{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T02:11:16Z","timestamp":1784686276278,"version":"3.55.0"},"reference-count":54,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2018,7,19]],"date-time":"2018-07-19T00:00:00Z","timestamp":1531958400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Vision and Applications"],"published-print":{"date-parts":[[2019,7]]},"DOI":"10.1007\/s00138-018-0960-9","type":"journal-article","created":{"date-parts":[[2018,7,19]],"date-time":"2018-07-19T15:41:03Z","timestamp":1532014863000},"page":"975-985","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":137,"title":["Audiovisual emotion recognition in wild"],"prefix":"10.1007","volume":"30","author":[{"given":"Egils","family":"Avots","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tomasz","family":"Sapi\u0144ski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maie","family":"Bachmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3416-5554","authenticated-orcid":false,"given":"Dorota","family":"Kami\u0144ska","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,7,19]]},"reference":[{"key":"960_CR1","doi-asserted-by":"crossref","unstructured":"El\u00a0Kaliouby, R., Robinson, P.: 2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE, 2004), vol.\u00a01, pp. 682\u2013688 (2004)","DOI":"10.1109\/ICSMC.2004.1398380"},{"key":"960_CR2","unstructured":"Ofodile, I., Kulkarni, K., Corneanu, C.A., Escalera, S., Baro, X., Hyniewska, S., Allik, J., Anbarjafari, J.: Automatic recognition of deceptive facial expressions of emotion. arXiv:1707.04061 (2017)"},{"issue":"7","key":"960_CR3","doi-asserted-by":"publisher","first-page":"1063","DOI":"10.1007\/s00138-016-0794-2","volume":"27","author":"S Shojaeilangari","year":"2016","unstructured":"Shojaeilangari, S., Yau, W.Y., Teoh, E.K.: Pose-invariant descriptor for facial emotion recognition. Mach. Vis. Appl. 27(7), 1063 (2016)","journal-title":"Mach. Vis. Appl."},{"key":"960_CR4","doi-asserted-by":"crossref","unstructured":"Loob, C., Rasti, P., L\u00fcsi, I., Junior, J.C.J., Bar\u00f3, X., Escalera, S., Sapinski, T., Kaminska, D., Anbarjafari, G.: 2017 12th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2017) (IEEE, 2017), pp. 833\u2013838 (2017)","DOI":"10.1109\/FG.2017.106"},{"key":"960_CR5","doi-asserted-by":"crossref","unstructured":"Ekman, P., Friesen, W.V.: Facial action coding system (1977)","DOI":"10.1037\/t27734-000"},{"issue":"2","key":"960_CR6","doi-asserted-by":"publisher","first-page":"165","DOI":"10.2478\/v10177-012-0024-4","volume":"58","author":"D Kami\u0144ska","year":"2012","unstructured":"Kami\u0144ska, D., Pelikant, A.: Recognition of human emotion from a speech signal based on plutchik\u2019s model. Int. J. Electron. Telecommun. 58(2), 165 (2012)","journal-title":"Int. J. Electron. Telecommun."},{"issue":"2","key":"960_CR7","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1007\/s10772-017-9396-2","volume":"20","author":"F Noroozi","year":"2017","unstructured":"Noroozi, F., Sapi\u0144ski, T., Kami\u0144ska, D., Anbarjafari, G.: Vocal-based emotion recognition using random forests and decision tree. Int. J. Speech Technol. 20(2), 239 (2017)","journal-title":"Int. J. Speech Technol."},{"issue":"1","key":"960_CR8","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1186\/s13636-017-0100-x","volume":"2017","author":"D Kamiska","year":"2017","unstructured":"Kamiska, D., Sapiski, T., Anbarjafari, G.: Efficiency of chosen speech descriptors in relation to emotion recognition. EURASIP J. Audio Speech Music Process. 2017(1), 3 (2017)","journal-title":"EURASIP J. Audio Speech Music Process."