{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,16]],"date-time":"2025-05-16T09:06:53Z","timestamp":1747386413815,"version":"3.33.0"},"publisher-location":"Berlin, Heidelberg","reference-count":83,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540723462"},{"type":"electronic","value":"9783540723486"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1007\/978-3-540-72348-6_4","type":"book-chapter","created":{"date-parts":[[2007,7,16]],"date-time":"2007-07-16T15:58:50Z","timestamp":1184601530000},"page":"72-90","source":"Crossref","is-referenced-by-count":31,"title":["Audio-Visual Spontaneous Emotion Recognition"],"prefix":"10.1007","author":[{"given":"Zhihong","family":"Zeng","sequence":"first","affiliation":[]},{"given":"Yuxiao","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Glenn I.","family":"Roisman","sequence":"additional","affiliation":[]},{"given":"Zhen","family":"Wen","sequence":"additional","affiliation":[]},{"given":"Yun","family":"Fu","sequence":"additional","affiliation":[]},{"given":"Thomas S.","family":"Huang","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"4_CR1","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/1140.001.0001","volume-title":"Affective Computing","author":"R.W. Picard","year":"1997","unstructured":"Picard, R.W.: Affective Computing. MIT Press, Cambridge (1997)"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Litman, D.J., Forbes-Riley, K.: Predicting Student Emotions in Computer-Human Tutoring Dialogues. In: Proc. of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL) (July 2004)","DOI":"10.3115\/1218955.1219000"},{"key":"4_CR3","doi-asserted-by":"crossref","unstructured":"Kapoor, A., Picard, R.W.: Multimodal Affect Recognition in Learning Environments. In: ACM Multimedia, pp. 677\u2013682 (2005)","DOI":"10.1145\/1101149.1101300"},{"issue":"2","key":"4_CR4","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1023\/B:VISI.0000013087.49260.fb","volume":"57","author":"P. Viola","year":"2004","unstructured":"Viola, P.: Robust Real-Time Face Detection. Int. Journal of Computer Vision.\u00a057(2), 137\u2013154 (2004)","journal-title":"Int. Journal of Computer Vision."},{"key":"4_CR5","unstructured":"Polzin, S.T., Waibel, A.: Pronunciation Variations in Emotional Speech. In: Proceedings of the ESCA Workshop, pp. 103\u2013108 (1999)"},{"key":"4_CR6","doi-asserted-by":"publisher","first-page":"437","DOI":"10.1016\/j.neunet.2005.03.008","volume":"18","author":"T. Athanaselis","year":"2005","unstructured":"Athanaselis, T., et al.: ASR for Emotional Speech: Clarifying the Issues and Enhancing Performance. Neural Networks\u00a018, 437\u2013444 (2005)","journal-title":"Neural Networks"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Steeneken, H.J.M., Hansen, J.H.L.: Speech under stress conditions: Overview of the effect of speech production and on system performance. In: Int. Conf. on Acoustics, Speech, and Signal Processing, vol.