{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T21:20:55Z","timestamp":1774646455176,"version":"3.50.1"},"reference-count":61,"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":["62276242"],"award-info":[{"award-number":["62276242"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Aviation Science Foundation","award":["2022Z071078001"],"award-info":[{"award-number":["2022Z071078001"]}]},{"name":"Hefei Municipal Natural Science Foundation","award":["HZR2431"],"award-info":[{"award-number":["HZR2431"]}]},{"name":"Dreams Foundation of Jianghuai Advance Technology Center","award":["2023-ZM01Z001"],"award-info":[{"award-number":["2023-ZM01Z001"]}]},{"name":"CAAI-MindSpore Open Fund, Developed on OpenI Community"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tase.2025.3604018","type":"journal-article","created":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T17:44:37Z","timestamp":1756489477000},"page":"21311-21324","source":"Crossref","is-referenced-by-count":2,"title":["Visual and Textual Commonsense-Enhanced Layout Learning for Vision-and-Language Navigation"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1816-5420","authenticated-orcid":false,"given":"Fang","family":"Gao","sequence":"first","affiliation":[{"name":"School of Electrical Engineering, Guangxi University, Nanning, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3411-3077","authenticated-orcid":false,"given":"Lei","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Guangxi University, Nanning, China"}]},{"given":"Jingfeng","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Guangxi University, Nanning, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6371-9739","authenticated-orcid":false,"given":"Jiabao","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Guangxi University, Nanning, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5034-8721","authenticated-orcid":false,"given":"Shaodong","family":"Li","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Guangxi University, Nanning, China"}]},{"given":"Shengheng","family":"Ma","sequence":"additional","affiliation":[{"name":"Guangxi China-Tek Blue Valley Semiconductor Technology Company Ltd., Guangxi, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3197-8103","authenticated-orcid":false,"given":"Jun","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Automation, University of Science and Technology of China, Hefei, China"}]}],"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":"10.1109\/CVPR46437.2021.01250"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_18"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref8","first-page":"3314","article-title":"Speaker-follower models for vision-and-language navigation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fried"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01497"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01564"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00169"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.332"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687470"},{"key":"ref15","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref16","first-page":"12888","article-title":"Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3260099"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2021.3081406"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI.2018.00134"},{"key":"ref21","article-title":"Human\u2013robot collaboration and machine learning: A systematic review of recent research","author":"Semeraro","year":"2021","journal-title":"arXiv:2110.07448"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00167"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00690"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01315"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00166"},{"key":"ref28","first-page":"5834","article-title":"History aware multimodal transformer for vision-and-language navigation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01498"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICDEW.2007.4400998"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/164"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01416"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01040"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01103"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32679"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3159595"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00254"},{"key":"ref39","first-page":"1386","article-title":"Layout-aware dreamer for embodied referring expression grounding","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Li"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28223"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3407759"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3477129"},{"key":"ref43","first-page":"492","article-title":"LM-nav: Robotic navigation with large pre-trained models of language, vision, and action","volume-title":"Proc. 6th Conf. Robot Learn.","author":"Shah"},{"key":"ref44","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref45","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"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28597"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01444"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.529"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.60"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.60"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72667-5_15"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611565"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i22.34526"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.079"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3554559"},{"key":"ref56","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref58","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":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.rineng.2024.102042"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2972281"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/10839176\/11145171.pdf?arnumber=11145171","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T20:10:15Z","timestamp":1773951015000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11145171\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/tase.2025.3604018","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}