{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T07:08:58Z","timestamp":1726038538896},"reference-count":222,"publisher":"Elsevier BV","issue":"2","license":[{"start":{"date-parts":[[2013,2,1]],"date-time":"2013-02-01T00:00:00Z","timestamp":1359676800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Image and Vision Computing"],"published-print":{"date-parts":[[2013,2]]},"DOI":"10.1016\/j.imavis.2012.07.003","type":"journal-article","created":{"date-parts":[[2012,8,10]],"date-time":"2012-08-10T18:01:40Z","timestamp":1344621700000},"page":"203-221","source":"Crossref","is-referenced-by-count":58,"title":["Towards the automatic detection of spontaneous agreement and disagreement based on nonverbal behaviour: A survey of related cues, databases, and tools"],"prefix":"10.1016","volume":"31","author":[{"given":"Konstantinos","family":"Bousmalis","sequence":"first","affiliation":[]},{"given":"Marc","family":"Mehu","sequence":"additional","affiliation":[]},{"given":"Maja","family":"Pantic","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/j.imavis.2012.07.003_bb0005","first-page":"57","article-title":"A computerized scale for monitoring levels of agreement during a conversation","volume":"8","author":"Cohen","year":"2003","journal-title":"Univ. Pa. Working Pap. Linguist."},{"issue":"12","key":"10.1016\/j.imavis.2012.07.003_bb0010","doi-asserted-by":"crossref","first-page":"1743","DOI":"10.1016\/j.imavis.2008.11.007","article-title":"Social signal processing: survey of an emerging domain","volume":"27","author":"Vinciarelli","year":"2009","journal-title":"Image Vision Comput."},{"key":"10.1016\/j.imavis.2012.07.003_bb0015","series-title":"Social Signal Processing: The Research Agenda","first-page":"511","author":"Pantic","year":"2011"},{"issue":"2","key":"10.1016\/j.imavis.2012.07.003_bb0020","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1504\/IJAACS.2008.019799","article-title":"Human-centred intelligent human\u2013computer interaction (HCI2): how far are we from attaining it?","volume":"1","author":"Pantic","year":"2008","journal-title":"J. Auton. Adapt. Commun. Syst."},{"key":"10.1016\/j.imavis.2012.07.003_bb0025","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1007\/978-3-540-72348-6_3","article-title":"Human computing and machine understanding of human behavior: a survey","volume":"4451","author":"Pantic","year":"2007","journal-title":"Lect. Notes Comput. Sci."},{"issue":"1","key":"10.1016\/j.imavis.2012.07.003_bb0030","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1109\/TPAMI.2008.52","article-title":"A survey of affect recognition methods: audio, visual, and spontaneous expressions","volume":"31","author":"Zeng","year":"2009","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"10.1016\/j.imavis.2012.07.003_bb0035","doi-asserted-by":"crossref","first-page":"68","DOI":"10.4018\/jse.2010101605","article-title":"Automatic, dimensional and continuous emotion recognition","volume":"1","author":"Gunes","year":"2010","journal-title":"Int. J. Synth. Emotion"},{"issue":"12","key":"10.1016\/j.imavis.2012.07.003_bb0040","doi-asserted-by":"crossref","first-page":"1775","DOI":"10.1016\/j.imavis.2009.01.004","article-title":"Automatic nonverbal analysis of social interaction in small groups: a review","volume":"27","author":"Gatica-Perez","year":"2009","journal-title":"Image Vision Comput."},{"key":"10.1016\/j.imavis.2012.07.003_bb0045","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1109\/MSP.2009.933382","article-title":"Capturing order in social interactions","volume":"26","author":"Vinciarelli","year":"2009","journal-title":"IEEE Signal Process. Mag."},{"key":"10.1016\/j.imavis.2012.07.003_bb0050","series-title":"Proc. ACM Int'l Conf. on Multimedia","first-page":"677","article-title":"Multimodal affect recognition in learning environments","author":"Kapoor","year":"2005"},{"key":"10.1016\/j.imavis.2012.07.003_bb0055","series-title":"Proc. IEEE Int'l Conf. on Acoustics, Speech and Signal Processing","first-page":"489","article-title":"Detecting group interest-level in meetings","author":"Gatica-Perez","year":"2005"},{"key":"10.1016\/j.imavis.2012.07.003_bb0060","series-title":"Modeling Interest in Face-to-face Conversation from Multimodal Nonverbal Behavior","author":"Gatica-Perez","year":"2009"},{"issue":"3","key":"10.1016\/j.imavis.2012.07.003_bb0065","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1007\/s11042-008-0240-1","article-title":"Estimation of behavioral user state based on eye gaze and head pose-application in an e-learning environment","volume":"41","author":"Asteriadis","year":"2009","journal-title":"Multimed. Tools Appl."},{"key":"10.1016\/j.imavis.2012.07.003_bb0070","series-title":"Proc. IEEE Int'l Conf. Affective Computing and Intelligent Interfaces","first-page":"1","article-title":"Spotting agreement and disagreement: a survey of nonverbal audiovisual cues and tools","author":"Bousmalis","year":"2009"},{"key":"10.1016\/j.imavis.2012.07.003_bb0075","first-page":"1","article-title":"Agreement and its multimodal communication in debates: a qualitative analysis","author":"Poggi","year":"2010","journal-title":"Cogn. Comput."},{"key":"10.1016\/j.imavis.2012.07.003_bb0080","series-title":"The Nonverbal Context of Verbal Listener Responses","first-page":"193","article-title":"The relationship of verbal and nonverbal communication","author":"Rosenfeld","year":"1980"},{"key":"10.1016\/j.imavis.2012.07.003_bb0085","series-title":"Ch. 3.1: About Brows: Emotional and Conversational Signals","article-title":"Human ethology","author":"Ekman","year":"1979"},{"key":"10.1016\/j.imavis.2012.07.003_bb0090","series-title":"Bodily Communication","author":"Argyle","year":"1988"},{"key":"10.1016\/j.imavis.2012.07.003_bb0095","doi-asserted-by":"crossref","first-page":"855","DOI":"10.2466\/pr0.1999.84.3.855","article-title":"Does communicating nonverbal disagreement during an opponent's speech affect the credibility of the debater in the background?","volume":"84","author":"Seiter","year":"1999","journal-title":"Psychol. Rep."},{"issue":"2","key":"10.1016\/j.imavis.2012.07.003_bb0100","doi-asserted-by":"crossref","first-page":"225","DOI":"10.3200\/SOCP.145.2.225-236","article-title":"Audience perceptions of candidates' appropriateness as a function of nonverbal behaviors displayed during televised political debates","volume":"145","author":"Seiter","year":"2005","journal-title":"J. Soc. Psychol."},{"issue":"1","key":"10.1016\/j.imavis.2012.07.003_bb0105","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1080\/08934210600626856","article-title":"Background behavior in live debates: the effects of the implicit ad hominem fallacy","volume":"19","author":"Seiter","year":"2006","journal-title":"Commun. Rep."},{"key":"10.1016\/j.imavis.2012.07.003_bb0110","series-title":"Second Assessments: A Study of Some Features of Agreements\/disagreements","author":"Pomerantz","year":"1975"},{"key":"10.1016\/j.imavis.2012.07.003_bb0115","series-title":"Agreeing and Disagreeing with Assessments: Some Features of Preferred\/dispreferred Turn Shapes","article-title":"Structures of social action: studies in conversation analysis, studies in emotion and social interaction","author":"Pomerantz","year":"1984"},{"key":"10.1016\/j.imavis.2012.07.003_bb0120","series-title":"Proc. Symp. on Applied Perception in Graphics and Visualization","first-page":"143","article-title":"The components of conversational facial expressions","author":"Cunningham","year":"2004"},{"key":"10.1016\/j.imavis.2012.07.003_bb0125","doi-asserted-by":"crossref","unstructured":"M. Nicolaou, H. Gunes, M. Pantic, Continuous prediction of spontaneous affect from multiple cues and modalities in valence-arousal space, IEEE Transactions on Affective Computing, 2011.","DOI":"10.1109\/T-AFFC.2011.9"},{"key":"10.1016\/j.imavis.2012.07.003_bb0130","series-title":"The Expression of Emotions in Man and Animals","author":"Darwin","year":"2002"},{"issue":"4","key":"10.1016\/j.imavis.2012.07.003_bb0135","doi-asserted-by":"crossref","first-page":"214","DOI":"10.1007\/BF00986881","article-title":"Head movement during listening turns in conversation","volume":"9","author":"Hadar","year":"1985","journal-title":"J. Nonverbal Behav."