\u00a04, pp. 2079\u20132082 (1999)","DOI":"10.1109\/ICASSP.1999.758342"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Okawa, S., Bocchieri, E., Potamianos, A.: Multi-band Speech Recognition in noisy environments. In: ICASSP, pp. 641\u2013644 (1998)","DOI":"10.1109\/ICASSP.1998.675346"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Garg, A., et al.: Frame-dependent multi-stream reliability indicators for audio-visual speech recognition. In: ICASSP (2003)","DOI":"10.1109\/ICME.2003.1221384"},{"key":"4_CR10","volume-title":"Emotion in the Human Face","author":"P. Ekman","year":"1972","unstructured":"Ekman, P., Friesen, W.V., Ellsworth, P.: Emotion in the Human Face. Pergamon Press, Elmsford (1972)"},{"key":"4_CR11","volume-title":"The face of Emotion","author":"C.. Izard","year":"1971","unstructured":"Izard, C.: The face of Emotion. Appleton-Century-Crofts, New York (1971)"},{"key":"4_CR12","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1017\/CBO9780511806582.009","volume-title":"Feelings and emotions, The Amsterdam symposium","author":"K.R. Scherer","year":"2004","unstructured":"Scherer, K.R.: Feelings integrate the central representation of appraisal-driven response organization in emotion. In: Manstead, A.S.R., Frijda, N.H., Fischer, A.H. (eds.) Feelings and emotions, The Amsterdam symposium, pp. 136\u2013157. Cambridge University Press, Cambridge (2004)"},{"key":"4_CR13","unstructured":"Ekman, P., Friensen, W.V., Hager, J.: Facial Action Unit System. A Human Face (2002)"},{"key":"4_CR14","doi-asserted-by":"crossref","DOI":"10.1093\/acprof:oso\/9780195179644.001.0001","volume-title":"What the Face Reveals: Basic and Applied Studies of Spontaneous Expression Using Facial Action Coding System","author":"P. Ekman","year":"2005","unstructured":"Ekman, P., Rosenberg, E.L.: What the Face Reveals: Basic and Applied Studies of Spontaneous Expression Using Facial Action Coding System, 2nd edn. Oxford University Express, Oxford (2005)","edition":"2"},{"key":"4_CR15","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1146\/annurev.psych.54.101601.145102","volume":"54","author":"J.A. Russell","year":"2003","unstructured":"Russell, J.A., Bachorowski, J.A., Fernandez-Dols, J.: Facial and Vocal Expressions of Emotion. Annual Review Psychology\u00a054, 329\u2013349 (2003)","journal-title":"Annual Review Psychology"},{"key":"4_CR16","doi-asserted-by":"publisher","first-page":"527","DOI":"10.1146\/annurev.ps.30.020179.002523","volume":"30","author":"P. Ekman","year":"1979","unstructured":"Ekman, P., Oster, H.: Facial Expressions of Emotion. Annual Review Psychology\u00a030, 527\u2013554 (1979)","journal-title":"Annual Review Psychology"},{"issue":"5","key":"4_CR17","doi-asserted-by":"publisher","first-page":"776","DOI":"10.1037\/0012-1649.40.5.776","volume":"40","author":"G.I. Roisman","year":"2004","unstructured":"Roisman, G.I., Tsai, J.L., Chiang, K.S.: The Emotional Integration of Childhood Experience: Physiological, Facial Expressive, and Self-reported Emotional Response During the Adult Attachment Interview. Developmental Psychology\u00a040(5), 776\u2013789 (2004)","journal-title":"Developmental Psychology"},{"key":"4_CR18","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1037\/0012-1649.23.1.68","volume":"23","author":"J.F. Cohn","year":"1988","unstructured":"Cohn, J.F., Tronick, E.: Mother Infant Interaction: the sequence of dyadic states at three, six and nine months. Development Psychology\u00a023, 68\u201377 (1988)","journal-title":"Development Psychology"},{"key":"4_CR19","unstructured":"Fried, E.: The impact of nonverbal communication of facial affect on children\u2019s learning. PhD thesis, Rutgers University, New Brunswick, NJ (1976)"},{"key":"4_CR20","doi-asserted-by":"crossref","unstructured":"Ekman, P., Matsumoto, D., Friesen, W.: Facial Expression in Affective