{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T20:07:14Z","timestamp":1780949234718,"version":"3.54.1"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/tcsvt.2026.3657756","type":"journal-article","created":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T06:05:44Z","timestamp":1769493944000},"page":"8590-8601","source":"Crossref","is-referenced-by-count":0,"title":["DHPT: Dual-Modality Heterogeneous Prompt Tuning for Online Test-Time Adaption in Vision-Language Models"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3369-5043","authenticated-orcid":false,"given":"Guiqin","family":"Wang","sequence":"first","affiliation":[{"name":"National Engineering Laboratory for Big Data Analytics and the School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7033-9315","authenticated-orcid":false,"given":"Peng","family":"Zhao","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Big Data Analytics and the School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Advanced Computing and Storage Laboratory, Huawei Technologies Company Ltd., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoran","family":"Guo","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Big Data Analytics and the School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7492-8308","authenticated-orcid":false,"given":"Nan","family":"Qi","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Big Data Analytics and the School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4495-6237","authenticated-orcid":false,"given":"Shusen","family":"Yang","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Big Data Analytics and the School of Mathematics and Statistics, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4697-9464","authenticated-orcid":false,"given":"Qinghai","family":"Guo","sequence":"additional","affiliation":[{"name":"Advanced Computing and Storage Laboratory, Huawei Technologies Company Ltd., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","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":"ref2","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Jia"},{"key":"ref3","first-page":"65252","article-title":"Swapprompt: Test-time prompt adaptation for vision-language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ma"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3034233"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261659"},{"key":"ref6","article-title":"Learning clustering-based prototypes for compositional zero-shot learning","author":"Qu","year":"2025","journal-title":"arXiv:2502.06501"},{"key":"ref7","article-title":"OmniGaze: Reward-inspired generalizable gaze estimation in the wild","author":"Qu","year":"2025","journal-title":"arXiv:2510.13660"},{"key":"ref8","first-page":"1","article-title":"Tent: Fully test-time adaptation by entropy minimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00706"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02181-w"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3525"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00255"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2165"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01343"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICME59968.2025.11209257"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i13.29320"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1010"},{"key":"ref18","first-page":"14274","article-title":"Test-time prompt tuning for zero-shot generalization in vision-language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Shu"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.4737-06.2007"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.56972"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.bandl.2016.02.001"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680678"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72855-6_20"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02688"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3424566"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3557474"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01228"},{"key":"ref32","article-title":"A closer look at conditional prompt tuning for vision-language models","author":"Zhang","year":"2025","journal-title":"arXiv:2506.23856"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3584051"},{"key":"ref34","first-page":"32924","article-title":"Beyond sole strength: Customized ensembles for generalized vision-language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lu"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3599830"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3521702"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3413318"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3641289"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref40","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NIPS","author":"Brown"},{"key":"ref41","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref42","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref43","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref44","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv:2407.21783"},{"key":"ref45","article-title":"Qwen3 technical report","volume-title":"arXiv:2505.09388","author":"Yang","year":"2025"},{"key":"ref46","article-title":"DeepSeek-v2: A strong, economical, and efficient mixture-of-experts language model","author":"Liu","year":"2024","journal-title":"arXiv:2405.04434"},{"key":"ref47","article-title":"DeepSeek-V3 technical report","volume-title":"arXiv:2412.19437","author":"Liu","year":"2024"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3412243"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3526998"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02245"},{"key":"ref51","first-page":"1","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hu"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00532"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01394"},{"key":"ref54","first-page":"606","article-title":"Efficiently scaling transformer inference","volume-title":"Proc. Conf. Mach. Learn. Syst.","author":"Pope"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.5244\/C.34.191"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"ref57","first-page":"5389","article-title":"Do ImageNet classifiers generalize to ImageNet","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Recht"},{"key":"ref58","first-page":"10506","article-title":"Learning robust global representations by penalizing local predictive power","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02792"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11552944\/11363627.pdf?arnumber=11363627","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T19:54:58Z","timestamp":1780948498000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11363627\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":67,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3657756","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}