},{"key":"10.1016\/j.imavis.2012.07.003_bb0140","series-title":"Bodytalk: A World Guide to Gestures","author":"Morris","year":"1994"},{"issue":"3","key":"10.1016\/j.imavis.2012.07.003_bb0145","doi-asserted-by":"crossref","first-page":"640","DOI":"10.1111\/j.1460-2466.2002.tb02566.x","article-title":"\u201cAre you kidding me?\u201d: the role of nonverbal cues in the verbal accounting process","volume":"52","author":"Manusov","year":"2002","journal-title":"J. Commun."},{"key":"10.1016\/j.imavis.2012.07.003_bb0150","series-title":"The Nonverbal Dictionary of Gestures, Signs and Body Language Cue","author":"Givens","year":"2002"},{"key":"10.1016\/j.imavis.2012.07.003_bb0155","series-title":"Proc. Int'l Conf. Language Resources and Evaluation","first-page":"17","article-title":"Types of nods. the polysemy of a social signal","author":"Poggi","year":"2010"},{"issue":"5","key":"10.1016\/j.imavis.2012.07.003_bb0160","doi-asserted-by":"crossref","first-page":"728","DOI":"10.1037\/0022-3514.37.5.728","article-title":"Smiles can be back channels","volume":"37","author":"Brunner","year":"1979","journal-title":"J. Pers. Soc. Psychol."},{"issue":"4","key":"10.1016\/j.imavis.2012.07.003_bb0165","doi-asserted-by":"crossref","first-page":"404","DOI":"10.1111\/j.1460-2466.1972.tb00165.x","article-title":"Developmental factors in conversational behavior","volume":"22","author":"Dittmann","year":"1972","journal-title":"J. Commun."},{"key":"10.1016\/j.imavis.2012.07.003_bb0170","series-title":"The Encoding of Disagreement and Agreement","first-page":"62","article-title":"Posture and gesture","author":"Bull","year":"1987"},{"key":"10.1016\/j.imavis.2012.07.003_bb0175","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1007\/978-3-540-76442-7_8","article-title":"Prosodic and gestural expression of interactional agreement","volume":"4775","author":"Keller","year":"2007","journal-title":"Lect. Notes Comput. Sci."},{"key":"10.1016\/j.imavis.2012.07.003_bb0180","series-title":"Facial Action Coding System","author":"Ekman","year":"2002"},{"issue":"1","key":"10.1016\/j.imavis.2012.07.003_bb0185","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1037\/0033-2909.95.1.52","article-title":"The neuropsychology of facial expression: a review of the neurological and psychological mechanisms for producing facial expressions","volume":"95","author":"Rinn","year":"1984","journal-title":"Psychol. Bull."},{"issue":"1-4","key":"10.1016\/j.imavis.2012.07.003_bb0190","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1080\/08351819109389361","article-title":"Discource-oriented facial displays in conversation","volume":"25","author":"Chovil","year":"1991","journal-title":"Res. Lang. Soc. Interact."},{"key":"10.1016\/j.imavis.2012.07.003_bb0195","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1017\/S0047404500006564","article-title":"Motor signs for \u2018yes\u2019 and \u2018no\u2019","author":"Jakobson","year":"1972","journal-title":"Lang. Soc."},{"key":"10.1016\/j.imavis.2012.07.003_bb0200","series-title":"Proc. Conf. North American Chapter of the Association for Computational Linguistics on Human Language Technology","first-page":"34","article-title":"Detection of agreement vs. disagreement in meetings: training with unlabeled data","author":"Hillard","year":"2003"},{"key":"10.1016\/j.imavis.2012.07.003_bb0205","series-title":"Proc. Meeting Association for Computational Linguistics","first-page":"669","article-title":"Identifying agreement and disagreement in conversational speech: use of Bayesian networks to model pragmatic dependencies","author":"Galley","year":"2004"},{"key":"10.1016\/j.imavis.2012.07.003_bb0210","series-title":"On the Management of Disagreement Between News Interviewees","article-title":"Talk at work","author":"Greatbatch","year":"1992"},{"key":"10.1016\/j.imavis.2012.07.003_bb0215","series-title":"Telling Lies","author":"Ekman","year":"1985"},{"issue":"3","key":"10.1016\/j.imavis.2012.07.003_bb0220","doi-asserted-by":"crossref","first-page":"461","DOI":"10.2307\/350902","article-title":"The topography of marital conflict: a sequential analysis of verbal and nonverbal behavior","volume":"39","author":"Gottman","year":"1977","journal-title":"J. Marriage Fam."},{"key":"10.1016\/j.imavis.2012.07.003_bb0225","series-title":"Proc. Conf. Multi-modal Communication","first-page":"137","article-title":"Linguistic functions of head nods","author":"Cerrato","year":"2005"},{"key":"10.1016\/j.imavis.2012.07.003_bb0230","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1037\/h0033031","article-title":"Some signals and rules for speaking turns in conversation","volume":"23","author":"Duncan","year":"1972","journal-title":"J. Pers. Soc. Psychol."},{"key":"10.1016\/j.imavis.2012.07.003_bb0235","series-title":"Canal9: A database of political debates for analysis of social interactions","first-page":"96","volume":"2","author":"Vinciarelli","year":"2009"},{"key":"10.1016\/j.imavis.2012.07.003_bb0240","first-page":"291","article-title":"Conversational control functions of non-verbal behaviour","author":"Rosenfeld","year":"1978","journal-title":"Non-verbal Behav. Commun."},{"issue":"2","key":"10.1016\/j.imavis.2012.07.003_bb0245","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1075\/gest.2.2.03ken","article-title":"Some uses of the head shake","volume":"2","author":"Kendon","year":"2002","journal-title":"Gesture"},{"key":"10.1016\/j.imavis.2012.07.003_bb0250","series-title":"Ch. 6: The Decoding of Interest\/Boredom and Disagreement\/Agreement","first-page":"70","article-title":"Posture and gesture","author":"Bull","year":"1987"},{"issue":"6","key":"10.1016\/j.imavis.2012.07.003_bb0255","doi-asserted-by":"crossref","first-page":"893","DOI":"10.1037\/0022-3514.76.6.893","article-title":"The chameleon effect: the perception\u2013behavior link and social interaction","volume":"76","author":"Chartrand","year":"1999","journal-title":"J. Pers. Soc. Psychol."},{"key":"10.1016\/j.imavis.2012.07.003_bb0260","first-page":"53","author":"Tannen","year":"1993","journal-title":"Interpreting Interruption Conversation"},{"issue":"10","key":"10.1016\/j.imavis.2012.07.003_bb0265","doi-asserted-by":"crossref","first-page":"1752","DOI":"10.1016\/j.pragma.2005.04.011","article-title":"Phonetics and social action in agreements and disagreements","volume":"38","author":"Ogden","year":"2006","journal-title":"J. Pragmat."