{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,6,15]],"date-time":"2024-06-15T05:15:29Z","timestamp":1718428529793},"reference-count":54,"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.2012.08.018","type":"journal-article","created":{"date-parts":[[2012,9,21]],"date-time":"2012-09-21T04:04:24Z","timestamp":1348200264000},"page":"137-152","source":"Crossref","is-referenced-by-count":68,"title":["Tracking continuous emotional trends of participants during affective dyadic interactions using body language and speech information"],"prefix":"10.1016","volume":"31","author":[{"given":"Angeliki","family":"Metallinou","sequence":"first","affiliation":[]},{"given":"Athanasios","family":"Katsamanis","sequence":"additional","affiliation":[]},{"given":"Shrikanth","family":"Narayanan","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.imavis.2012.08.018_bb0005","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1016\/0092-6566(77)90037-X","article-title":"Evidence for a three-factor theory of emotions","volume":"11","author":"Russell","year":"1977","journal-title":"J. Res. Pers."},{"key":"10.1016\/j.imavis.2012.08.018_bb0010","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1037\/h0054570","article-title":"Three dimensions of emotion","volume":"61","author":"Schlosberg","year":"1954","journal-title":"Psychol. Rev."},{"key":"10.1016\/j.imavis.2012.08.018_bb0015","first-page":"51","article-title":"Affective judgment and psychophysiological response: dimensional covariation in the evaluation of pictorial stimuli","volume":"3","author":"Greenwald","year":"1989","journal-title":"J. Psychophysiol."},{"key":"10.1016\/j.imavis.2012.08.018_bb0020","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1016\/j.specom.2007.09.001","article-title":"Statistical mapping between articulatory movements and acoustic spectrum using a Gaussian mixture model","volume":"50","author":"Toda","year":"2008","journal-title":"Speech Commun."},{"key":"10.1016\/j.imavis.2012.08.018_bb0025","series-title":"Proc. of ICASSP","article-title":"Tracking changes in continuous emotion states using body language and prosodic cues","author":"Metallinou","year":"2010"},{"key":"10.1016\/j.imavis.2012.08.018_bb0030","series-title":"Workshop on Multimodal Corpora, LREC","article-title":"The USC CreativeIT database: a multimodal database of theatrical improvisation","author":"Metallinou","year":"2010"},{"key":"10.1016\/j.imavis.2012.08.018_bb0035","doi-asserted-by":"crossref","first-page":"762","DOI":"10.1109\/TASL.2010.2064164","article-title":"Ranking-based emotion recognition for music organization and retrieval","volume":"19","author":"Yang","year":"2011","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.imavis.2012.08.018_bb0040","doi-asserted-by":"crossref","first-page":"787","DOI":"10.1016\/j.specom.2007.01.010","article-title":"Primitives based estimation and evaluation of emotions in speech","volume":"49","author":"Grimm","year":"2007","journal-title":"Speech Commun."},{"key":"10.1016\/j.imavis.2012.08.018_bb0045","series-title":"Proc. of IEEE Intl. Conf. on Multimedia & Expo (ICME)","article-title":"Speech emotion estimation in 3D space","author":"Wu","year":"2010"},{"key":"10.1016\/j.imavis.2012.08.018_bb0050","series-title":"Proc. of ACII","article-title":"Naturalistic affective expression classification by a multi-stage approach based on hidden Markov models","author":"Meng","year":"2011"},{"key":"10.1016\/j.imavis.2012.08.018_bb0055","series-title":"IEEE Trans. of Affective Computing to Appear","article-title":"Context-sensitive learning for enhanced audiovisual emotion classification","author":"Metallinou","year":"2012"},{"key":"10.1016\/j.imavis.2012.08.018_bb0060","series-title":"Proc. of ICASSP","article-title":"A supervised approach to movie emotion tracking","author":"Malandrakis","year":"2011"},{"key":"10.1016\/j.imavis.2012.08.018_bb0065","series-title":"IEEE Trans. on Affective Computing","article-title":"Continuous prediction of spontaneous affect from multiple cues and modalities in valence-arousal space","author":"Nicolaou","year":"2011"},{"key":"10.1016\/j.imavis.2012.08.018_bb0070","series-title":"Proc. of Interspeech","article-title":"Abandoning emotion classes \u2014 towards continuous emotion recognition with modelling of long-range dependencies","author":"Woellmer","year":"2008"},{"key":"10.1016\/j.imavis.2012.08.018_bb0075","doi-asserted-by":"crossref","first-page":"867","DOI":"10.1109\/JSTSP.2010.2057200","article-title":"Combining long short-term memory and dynamic Bayesian networks for incremental emotion-sensitive artificial listening","volume":"4","author":"Wollmer","year":"2010","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"10.1016\/j.imavis.2012.08.018_bb0080","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1109\/TMM.2004.840618","article-title":"Affective video content representation and modeling","volume":"7","author":"Hanjalic","year":"2005","journal-title":"IEEE Trans. Multimedia"},{"key":"10.1016\/j.imavis.2012.08.018_bb0085","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1109\/MSP.2006.1621452","article-title":"Extracting moods from pictures and sounds: towards truly personalized TV","author":"Hanjalic","year":"2006","journal-title":"IEEE Signal Process Mag."