for head pose tracking. In: Proc. ACM-ICMI-MMMP, pp 9\u201316"},{"key":"16_CR5","unstructured":"Bachour K, Kaplan F, Dillenbourg P (Sept, 2008) An interactive table for regulating face-to-face collaborative learning. In: Proc. European Conf. on Technology-Enhanced Learning (ECTEL), Maastricht"},{"key":"16_CR6","unstructured":"Basu S, Choudhury T, Clarkson B, Pentland A (Dec. 2001) Towards measuring human interactions in conversational settings. In: Proc. IEEE CVPR Int. Workshop on Cues in Communication (CVPR-CUES), Kauai"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Burgoon JK, Dunbar NE (2006) The Sage Handbook of Nonverbal Communication, Sage, chap Nonverbal expressions of dominance and power in human relationships","DOI":"10.4135\/9781412976152.n15"},{"key":"16_CR8","unstructured":"Cappella J (1985) Multichannel integrations of nonverbal behavior, Erlbaum, chap Controlling the floor in conversation"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Carletta J, Ashby S, Bourban S, Flynn M, Guillemot M, T Hain JK, Karaiskos V, Kraaij W, Kronenthal M, Lathoud G, Lincoln M, A Lisowska IM, Post W, Reidsma D, Wellner P (2005) The AMI meeting corpus: A pre-announcement. In: Proc. Workshop on Machine Learning for Multimodal Interaction (MLMI), Edinburgh","DOI":"10.1007\/11677482_3"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Chen L, Harper M, Franklin A, Rose T, Kimbara I (2005) A Multimodal Analysis of Floor Control in Meetings. In: Proc. Workshop on Machine Learning for Multimodal Interaction (MLMI)","DOI":"10.1007\/11965152_4"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Cook M, Smith JMC (1975) The role of gaze in impression formation. British Journal of Social and Clinical Psychology","DOI":"10.1111\/j.2044-8260.1975.tb00144.x"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"DiMicco JM, Pandolfo A, Bender W (2004) Influencing group participation with a shared display. In: Proc. ACM Conf. on Computer Supported Cooperative Work (CSCW), Chicago","DOI":"10.1145\/1031607.1031713"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Dines J, Vepa J, Hain T (2006) The segmentation of multi-channel meeting recordings for automatic speech recognition. In: Int. Conf. on Spoken Language Processing (Interspeech ICSLP)","DOI":"10.21437\/Interspeech.2006-366"},{"issue":"2","key":"16_CR14","doi-asserted-by":"publisher","first-page":"106","DOI":"10.2307\/3033933","volume":"45","author":"JF Dovidio","year":"1982","unstructured":"Dovidio JF, Ellyson SL (1982) Decoding visual dominance: atributions of power based on relative percentages of looking while speaking and looking while listening. Social Psychology Quarterly 45(2):106\u2013113","journal-title":"Social Psychology Quarterly"},{"issue":"2","key":"16_CR15","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1177\/0265407505050944","volume":"22","author":"NE Dunbar","year":"2005","unstructured":"Dunbar NE, Burgoon JK (2005) Perceptions of power and interactional dominance in interpersonal relationships. Journal of Social and Personal Relationships 22(2):207\u2013233","journal-title":"Journal of Social and Personal Relationships"},{"issue":"2","key":"16_CR16","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1037\/h0033031","volume":"23","author":"S Duncan Jr","year":"1972","unstructured":"Duncan Jr S (1972) Some signals and rules for taking speaking turns in conversations. Journal of Personality and Social Psychology 23(2):283\u2013292","journal-title":"Journal of Personality and Social Psychology"},{"issue":"1","key":"16_CR17","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1037\/h0026383","volume":"10","author":"JS Efran","year":"1968","unstructured":"Efran