{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T16:04:22Z","timestamp":1774541062089,"version":"3.50.1"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2015,9,29]],"date-time":"2015-09-29T00:00:00Z","timestamp":1443484800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"name":"The Scientific and Technical Research Council of Turkey (TUBITAK)","award":["110E056"],"award-info":[{"award-number":["110E056"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2016,7]]},"DOI":"10.1007\/s11760-015-0822-0","type":"journal-article","created":{"date-parts":[[2015,9,29]],"date-time":"2015-09-29T06:55:11Z","timestamp":1443509711000},"page":"827-834","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":31,"title":["Multimodal emotion recognition based on peak frame selection from video"],"prefix":"10.1007","volume":"10","author":[{"given":"Sara","family":"Zhalehpour","sequence":"first","affiliation":[]},{"given":"Zahid","family":"Akhtar","sequence":"additional","affiliation":[]},{"given":"Cigdem","family":"Eroglu\u00a0Erdem","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2015,9,29]]},"reference":[{"key":"822_CR1","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1007\/s00530-010-0182-0","volume":"16","author":"PK Atrey","year":"2010","unstructured":"Atrey, P.K., Hossain, M.A., Saddik, A.E., Kankanhalli, M.S.: Multimodal fusion for multimedia analysis: a survey. Multimed. Syst. 16, 345\u2013379 (2010)","journal-title":"Multimed. Syst."},{"key":"822_CR2","doi-asserted-by":"crossref","first-page":"572","DOI":"10.1016\/j.patcog.2010.09.020","volume":"44","author":"ME Ayadi","year":"2011","unstructured":"Ayadi, M.E., Kamel, M.S., Karray, F.: Survey on speech emotion recognition: features, classification schemes, and databases. Pattern Recognit. 44, 572\u2013587 (2011)","journal-title":"Pattern Recognit."},{"key":"822_CR3","doi-asserted-by":"crossref","first-page":"1186","DOI":"10.1016\/j.specom.2011.04.003","volume":"53","author":"E Bozkurt","year":"2011","unstructured":"Bozkurt, E., Erzin, E., Erdem, C.E., Erdem, A.T.: Formant position based weighted spectral features for emotion recognition. Speech Commun. 53, 1186\u20131197 (2011)","journal-title":"Speech Commun."},{"key":"822_CR4","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1145\/1961189.1961199","volume":"2","author":"CC Chang","year":"2011","unstructured":"Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2, 27 (2011)","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"822_CR5","doi-asserted-by":"crossref","unstructured":"Datcu, D., Rothkrantz, L.J.: Emotion recognition using bimodal data fusion. In: Proceedings of the international conference on computer systems and technologies, pp 122\u2013128 (2011)","DOI":"10.1145\/2023607.2023629"},{"key":"822_CR6","doi-asserted-by":"crossref","unstructured":"Erdem, C.E., Bozkurt, E., Erzin, E., Erdem, A.T.: Ransac-based training data selection for emotion recognition from spontaneous speech. In: AFFINE (2010)","DOI":"10.1145\/1877826.1877831"},{"key":"822_CR7","doi-asserted-by":"crossref","first-page":"7429","DOI":"10.1007\/s11042-014-1986-2","volume":"74","author":"CE Erdem","year":"2014","unstructured":"Erdem, C.E., Turan, C., Aydin, Z.: BAUM-2: a multilingual audio-visual affective face database. Multimed. Tools Appl. 74, 7429\u20137459 (2014)","journal-title":"Multimed. Tools Appl."},{"key":"822_CR8","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1016\/S0031-3203(02)00052-3","volume":"36","author":"B Fasel","year":"2003","unstructured":"Fasel, B., Luettin, J.: Automatic facial expression analysis: a survey. Pattern Recognit. 36, 259\u2013275 (2003)","journal-title":"Pattern Recognit."