},{"key":"10.1016\/j.imavis.2012.08.018_bb0090","series-title":"Handbook of Pattern Recognition and Computer Vision","article-title":"Multimodal emotion recognition","author":"Sebe","year":"2005"},{"key":"10.1016\/j.imavis.2012.08.018_bb0095","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":"Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.imavis.2012.08.018_bb0100","doi-asserted-by":"crossref","first-page":"1334","DOI":"10.1016\/j.jnca.2006.09.007","article-title":"Bi-modal emotion recognition from expressive face and body gestures","volume":"30","author":"Gunes","year":"2007","journal-title":"J. Netw. Comput. Appl."},{"key":"10.1016\/j.imavis.2012.08.018_bb0105","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1109\/TSMCB.2008.927269","article-title":"Automatic temporal segment detection and affect recognition from face and body display","volume":"39","author":"Gunes","year":"2009","journal-title":"IEEE Trans. Syst. Man Cybern. Part B Spec. Issue Hum. Comput."},{"key":"10.1016\/j.imavis.2012.08.018_bb0110","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1109\/T-AFFC.2011.7","article-title":"Towards a minimal representation of affective gestures","volume":"2","author":"Glowinski","year":"2011","journal-title":"IEEE Trans. Affective Comput."},{"key":"10.1016\/j.imavis.2012.08.018_bb0115","series-title":"Proc. of ACII","article-title":"Multimodal emotion recognition from expressive faces, body gestures and speech","author":"Castellano","year":"2007"},{"key":"10.1016\/j.imavis.2012.08.018_bb0120","series-title":"Proc. of ACII","article-title":"Recognising human emotions from body movement and gesture dynamics","author":"Castellano","year":"2007"},{"key":"10.1016\/j.imavis.2012.08.018_bb0125","doi-asserted-by":"crossref","first-page":"1027","DOI":"10.1109\/TSMCB.2010.2103557","article-title":"Automatic recognition of non-acted affective postures","volume":"41","author":"Kleinsmith","year":"2011","journal-title":"IEEE Trans. Syst. Man Cybern. Part B"},{"key":"10.1016\/j.imavis.2012.08.018_bb0130","doi-asserted-by":"crossref","first-page":"576","DOI":"10.1109\/TMM.2010.2052592","article-title":"A system for real-time multimodal analysis of nonverbal affective social interaction in user-centric media","volume":"12","author":"Varni","year":"2011","journal-title":"IEEE Trans. Multimedia"},{"key":"10.1016\/j.imavis.2012.08.018_bb0135","series-title":"Proc. of ICASSP","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP.2011.5946959","article-title":"Estimation of ordinal approach\u2013avoidance labels in dyadic interactions: ordinal logistic regression approach.","author":"Rozgic","year":"2011"},{"key":"10.1016\/j.imavis.2012.08.018_bb0140","series-title":"Proc. of ACII","article-title":"Detecting affect from non-stylised body motions","author":"Bernhardt","year":"2007"},{"key":"10.1016\/j.imavis.2012.08.018_bb0145","series-title":"Proceedings of the 2nd Intl Conf on Affective Computing and Intelligent Interaction (ACII)","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-74889-2_5","article-title":"Recognizing affective dimensions from body posture","author":"Kleinsmith","year":"2007"},{"key":"10.1016\/j.imavis.2012.08.018_bb0150","series-title":"Proc. of ACM\/IEEE Intl Conf. on Human-Robot Interaction","article-title":"Automatic analysis of affective postures and body motion to detect engagement with a game companion","author":"Sanghvi","year":"2011"},{"key":"10.1016\/j.imavis.2012.08.018_bb0155","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/T-AFFC.2012.16","article-title":"Affective body expression perception and recognition: a survey","author":"Kleinsmith","year":"2012","journal-title":"IEEE Trans. Affective Comput."},{"key":"10.1016\/j.imavis.2012.08.018_bb0160","doi-asserted-by":"crossref","first-page":"2222","DOI":"10.1109\/TASL.2007.907344","article-title":"Voice conversion based on maximum likelihood estimation of spectral parameter trajectory","volume":"15","author":"Toda","year":"2007","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.imavis.2012.08.018_bb0165","series-title":"Proc. of Interspeech","article-title":"A theoretical analysis of speech recognition based on feature trajectory models","author":"Minami","year":"2004"},{"key":"10.1016\/j.imavis.2012.08.018_bb0170","series-title":"Proc. of Interspeech","article-title":"A minimum converted trajectory error (MCTE) approach to high quality speech-to-lips conversion","author":"Zhuang","year":"2010"},{"key":"10.1016\/j.imavis.2012.08.018_bb0175","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1007\/s10579-008-9076-6","article-title":"IEMOCAP: interactive emotional dyadic motion capture database","volume":"42","author":"Busso","year":"2008","journal-title":"Lang. Resour. Eval."