Disorders. In: Ekman, P., Rosenberg, E.L. (eds.) What the Face Reveals, pp. 429\u2013439 (2005)","DOI":"10.1093\/acprof:oso\/9780195179644.003.0020"},{"key":"4_CR21","doi-asserted-by":"crossref","unstructured":"Zeng, Z., et al.: One-class classification on spontaneous facial expressions. In: Automatic Face and Gesture Recognition, pp. 281\u2013286 (2006)","DOI":"10.1109\/FGR.2006.83"},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Bourlard, H., Dupont, S.: A new ASR approach based on independent processing and recombination of partial frequency bands. In: ICSLP (1996)","DOI":"10.21437\/ICSLP.1996-90"},{"key":"4_CR23","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1016\/j.neunet.2005.03.007","volume":"18","author":"L. Devillers","year":"2005","unstructured":"Devillers, L., Vidrascu, L., Lamel, L.: Challenges in real-life emotion annotation and machine learning based detection. Neural Networks\u00a018, 407\u2013422 (2005)","journal-title":"Neural Networks"},{"key":"4_CR24","unstructured":"Ekman, P., et al.: Ekman-Hager Facial Action Exemplars. Human Interaction Laboratory, University of California, San Francisco (unpublished)"},{"key":"4_CR25","doi-asserted-by":"crossref","unstructured":"Kanade, T., Cohn, J., Tian, Y.: Comprehensive Database for Facial Expression Analysis. In: Proceeding of International Conference on Face and Gesture Recognition, pp. 46\u201353 (2000)","DOI":"10.1109\/AFGR.2000.840611"},{"key":"4_CR26","doi-asserted-by":"crossref","unstructured":"Pantic, M., et al.: Web-based database for facial expression analysis. In: Int. Conf. on Multimedia and Expo (2005)","DOI":"10.1109\/ICME.2005.1521424"},{"key":"4_CR27","unstructured":"JAFFE: http:\/\/www.mic.atr.co.jp\/~mlyons\/jaffe.html"},{"key":"4_CR28","unstructured":"Chen, L.S.: Joint Processing of Audio-Visual Informa-tion for the Recognition of Emotional Expressions in Human-Computer Interaction. PhD thesis, UIUC (2000)"},{"key":"4_CR29","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1016\/j.neunet.2005.03.002","volume":"18","author":"R. Cowie","year":"2005","unstructured":"Cowie, R., Douglas-Cowie, E., Cox, C.: Beyond emotion archetypes: Databases for emotion modelling using neural networks. Neural Networks\u00a018, 371\u2013388 (2005)","journal-title":"Neural Networks"},{"volume-title":"What the face reveals","year":"1997","key":"4_CR30","unstructured":"Ekman, P., Rosenberg, E. (eds.): What the face reveals. Oxford University Press, Oxford (1997)"},{"key":"4_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1142\/S021969130400041X","volume":"2","author":"J.F. Cohn","year":"2004","unstructured":"Cohn, J.F., Schmidt, K.L.: The timing of Facial Motion in Posed and Spontaneous Smiles. International Journal of Wavelets, Multiresolution and Information Processing\u00a02, 1\u201312 (2004)","journal-title":"International Journal of Wavelets, Multiresolution and Information Processing"},{"key":"4_CR32","doi-asserted-by":"crossref","unstructured":"Valstar, M.F., et al.: Spontaneous vs. Posed Facial Behavior: Automatic Analysis of Brow Actions. In: Int. Conf. on Multimedia Interfaces, pp. 162\u2013170 (2006)","DOI":"10.1145\/1180995.1181031"},{"issue":"2","key":"4_CR33","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1037\/0033-2909.115.2.268","volume":"115","author":"P. Ekman","year":"1994","unstructured":"Ekman, P.: Strong Evidence for Universals in Facial