{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:32:50Z","timestamp":1780637570099,"version":"3.54.1"},"reference-count":84,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2019YFA0706200"],"award-info":[{"award-number":["2019YFA0706200"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62222603"],"award-info":[{"award-number":["62222603"]}],"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":["62076102"],"award-info":[{"award-number":["62076102"]}],"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":["U1813203"],"award-info":[{"award-number":["U1813203"]}],"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":["U1801262"],"award-info":[{"award-number":["U1801262"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Natural Science Funds for Distinguished Young Scholar","award":["2020B1515020041"],"award-info":[{"award-number":["2020B1515020041"]}]},{"name":"Science and Technology Major Project of Guangzhou","award":["202007030006"],"award-info":[{"award-number":["202007030006"]}]},{"name":"Science and Technology Program of Guangzhou","award":["202002030250"],"award-info":[{"award-number":["202002030250"]}]},{"name":"Program for Guangdong Introducing Innovative and Entrepreneurial Teams","award":["2019ZT08X214"],"award-info":[{"award-number":["2019ZT08X214"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1109\/tcyb.2022.3195739","type":"journal-article","created":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T19:52:06Z","timestamp":1661197926000},"page":"7659-7671","source":"Crossref","is-referenced-by-count":33,"title":["AIA-Net: Adaptive Interactive Attention Network for Text\u2013Audio Emotion Recognition"],"prefix":"10.1109","volume":"53","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7025-6365","authenticated-orcid":false,"given":"Tong","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6847-6740","authenticated-orcid":false,"given":"Shuzhen","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5451-7230","authenticated-orcid":false,"given":"Bianna","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haozhang","family":"Yuan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"C. L.","family":"Philip Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2925966"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2766843"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2787717"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2987064"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2940520"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3050508"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2021.3112578"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2312"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3388861"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380000"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.09.005"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3068598"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1209"},{"key":"ref15","first-page":"12136","article-title":"Deep multimodal multilinear fusion with high-order polynomial pooling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Hou"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00200"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3078074"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1121\/1.2935783"},{"key":"ref20","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Vaswani"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.412"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1212"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413577"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1050"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2016.94"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1190"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3131"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/1178745.1178762"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1081"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2764438"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2719043"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1046"},{"key":"ref37","first-page":"1","article-title":"Learning factorized multimodal representations","volume-title":"Proc. 7th Int. Conf. Learn. Represent. (ICLR)","author":"Tsai"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3171679"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2797176"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2896100"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6431"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3247"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3380744"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107676"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60457-8_4"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-18576-3_19"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.06.019"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref49","first-page":"1","article-title":"Roberta: A robustly optimized bert pretraining approach","volume-title":"Proc. 8th Int. Conf. Learn. Represent. (ICLR)","author":"Liu"},{"issue":"8","key":"ref50","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-200"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1242"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3267935.3267948"},{"key":"ref54","first-page":"1","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Baevski"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00374"},{"key":"ref58","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Lu"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2957872"},{"key":"ref60","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ioffe"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299173"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1132"},{"key":"ref64","first-page":"892","article-title":"SoundNet: Learning sound representations from unlabeled video","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Aytar"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14-1181"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-1062"},{"key":"ref67","first-page":"5999","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858826"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1050"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3049898"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2020.3005660"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.08.006"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2021.3057757"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413690"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016818"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1705"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747397"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2021.3065678"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref80","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Represent. (ICLR)","author":"Kingma"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.09.041"},{"key":"ref82","volume-title":"Cognitive Neuroscience: The Biology of the Mind","author":"Gazzaniga","year":"2013"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.10.021"},{"issue":"86","key":"ref84","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Laurens","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221036\/10334428\/09863920.pdf?arnumber=9863920","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T17:16:04Z","timestamp":1747761364000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9863920\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":84,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2022.3195739","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12]]}}}