{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T18:05:01Z","timestamp":1783101901923,"version":"3.54.6"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2021,7,27]],"date-time":"2021-07-27T00:00:00Z","timestamp":1627344000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2021,7,27]],"date-time":"2021-07-27T00:00:00Z","timestamp":1627344000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Open Foundation of Beijing Engineering Research Center of Smart Mechanical Innovation Design Service","award":["KF2019302"],"award-info":[{"award-number":["KF2019302"]}]},{"name":"General Projects of Science and Technology Plan of Beijing Municipal Commission of Education","award":["KM20201141700"],"award-info":[{"award-number":["KM20201141700"]}]},{"DOI":"10.13039\/501100010871","name":"Recruitment Program of Global Experts","doi-asserted-by":"publisher","award":["WQ20141100198"],"award-info":[{"award-number":["WQ20141100198"]}],"id":[{"id":"10.13039\/501100010871","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Ambient Intell Human Comput"],"published-print":{"date-parts":[[2023,3]]},"DOI":"10.1007\/s12652-021-03407-2","type":"journal-article","created":{"date-parts":[[2021,7,27]],"date-time":"2021-07-27T09:02:52Z","timestamp":1627376572000},"page":"1903-1917","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":38,"title":["Multimodal emotion recognition based on feature selection and extreme learning machine in video clips"],"prefix":"10.1007","volume":"14","author":[{"given":"Bei","family":"Pan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaoru","family":"Hirota","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3248-8875","authenticated-orcid":false,"given":"Zhiyang","family":"Jia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linhui","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoming","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaping","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,7,27]]},"reference":[{"key":"3407_CR1","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/j.specom.2019.12.001","volume":"116","author":"MB Ak\u00e7ay","year":"2020","unstructured":"Ak\u00e7ay MB, O\u011fuz K (2020) Speech emotion recognition: emotional models, databases, features, preprocessing methods, supporting modalities, and classifiers. Speech Commun 116:56\u201376","journal-title":"Speech Commun"},{"issue":"5","key":"3407_CR2","doi-asserted-by":"publisher","first-page":"975","DOI":"10.1007\/s00138-018-0960-9","volume":"30","author":"E Avots","year":"2019","unstructured":"Avots E, Sapi\u0144ski T, Bachmann M, Kami\u0144ska D (2019) Audiovisual emotion recognition in wild. Mach Vis Appl 30(5):975\u2013985","journal-title":"Mach Vis Appl"},{"issue":"2","key":"3407_CR3","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1007\/s00521-012-1228-3","volume":"24","author":"M Bejani","year":"2014","unstructured":"Bejani M, Gharavian D, Charkari NM (2014) Audiovisual emotion recognition using anova feature selection method and multi-classifier neural networks. Neural Comput Appl 24(2):399\u2013412","journal-title":"Neural Comput Appl"},{"key":"3407_CR4","doi-asserted-by":"publisher","unstructured":"Busso C, Deng Z, Yildirim S, Bulut M, Lee CM, Kazemzadeh A, Lee S, Neumann U, Narayanan S (2004) Analysis of emotion recognition using facial expressions, speech and multimodal information. In: Proceedings of the 6th International Conference on multimodal interfaces, pp 205\u2013211. https:\/\/doi.org\/10.1145\/1027933.1027968","DOI":"10.1145\/1027933.1027968"},{"issue":"1","key":"3407_CR5","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1109\/TAFFC.2016.2593719","volume":"9","author":"J Chen","year":"2016","unstructured":"Chen J, Chen Z, Chi Z, Fu H (2016) Facial expression recognition in video with multiple feature fusion. IEEE Trans Affect Comput 9(1):38\u201350","journal-title":"IEEE