Expressions: A Reply to Russell\u2019s Mistaken Critique. Psychological Bulletin\u00a0115(2), 268\u2013287 (1994)","journal-title":"Psychological Bulletin"},{"issue":"9","key":"4_CR34","doi-asserted-by":"publisher","first-page":"1370","DOI":"10.1109\/JPROC.2003.817122","volume":"91","author":"M. Pantic","year":"2003","unstructured":"Pantic, M., Rothkrantz, L.J.M.: Toward an affect-sensitive multimodal human-computer interaction. Proceedings of the IEEE\u00a091(9), 1370\u20131390 (2003)","journal-title":"Proceedings of the IEEE"},{"key":"4_CR35","doi-asserted-by":"crossref","unstructured":"Pantic, M., et al.: Affective Multimodal Human-Computer Interaction. In: Proc. ACM Int\u2019l Conf. on Multimedia, November 2005, pp. 669\u2013676 (2005)","DOI":"10.1145\/1101149.1101299"},{"key":"4_CR36","doi-asserted-by":"crossref","unstructured":"Sebe, N., et al.: Multimodal Approaches for Emotion Recognition: A Survey. In: Proc. Of SPIE-IS&T Electronic Imaging. SPIE, vol.\u00a05670, pp. 56\u201367 (2005)","DOI":"10.1117\/12.600746"},{"key":"4_CR37","doi-asserted-by":"crossref","unstructured":"Cowie, R., et al.: Emotion Recognition in Human-Computer Interaction. IEEE Signal Processing Magazine, 32\u201380 (January 2001)","DOI":"10.1109\/79.911197"},{"key":"4_CR38","doi-asserted-by":"crossref","unstructured":"Chen, L., Huang, T.S.: Emotional expressions in audiovisual human computer interaction. In: Int. Conf. on Multimedia & Expo, pp. 423\u2013426 (2000)","DOI":"10.1109\/ICME.2000.869630"},{"key":"4_CR39","doi-asserted-by":"crossref","unstructured":"Chen, L., et al.: Multimodal human emotion\/ expression recognition. In: Int. Conf. on Automatic Face & Gesture Recognition, pp. 396\u2013401 (1998)","DOI":"10.1109\/AFGR.1998.670976"},{"key":"4_CR40","doi-asserted-by":"crossref","unstructured":"De Silva, L.C., Ng, P.C.: Bimodal emotion recognition. In: Int. Conf. on Automatic Face & Gesture Recognition, pp. 332\u2013335 (2000)","DOI":"10.1109\/AFGR.2000.840655"},{"key":"4_CR41","doi-asserted-by":"crossref","unstructured":"Yoshitomi, Y., et al.: Effect of sensor fusion for recognition of emotional states using voice, face image and thermal image of face. In: Proc. ROMAN, pp. 178\u2013183 (2000)","DOI":"10.1109\/ROMAN.2000.892491"},{"key":"4_CR42","doi-asserted-by":"crossref","unstructured":"Hoch, S., et al.: Bimodal fusion of emotional data in an automotive environment. In: ICASSP, vol. II, pp. 1085\u20131088 (2005)","DOI":"10.1109\/ICASSP.2005.1415597"},{"key":"4_CR43","unstructured":"Wang, Y., Guan, L.: Recognizing human emotion from audiovisual information. In: ICASSP, vol. II, pp. 1125\u20131128 (2005)"},{"key":"4_CR44","doi-asserted-by":"crossref","unstructured":"Zeng, Z., et al.: Training Combination Strategy of Multi-stream Fused Hidden Markov Model for Audio-visual Affect Recognition. In: Proc. ACM Int\u2019l Conf. on Multimedia, pp. 65\u201368 (2005)","DOI":"10.1145\/1180639.1180661"},{"key":"4_CR45","doi-asserted-by":"crossref","unstructured":"Zeng, Z., et al.: Audio-visual Affect Recognition through Multi-stream Fused HMM for HCI. In: Int. Conf. Computer Vision and Pattern Recognition, pp. 967\u2013972 (2005)","DOI":"10.1109\/CVPR.2005.77"},{"key":"4_CR46","doi-asserted-by":"crossref","unstructured":"Zeng, Z., et al.: Multi-stream Confidence Analysis for Audio-Visual Affect Recognition. In: Int. Conf. on Affective Computing and Intelligent Interaction, pp. 