{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T21:11:42Z","timestamp":1774473102326,"version":"3.50.1"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11127961","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"5236-5243","source":"Crossref","is-referenced-by-count":1,"title":["VLN-KHVR: Knowledge-And-History Aware Visual Representation for Continuous Vision-and-Language Navigation"],"prefix":"10.1109","author":[{"given":"Ping","family":"Kong","sequence":"first","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University,Tianjin,China,300350"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruonan","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Automation,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zongxia","family":"Xie","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University,Tianjin,China,300350"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhibo","family":"Pang","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology, ABB Corporate Research,V&#x00E4;ster&#x00E5;s, Stockholm,Sweden"}],"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\/CVPR46437.2021.00169"},{"key":"ref3","first-page":"5834","article-title":"History aware multimodal transformer for vision-and-language navigation","volume":"34","author":"Chen","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01488"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.328"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01500"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_34"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3386695"},{"key":"ref11","first-page":"2737","article-title":"Bevbert: Multimodal map pre-training for language-guided navigation","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"An","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01502"},{"key":"ref13","first-page":"38149","article-title":"Weaklysupervised multi-granularity map learning for vision-and-language navigation","volume":"35","author":"Chen","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1181"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01250"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3039522"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01003"},{"key":"ref21","first-page":"2610","article-title":"Learning to navigate unseen environments: Back translation with environmental dropout","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, June 2\u20137, 2019, Volume 1 (Long and Short Papers)","author":"Yu","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00167"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01497"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00168"},{"key":"ref25","first-page":"7357","article-title":"Soat: A scene-and object-aware transformer for vision-and-language navigation","volume":"34","author":"Moudgil","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3234243"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01112"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956561"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01432"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00538"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00470"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_36"},{"key":"ref33","first-page":"15558","article-title":"K-lite: Learning transferable visual models with external knowledge","volume":"35","author":"Shen","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00308"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00254"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28223"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11164"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00284"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref40","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3\u20137, 2021","author":"Dosovitskiy","year":"2021"},{"key":"ref41","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning.","author":"Radford","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref43","article-title":"DD-PPO: learning near-perfect pointgoal navigators from 2.5 billion frames","volume-title":"8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26\u201330, 2020","author":"Wijmans","year":"2020"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11127961.pdf?arnumber=11127961","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:14:41Z","timestamp":1756880081000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127961\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127961","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}