{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T09:44:51Z","timestamp":1784454291964,"version":"3.55.0"},"reference-count":83,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Machine Intelligence Lab, Indian Institute of Technology Roorkee, India"},{"name":"Center for Machine Vision & Signal Analysis, University of Oulu, Finland"},{"name":"Research Council of Finland Profi 5 HiDyn","award":["24630111132"],"award-info":[{"award-number":["24630111132"]}]},{"name":"Eudaimonia Institute of the University of Oulu"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Affective Comput."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/taffc.2025.3573180","type":"journal-article","created":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T13:05:16Z","timestamp":1748005516000},"page":"2881-2893","source":"Crossref","is-referenced-by-count":3,"title":["VISTANet: VIsual Spoken Textual Additive Net for Interpretable Multimodal Emotion Recognition"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4318-1353","authenticated-orcid":false,"given":"Puneet","family":"Kumar","sequence":"first","affiliation":[{"name":"Center for Machine Vision and Signal Analysis, University of Oulu, Oulu, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5224-1445","authenticated-orcid":false,"given":"Sarthak","family":"Malik","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Roorkee, Roorkee, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6277-6267","authenticated-orcid":false,"given":"Balasubramanian","family":"Raman","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Roorkee, Roorkee, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4519-7823","authenticated-orcid":false,"given":"Xiaobai","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101847"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2019.2902091"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3286351"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACII55700.2022.9953864"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3304015"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016818"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3490035.3490271"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2017.8273575"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-33607-3_33"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.45"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2023.103501"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2015.03.008"},{"key":"ref15","article-title":"Explainable convolutional neural network with facial emotion enabled music recommender system","volume-title":"Proc. 4th Int. Conf. Inf. Manage. Mach. Intell.","author":"Udendhran"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2019.8683765"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-555"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2360798"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3271019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3261279"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/INDICON56171.2022.10039878"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3260635"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-019-07813-9"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2934529"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2515606"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3071503"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892315"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688036"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639583"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1212"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.01.095"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2764438"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3214989"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126649"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210093"},{"key":"ref36","article-title":"Multi-modal emotion recognition by text, speech and video using pretrained transformers","author":"Shayaninasab","year":"2024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3171679"},{"key":"ref38","article-title":"Deep learning-based multimodal emotion recognition: A systematic review of recent advancements and future prospects","volume":"237","author":"Zhang","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102161"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2022.3215245"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.534"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/SMC53992.2023.10394418"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746910"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3282704"},{"key":"ref45","first-page":"892","article-title":"SoundNet: Learning sound representations from unlabeled video","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Aytar"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3055755"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1718"},{"key":"ref48","first-page":"4768","article-title":"A unified approach to interpreting model predictions","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lundberg"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1177\/0263276420966386"},{"key":"ref50","first-page":"3145","article-title":"Learning important features through propagating activation differences","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Shrikumar"},{"key":"ref51","volume-title":"A Value for N-Person Games, Contributions to the Theory of Games II","author":"Shapley","year":"1953"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2008.04.004"},{"key":"ref53","article-title":"An interpretability illusion for BERT","author":"Bolukbasi","year":"2021"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00304"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"ref56","article-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","author":"Simonyan"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-28954-6_14"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612836"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1050"},{"key":"ref61","article-title":"YOLOv8 guide: Step-by-step implementation of the latest YOLO architecture","year":"2024"},{"key":"ref62","article-title":"DeepVoice 3: Scaling text-to-speech with convolutional sequence learning","volume-title":"arXiv:1710.07654","author":"Ping"},{"key":"ref63","article-title":"WaveNet: A generative model for raw audio","author":"Oord","year":"2016"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9987"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1037\/0022-3514.66.2.310"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1511\/2001.4.344"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-41299-9_45"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1037\/h0077714"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/S0959-4388(02)00301-X"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1038\/nrn2317"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1080\/026999300378824"},{"key":"ref72","article-title":"Very deep ConvNet for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref73","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-49430-8_3"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/FUZZY.2010.5584447"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01036"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1015"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.547"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747397"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506714"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533552"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_35"}],"container-title":["IEEE Transactions on Affective Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5165369\/11269911\/11014508.pdf?arnumber=11014508","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:58:44Z","timestamp":1764269924000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11014508\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":83,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/taffc.2025.3573180","relation":{},"ISSN":["1949-3045","2371-9850"],"issn-type":[{"value":"1949-3045","type":"electronic"},{"value":"2371-9850","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}