{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T05:27:07Z","timestamp":1778909227318,"version":"3.51.4"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Ministry of Research, Innovation and Digitization, CCCDI-UEFISCDI","award":["PN-III-P2-2.1-PED-2021-3486 (MES-ER), within PNCDI III"],"award-info":[{"award-number":["PN-III-P2-2.1-PED-2021-3486 (MES-ER), within PNCDI III"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3450674","type":"journal-article","created":{"date-parts":[[2024,8,27]],"date-time":"2024-08-27T17:25:00Z","timestamp":1724779500000},"page":"120362-120374","source":"Crossref","is-referenced-by-count":10,"title":["Uncertainty-Based Learning of a Lightweight Model for Multimodal Emotion Recognition"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7577-1067","authenticated-orcid":false,"given":"Anamaria","family":"Radoi","sequence":"first","affiliation":[{"name":"Department of Applied Electronics and Information Engineering, NUST Politehnica Bucharest, Bucharest, Romania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2443-315X","authenticated-orcid":false,"given":"George","family":"Cioroiu","sequence":"additional","affiliation":[{"name":"Department of Applied Electronics and Information Engineering, NUST Politehnica Bucharest, Bucharest, Romania"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s42235-018-0015-y"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IWCMC51323.2021.9498861"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1186\/s40359-024-01581-4"},{"issue":"21","key":"ref4","doi-asserted-by":"crossref","first-page":"10951","DOI":"10.3390\/app122110951","article-title":"Emotion recognition method for call\/contact centre systems","volume":"12","author":"P\u0142aza","year":"2022","journal-title":"Appl. Sci."},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593503"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.4324\/9781003052272-13"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s00146-022-01435-w"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2512530.2512533"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SPED.2019.8906538"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.1188976"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2019.2960219"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2928625"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2360798"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956730"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054317"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2764438"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/34.908962"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1080\/02699939208411068"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1037\/\/0003-066X.48.4.384"},{"key":"ref22","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref25","article-title":"DeXpression: Deep convolutional neural network for expression recognition","author":"Burkert","year":"2015","journal-title":"arXiv:1509.05371"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-023-01188-6"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2830595"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IDEA49133.2020.9170675"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3321100"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/AIIoT52608.2021.9454174"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K18-1025"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2019.8925444"},{"issue":"9","key":"ref33","doi-asserted-by":"crossref","first-page":"4373","DOI":"10.3390\/s23094373","article-title":"A hybrid multimodal emotion recognition framework for UX evaluation using generalized mixture functions","volume":"23","author":"Razzaq","year":"2023","journal-title":"Sensors"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3099900"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2021.3071503"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3340555.3355713"},{"key":"ref37","article-title":"Multimodal fusion with deep neural networks for audio-video emotion recognition","author":"Ortega","year":"2019","journal-title":"arXiv:1907.03196"},{"key":"ref38","first-page":"13286","article-title":"MMTM: Multimodal transfer module for CNN fusion","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Vaezi Joze"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.502"},{"key":"ref40","first-page":"892","article-title":"SoundNet: Learning sound representations from unlabeled video","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Aytar"},{"key":"ref41","article-title":"A personalized affective memory neural model for improving emotion recognition","author":"Barros","year":"2019","journal-title":"arXiv:1904.12632"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCS58449.2023.10190872"},{"key":"ref43","article-title":"MSAF: Multimodal split attention fusion","author":"Su","year":"2020","journal-title":"arXiv:2012.07175"},{"key":"ref44","article-title":"A cross-modal fusion network based on self-attention and residual structure for multimodal emotion recognition","author":"Fu","year":"2021","journal-title":"arXiv:2111.02172"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9191019"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref47","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":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747278"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747157"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00559"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3116530"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-45528-0"},{"issue":"56","key":"ref53","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"ref56","article-title":"Deep representation learning in speech processing: Challenges, recent advances, and future trends","author":"Latif","year":"2020","journal-title":"arXiv:2001.00378"},{"key":"ref57","volume-title":"Fundamentals of Speech Recognition","author":"Rabiner","year":"1993"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2938007"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1977.10770"},{"key":"ref60","first-page":"612","article-title":"Comparing time-frequency representations for directional derivative features","volume-title":"Proc. Interspeech","author":"Gibson"},{"key":"ref61","volume-title":"Speech Communications\u2014Human and Machine","author":"O\u2019Shaughnessy","year":"2000"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1002\/047174882X"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TSP49548.2020.9163474"},{"key":"ref64","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Kingma"},{"key":"ref65","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist.","author":"Glorot"},{"key":"ref66","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.","volume":"33","author":"Baevski"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095036"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-703"},{"issue":"1","key":"ref69","doi-asserted-by":"crossref","first-page":"327","DOI":"10.3390\/app12010327","article-title":"A proposal for multimodal emotion recognition using aural transformers and action units on RAVDESS dataset","volume":"12","author":"Luna-Jim\u00e9nez","year":"2021","journal-title":"Appl. Sci."},{"issue":"11","key":"ref70","doi-asserted-by":"crossref","first-page":"2191","DOI":"10.3390\/electronics13112191","article-title":"Speech emotion recognition using dual-stream representation and cross-attention fusion","volume":"13","author":"Yu","year":"2024","journal-title":"Electronics"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref72","volume-title":"Hugging Face","year":"2024"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10649564.pdf?arnumber=10649564","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T04:01:45Z","timestamp":1725768105000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10649564\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3450674","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}