},{"issue":"2","key":"10.1016\/j.imavis.2012.07.003_bb0270","doi-asserted-by":"crossref","first-page":"262","DOI":"10.1080\/08838150902907918","article-title":"The rivalry of nonverbal cues on the perception of politicians by television viewers","volume":"53","author":"Haumer","year":"2009","journal-title":"J. Broadcast. Electron. Media"},{"key":"10.1016\/j.imavis.2012.07.003_bb0275","series-title":"Proc. IEEE Conf. on Automatic Face and Gesture Recognition","first-page":"746","article-title":"Modeling hidden dynamics of multimodal cues for spontaneous agreement and disagreement recognition","author":"Bousmalis","year":"2011"},{"issue":"2","key":"10.1016\/j.imavis.2012.07.003_bb0280","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1007\/s10579-007-9040-x","article-title":"Unleashing the killer corpus: experiences in creating the multi-everything AMI Meeting Corpus","volume":"41","author":"Carletta","year":"2007","journal-title":"Lang. Resour. Eval. J."},{"key":"10.1016\/j.imavis.2012.07.003_bb0285","series-title":"Proc. ACM Int'l Conf. Multimodal Interfaces","first-page":"7","article-title":"Agreement detection in multiparty conversation","author":"Germesin","year":"2009"},{"issue":"3","key":"10.1016\/j.imavis.2012.07.003_bb0290","doi-asserted-by":"crossref","first-page":"501","DOI":"10.1109\/TASL.2008.2008238","article-title":"Modeling dominance in group conversations from nonverbal activity cues","volume":"17","author":"Jayagopi","year":"2009","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.imavis.2012.07.003_bb0295","series-title":"Proc. ACM Int'l Conf. Multimodal Interfaces","article-title":"Discovering group nonverbal conversational patterns with topics","author":"Jayagopi","year":"2009"},{"issue":"6","key":"10.1016\/j.imavis.2012.07.003_bb0300","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1109\/TMM.2010.2055233","article-title":"Estimating cohesion in small groups using audio\u2013visual nonverbal behavior","volume":"12","author":"Hung","year":"2010","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.imavis.2012.07.003_bb0305","series-title":"ICSI meeting corpus","first-page":"364","volume":"1","author":"Janin","year":"2003"},{"key":"10.1016\/j.imavis.2012.07.003_bb0310","series-title":"Proc. ACM Int'l Conf. on Multimedia","first-page":"879","article-title":"The idiap wolf corpus: exploring group behaviour in a competitive role-playing game","author":"Hung","year":"2010"},{"key":"10.1016\/j.imavis.2012.07.003_bb0315","doi-asserted-by":"crossref","first-page":"409","DOI":"10.1007\/s10579-007-9060-6","article-title":"A multimodal annotated corpus of consensus decision making meetings","volume":"41","author":"Pianesi","year":"2007","journal-title":"Lang. Resour. Eval."},{"key":"10.1016\/j.imavis.2012.07.003_bb0320","series-title":"Proc. Human Language Technology Conf. of the NAACL","first-page":"53","article-title":"Agreement\/disagreement classification: exploiting unlabeled data using contrast classifiers","author":"Hahn","year":"2006"},{"key":"10.1016\/j.imavis.2012.07.003_bb0325","first-page":"483","article-title":"The HUMAINE database: addressing the collection and annotation of naturalistic and induced emotional data","volume":"4738","author":"Douglas-Cowie","year":"2007","journal-title":"Lect. Notes Comput. Sci."},{"key":"10.1016\/j.imavis.2012.07.003_bb0330","series-title":"Proc. Int'l Conf. Multimedia & Expo","first-page":"1079","article-title":"The SEMAINE corpus of emotionally coloured character interactions","author":"McKeown","year":"2010"},{"key":"10.1016\/j.imavis.2012.07.003_bb0335","series-title":"Int'l Conf. Automatic Face and Gesture Recognition","first-page":"46","article-title":"Comprehensive database for facial expression analysis","author":"Kanade","year":"2000"},{"key":"10.1016\/j.imavis.2012.07.003_bb0340","series-title":"Proc. IEEE Int'l Conf. Automatic Face and Gesture Recognition","first-page":"223","article-title":"Fully automatic facial action recognition in spontaneous behavior","author":"Bartlett","year":"2006"},{"key":"10.1016\/j.imavis.2012.07.003_bb0345","series-title":"IEEE Conf. Multimedia and Expo","first-page":"317","article-title":"Web-based database for facial expression analysis","author":"Pantic","year":"2005"},{"issue":"2","key":"10.1016\/j.imavis.2012.07.003_bb0350","doi-asserted-by":"crossref","first-page":"258","DOI":"10.1109\/TPAMI.2008.293","article-title":"A unified probabilistic framework for spontaneous facial action modeling and understanding","volume":"32","author":"Tong","year":"2010","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.imavis.2012.07.003_bb0355","series-title":"Proc. IEEE Int'l Congress of Phonetic Sciences","first-page":"2877","article-title":"The description of naturally occurring emotional speech","author":"Douglas-Cowie","year":"2003"},{"key":"10.1016\/j.imavis.2012.07.003_bb0365","series-title":"Proc. IEEE Int'l Conf. Face and Gesture Recognition","first-page":"97","article-title":"Haar features for facs au recognition","author":"Whitehill","year":"2006"},{"key":"10.1016\/j.imavis.2012.07.003_bb0370","series-title":"Face Recognition","article-title":"Investigating spontaneous facial action recognition through an representations of the face","author":"Lucey","year":"2007"},{"key":"10.1016\/j.imavis.2012.07.003_bb0375","first-page":"3358","article-title":"Detecting facial actions and their temporal segments in nearly frontal-view face image sequences","volume":"4","author":"Pantic","year":"2005","journal-title":"IEEE Trans. Syst. Man Cybern. Part B"},{"key":"10.1016\/j.imavis.2012.07.003_bb0380","series-title":"Proc. IEEE Conf. Computer Vision and Pattern Recognition","first-page":"149","article-title":"Fully automatic facial action unit detection and temporal analysis","author":"Valstar","year":"2006"},{"key":"10.1016\/j.imavis.2012.07.003_bb0385","doi-asserted-by":"crossref","first-page":"118","DOI":"10.1007\/978-3-540-75773-3_13","article-title":"Combined support vector machines and hidden markov models for modeling facial action temporal dynamics","volume":"4796","author":"Valstar","year":"2007","journal-title":"Lect. Notes Comput. Sci."},{"issue":"6","key":"10.1016\/j.imavis.2012.07.003_bb0390","doi-asserted-by":"crossref","first-page":"615","DOI":"10.1016\/j.imavis.2005.09.011","article-title":"Dynamics of facial expression extracted automatically from video","volume":"24","author":"Littlewort","year":"2006","journal-title":"Image Vision Comput."},{"key":"10.1016\/j.imavis.2012.07.003_bb0395","series-title":"Proc. Int'l Conf. Automotive Technologies","article-title":"Automated drowsiness detection for improved driving safety","author":"Vural","year":"2008"},{"key":"10.1016\/j.imavis.2012.07.003_bb0400","series-title":"Proc. IEEE Int'l Conf. Computer Vision and Pattern Recognition","first-page":"1","article-title":"Boosting coded dynamic features for facial action units and facial expression recognition","author":"Yang","year":"2007"},{"issue":"2","key":"10.1016\/j.imavis.2012.07.003_bb0405","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1016\/j.patrec.2008.03.014","article-title":"Boosting encoded dynamic features for facial expression recognition","volume":"30","author":"Yang","year":"2009","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.imavis.2012.07.003_bb0410","series-title":"Proc. IEEE Int'l Conf. Automatic Face and Gesture Recognition","article-title":"Non-rigid registration using free-form deformations for recognition of facial actions and their temporal dynamics","author":"Koelstra","year":"2008"},{"key":"10.1016\/j.imavis.2012.07.003_bb0415","doi-asserted-by":"crossref","first-page":"1940","DOI":"10.1109\/TPAMI.2010.50","article-title":"Dynamic texture based approach to recognition of facial actions and their temporal models","volume":"99","author":"Koelstra","year":"2010","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"10","key":"10.1016\/j.imavis.2012.07.003_bb0420","first-page":"1683","article-title":"Facial action unit recognition by exploiting their dynamic and semantic relationships, Pattern Analysis and Machine Intelligence","volume":"29","author":"Tong","year":"2007","journal-title":"IEEE Trans."