},{"issue":"6","key":"960_CR9","doi-asserted-by":"publisher","first-page":"487","DOI":"10.1016\/j.specom.2008.03.012","volume":"50","author":"C Clavel","year":"2008","unstructured":"Clavel, C., Vasilescu, I., Devillers, L., Richard, G., Ehrette, T.: Fear-type emotion recognition for future audio-based surveillance systems. Speech Commun. 50(6), 487 (2008)","journal-title":"Speech Commun."},{"key":"960_CR10","doi-asserted-by":"crossref","unstructured":"Noroozi, F., Marjanovic, M., Njegus, A., Escalera, S., Anbarjafari, G.: 2016 23rd International Conference on Pattern Recognition (ICPR) (IEEE, 2016), pp. 61\u201366 (2016)","DOI":"10.1109\/ICPR.2016.7899608"},{"issue":"3","key":"960_CR11","doi-asserted-by":"publisher","first-page":"1104","DOI":"10.1109\/TII.2016.2550528","volume":"12","author":"P P\u0142awiak","year":"2016","unstructured":"P\u0142awiak, P., So\u015bnicki, T., Nied\u017awiecki, M., Tabor, Z., Rzecki, K.: Hand body language gesture recognition based on signals from specialized glove and machine learning algorithms. IEEE Trans. Indus. Inf. 12(3), 1104 (2016)","journal-title":"IEEE Trans. Indus. Inf."},{"key":"960_CR12","doi-asserted-by":"crossref","unstructured":"Kiforenko, L., Kraft, D.: 11th International Conference on Computer Vision Theory and Applications Computer Vision Theory and Applications (SCITEPRESS Digital Library, 2016), pp. 398\u2013405 (2016)","DOI":"10.5220\/0005783403980405"},{"issue":"1","key":"960_CR13","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1109\/T-AFFC.2012.16","volume":"4","author":"A Kleinsmith","year":"2013","unstructured":"Kleinsmith, A., Bianchi-Berthouze, N.: Affective body expression perception and recognition: a survey. IEEE Trans. Affect. Comput. 4(1), 15 (2013)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"960_CR14","doi-asserted-by":"crossref","unstructured":"Noroozi, F., Corneanu, C.A., Kami\u0144ska, D., Sapi\u0144ski, T., Escalera, S., Anbarjafari, G.: Survey on emotional body gesture recognition. arXiv:1801.07481 (2018)","DOI":"10.1109\/TAFFC.2018.2874986"},{"key":"960_CR15","unstructured":"Haamer, R.E., Kulkarni, K., Imanpour, N., Haque, M.A., Avots, E., Breisch, M., Nasrollahi, K., Guerrero, S.E., Ozcinar, C., Baro, X., et\u00a0al.: IEEE Conference on Automatic Face and Gesture Recognition Workshops (IEEE, 2018) (2018)"},{"issue":"3","key":"960_CR16","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1109\/TAFFC.2014.2339834","volume":"5","author":"R Jenke","year":"2014","unstructured":"Jenke, R., Peer, A., Buss, M.: Feature extraction and selection for emotion recognition from eeg. IEEE Trans. Affect. Comput. 5(3), 327 (2014)","journal-title":"IEEE Trans. Affect. Comput."},{"issue":"3","key":"960_CR17","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1080\/02533839.2013.799946","volume":"37","author":"S Jerritta","year":"2014","unstructured":"Jerritta, S., Murugappan, M., Wan, K., Yaacob, S.: Emotion recognition from facial emg signals using higher order statistics and principal component analysis. J. Chin. Inst. Eng. 37(3), 385 (2014)","journal-title":"J. Chin. Inst. Eng."},{"issue":"3","key":"960_CR18","doi-asserted-by":"publisher","first-page":"716","DOI":"10.1109\/JSEN.2016.2623677","volume":"17","author":"A Greco","year":"2017","unstructured":"Greco, A., Valenza, G., Citi, L., Scilingo, E.P.: Arousal and valence recognition of affective sounds based on electrodermal activity. IEEE Sens. J. 17(3), 716 (2017)","journal-title":"IEEE Sens. J."},{"key":"960_CR19","doi-asserted-by":"publisher","first-page":"3475","DOI":"10.1098\/rstb.2009.0190","volume":"364","author":"BD Gelder","year":"2009","unstructured":"Gelder, B.D.: Why bodies? twelve reasons for including bodily expressions in affective neuroscience. Philos. Trans. R. Soc. B Biol. Sci. 364, 3475\u20133484 (2009). https:\/\/doi.org\/10.1098\/rstb.2009.0190","journal-title":"Philos. Trans. R. Soc. B Biol. Sci."