},{"key":"10.1016\/j.imavis.2012.08.018_bb0180","series-title":"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.2012.08.018_bb0185","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1109\/T-AFFC.2011.25","article-title":"A multimodal database for affect recognition and implicit tagging","volume":"3","author":"Soleymani","year":"2012","journal-title":"IEEE Trans. Affective Comput."},{"key":"10.1016\/j.imavis.2012.08.018_bb0190","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1016\/S1071-5819(03)00050-8","article-title":"Recognizing emotion from dance movement: comparison of spectator recognition and automated techniques","volume":"59","author":"Camurri","year":"2003","journal-title":"Int. J. Hum. Comput. Stud."},{"key":"10.1016\/j.imavis.2012.08.018_bb0195","author":"Cowie"},{"key":"10.1016\/j.imavis.2012.08.018_bb0200","unstructured":"K. Audhkhasi, S. Narayanan, A globally-variant locally-constant model for fusion of labels from multiple diverse experts without using reference labels, IEEE Trans. Pattern Anal. Mach. Intell. (in press)."},{"key":"10.1016\/j.imavis.2012.08.018_bb0205","series-title":"Proc. of ACII","article-title":"Multi-score learning for affect recognition: the case of body postures","author":"Meng","year":"2011"},{"key":"10.1016\/j.imavis.2012.08.018_bb0210","series-title":"The new handbook of Methods in Nonverbal Behavior Research","author":"Harrigan","year":"2005"},{"key":"10.1016\/j.imavis.2012.08.018_bb0215","doi-asserted-by":"crossref","first-page":"1226","DOI":"10.1109\/TPAMI.2005.159","article-title":"Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy","volume":"27","author":"Peng","year":"2005","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.imavis.2012.08.018_bb0220","series-title":"Pattern Classification","author":"Duda","year":"2007"},{"key":"10.1016\/j.imavis.2012.08.018_bb0225","doi-asserted-by":"crossref","first-page":"1162","DOI":"10.1016\/j.specom.2006.04.003","article-title":"Emotional speech recognition: resources, features, and methods","volume":"48","author":"Ververidis","year":"2006","journal-title":"Speech Commun."},{"key":"10.1016\/j.imavis.2012.08.018_bb0230","series-title":"The HTK Book","author":"Young","year":"2006"},{"issue":"8","key":"10.1016\/j.imavis.2012.08.018_bb0235","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"10.1016\/j.imavis.2012.08.018_bb0240","doi-asserted-by":"crossref","first-page":"602","DOI":"10.1016\/j.neunet.2005.06.042","article-title":"Framewise phoneme classification with bidirectional LSTM and other neural network architectures","volume":"18","author":"Graves","year":"2005","journal-title":"Neural Netw."},{"key":"10.1016\/j.imavis.2012.08.018_bb0245","series-title":"Proc. of Interspeech, Japan","article-title":"Context-sensitive multimodal emotion recognition from speech and facial expression using bidirectional LSTM modeling","author":"W\u00f6llmer","year":"2010"},{"key":"10.1016\/j.imavis.2012.08.018_bb0250","author":"Graves"},{"key":"10.1016\/j.imavis.2012.08.018_bb0255","series-title":"The New Handbook of Methods in Nonverbal Behavior Research","first-page":"65","article-title":"Chapter 3: vocal expression of affect","author":"Juslin","year":"2005"},{"key":"10.1016\/j.imavis.2012.08.018_bb0260","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1007\/s12193-009-0032-6","article-title":"On-line emotion recognition in a 3-D activation\u2013valence\u2013time continuum using acoustic and linguistic cues","volume":"3","author":"Eyben","year":"2010","journal-title":"J. Multimodal User Interfaces"},{"key":"10.1016\/j.imavis.2012.08.018_bb0265","series-title":"Proc. of EUSIPCO","article-title":"Audio\u2013visual emotion recognition using an emotion space concept","author":"Kanluan","year":"2008"},{"key":"10.1016\/j.imavis.2012.08.018_bb0270","series-title":"Gender, Power, and Communication in Human Relationships","article-title":"Body politics revisited: what do we know today?","author":"Henley","year":"1995"}],"container-title":["Image and Vision Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0262885612001710?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0262885612001710?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2018,11,20]],"date-time":"2018-11-20T16:27:34Z","timestamp":1542731254000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0262885612001710"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,2]]},"references-count":54,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2013,2]]}},"alternative-id":["S0262885612001710"],"URL":"https:\/\/doi.org\/10.1016\/j.imavis.2012.08.018","relation":{},"ISSN":["0262-8856"],"issn-type":[{"value":"0262-8856","type":"print"}],"subject":[],"published":{"date-parts":[[2013,2]]}}}