},{"key":"10.1016\/j.imavis.2012.07.003_bb0425","series-title":"Ch. 10: Automatic Facial Action Unit Recognition by Modeling Their Semantic and Dynamic Relationships","first-page":"159","article-title":"Affective information processing","author":"Tong","year":"2009"},{"issue":"2","key":"10.1016\/j.imavis.2012.07.003_bb0430","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1109\/TSMCB.2005.859075","article-title":"Dynamics of facial expressions \u2014 recognition of facial actions and their temporal segments from face profile image sequences","volume":"36","author":"Pantic","year":"2006","journal-title":"IEEE Trans. Syst. Man Cybern. Part B"},{"key":"10.1016\/j.imavis.2012.07.003_bb0435","series-title":"Face Recognition","first-page":"377","article-title":"Machine analysis of facial expressions","author":"Pantic","year":"2007"},{"key":"10.1016\/j.imavis.2012.07.003_bb0440","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1196\/annals.1280.010","article-title":"Darwin, deception, and facial expression","volume":"1000","author":"Ekman","year":"2003","journal-title":"Ann. N. Y. Acad. Sci."},{"key":"10.1016\/j.imavis.2012.07.003_bb0445","series-title":"Proc. Int'l Workshop Analysis and Modelling of Faces and Gestures","first-page":"293","article-title":"Automatic 3D facial expression analysis in videos","author":"Chang","year":"2005"},{"key":"10.1016\/j.imavis.2012.07.003_bb0450","series-title":"Proc. European Conf. on Computer Vision","first-page":"58","article-title":"Facial expression recognition based on 3D dynamic range model sequences","author":"Sun","year":"2008"},{"key":"10.1016\/j.imavis.2012.07.003_bb0455","doi-asserted-by":"crossref","first-page":"1313","DOI":"10.1016\/j.imavis.2008.11.010","article-title":"Real-time facial expression recognition using STAAM and layered GDA classifier","volume":"27","author":"Sung","year":"2009","journal-title":"Image Vision Comput."},{"key":"10.1016\/j.imavis.2012.07.003_bb0460","doi-asserted-by":"crossref","first-page":"1340","DOI":"10.1016\/j.patcog.2008.10.010","article-title":"Natural facial expression recognition using differential-AAM and manifold learning","volume":"42","author":"Cheon","year":"2009","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.imavis.2012.07.003_bb0465","doi-asserted-by":"crossref","first-page":"962","DOI":"10.1016\/j.patcog.2008.09.035","article-title":"Facial expression recognition system based on rigid and non-rigid motion separation and 3D pose estimation","volume":"42","author":"Wang","year":"2009","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.imavis.2012.07.003_bb0470","series-title":"Proc. IEEE Conf. Computer Vision and Pattern Recognition","first-page":"1","article-title":"A study of non-frontal-view facial expressions recognition","author":"Hu","year":"2008"},{"key":"10.1016\/j.imavis.2012.07.003_bb0475","series-title":"Coupled gaussian process regression for pose-invariant facial expression recognition","first-page":"350","volume":"2","author":"Rudovic","year":"2010"},{"issue":"1535","key":"10.1016\/j.imavis.2012.07.003_bb0480","doi-asserted-by":"crossref","first-page":"3505","DOI":"10.1098\/rstb.2009.0135","article-title":"Machine analysis of facial behaviour: naturalistic and dynamic behaviour","volume":"364","author":"Pantic","year":"2009","journal-title":"Philos. Trans. Royal Soc. B"},{"key":"10.1016\/j.imavis.2012.07.003_bb0485","series-title":"Proc. IEEE Int'l Conf. Automatic Face and Gesture Recognition","first-page":"40","article-title":"Real-time detection of nodding and head-shaking by directly detecting and tracking the \u201cbetween-eyes\u201d","author":"Kawato","year":"2000"},{"key":"10.1016\/j.imavis.2012.07.003_bb0490","series-title":"A real-time head nod and shake detector","first-page":"1","volume":"15","author":"Kapoor","year":"2001"},{"issue":"3","key":"10.1016\/j.imavis.2012.07.003_bb0495","doi-asserted-by":"crossref","first-page":"461","DOI":"10.1016\/S0957-4174(03)00088-5","article-title":"A real-time head nod and shake detector using HMMs","volume":"25","author":"Tan","year":"2003","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.imavis.2012.07.003_bb0500","series-title":"Proc. IEEE Int'l Workshop Robot and Human Interactive Communication","first-page":"159","article-title":"A conversation robot using head gesture recognition as para-linguistic information","author":"Fujie","year":"2004"},{"key":"10.1016\/j.imavis.2012.07.003_bb0505","series-title":"Proc. ACM Int'l Conf. Multimodal Interfaces","first-page":"18","article-title":"Contextual recognition of head gestures","author":"Morency","year":"2005"},{"key":"10.1016\/j.imavis.2012.07.003_bb0510","series-title":"Proc. Int'l Conf. Automatic Face and Gesture Recognition","article-title":"Generalized adaptive view-based appearance model: integrated framework for monocular head pose estimation","author":"Morency","year":"2008"},{"key":"10.1016\/j.imavis.2012.07.003_bb0515","series-title":"Hidden conditional random fields for gesture recognition","first-page":"1521","volume":"2","author":"Wang","year":"2006"},{"key":"10.1016\/j.imavis.2012.07.003_bb0520","series-title":"Proc. IEEE Conf. Computer Vision and Pattern Recognition","first-page":"1","article-title":"Latent-dynamic discriminative models for continuous gesture recognition","author":"Morency","year":"2007"},{"issue":"4","key":"10.1016\/j.imavis.2012.07.003_bb0525","doi-asserted-by":"crossref","first-page":"607","DOI":"10.1109\/TPAMI.2008.106","article-title":"Head pose estimation in computer vision: a survey","volume":"31","author":"Murphy-Chutorian","year":"2009","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1-2","key":"10.1016\/j.imavis.2012.07.003_bb0530","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1016\/j.cviu.2006.10.012","article-title":"Vision-based hand pose estimation: a review","volume":"108","author":"Erol","year":"2007","journal-title":"Comput. Vis. Image Underst."},{"issue":"8","key":"10.1016\/j.imavis.2012.07.003_bb0535","doi-asserted-by":"crossref","first-page":"1061","DOI":"10.1109\/TPAMI.2002.1023803","article-title":"Extraction of 2d motion trajectories and its application to hand gesture recognition","volume":"24","author":"Yang","year":"2002","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.imavis.2012.07.003_bb0540","doi-asserted-by":"crossref","unstructured":"L. Ding, A. Martinez, Modelling and recognition of the linguistic components in american sign language, Image and Vision Computing 27 (12) (2009).","DOI":"10.1016\/j.imavis.2009.02.005"},{"key":"10.1016\/j.imavis.2012.07.003_bb0545","doi-asserted-by":"crossref","first-page":"481","DOI":"10.1007\/978-3-642-02611-9_48","article-title":"Towards communicative face occlusions: machine detection of hand-over-face gestures","volume":"5627","author":"Mahmoud","year":"2009","journal-title":"Lect. Notes Comput. Sci."