{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T06:46:58Z","timestamp":1774680418034,"version":"3.50.1"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62176077"],"award-info":[{"award-number":["62176077"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003453","name":"Guangdong Natural Science Foundation","doi-asserted-by":"publisher","award":["2023A1515010057"],"award-info":[{"award-number":["2023A1515010057"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Key Technical Project","award":["2022N001"],"award-info":[{"award-number":["2022N001"]}]},{"name":"Shenzhen Fundamental Research","award":["JCYJ20210324132210025"],"award-info":[{"award-number":["JCYJ20210324132210025"]}]},{"DOI":"10.13039\/501100017610","name":"Shenzhen Science and Technology Program","doi-asserted-by":"publisher","award":["RCYX20221008092852077"],"award-info":[{"award-number":["RCYX20221008092852077"]}],"id":[{"id":"10.13039\/501100017610","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies","award":["2022B1212010005"],"award-info":[{"award-number":["2022B1212010005"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1109\/tcsvt.2023.3247822","type":"journal-article","created":{"date-parts":[[2023,2,22]],"date-time":"2023-02-22T18:35:31Z","timestamp":1677090931000},"page":"5318-5329","source":"Crossref","is-referenced-by-count":43,"title":["Semantic Alignment Network for Multi-Modal Emotion Recognition"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6470-0351","authenticated-orcid":false,"given":"Mixiao","family":"Hou","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology at Shenzhen, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1470-6998","authenticated-orcid":false,"given":"Zheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology at Shenzhen, Shenzhen, China"}]},{"given":"Chang","family":"Liu","sequence":"additional","affiliation":[{"name":"Software Development Center, Industrial and Commercial Bank of China, Zhuhai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1578-2634","authenticated-orcid":false,"given":"Guangming","family":"Lu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology at Shenzhen, Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1132"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1703"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2860246"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2984368"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11431-020-1647-3"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3049898"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461757"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413579"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11280"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3156"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3247"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016818"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3136801"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414880"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3014889"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2719043"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.10.009"},{"key":"ref16","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"Proc Annu Conf Neural Inf Process Syst"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i15.17567"},{"key":"ref19","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"kenton","year":"2019","journal-title":"Proc Annu Conf North Amer Chapter Assoc Comput Linguistics"},{"key":"ref18","author":"radford","year":"2018","journal-title":"Improving language understanding by generative pre-training"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-158"},{"key":"ref46","article-title":"MSAF: Multimodal split attention fusion","author":"su","year":"2020","journal-title":"arXiv 2012 07175"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2067"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129331"},{"key":"ref47","article-title":"On the use of modality-specific large-scale pre-trained encoders for multimodal sentiment analysis","author":"ando","year":"2022","journal-title":"arXiv 2210 15937"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1207"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3390\/s21144913"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1504\/IJIEI.2020.105430"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2283"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6431"},{"key":"ref28","first-page":"4243","article-title":"Multimodal emotion recognition using cross-modal attention and 1D convolutional neural networks","author":"n","year":"2020","journal-title":"Proc INTERSPEECH"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1050"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2044"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475548"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1577"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00504"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053192"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3163445"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.547"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683293"},{"key":"ref40","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der maaten","year":"2008","journal-title":"J Mach Learn Res"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10241245\/10050091.pdf?arnumber=10050091","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T18:42:30Z","timestamp":1695667350000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10050091\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":47,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3247822","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9]]}}}