{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T06:22:23Z","timestamp":1777702943383,"version":"3.51.4"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Anhui Key Laboratory of Bionic Sensing and Advanced Robot Technology","award":["AHFS2024KF05"],"award-info":[{"award-number":["AHFS2024KF05"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/lra.2024.3483042","type":"journal-article","created":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T17:46:35Z","timestamp":1729187195000},"page":"10874-10881","source":"Crossref","is-referenced-by-count":5,"title":["Enhancing Scene Understanding for Vision-and-Language Navigation by Knowledge Awareness"],"prefix":"10.1109","volume":"9","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"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingfeng","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Guangxi University, Nanning, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiabao","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Guangxi University, Nanning, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"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"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"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"}],"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\/P19-1181"},{"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","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01003"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01564"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01112"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00308"},{"key":"ref13","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":"ref14","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01250"},{"key":"ref16","first-page":"394","article-title":"Vision-and-dialog navigation","volume-title":"Proc. Conf. Robot Learn.","author":"Thomason"},{"key":"ref17","first-page":"3314","article-title":"Speaker-follower models for vision-and-language navigation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Fried"},{"key":"ref18","article-title":"Semi-parametric topo-logical memory for navigation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Savinov"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01289"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00835"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01315"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00166"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00169"},{"key":"ref25","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":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01498"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01826"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/164"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3387171"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3141150"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.077"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475282"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.073"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3451395"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01501"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00254"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2972281"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01444"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/10726578\/10720886.pdf?arnumber=10720886","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T01:40:22Z","timestamp":1732671622000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10720886\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":41,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/lra.2024.3483042","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}