{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T14:42:45Z","timestamp":1777128165218,"version":"3.51.4"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["62173195"],"award-info":[{"award-number":["62173195"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Academy of Artificial Intelligence"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3267882","type":"journal-article","created":{"date-parts":[[2023,4,17]],"date-time":"2023-04-17T14:04:51Z","timestamp":1681740291000},"page":"529-539","source":"Crossref","is-referenced-by-count":62,"title":["Noise Imitation Based Adversarial Training for Robust Multimodal Sentiment Analysis"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2397-2163","authenticated-orcid":false,"given":"Ziqi","family":"Yuan","sequence":"first","affiliation":[{"name":"State Key Laboratory of Intelligent Technology and Systems, Department of Computer Science and Technology, Tsinghua University, Beijing, China"}]},{"given":"Yihe","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Hebei University of Science and Technology, Shijiazhuang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7401-307X","authenticated-orcid":false,"given":"Hua","family":"Xu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Intelligent Technology and Systems, Department of Computer Science and Technology, Tsinghua University, Beijing, China"}]},{"given":"Kai","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Hebei University of Science and Technology, Shijiazhuang, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.723"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3183830"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3171679"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2017.08.003"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref6","article-title":"Multibench: Multiscale benchmarks for multimodal representation learning","author":"Liang","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01764"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.50"},{"key":"ref9","first-page":"121","article-title":"Missing modality meets meta sampling (M3S): An efficient universal approach for multimodal sentiment analysis with missing modality","volume-title":"Proc. 2nd Conf. Asia-Pacific Chapter Assoc. Comput. Linguistics 12th Int. Joint Conf. Natural Lang. Process.","author":"Chi","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3610661.3617602"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3234553"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.203"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.109"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3274829"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1049\/cit2.12028"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00335"},{"key":"ref17","article-title":"Adversarial autoencoders","author":"Makhzani","year":"2015"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5347"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475585"},{"key":"ref20","article-title":"Learning factorized multimodal representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tsai","year":"2019"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16330"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.717"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016892"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380000"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-3308"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.412"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3207572"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794468"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1152"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_26"},{"key":"ref31","article-title":"Beit: BERT pre-training of image transformers","author":"Bao","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref33","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Baevski","year":"2020"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3395035.3425202"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956592"},{"key":"ref37","article-title":"Generative adversarial nets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Goodfellow","year":"2014"},{"key":"ref38","article-title":"Bag of tricks for adversarial training","author":"Pang","year":"2020"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765202"},{"key":"ref40","first-page":"1060","article-title":"Generative adversarial text to image synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Reed","year":"2016"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/vl\/N19-142"},{"key":"ref43","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2016.94"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref47","article-title":"MISA: Modality-invariant and -specific representations for multimodal sentiment analysis","author":"Hazarika","year":"2005"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"ref50","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref51","article-title":"Fine-tuned XLSR-53 large model for speech recognition in english","author":"Grosman","year":"2021"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.finnlp-1.9"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-demo.20"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i13.27078"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10103636.pdf?arnumber=10103636","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T21:02:04Z","timestamp":1772830924000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10103636\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3267882","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}