},{"key":"10.1016\/j.imavis.2012.07.003_bb0550","series-title":"Proc. Int'l Conf. Multimedia","first-page":"357","article-title":"A 3-dimensional sift descriptor and its application to action recognition","author":"Scovanner","year":"2007"},{"key":"10.1016\/j.imavis.2012.07.003_bb0555","series-title":"Proc. British Machine Vision Conf","article-title":"Evaluation of local spatio-temporal features for action recognition","author":"Wang","year":"2009"},{"key":"10.1016\/j.imavis.2012.07.003_bb0560","series-title":"Proc. IEEE Conf. Computer Vision and Pattern Recognition","first-page":"1","article-title":"Learning realistic human actions from movies","author":"Laptev","year":"2008"},{"key":"10.1016\/j.imavis.2012.07.003_bb0565","series-title":"Proc. Int'l Conf. Computer Vision","first-page":"1","article-title":"Retrieving actions in movies","author":"Laptev","year":"2007"},{"key":"10.1016\/j.imavis.2012.07.003_bb0570","series-title":"Proc. Int'l Conf. on Computer Vision","first-page":"925","article-title":"Fast realistic multi-action recognition using mined dense spatio-temporal features","author":"Gilbert","year":"2009"},{"key":"10.1016\/j.imavis.2012.07.003_bb0575","series-title":"Proc. Int'l Conf. on Computer Vision","first-page":"1933","article-title":"Selection and context for action recognition","author":"Han","year":"2009"},{"key":"10.1016\/j.imavis.2012.07.003_bb0580","series-title":"Proc. IEEE Conf. Computer Vision and Pattern Recognition","first-page":"1","article-title":"Action recognition with motion-appearance vocabulary forest","author":"Mikolajczyk","year":"2008"},{"key":"10.1016\/j.imavis.2012.07.003_bb0585","series-title":"Proc. IEEE Conf. Computer Vision and Pattern Recognition","first-page":"1","article-title":"Recognising action as clouds of space-time interest points","author":"Bregonzio","year":"2009"},{"key":"10.1016\/j.imavis.2012.07.003_bb0590","series-title":"Proc. Int'l Conf. on Computer Vision","first-page":"1","article-title":"A biologically inspired system for action recognition","author":"Jhuang","year":"2007"},{"key":"10.1016\/j.imavis.2012.07.003_bb0595","series-title":"Proc. Int'l Conf. on Computer Vision","article-title":"Incremental action recognition using feature-tree","author":"Reddy","year":"2009"},{"key":"10.1016\/j.imavis.2012.07.003_bb0600","series-title":"Proc. Conf. Computer Vision and Pattern Recognition","first-page":"1454","article-title":"Dense saliency-based spatiotemporal feature points for action recognition","author":"Rapantzikos","year":"2009"},{"key":"10.1016\/j.imavis.2012.07.003_bb0605","series-title":"Proc. IEEE Conf. Computer Vision and Pattern Recognition","first-page":"1","article-title":"Action snippets: how many frames does human action require?","author":"Schindler","year":"2008"},{"key":"10.1016\/j.imavis.2012.07.003_bb0610","series-title":"Discriminative sub-sequence mining for action classification","first-page":"1","volume":"1","author":"Nowozin","year":"2007"},{"key":"10.1016\/j.imavis.2012.07.003_bb0615","series-title":"Proc. IEEE Conf. Computer Vision and Pattern Recognition","first-page":"1","article-title":"A hierarchical model of shape and appearance for human action classification","author":"Niebles","year":"2007"},{"key":"10.1016\/j.imavis.2012.07.003_bb0620","series-title":"Proc. Int'l Workshop Visual Surveillance and Performance Evaluation of Tracking and Surveillance","first-page":"65","article-title":"Behavior recognition via sparse spatio-temporal features","author":"Doll\u00e1r","year":"2005"},{"key":"10.1016\/j.imavis.2012.07.003_bb0625","series-title":"Recognizing human actions: a local svm approach","first-page":"32","volume":"3","author":"Sch\u00fcldt","year":"2004"},{"key":"10.1016\/j.imavis.2012.07.003_bb0630","series-title":"Proc. IEEE Conf. Computer Vision and Pattern Recognition","first-page":"2929","article-title":"Actions in context","author":"Marsza\u0142ek","year":"2009"},{"issue":"9","key":"10.1016\/j.imavis.2012.07.003_bb0635","doi-asserted-by":"crossref","first-page":"1530","DOI":"10.1109\/TPAMI.2006.194","article-title":"Statistical analysis of dynamic actions","volume":"28","author":"Zelnik\u2212Manor","year":"2006","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.imavis.2012.07.003_bb0640","series-title":"Searching human behaviors using spatial\u2013temporal words","first-page":"337","volume":"6","author":"Ning","year":"2007"},{"issue":"11","key":"10.1016\/j.imavis.2012.07.003_bb0645","doi-asserted-by":"crossref","first-page":"2045","DOI":"10.1109\/TPAMI.2007.1119","article-title":"Space\u2013time behavior-based correlation-or-how to tell if two underlying motion fields are similar without computing them?","volume":"29","author":"Shechtman","year":"2007","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.imavis.2012.07.003_bb0650","series-title":"Proc. British Machine Vision Conf","first-page":"1055","article-title":"Fast motion consistency through matrix quantization","author":"Matikainen","year":"2008"},{"key":"10.1016\/j.imavis.2012.07.003_bb0655","series-title":"Proc. IEEE Conf. Computer Vision and Pattern Recognition","first-page":"1","article-title":"Matching local self-similarities across images and videos","author":"Shechtman","year":"2007"},{"key":"10.1016\/j.imavis.2012.07.003_bb0660","series-title":"Proc. Int'l Conf. Computer Vision","first-page":"1","article-title":"Detection of human actions from a single example","author":"Seo","year":"2009"},{"key":"10.1016\/j.imavis.2012.07.003_bb0665","series-title":"Proc. Int'l Conf. on Computer Vision","first-page":"1","article-title":"Action detection in complex scenes with spatial and temporal ambiguities","author":"Hu","year":"2009"},{"key":"10.1016\/j.imavis.2012.07.003_bb0670","series-title":"Proc. IEEE Conf. Computer Vision and Pattern Recognition","first-page":"1","article-title":"Discriminative subvolume search for efficient action detection","author":"Yuan","year":"2009"},{"key":"10.1016\/j.imavis.2012.07.003_bb0675","series-title":"Cross-view action recognition from temporal self-similarities","first-page":"293","volume":"2","author":"Junejo","year":"2008"},{"issue":"1","key":"10.1016\/j.imavis.2012.07.003_bb0680","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1007\/s11263-006-0009-9","article-title":"Detecting irregularities in images and in video","volume":"74","author":"Boiman","year":"2007","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.imavis.2012.07.003_bb0685","series-title":"Action mach: a spatio-temporal maximum average correlation height filter for action recognition","first-page":"1","volume":"8","author":"Rodriguez","year":"2006"},{"key":"10.1016\/j.imavis.2012.07.003_bb0690","unstructured":"A. Oikonomopoulos, Spatiotemporal visual analysis of human actions, Ph.D. thesis, Imperial College London (2010)."},{"key":"10.1016\/j.imavis.2012.07.003_bb0695","doi-asserted-by":"crossref","first-page":"976","DOI":"10.1016\/j.imavis.2009.11.014","article-title":"A survey on vision-based human action recognition","volume":"28","author":"Poppe","year":"2010","journal-title":"Image Vision Comput."},{"issue":"12","key":"10.1016\/j.imavis.2012.07.003_bb0700","doi-asserted-by":"crossref","first-page":"1814","DOI":"10.1016\/j.imavis.2009.05.010","article-title":"Sparse B-spline polynomial descriptors for human activity recognition","volume":"27","author":"Oikonomopoulos","year":"2009","journal-title":"Image Vision Comput."},{"key":"10.1016\/j.imavis.2012.07.003_bb0705","doi-asserted-by":"crossref","first-page":"650","DOI":"10.1007\/978-3-540-88688-4_48","article-title":"An efficient dense and scale-invariant spatio-temporal interest point detector","volume":"5303","author":"Willems","year":"2008","journal-title":"Lect. Notes Comput. Sci."