{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:17:34Z","timestamp":1777655854200,"version":"3.51.4"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61876209"],"award-info":[{"award-number":["61876209"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61936004"],"award-info":[{"award-number":["61936004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1913602"],"award-info":[{"award-number":["U1913602"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3144885","type":"journal-article","created":{"date-parts":[[2022,1,25]],"date-time":"2022-01-25T20:31:47Z","timestamp":1643142707000},"page":"2213-2225","source":"Crossref","is-referenced-by-count":41,"title":["Multi-Channel Weight-Sharing Autoencoder Based on Cascade Multi-Head Attention for Multimodal Emotion Recognition"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5169-3183","authenticated-orcid":false,"given":"Jiahao","family":"Zheng","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence and Automation and the Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9265-1876","authenticated-orcid":false,"given":"Sen","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Automation and the Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5638-4574","authenticated-orcid":false,"given":"Zilu","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Automation and the Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4909-8286","authenticated-orcid":false,"given":"Xiaoping","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Automation and the Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4587-3588","authenticated-orcid":false,"given":"Zhigang","family":"Zeng","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Automation and the Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"873","article-title":"Sparse deep belief net model for visual area v2","author":"lee","year":"0","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1637"},{"key":"ref12","first-page":"689","article-title":"Multimodal deep learning","author":"ngiam","year":"0","journal-title":"Proc 28th Int Conf Mach Learn"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016892"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.41"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"ref58","first-page":"269","article-title":"Modality-transferable emotion embeddings for low-resource multimodal emotion recognition","author":"dai","year":"0","journal-title":"Proc 1st Conf Asia Pacific Chapter Assoc Comput Linguistics 10th Int Joint Conf Natural Lang Process"},{"key":"ref53","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013","journal-title":"Int Conf Learn Representations"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2016.10.043"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1209"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2576761"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/673"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3252"},{"key":"ref18","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Int Conf e-Learning"},{"key":"ref51","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"0","journal-title":"Proc 13th Int Conf Artif Intell Statist"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2825432"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952552"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1423"},{"key":"ref48","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/703"},{"key":"ref42","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"0","journal-title":"Int Conf Learn Representations"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.2983669"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.518"},{"key":"ref43","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"0","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2602884"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2764438"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.275"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0055"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682916"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2006-157"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2012.2228851"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2020.2972926"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2013.90"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3284750"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2019.2940224"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2759338"},{"key":"ref31","first-page":"1","article-title":"Audio-visual fusion for sentiment classification using cross-modal autoencoder","author":"dumpala","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref30","first-page":"1247","article-title":"Deep canonical correlation analysis","author":"andrew","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12024"},{"key":"ref32","article-title":"Multimodal emotion recognition using deep canonical correlation analysis","author":"liu","year":"2019"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.3014842"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-84800-306-4"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1568"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413579"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12277"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3340555.3355713"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2515617"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2360798"},{"key":"ref63","first-page":"531","article-title":"Mutual information neural estimation","volume":"80","author":"belghazi","year":"0","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2766843"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-1068"},{"key":"ref27","first-page":"2291","article-title":"Deep multimodal hashing with orthogonal regularization","author":"wang","year":"0","journal-title":"Proc 24th Int Conf Artif Intell"},{"key":"ref29","first-page":"162","author":"hotelling","year":"1992","journal-title":"Relations between two sets of variates"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053762"},{"key":"ref62","first-page":"2579","article-title":"Visualizing data using T-SNE","volume":"9","author":"maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380000"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09693238.pdf?arnumber=9693238","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T22:38:56Z","timestamp":1733956736000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9693238\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3144885","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}