Trans Affect Comput"},{"key":"3407_CR6","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1016\/j.ins.2017.10.044","volume":"428","author":"L Chen","year":"2018","unstructured":"Chen L, Zhou M, Su W, Wu M, She J, Hirota K (2018a) Softmax regression based deep sparse autoencoder network for facial emotion recognition in human-robot interaction. Inf Sci 428:49\u201361","journal-title":"Inf Sci"},{"issue":"5","key":"3407_CR7","doi-asserted-by":"publisher","first-page":"2524","DOI":"10.1109\/TFUZZ.2018.2809691","volume":"26","author":"L Chen","year":"2018","unstructured":"Chen L, Zhou M, Wu M, She J, Liu Z, Dong F, Hirota K (2018b) Three-layer weighted fuzzy support vector regression for emotional intention understanding in human\u2013robot interaction. IEEE Trans Fuzzy Syst 26(5):2524\u20132538","journal-title":"IEEE Trans Fuzzy Syst"},{"key":"3407_CR8","unstructured":"Chu WS (2017) Automatic analysis of facial actions: learning from transductive, supervised and unsupervised frameworks. PhD thesis, Carnegie Mellon University"},{"key":"3407_CR9","volume-title":"Facial action coding system: investigators guide","author":"P Ekman","year":"1978","unstructured":"Ekman P, Friesen WV (1978) Facial action coding system: investigators guide. Consulting Psychologists Press"},{"issue":"3","key":"3407_CR10","doi-asserted-by":"publisher","first-page":"572","DOI":"10.1016\/j.patcog.2010.09.020","volume":"44","author":"M El Ayadi","year":"2011","unstructured":"El Ayadi M, Kamel MS, Karray F (2011) Survey on speech emotion recognition: features, classification schemes, and databases. Pattern Recognit 44(3):572\u2013587","journal-title":"Pattern Recognit"},{"key":"3407_CR11","doi-asserted-by":"crossref","unstructured":"Han K, Yu D, Tashev I (2014) Speech emotion recognition using deep neural network and extreme learning machine. In: Fifteenth Annual Conference of the international speech communication association, pp 223\u2013227","DOI":"10.21437\/Interspeech.2014-57"},{"key":"3407_CR12","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1016\/j.inffus.2018.09.008","volume":"49","author":"MS Hossain","year":"2019","unstructured":"Hossain MS, Muhammad G (2019) Emotion recognition using deep learning approach from audio-visual emotional big data. Inf Fusion 49:69\u201378","journal-title":"Inf Fusion"},{"issue":"1\u20133","key":"3407_CR13","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1016\/j.neucom.2005.12.126","volume":"70","author":"GB Huang","year":"2006","unstructured":"Huang GB, Zhu QY, Siew CK (2006) Extreme learning machine: theory and applications. Neurocomputing 70(1\u20133): 489\u2013501","journal-title":"Neurocomputing"},{"key":"3407_CR14","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1016\/j.patrec.2019.01.008","volume":"120","author":"DK Jain","year":"2019","unstructured":"Jain DK, Shamsolmoali P, Sehdev P (2019) Extended deep neural network for facial emotion recognition. Pattern Recognit Lett 120:69\u201374","journal-title":"Pattern Recognit Lett"},{"key":"3407_CR15","doi-asserted-by":"publisher","unstructured":"Jung H, Lee S, Yim J, Park S, Kim J (2015) Joint fine-tuning in deep neural networks for facial expression recognition. In: Proceedings of the IEEE International Conference on computer vision, pp 2983\u20132991. https:\/\/doi.org\/10.1109\/ICCV.2015.341","DOI":"10.1109\/ICCV.2015.341"},{"key":"3407_CR16","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2019.2961089","author":"I Kansizoglou","year":"2019","unstructured":"Kansizoglou I, Bampis L, Gasteratos A (2019) An active learning paradigm for online audio-visual emotion recognition. IEEE Trans Affect Comput. https:\/\/doi.org\/10.1109\/TAFFC.2019.2961089","journal-title":"IEEE Trans Affect Comput"},{"key":"3407_CR17","doi-asserted-by":"publisher","unstructured":"Kazemi V, Sullivan J (2014) One millisecond face alignment with an ensemble of regression trees. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 1867\u20131874. https:\/\/doi.org\/10.1109\/CVPR.2014.241","DOI":"10.1109\/CVPR.2014.241"},{"key":"3407_CR18","doi-asserted-by":"publisher","first-page":"2131","DOI":"10.1007\/s12652-020-02311-5","volume":"12","author":"L Krithika","year":"2020","unstructured":"Krithika L, Priya GL (2020) Graph based feature extraction and hybrid classification approach for facial expression recognition. J Ambient Intell Human Comput 12:2131\u20132147. https:\/\/doi.org\/10.1007\/s12652-020-02311-5","journal-title":"J Ambient Intell Human Comput"},{"issue":"7553","key":"3407_CR19","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436\u2013444","journal-title":"Nature"},{"key":"3407_CR20","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1016\/j.patcog.2018.07.016","volume":"84","author":"Y Liu","year":"2018","unstructured":"Liu Y, Yuan X, Gong X, Xie Z, Fang F, Luo Z (2018) Conditional convolution neural network enhanced random forest for facial expression recognition. Pattern Recognit 84:251\u2013261","journal-title":"Pattern Recognit"},{"key":"3407_CR21","doi-asserted-by":"publisher","unstructured":"Lucey P, Cohn JF, Kanade T, Saragih J, Ambadar Z, Matthews I (2010) The extended cohn-kanade dataset (ck+): a complete dataset for action unit and emotion-specified expression. In: 2010 IEEE Computer Society Conference on computer vision and pattern recognition-workshops, IEEE, pp 94\u2013101. https:\/\/doi.org\/10.1109\/CVPRW.2010.5543262","DOI":"10.1109\/CVPRW.2010.5543262"},{"key":"3407_CR22","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1016\/j.inffus.2018.06.003","volume":"46","author":"Y Ma","year":"2019","unstructured":"Ma Y, Hao Y, Chen M, Chen J, Lu P, Ko\u0161ir A (2019) Audio-visual emotion fusion (avef): a deep efficient weighted approach. Inf Fusion 46:184\u2013192","journal-title":"Inf Fusion"},{"key":"3407_CR23","doi-asserted-by":"publisher","unstructured":"Martin O, Kotsia I, Macq B, Pitas I (2006) The enterface\u201905 audio-visual emotion database. In: 22nd International Conference on Data Engineering Workshops (ICDEW\u201906), IEEE. https:\/\/doi.org\/10.1109\/ICDEW.2006.145","DOI":"10.1109\/ICDEW.2006.145"},{"issue":"10","key":"3407_CR24","doi-asserted-by":"publisher","first-page":"3955","DOI":"10.1007\/s12652-018-1065-z","volume":"10","author":"F Mendoza-Palechor","year":"2019","unstructured":"Mendoza-Palechor F, Menezes ML, Sant\u2019Anna A, Ortiz-Barrios M, Samara A, Galway L (2019) Affective recognition from eeg signals: an integrated data-mining approach. J Ambient Intell Hum Comput 10(10):3955\u20133974","journal-title":"J Ambient Intell Hum Comput"},{"key":"3407_CR25","doi-asserted-by":"publisher","unstructured":"Miyoshi R, Nagata N, Hashimoto M (2021) Enhanced convolutional lstm with spatial and temporal skip connections and temporal gates for facial expression recognition from video. Neural Comput Appl 33:7381\u20137392. https:\/\/doi.org\/10.1007\/s00521-020-05557-4","DOI":"10.1007\/s00521-020-05557-4"},{"issue":"1","key":"3407_CR26","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1109\/TAFFC.2017.2713783","volume":"10","author":"F Noroozi","year":"2017","unstructured":"Noroozi F, Marjanovic M, Njegus A, Escalera S, Anbarjafari G (2017) Audio-visual emotion recognition in video clips. IEEE Trans Affect Comput 10(1):60\u201375","journal-title":"IEEE Trans Affect Comput"},{"key":"3407_CR27","doi-asserted-by":"publisher","unstructured":"Pons G, Masip D (2020) Multitask, multilabel, and multidomain learning with convolutional networks for emotion recognition. IEEE Trans Cybern 99:1\u20138. https:\/\/doi.org\/10.1109\/TCYB.2020.3036935","DOI":"10.1109\/TCYB.2020.3036935"},{"key":"3407_CR28","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1016\/j.neucom.2015.01.095","volume":"174","author":"S