},{"key":"10.1016\/j.imavis.2012.07.003_bb0710","series-title":"An implicit spatiotemporal shape model for human activity localisation and recognition","first-page":"27","volume":"3","author":"Oikonomopoulos","year":"2009"},{"key":"10.1016\/j.imavis.2012.07.003_bb0715","series-title":"Proc. Int'l Conf. Image and Video Retrieval","first-page":"294","article-title":"Spatiotemporal saliency for event detection and representation in the 3D wavelet domain: potential in human action recognition","author":"Rapantzikos","year":"2007"},{"issue":"11","key":"10.1016\/j.imavis.2012.07.003_bb0720","first-page":"1","article-title":"Human pose estimation for image monitoring","volume":"5","author":"Ando","year":"2007","journal-title":"NTT Tech. Rev."},{"key":"10.1016\/j.imavis.2012.07.003_bb0725","series-title":"Proc. Int'l Conf. on Pattern Recognition","first-page":"1","article-title":"Discriminative estimation of 3D human pose using gaussian processes","author":"Zhao","year":"2008"},{"key":"10.1016\/j.imavis.2012.07.003_bb0730","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1007\/s11263-009-0218-0","article-title":"Real-time body pose recognition using 2D and 3D haarlets","volume":"83","author":"den Bergh","year":"2009","journal-title":"Image Vision Comput."},{"key":"10.1016\/j.imavis.2012.07.003_bb0735","series-title":"Proc. IEEE Conf. Computer Vision and Pattern Recognition","first-page":"982","article-title":"Integrated pedestrian classification and orientation estimation","author":"Enzweiler","year":"2010"},{"key":"10.1016\/j.imavis.2012.07.003_bb0740","series-title":"Model-based human body tracking","first-page":"552","volume":"1","author":"Huang","year":"2002"},{"issue":"3","key":"10.1016\/j.imavis.2012.07.003_bb0745","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1023\/A:1023012723347","article-title":"Human body model acquisition and tracking using voxel data","volume":"53","author":"Miki\u0107","year":"2003","journal-title":"Int. J. Comput. Vis."},{"issue":"7","key":"10.1016\/j.imavis.2012.07.003_bb0750","doi-asserted-by":"crossref","first-page":"1052","DOI":"10.1109\/TPAMI.2006.149","article-title":"Recovering 3D human body configurations using shape contexts","volume":"28","author":"Mori","year":"2006","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.imavis.2012.07.003_bb0755","series-title":"Proc. British Machine Vision Conf","article-title":"Hierarchical part-based human body pose estimation","author":"Navaratnam","year":"2005"},{"key":"10.1016\/j.imavis.2012.07.003_bb0760","series-title":"Conditional random people: tracking humans with CRFs and grid filters","first-page":"222","volume":"1","author":"Taycher","year":"2006"},{"key":"10.1016\/j.imavis.2012.07.003_bb0765","series-title":"Fast pose estimation with parameter-sensitive hashing","first-page":"750","volume":"2","author":"Shakhnarovich","year":"2003"},{"issue":"2-3","key":"10.1016\/j.imavis.2012.07.003_bb0770","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1016\/j.cviu.2006.08.004","article-title":"Viewpoint invariant exemplar-based 3D human tracking","volume":"104","author":"Ong","year":"2006","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.imavis.2012.07.003_bb0775","series-title":"Inferring 3D body pose from silhouettes using activity manifold learning","first-page":"681","volume":"2","author":"Elgammal","year":"2004"},{"key":"10.1016\/j.imavis.2012.07.003_bb0780","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1007\/11612032_6","article-title":"A local basis representation for estimating human pose from cluttered images","volume":"3851","author":"Agarwal","year":"2006","journal-title":"Lect. Notes Comput. Sci."},{"issue":"3","key":"10.1016\/j.imavis.2012.07.003_bb0785","doi-asserted-by":"crossref","first-page":"585","DOI":"10.1016\/S0031-3203(02)00100-0","article-title":"Recent developments in human motion analysis","volume":"36","author":"Wang","year":"2003","journal-title":"Pattern Recognit."},{"issue":"5","key":"10.1016\/j.imavis.2012.07.003_bb0790","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1016\/j.rti.2003.08.001","article-title":"Video analysis of human dynamics: a survey","volume":"9","author":"Wang","year":"2003","journal-title":"Real-Time Imaging"},{"issue":"1","key":"10.1016\/j.imavis.2012.07.003_bb0795","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1006\/cviu.1998.0716","article-title":"The visual analysis of human movement: a survey","volume":"73","author":"Gavrila","year":"1999","journal-title":"Comput. Vis. Image Underst."},{"issue":"3","key":"10.1016\/j.imavis.2012.07.003_bb0800","doi-asserted-by":"crossref","first-page":"428","DOI":"10.1006\/cviu.1998.0744","article-title":"Human motion analysis: a review","volume":"73","author":"Aggarwal","year":"1999","journal-title":"Comput. Vis. Image Underst."},{"issue":"3","key":"10.1016\/j.imavis.2012.07.003_bb0805","doi-asserted-by":"crossref","first-page":"478","DOI":"10.1109\/TPAMI.2009.30","article-title":"In the eye of the beholder: a survey of models for eyes and gaze","volume":"32","author":"Hansen","year":"2010","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.imavis.2012.07.003_bb0810","series-title":"Proc. IEEE Workshop Applications on Computer Vision","first-page":"132","article-title":"Eye typing using markov and active appearance models","author":"Hansen","year":"2003"},{"key":"10.1016\/j.imavis.2012.07.003_bb0815","series-title":"Proc. World Congress Intelligent Transportation Systems","first-page":"1","article-title":"Passive driver gaze tracking with active appearance models","author":"Ishikawa","year":"2004"},{"issue":"1","key":"10.1016\/j.imavis.2012.07.003_bb0820","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1016\/j.cviu.2004.07.013","article-title":"Eye tracking in the wild","volume":"98","author":"Hansen","year":"2005","journal-title":"Comput. Vis. Image Underst."},{"issue":"1","key":"10.1016\/j.imavis.2012.07.003_bb0825","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1016\/j.cviu.2004.07.008","article-title":"Estimating the eye gaze from one eye","volume":"98","author":"Wang","year":"2005","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.imavis.2012.07.003_bb0830","series-title":"Proc. IEEE Conf. Computer Vision and Pattern Recognition","first-page":"230","article-title":"Sparse and semi-supervised visual mapping with the s3p","author":"Williams","year":"2006"},{"key":"10.1016\/j.imavis.2012.07.003_bb0835","series-title":"Proc. Symp. Eye Tracking Research and Applications","first-page":"140","article-title":"Remote gaze estimation with a single camera based on facial-feature tracking without special calibration actions","author":"Yamazoe","year":"2008"},{"key":"10.1016\/j.imavis.2012.07.003_bb0840","series-title":"Proc. of the Int'l Conf. on Multi-modal Interfaces","first-page":"287","article-title":"Recognizing gaze aversion gestures in embodied conversational discourse","author":"Morency","year":"2006"},{"key":"10.1016\/j.imavis.2012.07.003_bb0845","series-title":"Proc. ACM Int'l Conf. Multimodal Interfaces","first-page":"173","article-title":"Deducing the visual focus of attention from head pose estimation in dynamic multi-view meeting scenarios","author":"Voit","year":"2008"},{"key":"10.1016\/j.imavis.2012.07.003_bb0850","series-title":"Machine Learning for Multimodal Interaction, Vol. 5237 of Lecture Notes in Computer Science","first-page":"1","article-title":"Visual focus of attention in dynamic meeting scenarios","author":"Voit","year":"2008"},{"issue":"1","key":"10.1016\/j.imavis.2012.07.003_bb0855","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1109\/TSMCB.2008.927274","article-title":"Recognizing visual focus of attention from head pose in natural meetings","volume":"39","author":"Ba","year":"2009","journal-title":"IEEE Trans. Syst. Man and Cybern. Part B"},{"key":"10.1016\/j.imavis.2012.07.003_bb0860","series-title":"Proc. NIST Meeting Recognition Workshop","article-title":"Laughter detection in meetings","author":"Kennedy","year":"2004"},{"key":"10.1016\/j.imavis.2012.07.003_bb0865","series-title":"Proc. Europ. Conf. on Speech Commmunication and Technology","first-page":"465","article-title":"No laughing matter","author":"Campbell","year":"2005"},{"issue":"2","key":"10.1016\/j.imavis.2012.07.003_bb0870","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1016\/j.specom.2007.01.001","article-title":"Automatic discrimination between laughter and speech","volume":"49","author":"Truong","year":"2007","journal-title":"Speech Commun."