{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:58:22Z","timestamp":1759334302151,"version":"build-2065373602"},"reference-count":86,"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":[{"name":"Artificial Intelligence-National Science and Technology Major Project","award":["2023ZD0121200"],"award-info":[{"award-number":["2023ZD0121200"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376199","62206170","62206279","62437001"],"award-info":[{"award-number":["62376199","62206170","62206279","62437001"]}],"id":[{"id":"10.13039\/501100001809","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.2025.3581809","type":"journal-article","created":{"date-parts":[[2025,9,25]],"date-time":"2025-09-25T17:55:50Z","timestamp":1758822950000},"page":"6307-6318","source":"Crossref","is-referenced-by-count":0,"title":["FlexVLN: Flexible Adaptation for Diverse Vision-and-Language Navigation Tasks"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-3187-9332","authenticated-orcid":false,"given":"Siqi","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5606-0702","authenticated-orcid":false,"given":"Yanyuan","family":"Qiao","sequence":"additional","affiliation":[{"name":"Australian Institute for Machine Learning, School of Computer Science, The University of Adelaide, Adelaide, SA, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5607-7854","authenticated-orcid":false,"given":"Qunbo","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4340-4000","authenticated-orcid":false,"given":"Longteng","family":"Guo","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5937-3907","authenticated-orcid":false,"given":"Zhihua","family":"Wei","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0903-9131","authenticated-orcid":false,"given":"Jing","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.524"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01250"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01315"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3234243"},{"key":"ref7","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":"ref8","first-page":"2737","article-title":"Bevbert: Multimodal map pre-training for language-guided navigation","volume-title":"Proc. Int. Conf. Comput. Vis.","author":"An","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01432"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01103"},{"key":"ref11","first-page":"21878","article-title":"Panogen: Text-conditioned panoramic environment generation for vision-and-language navigation","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","volume":"36","author":"Li","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00764"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28597"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611565"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.529"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_27"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/21.44033"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/70.88137"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.438"},{"article-title":"Mo-vln: A multi-task benchmark for open-set zero-shot vision-and-language navigation","year":"2023","author":"Liang","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.82"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00646"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01432"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3358112"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/70.938381"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3001500"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2913324"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1181"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"ref31","first-page":"394","article-title":"Vision-and-dialog navigation","volume-title":"Proc. Conf. Robot Learn.","author":"Thomason","year":"2020"},{"key":"ref32","first-page":"7685","article-title":"Language and visual entity relationship graph for agent navigation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Hong","year":"2020"},{"key":"ref33","first-page":"20660","article-title":"Evolving graphical planner: Contextual global planning for vision-and-language navigation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Deng","year":"2020"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01112"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01502"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956561"},{"key":"ref38","first-page":"38149","article-title":"Weakly-supervised multi-granularity map learning for vision-and-language navigation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Chen","year":"2022"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00284"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00169"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00166"},{"key":"ref42","first-page":"5745","article-title":"LOViS: Learning orientation and visual signals for vision and language navigation","volume-title":"Proc. 29th Int. Conf. Comput. Linguistics","author":"Zhang","year":"2022"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01106"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_37"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01497"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.229"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.271"},{"key":"ref49","first-page":"652","article-title":"Landmark-RxR: Solving vision-and-language navigation with fine-grained alignment supervision","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"He","year":"2021"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00254"},{"key":"ref51","article-title":"Clip-nav: Using clip for zero-shot vision-and-language navigation","author":"Dorbala","year":"2022","journal-title":"Workshop Lang. Robot. CoRL."},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_5"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.322"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01499"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01503"},{"article-title":"Kefa: A knowledge enhanced and fine-grained aligned speaker for navigation instruction generation","year":"2023","author":"Zeng","key":"ref56"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.737"},{"key":"ref58","first-page":"22199","article-title":"Large language models are zero-shot reasoners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Kojima","year":"2022"},{"article-title":"Jarvis: A neuro-symbolic commonsense reasoning framework for conversational embodied agents","year":"2022","author":"Zheng","key":"ref59"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3233258"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3428317"},{"key":"ref62","first-page":"492","article-title":"LM-nav: Robotic navigation with large pre-trained models of language, vision, and action","volume-title":"Proc. Conf. Robot Learn.","author":"Shah","year":"2023"},{"key":"ref63","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown","year":"2020"},{"key":"ref64","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf, Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01444"},{"issue":"8","key":"ref66","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.60"},{"article-title":"Do as i can, not as i say: Grounding language in robotic affordances","year":"2022","author":"Ahn","key":"ref68"},{"key":"ref69","first-page":"9118","article-title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents","volume-title":"Proc. Int. Conf, Mach. Learn.","volume":"162","author":"Huang","year":"2022"},{"article-title":"$a^{2}$ nav: Action-aware zero-shot robot navigation by exploiting vision-and-language ability of foundation models","year":"2023","author":"Chen","key":"ref70"},{"key":"ref71","first-page":"32340","article-title":"ZSON: Zero-shot object-goal navigation using multimodal goal embeddings","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Majumdar","year":"2022"},{"key":"ref72","first-page":"42829","article-title":"ESC: Exploration with soft commonsense constraints for zero-shot object navigation","volume-title":"Proc. Int. Conf, Mach. Learn.","author":"Zhou","year":"2023"},{"journal-title":"The Eleventh Int. Conf. Learn Representations","article-title":"Debertav3: Improving deberta using electra-style pre-training with gradient-disentangled embedding sharing","author":"He","key":"ref73"},{"article-title":"GPT-4 technical report","year":"2023","author":"Achiam","key":"ref74"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00280"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3554559"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00945"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/3dv.2017.00081"},{"article-title":"Habitat-matterport 3 D dataset (hm3d): 1000 large-scale 3 D environments for embodied AI","year":"2021","author":"Ramakrishnan","key":"ref79"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"article-title":"Qwen2-vl: Enhancing vision-language models perception of the world at any resolution","year":"2024","author":"Wang","key":"ref82"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref84","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","year":"2023"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01826"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01416"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/11178223.pdf?arnumber=11178223","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T13:58:04Z","timestamp":1759240684000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11178223\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":86,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3581809","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2025]]}}}