{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T21:06:04Z","timestamp":1776978364317,"version":"3.51.4"},"reference-count":71,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62366055"],"award-info":[{"award-number":["62366055"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019410","name":"Yunnan Fundamental Research Projects","doi-asserted-by":"publisher","award":["202401BC070006"],"award-info":[{"award-number":["202401BC070006"]}],"id":[{"id":"10.13039\/501100019410","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3682113","type":"journal-article","created":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T19:56:00Z","timestamp":1776455760000},"page":"4091-4105","source":"Crossref","is-referenced-by-count":0,"title":["Ensemble Image and Text for Unsupervised Domain Adaptation Using Vision Language Models"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-8074-4178","authenticated-orcid":false,"given":"Qi","family":"Jia","sequence":"first","affiliation":[{"name":"School of Information Science and Engineering, Yunnan University, Kunming, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0776-819X","authenticated-orcid":false,"given":"Fei","family":"Du","sequence":"additional","affiliation":[{"name":"National Pilot School of Software, Yunnan University, Kunming, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5313-9140","authenticated-orcid":false,"given":"Zulong","family":"Lin","sequence":"additional","affiliation":[{"name":"National Pilot School of Software, Yunnan University, Kunming, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Guo","sequence":"additional","affiliation":[{"name":"National Pilot School of Software, Yunnan University, Kunming, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9893-3436","authenticated-orcid":false,"given":"Yun","family":"Yang","sequence":"additional","affiliation":[{"name":"National Pilot School of Software, Yunnan University, Kunming, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","volume-title":"Proc. 32nd Int. Conf. Mach. Learn. (ICML)","author":"Ganin"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3400066"},{"key":"ref3","article-title":"Harnessing out-of-distribution examples via augmenting content and style","author":"Huang","year":"2022","journal-title":"arXiv:2207.03162"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2021.3117407"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3006377"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2842767"},{"key":"ref7","first-page":"2110","article-title":"Learning transferrable representations for unsupervised domain adaptation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Sener"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"114","DOI":"10.1016\/j.future.2022.03.006","article-title":"Multiple-instance domain adaptation for cost-effective sensor-based human activity recognition","volume":"133","author":"Prabono","year":"2022","journal-title":"Future Gener. Comput. Syst."},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2020.3039196"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3028503"},{"issue":"1","key":"ref11","first-page":"723","article-title":"A kernel two-sample test","volume":"13","author":"Gretton","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref12","first-page":"97","article-title":"Learning transferable features with deep adaptation networks","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","volume":"37","author":"Long"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2988928"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-58347-1_10"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3819"},{"key":"ref16","first-page":"19973","article-title":"Machine vision therapy: Multimodal large language models can enhance visual robustness via denoising in-context learning","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Huang"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00470"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02206"},{"key":"ref19","article-title":"Overcoming the pitfalls of vision-language model finetuning for OOD generalization","author":"Zang","year":"2024","journal-title":"arXiv:2401.15914"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3004555"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00149"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM55620.2022.9995102"},{"key":"ref23","article-title":"Domain-adversarial neural networks","author":"Ajakan","year":"2014","journal-title":"arXiv:1412.4446"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6054"},{"key":"ref25","first-page":"1640","article-title":"Conditional adversarial domain adaptation","volume-title":"Proc. Adv. neural Inf. Process. Syst.","volume":"31","author":"Long"},{"key":"ref26","first-page":"1081","article-title":"Transferability vs. discriminability: Batch spectral penalization for adversarial domain adaptation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref27","first-page":"5468","article-title":"Understanding self-training for gradual domain adaptation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kumar"},{"key":"ref28","first-page":"22968","article-title":"Cycle self-training for domain adaptation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Liu"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01480"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530164"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00267"},{"key":"ref32","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3243"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3327962"},{"key":"ref35","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00875"},{"key":"ref39","first-page":"13834","article-title":"ToAlign: Task-oriented alignment for unsupervised domain adaptation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Wei"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01046"},{"key":"ref41","article-title":"An image is worth $16 \\times 16$\n words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref42","article-title":"CDTrans: Cross-domain transformer for unsupervised domain adaptation","author":"Xu","year":"2021","journal-title":"arXiv:2109.06165"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00059"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.316"},{"key":"ref45","first-page":"2208","article-title":"Deep transfer learning with joint adaptation networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Long"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00392"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00887"},{"key":"ref48","first-page":"4013","article-title":"Transferable adversarial training: A general approach to adapting deep classifiers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2991050"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1080\/24725854.2021.1949762"},{"key":"ref51","first-page":"6028","article-title":"Do we really need to access the source data? Source hypothesis transfer for unsupervised domain adaptation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liang"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_28"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01247"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01135"},{"key":"ref55","first-page":"3730","article-title":"Joint distribution optimal transportation for domain adaptation","volume-title":"Proc. Adv. neural Inf. Process. Syst.","volume":"30","author":"Courty"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_28"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/299"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00445"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01915"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3203574"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.572"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3112012"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_16"},{"key":"ref64","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref65","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Liu"},{"key":"ref66","article-title":"Qwen2-VL: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv:2409.12191"},{"key":"ref67","article-title":"Florence-2: Advancing a unified representation for a variety of vision tasks","author":"Xiao","year":"2023","journal-title":"arXiv:2311.06242"},{"key":"ref68","volume-title":"Moondream: Tiny Vision Language Model","year":"2023"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26263"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11483349.pdf?arnumber=11483349","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T20:00:35Z","timestamp":1776974435000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11483349\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3682113","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}