Poria","year":"2016","unstructured":"Poria S, Cambria E, Howard N, Huang GB, Hussain A (2016) Fusing audio, visual and textual clues for sentiment analysis from multimodal content. Neurocomputing 174:50\u201359","journal-title":"Neurocomputing"},{"key":"3407_CR29","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1016\/j.inffus.2017.02.003","volume":"37","author":"S Poria","year":"2017","unstructured":"Poria S, Cambria E, Bajpai R, Hussain A (2017) A review of affective computing: from unimodal analysis to multimodal fusion .Inf Fusion 37:98\u2013125","journal-title":"Inf Fusion"},{"issue":"1","key":"3407_CR30","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1007\/s40998-018-0142-9","volume":"43","author":"F Rahdari","year":"2019","unstructured":"Rahdari F, Rashedi E, Eftekhari M (2019) A multimodal emotion recognition system using facial landmark analysis. Iran J Sci Technol Trans Electric Eng 43(1):171\u2013189","journal-title":"Iran J Sci Technol Trans Electric Eng"},{"key":"3407_CR31","doi-asserted-by":"crossref","unstructured":"Schuller B, Steidl S, Batliner A, Burkhardt F, Devillers L, M\u00fcller C, Narayanan SS (2010) The interspeech 2010 paralinguistic challenge. In: Eleventh annual conference of the international speech communication association, pp 2794\u20132797","DOI":"10.21437\/Interspeech.2010-739"},{"issue":"6","key":"3407_CR32","doi-asserted-by":"publisher","first-page":"803","DOI":"10.1016\/j.imavis.2008.08.005","volume":"27","author":"C Shan","year":"2009","unstructured":"Shan C, Gong S, McOwan PW (2009) Facial expression recognition based on local binary patterns: a comprehensive study. Image Vis Comput 27(6):803\u2013816","journal-title":"Image Vis Comput"},{"issue":"5","key":"3407_CR33","doi-asserted-by":"publisher","first-page":"936","DOI":"10.1109\/TMM.2008.927665","volume":"10","author":"Y Wang","year":"2008","unstructured":"Wang Y, Guan L (2008) Recognizing human emotional state from audiovisual signals. IEEE Trans Multimed 10(5):936\u2013946","journal-title":"IEEE Trans Multimed"},{"issue":"2","key":"3407_CR34","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1007\/BF00175354","volume":"4","author":"D Whitley","year":"1994","unstructured":"Whitley D (1994) A genetic algorithm tutorial. Stat Comput 4(2):65\u201385","journal-title":"Stat Comput"},{"issue":"3","key":"3407_CR35","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1109\/MIS.2013.34","volume":"28","author":"M W\u00f6llmer","year":"2013","unstructured":"W\u00f6llmer M, Weninger F, Knaup T, Schuller B, Sun C, Sagae K, Morency LP (2013) Youtube movie reviews: Sentiment analysis in an audio-visual context. IEEE Intell Syst 28(3):46\u201353","journal-title":"IEEE Intell Syst"},{"issue":"3","key":"3407_CR36","doi-asserted-by":"publisher","first-page":"1473","DOI":"10.1109\/TSMC.2019.2897330","volume":"51","author":"M Wu","year":"2019","unstructured":"Wu M, Su W, Chen L, Liu Z, Cao W, Hirota K (2019) Weight-adapted convolution neural network for facial expression recognition in human-robot interaction. IEEE Trans Syst Man Cybern Syst 51(3):1473\u20131484","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"key":"3407_CR37","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.neucom.2016.09.120","volume":"261","author":"W Xiao","year":"2017","unstructured":"Xiao W, Zhang J, Li Y, Zhang S, Yang W (2017) Class-specific cost regulation extreme learning machine for imbalanced classification. Neurocomputing 261:70\u201382","journal-title":"Neurocomputing"},{"key":"3407_CR38","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1016\/j.patcog.2019.03.019","volume":"92","author":"S Xie","year":"2019","unstructured":"Xie S, Hu H, Wu Y (2019) Deep multi-path convolutional neural network joint with salient region attention for facial expression recognition. Pattern Recognit 