946\u2013971 (2005)","DOI":"10.1007\/11573548_123"},{"key":"4_CR47","doi-asserted-by":"crossref","unstructured":"Zeng, Z., et al.: Audio-visual Affect Recognition in Activation-evaluation Space. In: Int. Conf. on Multimedia & Expo, pp. 828\u2013831 (2005)","DOI":"10.1109\/ICME.2005.1521551"},{"key":"4_CR48","doi-asserted-by":"crossref","unstructured":"Zeng, Z., et al.: Audio-visual Affect Recognition. IEEE Transactions on Multimedia, in press (2007)","DOI":"10.1109\/TMM.2006.886310"},{"key":"4_CR49","unstructured":"Song, M., et al.: Audio-visual based emotion recognition\u2014A new approach. In: Int. Conf. Computer Vision and Pattern Recognition, pp. 1020\u20131025 (2004)"},{"key":"4_CR50","doi-asserted-by":"crossref","unstructured":"Busso, C., et al.: Analysis of Emotion Recognition using Facial Expressions, Speech and Multimodal Information. In: Int. Conf. Multimodal Interfaces, pp. 205\u2013211 (2004)","DOI":"10.1145\/1027933.1027968"},{"key":"4_CR51","doi-asserted-by":"crossref","unstructured":"Hoch, S., et al.: Bimodal fusion of emotional data in an automotive environment. In: ICASSP, vol. II, pp. 1085\u20131088 (2005)","DOI":"10.1109\/ICASSP.2005.1415597"},{"key":"4_CR52","unstructured":"Wang, Y., Guan, L.: Recognizing human emotion from audiovisual information. In: ICASSP, vol. II, pp. 1125\u20131128 (2005)"},{"key":"4_CR53","unstructured":"Go, H.J., et al.: Emotion recognition from facial image and speech signal. In: Int. Conf. of the Society of Instrument and Control Engineers, pp. 2890\u20132895 (2003)"},{"key":"4_CR54","unstructured":"Bartlett, M.S., et al.: Recognizing Facial Expression: Machine Learning and Application to Spontaneous Behavior. In: IEEE CVPR\u201905 (2005)"},{"key":"4_CR55","doi-asserted-by":"crossref","unstructured":"Sebe, N., et al.: Authentic Facial Expression Analysis. In: Int. Conf. on Automatic Face and Gesture Recognition (2004)","DOI":"10.1109\/AFGR.2004.1301585"},{"issue":"5","key":"4_CR56","doi-asserted-by":"publisher","first-page":"1","DOI":"10.4304\/jmm.1.5.1-8","volume":"1","author":"Z. Zeng","year":"2006","unstructured":"Zeng, Z., et al.: Spontaneous Emotional Facial Expression Detection. Journal of Multimedia\u00a01(5), 1\u20138 (2006)","journal-title":"Journal of Multimedia"},{"key":"4_CR57","doi-asserted-by":"crossref","unstructured":"Valstar, M.F., et al.: Spontaneous vs. Posed Facial Behavior: Automatic Analysis of Brow Actions. In: Int. Conf. on Multimodal Interfaces, pp. 162\u2013170 (2006)","DOI":"10.1145\/1180995.1181031"},{"key":"4_CR58","doi-asserted-by":"crossref","unstructured":"Cohn, J.F., et al.: Automatic Analysis and recognition of brow actions and head motion in spontaneous facial behavior. In: Int. Conf. on Systems, Man & Cybernetics, vol. 1, pp. 610\u2013616 (2004)","DOI":"10.1109\/ICSMC.2004.1398367"},{"key":"4_CR59","doi-asserted-by":"crossref","unstructured":"Litman, D.J., Forbes-Riley, K.: Predicting Student Emotions in Computer-Human Tutoring Dialogues. In: Proc. of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL) (July 2004)","DOI":"10.3115\/1218955.1219000"},{"key":"4_CR60","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1016\/S0167-6393(02)00079-1","volume":"40","author":"A. Batliner","year":"2003","unstructured":"Batliner, A., et al.: How to find trouble in communication. Speech Communication\u00a040, 117\u2013143 (2003)","journal-title":"Speech