JS (1968) Looking for approval: effects of visual behavior of approbation from persons differing in importance. Journal of Personality and Social Psychology 10(1):21\u201325","journal-title":"Journal of Personality and Social Psychology"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Exline RV, Ellyson SL, Long B (1975) Advances in the study of communication and affect, Plenum Press, chap Visual behavior as an aspect of power role relationships","DOI":"10.1007\/978-1-4684-2835-3_2"},{"issue":"6","key":"16_CR19","doi-asserted-by":"publisher","first-page":"487","DOI":"10.1111\/1467-9280.00292","volume":"11","author":"N Fay","year":"2000","unstructured":"Fay N, Garod S, Carletta J (2000) Group discussion as interactive dialogue or serial monologue: the influence of group size. Psychological Science 11(6):487\u2013492","journal-title":"Psychological Science"},{"key":"16_CR20","doi-asserted-by":"crossref","first-page":"2328","DOI":"10.1152\/jn.1997.77.5.2328","volume":"77","author":"EG Freedman","year":"1997","unstructured":"Freedman EG, Sparks DL (1997) Eye-head coordination during head-unrestrained gaze shifts in rhesus monkeys. Journal of Neurophysiology 77:2328\u20132348","journal-title":"Journal of Neurophysiology"},{"key":"16_CR21","doi-asserted-by":"crossref","unstructured":"Gatica-Perez D (2006) Analyzing human interaction in conversations: a review. In: Proc. IEEE Int. Conf. on Multisensor Fusion and Integration for Intelligent Systems (MFI), Heidelberg","DOI":"10.1109\/MFI.2006.265658"},{"key":"16_CR22","doi-asserted-by":"crossref","unstructured":"Gatica-Perez D (2009) Automatic Nonverbal Analysis of Social Interaction in Small Groups: a Review, Image and Vision Computing, Special Issue on Human Naturalistic Behavior","DOI":"10.1016\/j.imavis.2009.01.004"},{"key":"16_CR23","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1016\/0167-6393(92)90015-Y","volume":"11","author":"J Gauvain","year":"1992","unstructured":"Gauvain J, Lee CH (1992) Bayesian learning for hidden Markov model with Gaussian mixture state observation densities. Speech Communication 11:205\u2013213","journal-title":"Speech Communication"},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Goodwin C, Heritage J (1990) Conversation analysis. Annual Review of Anthropology pp 981\u2013987","DOI":"10.1146\/annurev.an.19.100190.001435"},{"issue":"6","key":"16_CR25","doi-asserted-by":"publisher","first-page":"898","DOI":"10.1037\/0033-2909.131.6.898","volume":"131","author":"JA Hall","year":"2005","unstructured":"Hall JA, Coats EJ, LeBeau LS (2005) Nonverbal behavior and the vertical dimension of social relations: A meta-analysis. Psychological Bulletin 131(6):898\u2013924","journal-title":"Psychological Bulletin"},{"issue":"4","key":"16_CR26","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1016\/j.tics.2005.02.009","volume":"9","author":"M Hayhoe","year":"2005","unstructured":"Hayhoe M, Ballard D (2005) Eye movements in natural behavior. TRENDS in Cognitive Sciences 9(4):188\u2013194","journal-title":"TRENDS in Cognitive Sciences"},{"key":"16_CR27","doi-asserted-by":"crossref","unstructured":"Hung H, Jayagopi D, Yeo C, Friedland G, Ba SO, Odobez JM, Ramchandran K, Mirghafori N, Gatica-Perez D (2007) Using audio and video features to classify the most dominant person in a group meeting. In: Proc. of ACM Multimedia","DOI":"10.1145\/1291233.1291423"},{"key":"16_CR28","doi-asserted-by":"crossref","unstructured":"Hung H, Huang Y, Friedland G, Gatica-Perez D (2008) Estimating the dominant person in multi-party conversations using speaker diarization strategies. In: International Conference on Acoustics, Speech and Signal Processing (ICASSP), Las Vegas","DOI":"10.1109\/ICASSP.2008.4518080"},{"key":"16_CR29","doi-asserted-by":"crossref","unstructured":"Hung H, Jayagopi D, Ba S, Odobez JM, Gatica-Perez D (2008) Investigating automatic dominance estimation in groups from visual attention and speaking activity. in Proc. Int. Conf. on Multimodal Interfaces (ICMI), Chania, October.","DOI":"10.1145\/1452392.1452441"},{"key":"16_CR30","doi-asserted-by":"crossref","first-page":"501","DOI":"10.1109\/TASL.2008.2008238","volume":"17","author":"D Jayagopi","year":"2009","unstructured":"Jayagopi D, Hung H, Yeo C, Gatica-Perez D (2009) Modeling dominance in group conversations using nonverbal activity cues. IEEE Trans. on Audio, Speech, and Language Processing, Special Issue on Multimodal Processing for Speech-based Interactions, Vol. 17, No. 3, pp. 501-513. March","journal-title":"IEEE Trans. on Audio, Speech, and Language Processing, Special Issue on Multimodal Processing for Speech-based Interactions"},{"key":"16_CR31","unstructured":"Jovanovic N, Op den Akker H (2004) Towards automatic addressee identification in multi-party dialogues. In: 5th SIGdial Workshop on Discourse and Dialogue"},{"key":"16_CR32","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1016\/0001-6918(67)90005-4","volume":"26","author":"A Kendon","year":"1967","unstructured":"Kendon A (1967) Some functions of gaze-direction in social interaction. Acta Psychologica 26:22\u201363","journal-title":"Acta Psychologica"},{"key":"16_CR33","doi-asserted-by":"crossref","unstructured":"Kim T, Chang A, Holland L, Pentland A (2008) Meeting mediator: Enhancing group collaboration with sociometric feedback. In: Proc. ACM Conf. on Computer Supported Cooperative Work (CSCW), San Diego","DOI":"10.1145\/1460563.1460636"},{"key":"16_CR34","unstructured":"Knapp ML, Hall JA (2005) Nonverbal Communication in Human Interaction. Wadsworth Publishing"},{"key":"16_CR35","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1006\/jnca.2002.0125","volume":"25","author":"M Kouadio","year":"2002","unstructured":"Kouadio M, Pooch U (2002) Technology on social issues of videoconferencing on the internet: a survey. Journal of Network and Computer Applications 25:37\u201356","journal-title":"Journal of Network and Computer Applications"},{"key":"16_CR36","doi-asserted-by":"crossref","unstructured":"Kulyk O, Wang J, Terken J (2006) Real-time feedback on nonverbal behaviour to enhance social dynamics in small group meetings. In: Proc. Workshop on Machine Learning for Multimodal Interaction (MLMI)","DOI":"10.1007\/11677482_13"},{"issue":"2","key":"16_CR37","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1016\/S1364-6613(99)01436-9","volume":"4","author":"S Langton","year":"2000","unstructured":"Langton S, Watt R, Bruce V (2000) Do the eyes have it ? cues to the direction of social attention. Trends in Cognitive Sciences 4(2):50\u201358","journal-title":"Trends in Cognitive Sciences"},{"key":"16_CR38","volume-title":"Spatio-temporal analysis of spontaneous speech with microphone arrays","author":"G Lathoud","year":"2006","unstructured":"Lathoud G (2006) Spatio-temporal analysis of spontaneous speech with microphone arrays. PhD thesis, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland"},{"key":"16_CR39","doi-asserted-by":"crossref","unstructured":"Lathoud G, McCowan I (2003) Location Based Speaker Segmentation. In: Proceedings of the 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP-03), Hong Kong","DOI":"10.1109\/ICME.2003.1221388"},{"key":"16_CR40","doi-asserted-by":"crossref","unstructured":"Matena L, Jaimes A, Popescu-Belis A (2008) Graphical representation of meetings on mobile devices. In: MobileHCI