},{"key":"10.1016\/j.imavis.2012.07.003_bb0875","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1007\/978-3-540-69369-7_12","article-title":"Static and dynamic modelling for the recognition of non-verbal vocalisations in conversational speech","volume":"5078","author":"Schuller","year":"2008","journal-title":"Lect. Notes Comput. Sci."},{"key":"10.1016\/j.imavis.2012.07.003_bb0880","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1007\/978-3-540-85853-9_14","article-title":"Detection of laughter-in-interaction in multichannel close-talk microphone recordings of meetings","volume":"5237","author":"Laskowski","year":"2008","journal-title":"Lect. Notes Comput. Sci."},{"key":"10.1016\/j.imavis.2012.07.003_bb0885","series-title":"Proc. INTERSPEECH","first-page":"797","article-title":"Getting the last laugh: automatic laughter segmentation in meetings","author":"Knox","year":"2008"},{"key":"10.1016\/j.imavis.2012.07.003_bb0890","series-title":"Highlight sound effects detection in audio stream","first-page":"37","volume":"3","author":"Cai","year":"2003"},{"key":"10.1016\/j.imavis.2012.07.003_bb0895","series-title":"Proc. Int'l Conf. on Cyberworlds","first-page":"8","article-title":"Smile and laughter recognition using speech processing and face recognition from conversation video","author":"Ito","year":"2005"},{"key":"10.1016\/j.imavis.2012.07.003_bb0900","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1007\/978-3-540-85853-9_13","article-title":"Decision-level fusion for audio\u2013visual laughter detection","volume":"5237","author":"Reuderink","year":"2008","journal-title":"Lect. Notes Comput. Sci."},{"issue":"2","key":"10.1016\/j.imavis.2012.07.003_bb0905","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1109\/TMM.2010.2101586","article-title":"Audiovisual discrimination between speech and laughter: why and when visual information might help","volume":"13","author":"Petridis","year":"2011","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.imavis.2012.07.003_bb0910","series-title":"Proc. IEEE Conf. on Automatic Face and Gesture Recognition, Santa Barbara, CA, USA","first-page":"619","article-title":"Prediction-based classification for audiovisual discrimination between laughter and speech","author":"Petridis","year":"2011"},{"key":"10.1016\/j.imavis.2012.07.003_bb0915","first-page":"99","article-title":"Recognizing communicative facial expressions for discovering interpersonal emotions in group meetings","author":"Kumano","year":"2009"},{"issue":"9\/10","key":"10.1016\/j.imavis.2012.07.003_bb0920","first-page":"341","article-title":"Praat, a system for doing phonetics by computer","volume":"5","author":"Boersma","year":"2002","journal-title":"Glot Int."},{"key":"10.1016\/j.imavis.2012.07.003_bb0925","doi-asserted-by":"crossref","unstructured":"B. Schuller, R. M\u00fcller, F. Eyben, J. Gast, B. H\u00f6rnler, R. W\u00f6llmer, G. Rigoll, A. H\u00f6thker, H. Konosu, Being bored? recognising natural interest by extensive audiovisual integration for real-life application, Image and Vision Computing 27 (12) (2009) 1760\u20131774.","DOI":"10.1016\/j.imavis.2009.02.013"},{"issue":"6","key":"10.1016\/j.imavis.2012.07.003_bb0930","doi-asserted-by":"crossref","first-page":"1078","DOI":"10.1109\/TBME.2006.873548","article-title":"Detection of cough signals in continuous audio recordings using hidden markov models","volume":"53","author":"Matos","year":"2006","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"10.1016\/j.imavis.2012.07.003_bb0935","series-title":"Proc. Int'l Conf. on Image and Graphics","first-page":"463","article-title":"A visual silence detector constraining speech source separation","author":"Gonzalez","year":"2009"},{"issue":"5","key":"10.1016\/j.imavis.2012.07.003_bb0940","doi-asserted-by":"crossref","first-page":"1526","DOI":"10.1109\/TASL.2006.878255","article-title":"Enriching speech recognition with automatic detection of sentence boundaries and disfluencies, IEEE Trans","volume":"14","author":"Liu","year":"2006","journal-title":"Audio Speech Lang. Process."},{"key":"10.1016\/j.imavis.2012.07.003_bb0945","series-title":"Proc. European Conf. Speech Communication and Technology","first-page":"1678","article-title":"An analysis of multimodal cues of interruption in dyadic spoken interactions","author":"Lee","year":"2008"},{"key":"10.1016\/j.imavis.2012.07.003_bb0950","series-title":"Proc. European Conf. Speech Communication and Technology","first-page":"227","article-title":"A real-time filled pause detection system for spontaneous speech recognition","author":"Goto","year":"1999"},{"key":"10.1016\/j.imavis.2012.07.003_bb0955","series-title":"Detection of filled pauses in spontaneous conversational speech","first-page":"678","volume":"3","author":"Gabrea","year":"2000"},{"issue":"2-3","key":"10.1016\/j.imavis.2012.07.003_bb0960","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VLSI.0000015089.17975.f4","article-title":"Acoustic feature analysis and discriminative modeling of filled pauses for spontaneous speech recognition","volume":"36","author":"Wu","year":"2004","journal-title":"J. VLSI Signal Process."},{"issue":"11","key":"10.1016\/j.imavis.2012.07.003_bb0965","doi-asserted-by":"crossref","first-page":"1590","DOI":"10.1016\/j.specom.2006.04.004","article-title":"Coping with disfluencies in spontaneous speech recognition: acoustic detection and linguistic context manipulation","volume":"48","author":"Stouten","year":"2006","journal-title":"Speech Commun."},{"key":"10.1016\/j.imavis.2012.07.003_bb0970","series-title":"Proc. IEEE Int'l Conf. Acoustics, Speech and Signal Processing","first-page":"4857","article-title":"Formant-based technique for automatic filled-pause detection in spoken english","author":"Audhkhasi","year":"2009"},{"issue":"3","key":"10.1016\/j.imavis.2012.07.003_bb0975","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1109\/34.910878","article-title":"The recognition of human movement using temporal templates","volume":"23","author":"Bobick","year":"2001","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"10.1016\/j.imavis.2012.07.003_bb0980","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1109\/MC.2005.104","article-title":"Socially aware, computation and communication","volume":"38","author":"Pentland","year":"2005","journal-title":"Computer"},{"key":"10.1016\/j.imavis.2012.07.003_bb0985","series-title":"Proc. Conf. Computer Supported Collaborative Work","first-page":"457","article-title":"Meeting mediator: enhancing group collaboration with sociometric feedback","author":"Kim","year":"2008"},{"key":"10.1016\/j.imavis.2012.07.003_bb0990","series-title":"Proc. Int'l