{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T18:21:19Z","timestamp":1775326879278,"version":"3.50.1"},"reference-count":190,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Nitte (Deemed to be University), India"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3636186","type":"journal-article","created":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T19:01:12Z","timestamp":1764010872000},"page":"201067-201097","source":"Crossref","is-referenced-by-count":3,"title":["Multimodal Emotion Recognition: A Comprehensive Survey of Datasets, Methods, and Applications"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3656-1486","authenticated-orcid":false,"given":"M. J.","family":"Dileep Kumar","sequence":"first","affiliation":[{"name":"NMAM Institute of Technology (NMAMIT), Department of Electronics and Communication Engineering, Nitte (Deemed to be University), Nitte, Karnataka, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3731-9771","authenticated-orcid":false,"given":"M.","family":"Sukesh Rao","sequence":"additional","affiliation":[{"name":"NMAM Institute of Technology (NMAMIT), Department of Electronics and Communication Engineering, Nitte (Deemed to be University), Nitte, Karnataka, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6152-4209","authenticated-orcid":false,"given":"K. C.","family":"Narendra","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, RV University, Bengaluru, Karnataka, India"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3430850"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/app14178071"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126866"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101847"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1563"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-emnlp.332"},{"key":"ref7","article-title":"Recent trends of multimodal affective computing: A survey from NLP perspective","author":"Hu","year":"2024","journal-title":"arXiv:2409.07388"},{"key":"ref8","article-title":"A comprehensive survey on multi-modal conversational emotion recognition with deep learning","author":"Shou","year":"2023","journal-title":"arXiv:2312.05735"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2929050"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s43681-023-00307-3"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00433"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s13347-025-00895-4"},{"issue":"2","key":"ref13","first-page":"962","article-title":"A survey on multimodal emotion recognition in conversations","volume":"16","author":"Wu","year":"2025","journal-title":"IEEE Trans. Affect. Comput."},{"key":"ref14","first-page":"1234","article-title":"Transformer-fused multimodal framework for speech and EEG-based emotion recognition","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Alam"},{"key":"ref15","first-page":"2456","article-title":"Self-supervised multimodal pretraining for emotion recognition","volume-title":"Proc. ACM Int. Conf. Multimedia","author":"Zhou"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1080\/02699939208411068"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1037\/h0077714"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1511\/2001.4.344"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.03.009"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2012.06.016"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8640.2012.00456.x"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/79.911197"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-56"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1037\/0022-3514.70.3.614"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(02)00082-1"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-012-9172-2"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-200"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-1"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.4236\/jcc.2015.36001"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.02.013"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3390\/s19122730"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref35","first-page":"12449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Baevski"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2010.8"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462417"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/89.326616"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.316"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1037\/t27734-000"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/34.895976"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/1322192.1322216"},{"issue":"2","key":"ref44","first-page":"163","article-title":"Expression automatic recognition based on facial action units and expression relationship model","volume":"36","author":"Xie","year":"2016","journal-title":"Trans. Beijing Inst. Technol."},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2731763"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2002.1017623"},{"key":"ref48","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Simonyan"},{"key":"ref49","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.cogsys.2020.03.002"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.04.030"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2015.7284874"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3596711.3596730"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ARSO.2007.4531421"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00525"},{"key":"ref57","first-page":"1","article-title":"Context-aware multimodal emotion recognition in conversations","volume-title":"Nature Sci. Rep.","volume":"15","author":"Wu","year":"2025"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.15"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1140.001.0001"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2714671"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1111\/j.1542-474X.1996.tb00275.x"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-1126-0"},{"key":"ref63","first-page":"180","article-title":"The psychophysiology of emotion","volume-title":"Handbook Emotions","author":"Larsen","year":"2000"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2625250"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/34.954607"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.jneumeth.2003.10.009"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM.2018.8621080"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.1985.325532"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.jneumeth.2010.04.028"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1037\/\/0022-3514.50.2.260"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2560\/11\/4\/046018"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2005.848368"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2013.117"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-85163-z"},{"key":"ref75","first-page":"1","article-title":"EEG-ECG fusion for improved multimodal emotion recognition","volume":"19","author":"Rahman","year":"2025","journal-title":"Frontiers Neurosci."