conference, Amsterdam, The Netherlands","DOI":"10.1145\/1409240.1409330"},{"key":"16_CR41","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1016\/j.cviu.2004.07.010","volume":"98","author":"C Morimoto","year":"2005","unstructured":"Morimoto C, Mimica M (2005) Eye gaze tracking techniques for interactive applications. Computer Vision and Image Understanding 98:4\u201324","journal-title":"Computer Vision and Image Understanding"},{"key":"16_CR42","doi-asserted-by":"crossref","unstructured":"Novick D, Hansen B, Ward K (1996) Coordinating turn taking with gaze. In: International Conference on Spoken Language Processing","DOI":"10.21437\/ICSLP.1996-485"},{"key":"16_CR43","doi-asserted-by":"crossref","unstructured":"Odobez JM, Ba S (2007) A Cognitive and Unsupervised MAP Adaptation Approach to the Recognition of Focus of Attention from Head pose. In: Proc. of ICME","DOI":"10.1109\/ICME.2007.4284916"},{"key":"16_CR44","doi-asserted-by":"crossref","unstructured":"Ohno T (2005) Weak gaze awareness in video-mediated communication. In: Proceedings of Conference on Human Factors in Computing Systems, pp 1709\u20131712","DOI":"10.1145\/1056808.1057003"},{"key":"16_CR45","doi-asserted-by":"crossref","unstructured":"Otsuka K, Takemae Y, Yamato J, Murase H (2005) A probabilistic inference of multiparty-conversation structure based on markov-switching models of gaze patterns, head directions, and utterances. In: Proc. of ICMI, pp 191\u2013198","DOI":"10.1145\/1088463.1088497"},{"key":"16_CR46","doi-asserted-by":"crossref","unstructured":"Otsuka K, Yamato J, Takemae Y, Murase H (2006) Conversation scene analysis with dynamic bayesian network based on visual head tracking. In: Proc. of ICME","DOI":"10.1109\/ICME.2006.262677"},{"key":"16_CR47","doi-asserted-by":"crossref","unstructured":"Otsuka K, Yamato J, Takemae Y, Murase H (2006) Quantifying interpersonal influence in face-to-face conversations based on visual attention patterns. In: Proc. ACM CHI Extended Abstract, Montreal","DOI":"10.1145\/1125451.1125672"},{"key":"16_CR48","doi-asserted-by":"crossref","unstructured":"Ram\u00edrez J, G\u00f3rriz J, Segura J (2007) Robust speech recognition and understanding, I-Tech, I-Tech Education and Publishing, Vienna, chap Voice activity detection: Fundamentals and speech recognition system robustness","DOI":"10.5772\/4740"},{"key":"16_CR49","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1145\/1357054.1357095","volume-title":"CHI \u201908: Proceeding of the twenty-sixth annual SIGCHI conference on Human factors in computing systems","author":"A Ranjan","year":"2008","unstructured":"Ranjan A, Birnholtz J, Balakrishnan R (2008) Improving meeting capture by applying television production principles with audio and motion detection. In: CHI \u201908: Proceeding of the twenty-sixth annual SIGCHI conference on Human factors in computing systems, ACM, New York, NY, USA, pp 227\u2013236, DOI http:\/\/doi.acm.org\/10.1145\/1357054.1357095"},{"key":"16_CR50","unstructured":"Rhee HS, Pirkul H, Jacob V, Barhki R (1995) Effects of computer-mediated communication on group negotiation: Au empirical study. In: Proceedings of the 28th Annual Hawaii International Conference on System Sciences, pp 981\u2013987"},{"key":"16_CR51","doi-asserted-by":"crossref","unstructured":"Rienks R, Heylen D (2005) Automatic dominance detection in meetings using easily detectable features. In: Proc. Workshop on Machine Learning for Multimodal Interaction (MLMI), Edinburgh","DOI":"10.1007\/11677482_7"},{"key":"16_CR52","doi-asserted-by":"crossref","unstructured":"Rienks R, Zhang D, Gatica-Perez D, Post W (2006) Detection and application of influence rankings in small-group meetings. In: Proc. Int. Conf. on Multimodal Interfaces (ICMI), Banff","DOI":"10.1145\/1180995.1181047"},{"issue":"3","key":"16_CR53","first-page":"420","volume":"28","author":"M Schmid Mast","year":"2002","unstructured":"Schmid Mast M (2002) Dominance as expressed and inferred through speaking time: A meta-analysis. Human Communication Research 28(3):420\u2013450","journal-title":"Human Communication Research"},{"key":"16_CR54","unstructured":"Shriberg E, Stolcke A, Baron D (2001) Can prosody aid the automatic processing of multi-party meetings? evidence from predicting punctuation, disfluencies, and overlapping speech. In: ISCA Tutorial and Research Workshop (ITRW) on Prosody in Speech Recognition and Understanding (Prosody 2001)"},{"key":"16_CR55","unstructured":"Stiefelhagen R (2002) Tracking and modeling focus of attention. PhD thesis, University of Karlsruhe"},{"issue":"4","key":"16_CR56","doi-asserted-by":"publisher","first-page":"928","DOI":"10.1109\/TNN.2002.1021893","volume":"13","author":"R Stiefelhagen","year":"2002","unstructured":"Stiefelhagen R, Yang J, Waibel A (2002) Modeling focus of attention for meeting indexing based on multiple cues. IEEE Trans on Neural Networks 13(4):928\u2013938","journal-title":"IEEE Trans on Neural Networks"},{"key":"16_CR57","doi-asserted-by":"crossref","unstructured":"Sturm J, Herwijnen OHV, Eyck A, Terken J (2007) Influencing social dynamics in meetings through a peripheral display. In: Proc. Int. Conf. on Multimodal Interfaces (ICMI), Nagoya","DOI":"10.1145\/1322192.1322238"},{"key":"16_CR58","doi-asserted-by":"crossref","unstructured":"Takemae Y, Otsuka K, Yamato J (2005) Automatic video editing system using stereo-based head tracking for multiparty conversation. In: ACM Conference on Human Factors in Computing Systems, pp 1817\u20131820","DOI":"10.1145\/1056808.1057030"},{"key":"16_CR59","doi-asserted-by":"crossref","unstructured":"Valente F (2006) Infinite models for speaker clustering. In: Int. Conf. on Spoken Language Processing (Interspeech ICSLP)","DOI":"10.21437\/Interspeech.2006-365"},{"key":"16_CR60","doi-asserted-by":"crossref","unstructured":"Vijayasenan D, Valente F, Bourlard H (2008) Integration of tdoa features in information bottleneck framework for fast speaker diarization. In: Interspeech 2008","DOI":"10.21437\/Interspeech.2008-8"},{"key":"16_CR61","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1109\/TSA.2004.838531","volume":"13","author":"SJ Wrigley","year":"2005","unstructured":"Wrigley SJ, Brown GJ, Wan V, Renals S (2005) Speech and crosstalk detection in multi-channel audio. IEEE Trans on Speech and Audio Processing 13:84\u201391","journal-title":"IEEE Trans on Speech and Audio Processing"},{"key":"16_CR62","volume-title":"Compressed domain video processing of meetings for activity estimation in dominance classification and slide transition detection","author":"C Yeo","year":"2008","unstructured":"Yeo C, Ramchandran K (2008) Compressed domain video processing of meetings for activity estimation in dominance classification and slide transition detection. Tech. Rep. UCB\/EECS-2008-79, EECS Department, University of California, Berkeley"}],"container-title":["Handbook of Ambient Intelligence and Smart Environments"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-0-387-93808-0_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T13:06:04Z","timestamp":1714568764000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-0-387-93808-0_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9780387938073","9780387938080"],"references-count":62,"URL":"https:\/\/doi.org\/10.1007\/978-0-387-93808-0_16","relation":{},"subject":[],"published":{"date-parts":[[2010]]}}}