92:177\u2013191","journal-title":"Pattern Recognit"},{"issue":"1","key":"3407_CR39","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1109\/TPAMI.2008.52","volume":"31","author":"Z Zeng","year":"2008","unstructured":"Zeng Z, Pantic M, Roisman GI, Huang TS (2008) A survey of affect recognition methods: Audio, visual, and spontaneous expressions. IEEE Trans Pattern Anal Mach Intell 31(1):39\u201358","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"3","key":"3407_CR40","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1109\/TAFFC.2016.2553038","volume":"8","author":"S Zhalehpour","year":"2016","unstructured":"Zhalehpour S, Onder O, Akhtar Z, Erdem CE (2016) Baum-1: a spontaneous audio-visual face database of affective and mental states. IEEE Trans Affect Comput 8(3):300\u2013313","journal-title":"IEEE Trans Affect Comput"},{"issue":"10","key":"3407_CR43","doi-asserted-by":"publisher","first-page":"3030","DOI":"10.1109\/TCSVT.2017.2719043","volume":"28","author":"S Zhang","year":"2017","unstructured":"Zhang S, Zhang S, Huang T, Gao W, Tian Q (2017) Learning affective features with a hybrid deep model for audio-visual emotion recognition. IEEE Trans Circ Syst Video Technol 28(10): 3030\u20133043","journal-title":"IEEE Trans Circ Syst Video Technol"},{"key":"3407_CR44","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TAFFC.2019.2947464","volume":"99","author":"S Zhang","year":"2019","unstructured":"Zhang S, Zhao X, Tian Q (2019) Spontaneous speech emotion recognition using multiscale deep convolutional lstm. IEEE Trans Affect Comput 99:1\u20131. https:\/\/doi.org\/10.1109\/TAFFC.2019.2947464","journal-title":"IEEE Trans Affect Comput"},{"issue":"13","key":"3407_CR41","doi-asserted-by":"publisher","first-page":"8925","DOI":"10.1016\/j.jfranklin.2020.04.033","volume":"357","author":"J Zhang","year":"2020","unstructured":"Zhang J, Li Y, Xiao W, Zhang Z (2020a) Non-iterative and fast deep learning: multilayer extreme learning machines. J Frankl Inst 357(13):8925\u20138955","journal-title":"J Frankl Inst"},{"issue":"14","key":"3407_CR42","doi-asserted-by":"publisher","first-page":"9885","DOI":"10.1016\/j.jfranklin.2020.06.027","volume":"357","author":"J Zhang","year":"2020","unstructured":"Zhang J, Li Y, Xiao W, Zhang Z (2020b) Robust extreme learning machine for modeling with unknown noise. J Frankl Inst 357(14):9885\u20139908","journal-title":"J Frankl Inst"},{"issue":"6","key":"3407_CR45","doi-asserted-by":"publisher","first-page":"915","DOI":"10.1109\/TPAMI.2007.1110","volume":"29","author":"G Zhao","year":"2007","unstructured":"Zhao G, Pietikainen M (2007) Dynamic texture recognition using local binary patterns with an application to facial expressions. IEEE Trans Pattern Anal Mach Intell 29(6):915\u2013928","journal-title":"IEEE Trans Pattern Anal Mach Intell"}],"container-title":["Journal of Ambient Intelligence and Humanized Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12652-021-03407-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12652-021-03407-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12652-021-03407-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,2]],"date-time":"2023-03-02T16:04:19Z","timestamp":1677773059000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12652-021-03407-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,27]]},"references-count":45,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,3]]}},"alternative-id":["3407"],"URL":"https:\/\/doi.org\/10.1007\/s12652-021-03407-2","relation":{},"ISSN":["1868-5137","1868-5145"],"issn-type":[{"value":"1868-5137","type":"print"},{"value":"1868-5145","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7,27]]},"assertion":[{"value":"3 February 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 July 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 July 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}