{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T17:59:49Z","timestamp":1775325589341,"version":"3.50.1"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFF0607001"],"award-info":[{"award-number":["2022YFF0607001"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023A1515010993"],"award-info":[{"award-number":["2023A1515010993"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Provincial Key Laboratory of Human Digital Twin","award":["2022B1212010004"],"award-info":[{"award-number":["2022B1212010004"]}]},{"name":"Guangzhou City Science and Technology Research Projects","award":["2023B01J0011"],"award-info":[{"award-number":["2023B01J0011"]}]},{"name":"Jiangmen Science and Technology Research Projects","award":["2021080200070009151"],"award-info":[{"award-number":["2021080200070009151"]}]},{"name":"Shaoguan Science and Technology Research Project","award":["230316116276286"],"award-info":[{"award-number":["230316116276286"]}]},{"name":"Foshan Science and Technology Research Project","award":["2220001018608"],"award-info":[{"award-number":["2220001018608"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1109\/tcsvt.2024.3391304","type":"journal-article","created":{"date-parts":[[2024,4,19]],"date-time":"2024-04-19T17:34:23Z","timestamp":1713548063000},"page":"8201-8214","source":"Crossref","is-referenced-by-count":16,"title":["Unsupervised Domain Adaption Harnessing Vision-Language Pre-Training"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7500-5581","authenticated-orcid":false,"given":"Wenlve","family":"Zhou","sequence":"first","affiliation":[{"name":"School of Electronic and Information Engineering and the Key Laboratory of Big Data and Intelligent Robot, Ministry of Education, South China University of Technology, Guangzhou, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4040-0175","authenticated-orcid":false,"given":"Zhiheng","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering and the Key Laboratory of Big Data and Intelligent Robot, Ministry of Education, South China University of Technology, Guangzhou, Guangdong, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3168547"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3015866"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3268757"},{"key":"ref4","first-page":"97","article-title":"Learning transferable features with deep adaptation networks","volume-title":"Proc. IMCL","author":"Long"},{"key":"ref5","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ganin"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2988928"},{"key":"ref7","first-page":"1","article-title":"CDTrans: Cross-domain transformer for unsupervised domain adaptation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Xu"},{"key":"ref8","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3327962"},{"key":"ref13","article-title":"CLIP itself is a strong fine-tuner: Achieving 85.7% and 88.0% top-1 accuracy with ViT-B and ViT-L on ImageNet","author":"Dong","year":"2022","journal-title":"arXiv:2212.06138"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/180"},{"key":"ref16","first-page":"1","article-title":"LoRa: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hu"},{"key":"ref17","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref20","first-page":"1","article-title":"An image is worth 16\u271716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref21","first-page":"1","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Su"},{"key":"ref22","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref23","first-page":"1","article-title":"SimVLM: Simple visual language model pretraining with weak supervision","volume-title":"Proc. ICLR","author":"Wang"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00968"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3099943"},{"key":"ref26","first-page":"18378","article-title":"A closer look at smoothness in domain adversarial training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rangwani"},{"key":"ref27","first-page":"22968","article-title":"Cycle self-training for domain adaptation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Liu"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01004"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00059"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00347"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3271124"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3234037"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01604"},{"key":"ref36","first-page":"1","article-title":"Facing the elephant in the room: Visual prompt tuning or full finetuning?","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Han"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref39","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.633"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.758"},{"key":"ref42","article-title":"Efficient multimodal semantic segmentation via dual-prompt learning","author":"Dong","year":"2023","journal-title":"arXiv:2312.00360"},{"issue":"2","key":"ref43","first-page":"896","article-title":"Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"3","author":"Lee"},{"key":"ref44","article-title":"Intrinsic dimensionality explains the effectiveness of language model fine-tuning","author":"Aghajanyan","year":"2020","journal-title":"arXiv:2012.13255"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3389\/fncel.2019.00066"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.572"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_16"},{"key":"ref48","first-page":"1","article-title":"Reading digits in natural images with unsupervised feature learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Netzer"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2211477"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/34.291440"},{"key":"ref51","first-page":"2208","article-title":"Deep transfer learning with joint adaptation networks","volume-title":"Proc. ICML","author":"Long"},{"key":"ref52","article-title":"VisDA: The visual domain adaptation challenge","author":"Peng","year":"2017","journal-title":"arXiv:1710.06924"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00149"},{"key":"ref54","first-page":"281","article-title":"Semi-supervised learning by entropy minimization","volume-title":"Proc. CAP","author":"Grandvalet"},{"key":"ref55","first-page":"1647","article-title":"Conditional adversarial domain adaptation","volume-title":"Proc. NIPS","volume":"31","author":"Long"},{"key":"ref56","first-page":"1081","article-title":"Transferability vs. discriminability: Batch spectral penalization for adversarial domain adaptation","volume-title":"Proc. ICML","volume":"97","author":"Chen"},{"key":"ref57","article-title":"Transferable normalization: Towards improving transferability of deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01053"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00753"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00400"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6801"},{"key":"ref62","first-page":"6028","article-title":"Do we really need to access the source data? Source hypothesis transfer for unsupervised domain adaptation","volume-title":"Proc. ICML","author":"Liang"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01636"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00393"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2950768"},{"key":"ref66","first-page":"1","article-title":"Adversarial dropout regularization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Saito"},{"key":"ref67","first-page":"1989","article-title":"CyCADA: Cycle-consistent adversarial domain adaptation","volume-title":"Proc. ICML","author":"Hoffman"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00705"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_28"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_35"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11767"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.1"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-short.107"},{"key":"ref74","first-page":"596","article-title":"FixMatch: Simplifying semi-supervised learning with consistency and confidence","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Sohn"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10700029\/10505301.pdf?arnumber=10505301","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T17:32:17Z","timestamp":1727803937000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10505301\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":74,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3391304","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9]]}}}