Conf. on Computational Science and Engineering","first-page":"801","article-title":"The benefits of synchronized genuine smiles in face-to-face service encounters","author":"Kim","year":"2009"},{"key":"10.1016\/j.imavis.2012.07.003_bb0995","series-title":"Proc. Int'l Conf. on Augmented Cognition","article-title":"Voices of attraction","author":"Madan","year":"2005"},{"key":"10.1016\/j.imavis.2012.07.003_bb1000","series-title":"Int'l Conf. Computer Vision","first-page":"838","article-title":"Do they like me? Using video cues to predict desires during speed-dates","author":"Veenstra","year":"2011"},{"key":"10.1016\/j.imavis.2012.07.003_bb1005","series-title":"Human Behavior Understanding, Vol. 7065 of Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"124","DOI":"10.1007\/978-3-642-25446-8_14","article-title":"Automatic modeling of dominance effects using granger causality","author":"Kalimeri","year":"2011"},{"key":"10.1016\/j.imavis.2012.07.003_bb1010","series-title":"Real-time inference of complex mental states from facial expressions and head gestures","first-page":"154","volume":"3","author":"el Kaliouby","year":"2004"},{"issue":"12","key":"10.1016\/j.imavis.2012.07.003_bb1015","doi-asserted-by":"crossref","first-page":"1424","DOI":"10.1109\/34.895976","article-title":"Automatic analysis of facial expressions: the state of the art","volume":"22","author":"Pantic","year":"2000","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"10.1016\/j.imavis.2012.07.003_bb1020","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1016\/S0031-3203(02)00052-3","article-title":"Automatic facial expression analysis: a survey","volume":"36","author":"Fasel","year":"2003","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.imavis.2012.07.003_bb1025","series-title":"Handbook of Face Recognition","first-page":"247","article-title":"Facial expression analysis","author":"Tian","year":"2004"},{"key":"10.1016\/j.imavis.2012.07.003_bb1030","series-title":"Proc. ACM Int'l Conf. Multimodal Interfaces","first-page":"38","article-title":"How to distinguish posed from spontaneous smiles using geometric features","author":"Valstar","year":"2007"},{"issue":"3","key":"10.1016\/j.imavis.2012.07.003_bb1035","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1109\/TSMCC.2007.893280","article-title":"Gesture recognition: a survey","volume":"37","author":"Mitra","year":"2007","journal-title":"IEEE Trans. Syst Man Cybern. Part C"},{"issue":"2","key":"10.1016\/j.imavis.2012.07.003_bb1040","first-page":"405","article-title":"A review of vision based hand gestures recognition","volume":"2","author":"Murthy","year":"2009","journal-title":"Int. J. Info. Technol. Knowl. Manage."},{"issue":"2-3","key":"10.1016\/j.imavis.2012.07.003_bb1045","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1016\/j.cviu.2006.08.002","article-title":"A survey of advances in vision-based human motion capture and analysis","volume":"104","author":"Moeslund","year":"2006","journal-title":"Comput. Vis. Image Underst."},{"issue":"13","key":"10.1016\/j.imavis.2012.07.003_bb1050","doi-asserted-by":"crossref","first-page":"1473","DOI":"10.1163\/156855307782148578","article-title":"The meaning of action: a review on action recognition and mapping","volume":"21","author":"Kr\u00fcger","year":"2007","journal-title":"Adv. Robot."},{"issue":"11","key":"10.1016\/j.imavis.2012.07.003_bb1055","doi-asserted-by":"crossref","first-page":"1473","DOI":"10.1109\/TCSVT.2008.2005594","article-title":"Machine recognition of human activities: a survey","volume":"18","author":"Turaga","year":"2008","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"10.1016\/j.imavis.2012.07.003_bb1060","series-title":"Proc. ACM Int'l Conf. Multimodal Interfaces","first-page":"11","article-title":"Conditional sequence model for context-based recognition of gaze aversion","author":"Morency","year":"2008"},{"key":"10.1016\/j.imavis.2012.07.003_bb1065","series-title":"Proc. CHI, Human Factors in Computing Systems","first-page":"574","article-title":"LAFCam: leveraging affective feedback camcorder","author":"Lockerd","year":"2002"},{"issue":"1","key":"10.1016\/j.imavis.2012.07.003_bb1070","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1109\/TNN.2002.806626","article-title":"Content-based audio classification and retrieval by support vector machines","volume":"14","author":"Guo","year":"2003","journal-title":"IEEE Trans. Neural Netw."},{"key":"10.1016\/j.imavis.2012.07.003_bb1075","series-title":"Proc. Int'l Conf. Spoken Language Processing","first-page":"949","article-title":"Automatic punctuation and disfluency detection in multi-party meetings using prosodic and lexical cues","author":"Baron","year":"2002"},{"issue":"2","key":"10.1016\/j.imavis.2012.07.003_bb1080","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1109\/89.985548","article-title":"Speech pause detection for noise spectrum estimation by tracking power envelope dynamics","volume":"10","author":"Marzinzik","year":"2002","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"10.1016\/j.imavis.2012.07.003_bb1085","series-title":"Mind Reading: the Interactive Guide to Emotions","author":"Baron-Cohen","year":"2004"},{"key":"10.1016\/j.imavis.2012.07.003_bb1090","series-title":"IEEE Int'l Conf. on Computer Vision Workshops","first-page":"1985","article-title":"Feature selection of facial displays for detection of non verbal communication in natural conversation","author":"Sheerman-Chase","year":"2009"},{"key":"10.1016\/j.imavis.2012.07.003_bb1095","series-title":"Neural Information Processing Systems (NIPS) Workshop on Bayesian Nonparametrics","article-title":"A discriminative nonparametric bayesian model: infinite hidden conditional random fields","author":"Bousmalis","year":"2011"},{"key":"10.1016\/j.imavis.2012.07.003_bb1100","series-title":"Proc. Association for Computational Linguistics","first-page":"374","article-title":"Detection of agreement and disagreement in broadcast conversations","author":"Wang","year":"2011"},{"key":"10.1016\/j.imavis.2012.07.003_bb1105","series-title":"Proc. Int'l Conf. Language Resources and Evaluation","first-page":"3052","article-title":"Integrated linguistic resources for language exploitation technologies","author":"Strassel","year":"2006"},{"key":"10.1016\/j.imavis.2012.07.003_bb1110","series-title":"Proc. ISCA Workshop on Speech and Emotion","first-page":"19","article-title":"FEELTRACE: an instrument for recording perceived emotion in real time","author":"Cowie","year":"2000"},{"key":"10.1016\/j.imavis.2012.07.003_bb1115","first-page":"1847","article-title":"Discriminative learning for dynamic state prediction, IEEE Trans","author":"Kim","year":"2009","journal-title":"Pattern Anal. Mach. Intell."}],"container-title":["Image and Vision Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0262885612001059?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0262885612001059?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2020,7,12]],"date-time":"2020-07-12T13:10:38Z","timestamp":1594559438000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0262885612001059"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,2]]},"references-count":222,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2013,2]]}},"alternative-id":["S0262885612001059"],"URL":"https:\/\/doi.org\/10.1016\/j.imavis.2012.07.003","relation":{},"ISSN":["0262-8856"],"issn-type":[{"value":"0262-8856","type":"print"}],"subject":[],"published":{"date-parts":[[2013,2]]}}}