{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T17:49:59Z","timestamp":1779904199271,"version":"3.53.1"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100008530","name":"European Regional Development Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008530","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10650105","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["Multimodal Fusion Strategies for Emotion Recognition"],"prefix":"10.1109","author":[{"given":"David","family":"Ortiz-Perez","sequence":"first","affiliation":[{"name":"University of Alicante,Department of Computer Technology,Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manuel","family":"Benavent-Lledo","sequence":"additional","affiliation":[{"name":"University of Alicante,Department of Computer Technology,Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Mulero-P\u00e9rez","sequence":"additional","affiliation":[{"name":"University of Alicante,Department of Computer Technology,Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Tom\u00e1s","sequence":"additional","affiliation":[{"name":"University of Alicante,Department of Software and Computing Systems,Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jose","family":"Garcia-Rodriguez","sequence":"additional","affiliation":[{"name":"University of Alicante,Department of Computer Technology,Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/0470013494.ch3"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/B978-0-12-558701-3.50007-7","article-title":"Chapter 1 - a general psychoevolutionary theory of emotion","volume-title":"Theories of Emotion","author":"PLUTCHIK","year":"1980"},{"key":"ref3","volume-title":"Attention is all you need","volume":"abs\/1706.03762","author":"Vaswani","year":"2017"},{"key":"ref4","volume-title":"BERT: pre-training of deep bidirectional transformers for language understanding","volume":"abs\/1810.04805","author":"Devlin","year":"2018"},{"key":"ref5","volume-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume":"abs\/2010.11929","author":"Dosovitskiy","year":"2020"},{"key":"ref6","volume-title":"Vivit: A video vision transformer","volume":"abs\/2103.15691","author":"Arnab","year":"2021"},{"key":"ref7","first-page":"2236","article-title":"Multimodal language analysis in the wild: CMU-MOSEI dataset and interpretable dynamic fusion graph","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Zadeh"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.15"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2018.2884461"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref11","volume-title":"MELD: A multimodal multi-party dataset for emotion recognition in conversations","volume":"abs\/1810.02508","author":"Poria","year":"2018"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0196391"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1037\/h0077722"},{"key":"ref15","first-page":"1532","article-title":"GloVe: Global vectors for word representation","volume-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Pennington"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803460"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2022.3187198"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3275156"},{"key":"ref19","volume-title":"VATT: transformers for multimodal self-supervised learning from raw video, audio and text","volume":"abs\/2104.11178","author":"Akbari","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26526"},{"issue":"2","key":"ref21","article-title":"A semantic enhancement framework for multimodal sarcasm detection","volume-title":"Mathematics","volume":"12","author":"Zhong","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2022.1086380"},{"issue":"12","key":"ref23","article-title":"Multimodal emotion detection via attention-based fusion of extracted facial and speech features","volume-title":"Sensors","volume":"23","author":"Mamieva","year":"2023"},{"issue":"1","key":"ref24","article-title":"A proposal for multimodal emotion recognition using aural transformers and action units on ravdess dataset","volume-title":"Applied Sciences","volume":"12","author":"Luna-Jim\u00e9nez","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3116530"},{"key":"ref26","article-title":"Husformer: A multi-modal transformer for multi-modal human state recognition","author":"Wang","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12024"},{"key":"ref28","first-page":"1","article-title":"Multizoo & multibench: A standardized toolkit for multimodal deep learning","volume":"24","author":"Liang","year":"2023","journal-title":"Journal of Machine Learning Research"},{"key":"ref29","article-title":"Multibench: Multiscale benchmarks for multimodal representation learning","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1)","author":"Liang"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3067460"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3049898"},{"issue":"10","key":"ref32","article-title":"A survey of deep learning-based multimodal emotion recognition: Speech, text, and face","volume-title":"Entropy","volume":"25","author":"Lian","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3183587"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i02.5492"},{"key":"ref35","volume-title":"Multimodal end-to-end sparse model for emotion recognition","volume":"abs\/2103.09666","author":"Dai","year":"2021"},{"issue":"9","key":"ref36","article-title":"Feature extraction network with attention mechanism for data enhancement and recombination fusion for multimodal sentiment analysis","volume-title":"Information","volume":"12","author":"Qi","year":"2021"},{"key":"ref37","volume-title":"Shapes of emotions: Multimodal emotion recognition in conversations via emotion shifts","volume":"abs\/2112.01938","author":"Agarwal","year":"2021"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","location":"Yokohama, Japan","start":{"date-parts":[[2024,6,30]]},"end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10650105.pdf?arnumber=10650105","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T04:59:41Z","timestamp":1725944381000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10650105\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10650105","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}