},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/1363686.1364052"},{"key":"ref77","first-page":"120","article-title":"Sentiment analysis in social media texts","volume-title":"Proc. 4th Workshop Comput. Approaches Subjectivity","author":"Balahur"},{"key":"ref78","volume-title":"Sentiment Analysis and Opinion Mining","author":"Liu","year":"2022"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8640.2012.00460.x"},{"issue":"1","key":"ref80","first-page":"61","article-title":"Developing affective lexical resources","volume":"2","author":"Valitutti","year":"2004","journal-title":"PsychNology J."},{"key":"ref81","article-title":"Affective norms for English words (ANEW): Instruction manual and affective ratings","author":"Bradley","year":"1999"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2016.31"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/2684822.2685316"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0026683"},{"key":"ref85","first-page":"41","article-title":"A comparison of event models for naive Bayes text classification","volume-title":"Proc. AAAI Workshop Learn. Text Categorization","author":"McCallum"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1181"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"issue":"8","key":"ref89","first-page":"1","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref90","first-page":"2666","article-title":"SenticNet 4: A semantic resource for sentiment analysis based on conceptual primitives","volume-title":"Proc. COLING","author":"Cambria"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-012-9196-x"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1116"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1177\/1470785320921779"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S18-1001"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CIHLI.2013.6613272"},{"key":"ref96","first-page":"101","article-title":"SemEval-2025 task 1: Multilingual multi-label emotion recognition in social media","volume-title":"Proc. 19th Int. Workshop Semantic Eval. (SemEval)","author":"Martinez"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2764438"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.06.001"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2829994"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00511"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/21.155943"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2860246"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.824"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2984368"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682583"},{"issue":"1","key":"ref107","first-page":"5634","article-title":"Memory fusion network for multi-view sequential learning","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"32","author":"Zadeh"},{"key":"ref108","first-page":"9758","article-title":"Self-supervised learning by cross-modal audio-video clustering","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Alwassel"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547754"},{"key":"ref110","first-page":"2345","article-title":"GS-MCC: Graph spectral multimodal contrastive consistency for emotion recognition","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Zheng"},{"key":"ref111","first-page":"5678","article-title":"Mer2025: A multimodal emotion recognition challenge dataset","volume-title":"Proc. ACM Int. Conf. Multimedia","author":"Tan"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1145\/3129340"},{"key":"ref113","volume-title":"Seed: Sjtu Emotion EEG Dataset","author":"Zheng","year":"2010"},{"issue":"4","key":"ref114","first-page":"2964","article-title":"Hybrid fusion network for multimodal emotion recognition","volume":"14","author":"Liang","year":"2023","journal-title":"IEEE Trans. Affect. Comput."},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016818"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0196391"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-446"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref120","volume-title":"Surrey Audio-Visual Expressed Emotion (SAVEE) Database","author":"Jackson","year":"2011"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.11.006"},{"key":"ref122","article-title":"Toronto emotional speech set (TESS)","author":"Pichora-Fuller","year":"2020"},{"key":"ref123","article-title":"Automatic classification of emotion related user states in spontaneous children\u2019s speech","author":"Steidl","year":"2009"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2010.5543262"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2025.3634523"},{"key":"ref126","article-title":"Facial emotion recognition: State of the art performance on FER2013","author":"Khaireddin","year":"2021","journal-title":"arXiv:2105.03588"},{"key":"ref127","first-page":"2106","article-title":"Static facial expression analysis in tough conditions: Data, evaluation protocol and benchmark","volume-title":"Proc. IEEE Int. Conf. Comput. Vis. Workshops (ICCV Workshops)","author":"Dhall"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3900990"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/afgr.1998.670949"},{"key":"ref130","first-page":"356","article-title":"Reliable crowdsourcing and deep locality-preserving learning for unconstrained facial expression recognition","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)","volume":"28","author":"Li"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2740923"},{"key":"ref132","volume-title":"MMI Face Database","author":"Valstar","year":"2005"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2018.2884461"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2017.2688239"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.25"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2015.2431497"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2025.3605833"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2016.7849931"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-020-00630-y"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3298405"},{"key":"ref141","article-title":"DailyDialog: A manually labelled multi-turn dialogue dataset","author":"Li","year":"2017","journal-title":"arXiv:1710.03957"},{"key":"ref142","first-page":"578","article-title":"EmoBank: Studying the impact of annotation perspective and representation format on dimensional emotion analysis","volume-title":"Proc. 15th Conf. Eur. Chapter Assoc. Comput. Linguistics, Short Papers","volume":"2","author":"Buechel"},{"key":"ref143","article-title":"EmotionX-HSU: Adopting pre-trained BERT for emotion classification","author":"Luo","year":"2019","journal-title":"arXiv:1907.09669"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.3758\/s13428-011-0064-1"},{"key":"ref145","first-page":"246","article-title":"Emotional tweets","volume-title":"Proc. 1st Joint Conf. Lexical Comput. Semantics (*SEM)","author":"Mohammad"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12024"},{"key":"ref147","first-page":"151","article-title":"MOSI: Multimodal corpus of sentiment intensity and subjectivity analysis in online opinion videos","volume-title":"Proc. 54th Annu. Meeting Assoc. Comput. Linguistics (Long Papers)","author":"Zadeh"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2018.8489099"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.20"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988258"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2013.6553805"},{"key":"ref152","first-page":"527","article-title":"MELD: A multimodal multi-party dataset for emotion recognition in conversations","volume-title":"Proc. 57th Annu. Meeting Assoc. Comput. Linguistics","author":"Poria"},{"key":"ref153","article-title":"MOSI: Multimodal corpus of sentiment intensity and subjectivity analysis in online opinion videos","author":"Zadeh","year":"2016","journal-title":"arXiv:1606.06259"},{"issue":"9","key":"ref154","first-page":"1162","article-title":"Automatic recognition of emotion in speech: A review of the literature and recommendations for practical realisation","volume":"53","author":"Schuller","year":"2011","journal-title":"Speech Commun."},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2010.101"},{"key":"ref156","first-page":"390","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Dosovitskiy"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1140.001.0001"},{"issue":"6","key":"ref159","article-title":"Electroencephalogram-based emotion recognition using discrete wavelet transform","volume":"7","author":"Murugappan","year":"2010","journal-title":"J. Neural Eng."},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1111\/1469-8986.00067"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1007\/s11517-006-0119-0"},{"key":"ref162","first-page":"97","article-title":"Continuous measurement of electrodermal activity with a wristband sensor","volume-title":"Proc. ACM Int. Conf. Ubiquitous Comput. (UbiComp)","author":"Poh"},{"key":"ref163","first-page":"29","article-title":"The psychophysiology of emotion","volume-title":"Handbook Emotions","author":"Cacioppo","year":"2008"},{"key":"ref164","first-page":"1083","article-title":"WordNet-affect: An affective extension of WordNet","volume-title":"Proc. 4th Int. Conf. Lang. Resour. Eval. (LREC)","author":"Strapparava"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1561\/15000000011"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref167","first-page":"136","article-title":"Multimodal emotion recognition with synchronized audio and video","volume-title":"Proc. 21st ACM Int. Conf. Multimodal Interact. (ICMI)","author":"Li"},{"key":"ref168","first-page":"1247","article-title":"Deep canonical correlation analysis","volume-title":"Proc. 30th Int. Conf. Mach. Learn. (ICML)","author":"Andrew"},{"issue":"6","key":"ref169","first-page":"96","article-title":"Multimodal emotion recognition: Current approaches and future directions","volume":"34","author":"Schuller","year":"2017","journal-title":"IEEE Signal Process. Mag."},{"key":"ref170","first-page":"134","article-title":"Decision-level fusion for multimodal emotion recognition","volume-title":"Proc. IEEE Int. Conf. Acoust., Speech Signal Process. (ICASSP)","author":"Lowe"},{"key":"ref171","first-page":"1426","article-title":"Contrastive cross-modal alignment for multimodal emotion recognition","volume-title":"Proc. 29th ACM Int. Conf. Multimedia (MM)","author":"Sun"},{"issue":"1","key":"ref172","first-page":"37","article-title":"Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation","volume":"2","author":"Powers","year":"2020","journal-title":"J. Mach. Learn. Technol."},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2009.03.002"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2005.10.010"},{"key":"ref175","first-page":"3","article-title":"The AVEC 2015 multimedia emotion recognition challenge and workshop","volume-title":"Proc. 5th Int. Workshop Audio\/Visual Emotion Challenge","author":"Ringeval"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2015.09.009"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1007\/BF00994018"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.29172\/7c2a6982-6d72-4cd8-bba6-2fccb06a7011"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1967.1053964"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178838"},{"key":"ref181","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Simonyan"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref183","first-page":"2947","article-title":"Real-life voice activity detection with LSTM recurrent neural networks","volume-title":"Proc. Interspeech","author":"Eyben"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"ref188","first-page":"1","article-title":"Graph-based facial representation for emotion recognition","volume-title":"Proc. IEEE Int. Conf. Autom. Face Gesture Recognit. (FG)","author":"Li"},{"key":"ref189","first-page":"1","article-title":"Graph attention networks","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Veli\u010dkovi\u0107"},{"key":"ref190","first-page":"630","article-title":"Emotion recognition using multimodal graph convolutional networks","volume-title":"Proc. Int. Conf. Multimodal Interact. (ICMI)","author":"Chen"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11264591.pdf?arnumber=11264591","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T18:44:03Z","timestamp":1764787443000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11264591\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":190,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3636186","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}