},{"key":"822_CR9","doi-asserted-by":"crossref","unstructured":"Gajsek, R., Struc, V., Mihelic, F.: Multi-modal emotion recognition using canonical correlations and acoustic features. In: International Conference on Pattern Recognition (2010)","DOI":"10.1109\/ICPR.2010.1005"},{"key":"822_CR10","doi-asserted-by":"crossref","first-page":"578","DOI":"10.1109\/89.326616","volume":"2","author":"H Hermansky","year":"1994","unstructured":"Hermansky, H., Morgan, N.: RASTA processing of speech. IEEE Trans. Speech Audio Process. 2, 578\u2013589 (1994)","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"822_CR11","volume-title":"Algorithms for Clustering Data","author":"AK Jain","year":"1988","unstructured":"Jain, A.K., Dubes, R.C.: Algorithms for Clustering Data. Prentice-Hall, Upper Saddle River (1988)"},{"issue":"3","key":"822_CR12","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1109\/34.667881","volume":"20","author":"J Kittler","year":"1998","unstructured":"Kittler, J., Duin, M.H.R.P., Matas, J.: On combining classifiers. IEEE TPAMI 20(3), 226\u2013239 (1998)","journal-title":"IEEE TPAMI"},{"key":"822_CR13","unstructured":"Kuan-Chieh, H., et\u00a0al.: Learning collaborative decision-making parameters for multimodal emotion recognition. In: IEEE International Conference on Multimedia and Expo (2013)"},{"issue":"12","key":"822_CR14","doi-asserted-by":"crossref","first-page":"1797","DOI":"10.1016\/j.imavis.2008.12.010","volume":"27","author":"GC Littlewort","year":"2009","unstructured":"Littlewort, G.C., et al.: Automatic coding of facial expressions displayed during posed and genuine pain. Image Vis. Comput. 27(12), 1797\u20131803 (2009)","journal-title":"Image Vis. Comput."},{"key":"822_CR15","doi-asserted-by":"crossref","unstructured":"Lucey, P., et\u00a0al.: The extended cohn-kanade dataset (CK+): a complete dataset for action unit and emotion-specified expression. In: IEEE CVPR Workshop (2010)","DOI":"10.1109\/CVPRW.2010.5543262"},{"key":"822_CR16","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1007\/s11042-009-0344-2","volume":"49","author":"M Mansoorizadeh","year":"2010","unstructured":"Mansoorizadeh, M., et al.: Multimodal information fusion application to human emotion recognition from face and speech. Multimed. Tools Appl. 49, 277\u2013297 (2010)","journal-title":"Multimed. Tools Appl."},{"key":"822_CR17","doi-asserted-by":"crossref","unstructured":"Martin, O., Kotsia, I., Macq, B., Pitas, I.: The eNTERFACE05 audio-visual emotion database. In: Proceedings of the IEEE Workshop on Multimedia Database Management (2006)","DOI":"10.1109\/ICDEW.2006.145"},{"key":"822_CR18","doi-asserted-by":"crossref","unstructured":"Onder, O., Zhalehpour, S., Erdem, CE.: A Turkish audio-visual emotional database. In: IEEE signal processing and applications conference (SIU), pp. 1\u20134. http:\/\/www.baum1.bahcesehir.edu.tr (2013)","DOI":"10.1109\/SIU.2013.6531441"},{"key":"822_CR19","doi-asserted-by":"crossref","unstructured":"Paleari, M., Huet, B.: Toward emotion indexing of multimedia excerpts. In: Proceedings of the CBMI, pp. 425\u2013432 (2008)","DOI":"10.1109\/CBMI.2008.4564978"},{"key":"822_CR20","doi-asserted-by":"crossref","unstructured":"Ryan, A., et al.: Automated facial expression recognition system. In: IEEE ICCST, pp. 172\u2013177 (2009)","DOI":"10.1109\/CCST.2009.5335546"},{"key":"822_CR21","doi-asserted-by":"crossref","first-page":"1113","DOI":"10.1109\/TPAMI.2014.2366127","volume":"37","author":"E Sariyanidi","year":"2014","unstructured":"Sariyanidi, E., Gunes, H., Cavallaro, A.: Automatic analysis of facial affect: a survey of registration, representation