{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T22:59:35Z","timestamp":1773961175572,"version":"3.50.1"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["62472079"],"award-info":[{"award-number":["62472079"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["N2417003"],"award-info":[{"award-number":["N2417003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2025.3599673","type":"journal-article","created":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:06:30Z","timestamp":1755911190000},"page":"5458-5472","source":"Crossref","is-referenced-by-count":1,"title":["Enhancing Multimodal Learning via Hierarchical Fusion Architecture Search With Inconsistency Mitigation"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9460-0052","authenticated-orcid":false,"given":"Kaifang","family":"Long","sequence":"first","affiliation":[{"name":"College of Software, Northeastern University, Shenyang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8433-8153","authenticated-orcid":false,"given":"Guoyang","family":"Xie","sequence":"additional","affiliation":[{"name":"Department of Intelligent Manufacturing, CATL, Ningde, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9969-211X","authenticated-orcid":false,"given":"Lianbo","family":"Ma","sequence":"additional","affiliation":[{"name":"College of Software, Northeastern University, Shenyang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6071-473X","authenticated-orcid":false,"given":"Qing","family":"Li","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3793-968X","authenticated-orcid":false,"given":"Min","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0884-6601","authenticated-orcid":false,"given":"Jianhui","family":"Lv","sequence":"additional","affiliation":[{"name":"First Affiliated Hospital, Jinzhou Medical University, Jinzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4618-3573","authenticated-orcid":false,"given":"Zhichao","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11024-6_44"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/88"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00713"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20872"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611947"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00223"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3409940"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3359815"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3362135"},{"key":"ref10","article-title":"Gated multimodal units for information fusion","volume-title":"Proc. ICLR","author":"Ar\u00e9valo"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3136801"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3143005"},{"key":"ref13","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. NeurIPS","author":"Lu"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01330"},{"key":"ref15","article-title":"Supervised multimodal bitransformers for classifying images and text","volume-title":"Proc. ViGIL-NeurIPS","author":"Kiela"},{"key":"ref16","article-title":"Designing neural network architectures using reinforcement learning","volume-title":"Proc. ICLR","author":"Baker"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2020.2963943"},{"key":"ref18","first-page":"1975","article-title":"XNAS: Neural architecture search with expert advice","volume-title":"Proc. Adv. NeurIPS","volume":"32","author":"Nayman"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3153065"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2025.3540650"},{"key":"ref21","first-page":"115","article-title":"Making a science of model search: Hyperparameter optimization in hundreds of dimensions for vision architectures","volume-title":"Proc. 30th Int. Conf. Mach. Learn.","author":"Bergstra"},{"key":"ref22","article-title":"ProxylessNAS: Direct neural architecture search on target task and hardware","volume-title":"Proc. ICLR","author":"Cai"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref24","article-title":"Hierarchical representations for efficient architecture search","author":"Liu","year":"2017","journal-title":"arXiv:1711.00436"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2024.3373792"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2023.3245322"},{"key":"ref28","article-title":"DARTS: Differentiable architecture search","volume-title":"Proc. ICLR","author":"Liu"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59728-3_74"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413977"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681351"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17260"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00353"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2024.3465037"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3530787"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3233089"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-44792-4_3"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3171983"},{"key":"ref39","article-title":"Trusted multi-view classification via evolutionary multi-view fusion","volume-title":"Proc. ICLR","author":"Liang"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3377136"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-024-00072-9"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10769"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02461-z"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.379"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2808769"},{"key":"ref47","first-page":"1319","article-title":"Maxout networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Goodfellow"},{"key":"ref48","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1250"},{"key":"ref50","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. ICLR","author":"Simonyan"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00056"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/109"},{"key":"ref56","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Adv. NeurIPS","author":"Simonyan"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.485"},{"key":"ref58","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"Harold Li","year":"2019","journal-title":"arXiv:1908.03557"},{"key":"ref59","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859654"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3587427"},{"key":"ref62","first-page":"374","article-title":"Harmonic-NAS: Hardware-aware multimodal neural architecture search on resource-constrained devices","volume-title":"Proc. ACML","author":"Ghebriout"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00256"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00256"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i12.29281"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3470996"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00040"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2021.3064943"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/440"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/11134693.pdf?arnumber=11134693","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T17:44:14Z","timestamp":1756489454000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11134693\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3599673","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}