},{"key":"960_CR20","doi-asserted-by":"crossref","unstructured":"Tacconi, D., Mayora, O., Lukowicz, P., Arnrich, B., Setz, C., Troster, G., Haring, C.: Second International Conference on Pervasive Computing Technologies for Healthcare, 2008. PervasiveHealth 2008 (IEEE, 2008), pp. 100\u2013102 (2008)","DOI":"10.1109\/PCTHEALTH.2008.4571041"},{"key":"960_CR21","unstructured":"Gorbova, J., L\u00fcsi, I., Litvin, A., Anbarjafari, G.: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 29\u201335 (2017)"},{"issue":"6","key":"960_CR22","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1109\/MIS.2012.110","volume":"27","author":"RA Calvo","year":"2012","unstructured":"Calvo, R.A., D\u2019Mello, S.: Frontiers of affect-aware learning technologies. IEEE Intell. Syst. 27(6), 86 (2012)","journal-title":"IEEE Intell. Syst."},{"key":"960_CR23","doi-asserted-by":"crossref","unstructured":"Noroozi, F., Akrami, N., Anbarjafari, G.: 2017 25th Signal Processing and Communications Applications Conference (SIU), (IEEE, 2017), pp. 1\u20134 (2017)","DOI":"10.1109\/SIU.2017.7960258"},{"key":"960_CR24","unstructured":"Schuller, B., Marchi, E., Baron-Cohen, S., Lassalle, A., OReilly, H., Pigat, D., Robinson, P., Davies, I., Baltrusaitis, T., Mahmoud, M., et\u00a0al.: Proceedings of the of the 3rd International Workshop on Intelligent Digital Games for Empowerment and Inclusion (IDGEI 2015) as Part of the 20th ACM International Conference on Intelligent User Interfaces, IUI 2015, p. 9 (2015)"},{"key":"960_CR25","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1515\/9781614515159.207","volume-title":"Speech and Automata in the Health Care","author":"E Marchi","year":"2014","unstructured":"Marchi, E., Ringeval, F., Schuller, B.: Voice-enabled assistive robots for handling autism spectrum conditions: an examination of the role of prosody. In: Neustein, A. (ed.) Speech and Automata in the Health Care, pp. 207\u2013236. Walter de Gruyter GmbH & Co KG, Berlin (2014)"},{"key":"960_CR26","doi-asserted-by":"crossref","unstructured":"Noroozi, F., Marjanovic, M., Njegus, A., Escalera, S., Anbarjafari, G.: Audio-visual emotion recognition in video clips. IEEE Trans. Affect. Comput. (2017). https:\/\/doi.org\/10.1109\/TAFFC.2017.2713783","DOI":"10.1109\/TAFFC.2017.2713783"},{"key":"960_CR27","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1007\/978-981-10-4235-5_3","volume-title":"Frontiers in Electronic Technologies","author":"R Chakraborty","year":"2017","unstructured":"Chakraborty, R., Pandharipande, M., Kopparapu, S.K.: Frontiers in Electronic Technologies, pp. 55\u201363. Springer, Berlin (2017)"},{"key":"960_CR28","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Ringeval, F., Han, J., Deng, J., Marchi, E., Schuller, B.: 17th Annual Conference of the International Speech Communication Association (INTERSPEECH 2016), pp. 3593\u20133597 (2016)","DOI":"10.21437\/Interspeech.2016-998"},{"key":"960_CR29","unstructured":"Wan, J., Escalera, S., Baro, X., Escalante, H.J., Guyon, I., Madadi, M., Allik, J., Gorbova, J., Anbarjafari, G.: ChaLearn LaP, Action, Gesture, and Emotion Recognition Workshop and Competitions: Large Scale Multimodal Gesture Recognition and Real versus Fake expressed emotions, ICCV, vol.