Communication"},{"key":"4_CR61","doi-asserted-by":"crossref","unstructured":"Neiberg, D., Elenius, K., Laskowski, K.: Emotion Recognition in Spontaneous Speech Using GMM. In: Int. Conf. on Spoken Language Processing, pp. 809\u2013812 (2006)","DOI":"10.21437\/Interspeech.2006-277"},{"key":"4_CR62","doi-asserted-by":"crossref","unstructured":"Ang, J., et al.: Prosody-based automatic detection of annoyance and frustration in human-computer dialog. In: ICSLP (2002)","DOI":"10.21437\/ICSLP.2002-559"},{"key":"4_CR63","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1016\/j.neunet.2005.03.006","volume":"18","author":"F. Fragopanagos","year":"2005","unstructured":"Fragopanagos, F., Taylor, J.G.: Emotion recognition in human-computer interaction. Neural Networks\u00a018, 389\u2013405 (2005)","journal-title":"Neural Networks"},{"key":"4_CR64","doi-asserted-by":"crossref","unstructured":"Garidakis, G., et al.: Modeling Naturalistic Affective States via Facial and Vocal Expression Recognition. In: Int. Conf. on Multimodal Interfaces, pp. 146\u2013154 (2006)","DOI":"10.1145\/1180995.1181029"},{"key":"4_CR65","unstructured":"Cowie, R., et al.: \u2019Feeltrace\u2019: an instrument for recording perceived emotion in real time. In: Proceedings of the ISCA Workshop on Speech and Emotion, pp. 19\u201324 (2000)"},{"key":"4_CR66","doi-asserted-by":"crossref","unstructured":"Maat, L., Pantic, M.: Gaze-X: Adaptive Affective Multimodal Interface for Single-User Office Scenarios. In: Int. Conf. on Multimodal Interfaces, pp. 171\u2013178 (2006)","DOI":"10.1145\/1180995.1181032"},{"key":"4_CR67","doi-asserted-by":"crossref","unstructured":"Lanitis, A., Taylor, C., Cootes, T.: A Unified Approach to Coding and Interpreting Face Images. In: Proc. International Conf. on Computer Vision, pp. 368\u2013373 (1995)","DOI":"10.1109\/ICCV.1995.466919"},{"key":"4_CR68","doi-asserted-by":"crossref","unstructured":"Black, M., Yacoob, Y.: Tracking and Recognizing Rigid and Non-rigid Facial Motions Using Local Parametric Models of Image Motion. In: Proc. Int. Conf. on Computer Vision, pp. 374\u2013381 (1995)","DOI":"10.1109\/ICCV.1995.466915"},{"issue":"5","key":"4_CR69","doi-asserted-by":"publisher","first-page":"1121","DOI":"10.1109\/72.536309","volume":"7","author":"M. Rosenblum","year":"1996","unstructured":"Rosenblum, M., Yacoob, Y., Davis, L.: Human Expression Recognition from Motion Using a Radial Basis Function Network Architecture. IEEE Trans. on Neural Network\u00a07(5), 1121\u20131138 (1996)","journal-title":"IEEE Trans. on Neural Network"},{"issue":"7","key":"4_CR70","doi-asserted-by":"publisher","first-page":"757","DOI":"10.1109\/34.598232","volume":"19","author":"I. Essa","year":"1997","unstructured":"Essa, I., Pentland, A.: Coding, Analysis, Interpretation, and Recognition of Facial Expressions. IEEE Trans. On Pattern Analysis and Machine Intelligence\u00a019(7), 757\u2013767 (1997)","journal-title":"IEEE Trans. On Pattern Analysis and Machine Intelligence"},{"issue":"1-2","key":"4_CR71","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1016\/S1077-3142(03)00081-X","volume":"91","author":"L. Cohen","year":"2003","unstructured":"Cohen, L., et al.: Facial expression recognition from video sequences: Temporal and static modeling. Computer Vision and Image Understanding\u00a091(1-2), 160\u2013187 (2003)","journal-title":"Computer Vision and Image