and recognition. IEEE TPAMI 37, 1113\u20131133 (2014)","journal-title":"IEEE TPAMI"},{"key":"822_CR22","doi-asserted-by":"crossref","unstructured":"Schuller, B., et\u00a0.al.: Acoustic emotion recognition: A benchmark comparison of performances. In: IEEE Workshop on Automatic Speech Recognition and Understanding, pp. 552\u2013557 (2009)","DOI":"10.1109\/ASRU.2009.5372886"},{"key":"822_CR23","unstructured":"Sharma, A., Anamika, D.: Facial expression recognition using virtual neutral image synthesis. In: Nat. Conf. Comp. Vi. Patt. Reco. Image Proc. and Graphics (2010)"},{"key":"822_CR24","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1111\/j.1468-2850.2007.00092.x","volume":"14","author":"DM Sloan","year":"2007","unstructured":"Sloan, D.M., Kring, A.M.: Measuring changes in emotion during psychotherapy: conceptual and methodological issues. Clin. Psychol. Sci. Pract. 14, 307\u2013322 (2007)","journal-title":"Clin. Psychol. Sci. Pract."},{"issue":"1","key":"822_CR25","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1162\/jocn.1991.3.1.71","volume":"3","author":"M Turk","year":"1991","unstructured":"Turk, M., Pentland, A.: Eigenfaces for recognition. J. Cogn. Neurosci. 3(1), 71\u201386 (1991)","journal-title":"J. Cogn. Neurosci."},{"key":"822_CR26","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/j.dsp.2014.05.013","volume":"32","author":"S Ulukaya","year":"2014","unstructured":"Ulukaya, S., Erdem, C.E.: Gaussian mixture model based estimation of the neutral face shape for emotion recognition. Digit. Signal Process. 32, 11\u201323 (2014)","journal-title":"Digit. Signal Process."},{"key":"822_CR27","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Kernel cross-modal factor analysis for information fusion with application to bimodal emotion recognition. IEEE Trans. Multimed. 14(3), 597\u2013607 (2012)","DOI":"10.1109\/TMM.2012.2189550"},{"key":"822_CR28","doi-asserted-by":"crossref","first-page":"936","DOI":"10.1109\/TMM.2008.927665","volume":"10","author":"W Yongjin","year":"2008","unstructured":"Yongjin, W., Ling, G.: Recognizing human emotional state from audiovisual signals. IEEE Trans. Multimed. 10, 936\u2013946 (2008)","journal-title":"IEEE Trans. Multimed."},{"issue":"1","key":"822_CR29","first-page":"38","volume":"31","author":"ZH Zeng","year":"2009","unstructured":"Zeng, Z.H., Pantic, M., Roisman, G.I., Huang, T.S.: A survey of affect recognition methods: audio, visual, and spontaneous expressions. IEEE TPAMI 31(1), 38\u201358 (2009)","journal-title":"IEEE TPAMI"},{"key":"822_CR30","doi-asserted-by":"crossref","unstructured":"Zhalehpour, S., Akhtar, Z., Erdem, C.: Multimodal emotion recognition with automatic peak frame selection. In: Proceedings of IEEE INISTA, pp. 116\u2013121 (2014)","DOI":"10.1109\/INISTA.2014.6873606"},{"key":"822_CR31","unstructured":"Zhu, X., Ramanan, D.: Face detection, pose estimation and landmark localization in the wild. In: Computer Vision and Pattern Recognition (CVPR) (2012)"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-015-0822-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11760-015-0822-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-015-0822-0","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,30]],"date-time":"2019-08-30T22:42:54Z","timestamp":1567204974000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11760-015-0822-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,9,29]]},"references-count":31,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2016,7]]}},"alternative-id":["822"],"URL":"https:\/\/doi.org\/10.1007\/s11760-015-0822-0","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,9,29]]}}}