{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T19:16:50Z","timestamp":1781983010795,"version":"3.54.5"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2023YFB3307300"],"award-info":[{"award-number":["2023YFB3307300"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72471145"],"award-info":[{"award-number":["72471145"]}],"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":["72371217"],"award-info":[{"award-number":["72371217"]}],"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":["72101148"],"award-info":[{"award-number":["72101148"]}],"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":["72401130"],"award-info":[{"award-number":["72401130"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangzhou Industrial Informatics and Intelligence Key Laboratory","award":["2024A03J0628"],"award-info":[{"award-number":["2024A03J0628"]}]},{"name":"Nansha Key Area Science and Technology Project","award":["2023ZD003"],"award-info":[{"award-number":["2023ZD003"]}]},{"name":"Nansha Key Area Science and Technology Project","award":["2021JC02X191"],"award-info":[{"award-number":["2021JC02X191"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tase.2026.3658782","type":"journal-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T21:01:46Z","timestamp":1769634106000},"page":"4454-4476","source":"Crossref","is-referenced-by-count":1,"title":["Adaptive Multimodal Industrial Fault Diagnosis With Attention-Driven Fusion Boosting Unimodal Performance"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7030-6521","authenticated-orcid":false,"given":"Di","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Industrial Engineering and Management, School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyu","family":"Pan","sequence":"additional","affiliation":[{"name":"Department of Industrial Engineering and Management, School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7663-5713","authenticated-orcid":false,"given":"Yuanyuan","family":"Gao","sequence":"additional","affiliation":[{"name":"Department of Management Science and Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0575-8254","authenticated-orcid":false,"given":"Fugee","family":"Tsung","sequence":"additional","affiliation":[{"name":"Department of Industrial Engineering and Decision Analytics, The Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2340-3622","authenticated-orcid":false,"given":"Fangyu","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Beijing Key Laboratory of Computational Intelligence and Intelligent Systems, Engineering Research Center of Digital Community, Ministry of Education, Beijing University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2019.1911804"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3353535"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2025.3571516"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CogMI62246.2024.00045"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.cherd.2024.07.018"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01631"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3491865"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1111\/coin.12646"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tase.2025.3591656"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/s23031305"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2025.03.021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2020.3042300"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2025.103197"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2024.3522678"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tase.2024.3519608"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1080\/24725854.2021.1987593"},{"key":"ref18","article-title":"Multimodal alignment and fusion: A survey","author":"Li","year":"2024","journal-title":"arXiv:2411.17040"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3023774"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-74399-w"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506108"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-23774-w"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3649447"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_1"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00054"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3549201"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00680"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref30","first-page":"24206","article-title":"VATT: Transformers for multimodal self-supervised learning from raw video, audio and text","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Akbari"},{"key":"ref31","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref32","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00967"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.41"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3315541"},{"key":"ref36","first-page":"527","article-title":"Multi-task learning as multi-objective optimization","volume-title":"Proc. NeurIPS","author":"\u015eener"},{"key":"ref37","first-page":"794","article-title":"GradNorm: Gradient normalization for adaptive loss balancing in deep multitask networks","volume-title":"Proc. ICML","author":"Chen"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02030"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00806"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3468315"},{"key":"ref41","article-title":"MMPareto: Boosting multimodal learning with innocent unimodal assistance","author":"Wei","year":"2024","journal-title":"arXiv:2405.17730"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01852"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2790388"},{"key":"ref44","first-page":"28541","article-title":"LLaVA-med: Training a large language-and-vision assistant for biomedicine in one day","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889616"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.dcan.2025.03.004"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"issue":"134","key":"ref50","first-page":"1","article-title":"Stochastic gradient descent as approximate Bayesian inference","volume":"18","author":"Mandt","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref51","article-title":"Gradient vaccine: Investigating and improving multi-task optimization in massively multilingual models","author":"Wang","year":"2020","journal-title":"arXiv:2010.05874"},{"key":"ref52","article-title":"Model merging by uncertainty-based gradient matching","author":"Daheim","year":"2023","journal-title":"arXiv:2310.12808"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/4235.797969"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.jprocont.2019.04.009"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1209"},{"key":"ref57","article-title":"MOSI: Multimodal corpus of sentiment intensity and subjectivity analysis in online opinion videos","author":"Zadeh","year":"2016","journal-title":"arXiv:1606.06259"},{"key":"ref58","article-title":"MultiBench: Multiscale benchmarks for multimodal representation learning","author":"Pu Liang","year":"2021","journal-title":"arXiv:2107.07502"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/11323516\/11366933.pdf?arnumber=11366933","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T21:01:43Z","timestamp":1771534903000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11366933\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/tase.2026.3658782","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}