{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T16:22:40Z","timestamp":1778257360029,"version":"3.51.4"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2024YFE0203100"],"award-info":[{"award-number":["2024YFE0203100"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476293"],"award-info":[{"award-number":["62476293"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012152","name":"National Postdoctoral Program for Innovative Talents","doi-asserted-by":"publisher","award":["BX20250379"],"award-info":[{"award-number":["BX20250379"]}],"id":[{"id":"10.13039\/501100012152","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2025M771521"],"award-info":[{"award-number":["2025M771521"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"General Embodied AI Center of Sun Yat-sen University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Major Key Project of PCL","doi-asserted-by":"publisher","award":["PCL2024A04"],"award-info":[{"award-number":["PCL2024A04"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Major Key Project of PCL","doi-asserted-by":"publisher","award":["PCL2025A12"],"award-info":[{"award-number":["PCL2025A12"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong S&T Programme","award":["2024B0101010003"],"award-info":[{"award-number":["2024B0101010003"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tnnls.2025.3624691","type":"journal-article","created":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T18:49:07Z","timestamp":1762800547000},"page":"1726-1738","source":"Crossref","is-referenced-by-count":3,"title":["Unseen From Seen: Rewriting Observation-Instruction Using Foundation Models for Augmenting Vision-Language Navigation"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-5350-7805","authenticated-orcid":false,"given":"Ziming","family":"Wei","sequence":"first","affiliation":[{"name":"Shenzhen Campus, Sun Yat-sen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8763-9530","authenticated-orcid":false,"given":"Bingqian","family":"Lin","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9717-2308","authenticated-orcid":false,"given":"Yunshuang","family":"Nie","sequence":"additional","affiliation":[{"name":"Shenzhen Campus, Sun Yat-sen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5126-3460","authenticated-orcid":false,"given":"Jiaqi","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8340-9762","authenticated-orcid":false,"given":"Shikui","family":"Ma","sequence":"additional","affiliation":[{"name":"Hunan Artificial Intelligence and Robotics Institute Company Ltd., Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3645-8972","authenticated-orcid":false,"given":"Hang","family":"Xu","sequence":"additional","affiliation":[{"name":"Huawei Noah’s Ark Lab, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3213-3062","authenticated-orcid":false,"given":"Xiaodan","family":"Liang","sequence":"additional","affiliation":[{"name":"Shenzhen Campus, Sun Yat-sen University, Shenzhen, 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":"10.1109\/CVPR42600.2020.01000"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"ref4","first-page":"394","article-title":"Vision-and-dialog navigation","volume-title":"Proc. Conf. Robot Learn. (CoRL)","author":"Thomason"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"},{"key":"ref7","first-page":"3314","article-title":"Speaker-follower models for vision-and-language navigation","volume-title":"Proc. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Fried"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00167"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_37"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01103"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_5"},{"key":"ref12","article-title":"Habitat-matterport 3D dataset (HM3D): 1000 large-scale 3D environments for embodied AI","author":"Ramakrishnan","year":"2021","journal-title":"arXiv:2109.08238"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00945"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00166"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00764"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1181"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"},{"key":"ref18","first-page":"5613","article-title":"Self-monitoring navigation agent via auxiliary progress estimation","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Ma"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_18"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01003"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_8"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3122579"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3273594"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3222871"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20050"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3097435"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3398300"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3183287"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref33","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Lu"},{"key":"ref34","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"Harold Li","year":"2019","journal-title":"arXiv:1908.03557"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01315"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00169"},{"key":"ref37","first-page":"5834","article-title":"History aware multimodal transformer for vision-and-language navigation","volume-title":"Proc. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Chen"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref39","first-page":"2737","article-title":"BEVBert: Multimodal map pre-training for language-guided navigation","volume-title":"Proc. IEEE Int. Conf. Comput. Vis. (ICCV)","author":"An"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548281"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00168"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3395633"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3386695"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3341828"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3586105"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3358112"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3401451"},{"key":"ref48","volume-title":"Introducing ChatGPT","year":"2022"},{"key":"ref49","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref50","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Radford"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28597"},{"key":"ref53","article-title":"Discuss before moving: Visual language navigation via multi-expert discussions","author":"Long","year":"2023","journal-title":"arXiv:2309.11382"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.529"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3407759"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01497"},{"key":"ref57","first-page":"21878","article-title":"PanoGen: Text-conditioned panoramic environment generation for vision-and-language navigation","volume-title":"Proc. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Li"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.029"},{"key":"ref59","article-title":"GenSim: Generating robotic simulation tasks via large language models","author":"Wang","year":"2023","journal-title":"arXiv:2310.01361"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01536"},{"key":"ref61","article-title":"RoboGen: Towards unleashing infinite data for automated robot learning via generative simulation","author":"Wang","year":"2023","journal-title":"arXiv:2311.01455"},{"key":"ref62","article-title":"EnvGen: Generating and adapting environments via LLMs for training embodied agents","author":"Zala","year":"2024","journal-title":"arXiv:2403.12014"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01500"},{"key":"ref64","first-page":"1737","article-title":"MultiDiffusion: Fusing diffusion paths for controlled image generation","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Bar-Tal"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICTC62082.2024.10827612"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00673"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00696"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00254"},{"key":"ref70","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proc. 14th Int. Conf. Artif. Intell. Statist.","author":"Ross"},{"key":"ref71","article-title":"Tag2Text: Guiding vision-language model via image tagging","author":"Huang","year":"2023","journal-title":"arXiv:2303.05657"},{"key":"ref72","article-title":"Multimodal attention networks for low-level vision-and-language navigation","author":"Landi","year":"2019","journal-title":"arXiv:1911.12377"},{"key":"ref73","first-page":"20660","article-title":"Evolving graphical planner: Contextual global planning for vision-and-language navigation","volume-title":"Proc. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Deng"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01112"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.328"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_34"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11475606\/11236502.pdf?arnumber=11236502","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T19:37:14Z","timestamp":1776109034000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11236502\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":76,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3624691","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}