\u00a04 (2017)"},{"key":"960_CR30","doi-asserted-by":"crossref","unstructured":"L\u00fcsi, I., Junior, J.C.J., Gorbova, J., Bar\u00f3, X., Escalera, S., Demirel, H., Allik, J., Ozcinar, C., Anbarjafari, G.: 2017 12th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2017) (IEEE, 2017), pp. 809\u2013813 (2017)","DOI":"10.1109\/FG.2017.102"},{"key":"960_CR31","unstructured":"Sagha, H., Matejka, P., Gavryukova, M., Povoln\u1ef3, F., Marchi, E., Schuller, B.W.: INTERSPEECH, pp. 2949\u20132953 (2016)"},{"key":"960_CR32","doi-asserted-by":"crossref","unstructured":"Tawari, A., Trivedi, M.M.: 2010 20th International Conference on Pattern Recognition (ICPR), (IEEE, 2010), pp. 4605\u20134608 (2010)","DOI":"10.1109\/ICPR.2010.1132"},{"key":"960_CR33","unstructured":"Li, W., Tsangouri, C., Abtahi, F., Zhu, Z.: A recursive framework for expression recognition: From web images to deep models to game dataset. arXiv:1608.01647 (2016)"},{"issue":"1\u20132","key":"960_CR34","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/S0167-6393(02)00070-5","volume":"40","author":"E Douglas-Cowie","year":"2003","unstructured":"Douglas-Cowie, E., Campbell, N., Cowie, R., Roach, P.: Emotional speech: towards a new generation of databases. Speech Commun. 40(1\u20132), 33 (2003)","journal-title":"Speech Commun."},{"key":"960_CR35","doi-asserted-by":"crossref","unstructured":"Baveye, Y., Bettinelli, J.N., Dellandr\u00e9a, E., Chen, L., Chamaret, C.: 2013 Humaine Association Conference on Affective Computing and Intelligent Interaction (ACII), (IEEE, 2013), pp. 13\u201318 (2013)","DOI":"10.1109\/ACII.2013.9"},{"key":"960_CR36","unstructured":"Bao, W., Li, Y., Gu, M., Yang, M., Li, H., Chao, L., Tao, J.: 2014 12th International Conference on Signal Processing (ICSP), (IEEE, 2014), pp. 583\u2013587 (2014)"},{"key":"960_CR37","unstructured":"Martin, O., Kotsia, I., Macq, B., Pitas, I.: Proceedings of 22nd International Conference on Data Engineering Workshops, (IEEE, 2006), pp. 8\u20138 (2006)"},{"key":"960_CR38","unstructured":"RML emotion database. http:\/\/www.rml.ryerson.ca\/rml-emotion-database.html . Accessed 30 Mar 2018"},{"issue":"4","key":"960_CR39","doi-asserted-by":"publisher","first-page":"678","DOI":"10.1037\/0022-3514.92.4.678","volume":"92","author":"GI Roisman","year":"2007","unstructured":"Roisman, G.I., Holland, A., Fortuna, K., Fraley, R.C., Clausell, E., Clarke, A.: The adult attachment interview and self-reports of attachment style: an empirical rapprochement. J. Pers. Soc. Psychol. 92(4), 678 (2007)","journal-title":"J. Pers. Soc. Psychol."},{"key":"960_CR40","volume-title":"Machine Audition: Principles, Algorithms and Systems: Principles, Algorithms and Systems","author":"W Wang","year":"2010","unstructured":"Wang, W.: Machine Audition: Principles, Algorithms and Systems: Principles, Algorithms and Systems. IGI Global, Hershey (2010)"},{"key":"960_CR41","doi-asserted-by":"crossref","unstructured":"Glowinski, D., Camurri, A., Volpe, G., Dael, N., Scherer, K.: CVPRW (IEEE, 2008), pp. 1\u20136 (2008)","DOI":"10.1109\/CVPRW.2008.4563173"},{"key":"960_CR42","doi-asserted-by":"crossref","unstructured":"Busso, C., Deng, Z., Yildirim, S., Bulut, M., Lee, C.M., Kazemzadeh, A., Lee, S., Neumann, U., Narayanan, S.: Proceedings of the 6th International Conference on Multimodal Interfaces (ACM, 2004), pp. 205\u2013211 (2004)","DOI":"10.1145\/1027933.1027968"},{"issue":"8","key":"960_CR43","doi-asserted-by":"publisher","first-page":"1301","DOI":"10.1109\/JSTSP.2017.2764438","volume":"11","author":"P Tzirakis","year":"2017","unstructured":"Tzirakis, P., Trigeorgis, G., Nicolaou, M.A., Schuller, B.W., Zafeiriou, S.: End-to-end multimodal emotion recognition using deep neural networks. IEEE J. Sel. Top. Signal Process. 