Understanding"},{"issue":"2","key":"4_CR72","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1109\/34.908962","volume":"23","author":"Y. Tian","year":"2001","unstructured":"Tian, Y., Kanade, T., Cohn, J.F.: Recognizing Action Units for Facial Expression Analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence\u00a023(2), 97\u2013115 (2001)","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"2","key":"4_CR73","doi-asserted-by":"publisher","first-page":"433","DOI":"10.1109\/TSMCB.2005.859075","volume":"36","author":"M. Pantic","year":"2006","unstructured":"Pantic, M., Patras, I.: Dynamics of Facial Expression: Recognition of Facial Actions and Their Temporal Segments from Face Profile Image Sequences. IEEE Transactions on Systems, Man and Cybernetics - Part B\u00a036(2), 433\u2013449 (2006)","journal-title":"IEEE Transactions on Systems, Man and Cybernetics - Part B"},{"key":"4_CR74","doi-asserted-by":"crossref","unstructured":"Kwon, O.W., et al.: Emotion Recognition by Speech Signals. In: EUROSPEECH (2003)","DOI":"10.21437\/Eurospeech.2003-80"},{"key":"4_CR75","unstructured":"Polzin, T.: Detecting Verbal and Non-verbal cues in the communication of emotion. PhD thesis, Carnegie Mellon University (1999)"},{"key":"4_CR76","doi-asserted-by":"crossref","unstructured":"Amir, N., Ron, S.: Toward Automatic Classification of Emotions in Speech. In: Proc. ICSLP, pp. 555\u2013558 (1998)","DOI":"10.21437\/ICSLP.1998-105"},{"key":"4_CR77","doi-asserted-by":"crossref","unstructured":"Dellaert, F., Polzin, T., Waibel, A.: Recognizing Emotion in Speech. In: Proc. ICSLP, pp. 1970\u20131973 (1996)","DOI":"10.1109\/ICSLP.1996.608022"},{"key":"4_CR78","unstructured":"Petrushin, V.A.: Emotion Recognition in Speech Signal. In: Proc. ICSLP, pp. 222\u2013225 (2000)"},{"key":"4_CR79","doi-asserted-by":"crossref","unstructured":"Pantic, M., et al.: Human Computing and Machine Understanding of Human Behavior: A Survey. In: Int. Conf. Multimodal Interfaces, pp. 233\u2013238 (2006)","DOI":"10.1145\/1180995.1181044"},{"key":"4_CR80","unstructured":"Huang, D.: Physiological, subjective, and behavioral Responses of Chinese American and European Americans during moments of peak emotional intensity. Honor Bachelor thesis, Psychology, University of Minnesota (1999)"},{"key":"4_CR81","unstructured":"Tao, H., Huang, T.S.: Explanation-based facial motion tracking using a piecewise Bezier volume deformation mode. In: IEEE CVPR\u201999, vol.\u00a01, pp. 611\u2013617 (1999)"},{"key":"4_CR82","doi-asserted-by":"crossref","unstructured":"Wen, Z., Huang, T.: Capturing Subtle Facial Motions in 3D Face Tracking. In: Intl. Conf. on Computer Vision (ICCV), pp. 1343\u20131350 (2003)","DOI":"10.1109\/ICCV.2003.1238646"},{"key":"4_CR83","unstructured":"He, X., et al.: Learning a Locality Preserving Subspace for Visual Recognition. In: Int. Conf. on Computer Vision (2003)"}],"container-title":["Lecture Notes in Computer Science","Artifical Intelligence for Human Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-72348-6_4.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,19]],"date-time":"2025-01-19T11:46:10Z","timestamp":1737287170000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-72348-6_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"ISBN":["9783540723462","9783540723486"],"references-count":83,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-72348-6_4","relation":{},"subject":[]}}