{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T18:43:24Z","timestamp":1771699404229,"version":"3.50.1"},"reference-count":69,"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":["62202311"],"award-info":[{"award-number":["62202311"]}],"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":["62072190"],"award-info":[{"award-number":["62072190"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100016804","name":"Natural Science Foundation of Shenzhen Municipality","doi-asserted-by":"publisher","award":["20220809180405001"],"award-info":[{"award-number":["20220809180405001"]}],"id":[{"id":"10.13039\/100016804","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Excellent Science and Technology Creative Talent Training Program of Shenzhen Municipality","award":["RCBS20221008093224017"],"award-info":[{"award-number":["RCBS20221008093224017"]}]},{"name":"Ministry of Science and Technology Foundation","award":["2020AAA0106900"],"award-info":[{"award-number":["2020AAA0106900"]}]},{"name":"Key-Area Research and Development Program Guangdong Province","award":["2019B010155002"],"award-info":[{"award-number":["2019B010155002"]}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023A1515011512"],"award-info":[{"award-number":["2023A1515011512"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3535356","type":"journal-article","created":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T13:44:24Z","timestamp":1738071864000},"page":"3953-3965","source":"Crossref","is-referenced-by-count":3,"title":["Source-Free Elastic Model Adaptation for Vision-and-Language Navigation"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8856-756X","authenticated-orcid":false,"given":"Mingkui","family":"Tan","sequence":"first","affiliation":[{"name":"School of Software Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6847-1621","authenticated-orcid":false,"given":"Peihao","family":"Chen","sequence":"additional","affiliation":[{"name":"X Lab, Tencent, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongyan","family":"Zhi","sequence":"additional","affiliation":[{"name":"School of Software Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0172-5981","authenticated-orcid":false,"given":"Jiajie","family":"Mai","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hongkong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Benjamin","family":"Rosman","sequence":"additional","affiliation":[{"name":"School of Computer Science and Applied Mathematics, The University of the Witwatersrand, Johannesburg, South Africa"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongyu","family":"Ji","sequence":"additional","affiliation":[{"name":"School of Software Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8694-4245","authenticated-orcid":false,"given":"Runhao","family":"Zeng","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Research Institute, Shenzhen MSU-BIT University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Anticipating the unseen discrepancy for vision and language navigation","author":"Lu","year":"2022","journal-title":""},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref3","article-title":"CLIP-Nav: Using CLIP for zero-shot vision-and-language navigation","volume-title":"Proc. Conf. Robot Learn.","author":"Dorbala","year":"2022"},{"key":"ref4","first-page":"3318","article-title":"Speaker-follower models for vision-and-language navigation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fried","year":"2018"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00167"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00166"},{"key":"ref8","article-title":"Tent: Fully test-time adaptation by entropy minimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2021"},{"key":"ref9","first-page":"16888","article-title":"Efficient test-time model adaptation without forgetting","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Niu","year":"2022"},{"key":"ref10","first-page":"38629","article-title":"MEMO: Test time robustness via adaptation and augmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00706"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00169"},{"key":"ref15","first-page":"5834","article-title":"History aware multimodal transformer for vision-and-language navigation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3243618"},{"key":"ref18","article-title":"DD-PPO: Learning near-perfect PointGoal navigators from 2.5 billion frames","author":"Wijmans","year":"2019"},{"key":"ref19","article-title":"GENESIS: Generative scene inference and sampling with object-centric latent representations","author":"Engelcke","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.518"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19-1197"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00308"},{"key":"ref23","article-title":"Embodied vision-and-language navigation with dynamic convolutional filters","author":"Landi","year":"2019"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01315"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1181"},{"key":"ref27","article-title":"General evaluation for instruction conditioned navigation using dynamic time warping","author":"Ilharco","year":"2019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2021.103255"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3039522"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"},{"key":"ref31","article-title":"Anticipating the unseen discrepancy for vision and language navigation","author":"Lu","year":"2022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_5"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475282"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00039"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3203574"},{"key":"ref36","first-page":"11539","article-title":"Improving robustness against common corruptions by covariate shift adaptation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Schneider","year":"2020"},{"key":"ref37","first-page":"2427","article-title":"Test-time classifier adjustment module for model-agnostic domain generalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Iwasawa","year":"2021"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3292597"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01411"},{"key":"ref40","first-page":"36000","article-title":"Extrapolative continuous-time Bayesian neural network for fast training-free test-time adaptation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Huang","year":"2022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3282492"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00127"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00949"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01642"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01722"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01444"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00055"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3078141"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3001522"},{"key":"ref50","article-title":"SlowFast-LLaVA: A strong training-free baseline for video large language models","author":"Xu","year":"2024"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9191290"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1002\/acs.3234"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2884462"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3133897"},{"key":"ref55","first-page":"14902","article-title":"Fast-slow test-time adaptation for online vision-and-language navigation","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Gao","year":"2024"},{"key":"ref56","article-title":"Self-monitoring navigation agent via auxiliary progress estimation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ma","year":"2019"},{"key":"ref57","first-page":"6179","article-title":"Robust question answering against distribution shifts with test-time adaptation: An empirical study","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Ye","year":"2023"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3147.3165"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1159"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01003"},{"key":"ref62","first-page":"7685","article-title":"Language and visual entity relationship graph for agent navigation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hong","year":"2020"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01498"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.82"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01496"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00168"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00696"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10856447.pdf?arnumber=10856447","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T17:48:48Z","timestamp":1752169728000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10856447\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3535356","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}