11(8), 1301 (2017)","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"960_CR44","doi-asserted-by":"crossref","unstructured":"Ringeval, F., Sonderegger, A., Sauer, J., Lalanne, D.: 2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG), (IEEE, 2013), pp. 1\u20138 (2013)","DOI":"10.1109\/FG.2013.6553805"},{"key":"960_CR45","doi-asserted-by":"crossref","unstructured":"Xue, J., Luo, Z., Eguchi, K., Takiguchi, T., Omoto, T.: 2017 IEEE International Conference on Multimedia and Expo (ICME), (IEEE, 2017), pp. 601\u2013606 (2017)","DOI":"10.1109\/ICME.2017.8019480"},{"key":"960_CR46","doi-asserted-by":"crossref","unstructured":"Kim, Y., Provost, E.M.: ISLA: Temporal segmentation and labeling for audio-visual emotion recognition. IEEE Trans. Affect. Comput. (2017). https:\/\/doi.org\/10.1109\/TAFFC.2017.2702653","DOI":"10.1109\/TAFFC.2017.2702653"},{"key":"960_CR47","doi-asserted-by":"crossref","unstructured":"Sidorov, M., Sopov, E., Ivanov, I., Minker, W.: 2015 12th International Conference on Informatics in Control, Automation and Robotics (ICINCO), (IEEE, 2015), vol.\u00a02, pp. 246\u2013251 (2015)","DOI":"10.5220\/0005527002460251"},{"key":"960_CR48","doi-asserted-by":"crossref","unstructured":"Song, P.: Transfer linear subspace learning for cross-corpus speech emotion recognition. IEEE Trans. Affect. Comput. (2017). https:\/\/doi.org\/10.1109\/TAFFC.2017.2705696","DOI":"10.1109\/TAFFC.2017.2705696"},{"key":"960_CR49","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1016\/j.specom.2016.07.010","volume":"83","author":"P Song","year":"2016","unstructured":"Song, P., Zheng, W., Ou, S., Zhang, X., Jin, Y., Liu, J., Yu, Y.: Cross-corpus speech emotion recognition based on transfer non-negative matrix factorization. Speech Commun. 83, 34 (2016)","journal-title":"Speech Commun."},{"issue":"2","key":"960_CR50","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1109\/T-AFFC.2010.8","volume":"1","author":"B Schuller","year":"2010","unstructured":"Schuller, B., Vlasenko, B., Eyben, F., Wollmer, M., Stuhlsatz, A., Wendemuth, A., Rigoll, G.: Cross-corpus acoustic emotion recognition: variances and strategies. IEEE Trans. Affect. Comput. 1(2), 119 (2010)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"960_CR51","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Weninger, F., W\u00f6llmer, M., Schuller, B.: 2011 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), (IEEE, 2011), pp. 523\u2013528 (2011)","DOI":"10.1109\/ASRU.2011.6163986"},{"key":"960_CR52","doi-asserted-by":"crossref","unstructured":"Chang, C.M., Su, B.H., Lin, S.C., Li, J.L., Lee, C.C.: 2017 Seventh International Conference on Affective Computing and Intelligent Interaction (ACII), (IEEE, 2017), pp. 377\u2013382 (2017)","DOI":"10.1109\/ACII.2017.8273627"},{"key":"960_CR53","unstructured":"Dhall, A., Goecke, R., Lucey, S., Gedeon, T.: Acted facial expressions in the wild database. Australian National University, Canberra, Australia, Technical Report TR-CS-11, vol. 2, p. 1 (2011)"},{"key":"960_CR54","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"}],"container-title":["Machine Vision and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-018-0960-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00138-018-0960-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-018-0960-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,5]],"date-time":"2025-07-05T22:14:21Z","timestamp":1751753661000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00138-018-0960-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7,19]]},"references-count":54,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2019,7]]}},"alternative-id":["960"],"URL":"https:\/\/doi.org\/10.1007\/s00138-018-0960-9","relation":{},"ISSN":["0932-8092","1432-1769"],"issn-type":[{"value":"0932-8092","type":"print"},{"value":"1432-1769","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,7,19]]},"assertion":[{"value":"6 April 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 July 2018","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 July 2018","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 July 2018","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}