{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T20:23:44Z","timestamp":1783628624517,"version":"3.55.0"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation General Program","doi-asserted-by":"publisher","award":["2024M751553"],"award-info":[{"award-number":["2024M751553"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100018919","name":"Key Research Project of Peng Cheng Laboratory","doi-asserted-by":"publisher","award":["PCL2025A12"],"award-info":[{"award-number":["PCL2025A12"]}],"id":[{"id":"10.13039\/100018919","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62572145"],"award-info":[{"award-number":["62572145"]}],"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":["62536003"],"award-info":[{"award-number":["62536003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Key Technical Project","award":["ZDCY20250901111404005"],"award-info":[{"award-number":["ZDCY20250901111404005"]}]},{"name":"Shenzhen Key Technical Project","award":["JCYJ20241202123728037"],"award-info":[{"award-number":["JCYJ20241202123728037"]}]},{"name":"Shenzhen Key Technical Project","award":["KJZD20230923115117033"],"award-info":[{"award-number":["KJZD20230923115117033"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tcsvt.2026.3671725","type":"journal-article","created":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T20:00:35Z","timestamp":1773086435000},"page":"9888-9900","source":"Crossref","is-referenced-by-count":0,"title":["Rethinking the Knowledge Gap Between Cloud and Device Models for Effective Co-Adaptation"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0653-4535","authenticated-orcid":false,"given":"Yingjian","family":"Li","sequence":"first","affiliation":[{"name":"Pengcheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7008-4401","authenticated-orcid":false,"given":"Yushi","family":"Zeng","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6238-8499","authenticated-orcid":false,"given":"Dongmei","family":"Jiang","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2197-9038","authenticated-orcid":false,"given":"Yaowei","family":"Wang","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1578-2634","authenticated-orcid":false,"given":"Guangming","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3641289"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00363"},{"key":"ref4","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":"ref5","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":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1410-8"},{"key":"ref7","article-title":"Faster segment anything: Towards lightweight SAM for mobile applications","author":"Zhang","year":"2023","journal-title":"arXiv:2306.14289"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_5"},{"key":"ref9","article-title":"Gemma 2: Improving open language models at a practical size","author":"Team","year":"2024","journal-title":"arXiv:2408.00118"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3495243.3560551"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3673038.3673120"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3586704"},{"key":"ref13","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":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00361"},{"key":"ref15","article-title":"SAM2-adapter: Evaluating & adapting segment anything 2 in downstream tasks: Camouflage, shadow, medical image segmentation, and more","author":"Chen","year":"2024","journal-title":"arXiv:2408.04579"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01170"},{"key":"ref17","first-page":"1","article-title":"Towards robust and efficient cloud-edge elastic model adaptation via selective entropy distillation","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Chen"},{"key":"ref18","first-page":"16888","article-title":"Efficient test-time model adaptation without forgetting","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Niu"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01051"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3578461"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3586282"},{"issue":"59","key":"ref22","first-page":"1","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"Ganin","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351070"},{"key":"ref24","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ganin"},{"key":"ref25","first-page":"1647","article-title":"Conditional adversarial domain adaptation","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Long"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6169"},{"key":"ref27","first-page":"17194","article-title":"A prototype-oriented framework for unsupervised domain adaptation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tanwisuth"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2924174"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3141604"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-13560-1_76"},{"issue":"1","key":"ref31","first-page":"723","article-title":"A kernel two-sample test","volume":"13","author":"Gretton","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref32","first-page":"2208","article-title":"Deep transfer learning with joint adaptation networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Long"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_18"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3318955"},{"key":"ref35","first-page":"9229","article-title":"Test-time training with self-supervision for generalization under distribution shifts","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sun"},{"key":"ref36","first-page":"1","article-title":"Active test-time adaptation: Theoretical analyses and an algorithm","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Gui"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3412243"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3526998"},{"key":"ref39","first-page":"1","article-title":"Tent: Fully test-time adaptation by entropy minimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref40","first-page":"1","article-title":"Entropy is not enough for test-time adaptation: From the perspective of disentangled factors","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Lee"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00706"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25922"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00172"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM58522.2023.00210"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref46","first-page":"11539","article-title":"Improving robustness against common corruptions by covariate shift adaptation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Schneider"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593862"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00816"},{"issue":"2","key":"ref49","first-page":"1","article-title":"Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks","volume-title":"Proc. Workshop Challenges Represent. Learn., Int. Conf. Mach. Learn.","volume":"3","author":"Lee"},{"key":"ref50","first-page":"1","article-title":"Selective label enhancement learning for test-time adaptation","volume-title":"Proc. 13th Int. Conf. Learn. Represent.","author":"Hu"},{"key":"ref51","first-page":"1","article-title":"SNAP: Low-latency test-time adaptation with sparse updates","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Cha"},{"key":"ref52","first-page":"1","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hendrycks"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref54","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11598845\/11424628.pdf?arnumber=11424628","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T19:45:45Z","timestamp":1783626345000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11424628\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":54,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3671725","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}