{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T16:23:50Z","timestamp":1778257430115,"version":"3.51.4"},"reference-count":75,"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":["62125201"],"award-info":[{"award-number":["62125201"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62020106007"],"award-info":[{"award-number":["62020106007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62002314"],"award-info":[{"award-number":["62002314"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LY23F020005"],"award-info":[{"award-number":["LY23F020005"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3586105","type":"journal-article","created":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T13:51:36Z","timestamp":1751637096000},"page":"6690-6704","source":"Crossref","is-referenced-by-count":4,"title":["MossVLN: Memory-Observation Synergistic System for Continuous Vision-Language Navigation"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4348-2671","authenticated-orcid":false,"given":"Ting","family":"Yu","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, Hangzhou Normal University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3474-2561","authenticated-orcid":false,"given":"Yifei","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Hangzhou Normal University, Hangzhou, China"}]},{"given":"Qiongjie","family":"Cui","sequence":"additional","affiliation":[{"name":"Information Systems Technology and Design Pillar, Singapore University of Technology and Design, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7542-296X","authenticated-orcid":false,"given":"Qingming","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1922-7283","authenticated-orcid":false,"given":"Jun","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Intelligence Science and Engineering, Harbin Institute of Technology, Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01544"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3358112"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3243618"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01498"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01007"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00646"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00254"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01826"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01040"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00764"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00835"},{"key":"ref13","first-page":"20660","article-title":"Evolving graphical planner: Contextual global planning for vision-and-language navigation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Deng","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3001500"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01502"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01500"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3386695"},{"key":"ref20","article-title":"BEVBert:Multimodal map pre-training for language-guided navigation","author":"An","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01432"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00998"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01305"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01542"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3387171"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_34"},{"key":"ref28","article-title":"DD-PPO: Learning near-perfect pointgoal navigators from 2.5 billion frames","author":"Wijmans","year":"2019"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01282"},{"key":"ref31","first-page":"394","article-title":"Vision-and-dialog navigation","volume-title":"Proc. Conf. Robot Learn.","author":"Thomason","year":"2020"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1063"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01250"},{"key":"ref35","first-page":"3318","article-title":"Speaker-follower models for vision-and-language navigation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fried","year":"2018"},{"key":"ref36","article-title":"Self-monitoring navigation agent via auxiliary progress estimation","author":"Ma","year":"2019"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475282"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_18"},{"key":"ref39","first-page":"7685","article-title":"Language and visual entity relationship graph for agent navigation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hong","year":"2020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00167"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01497"},{"key":"ref43","first-page":"5296","article-title":"Counterfactual vision-and-language navigation: Unravelling the unseen","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Parvaneh","year":"2020"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01041"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01503"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01499"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.111"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2995959"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01315"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00166"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_16"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3390984"},{"key":"ref55","first-page":"671","article-title":"Sim-to-real transfer for vision-and-language navigation","volume-title":"Proc. Conf. Robot Learn.","author":"Anderson","year":"2021"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.328"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956561"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01488"},{"key":"ref59","first-page":"38149","article-title":"Weakly-supervised multi-granularity map learning for vision-and-language navigation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen","year":"2022"},{"key":"ref60","article-title":"1st place solutions for RXR-habitat vision-and-language navigation competition (CVPR 2022)","author":"An","year":"2022"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01003"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00689"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2940677"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.271"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.229"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-025-06544-9"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3296889"},{"key":"ref68","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":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00169"},{"key":"ref70","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref71","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","year":"2011"},{"key":"ref72","article-title":"An image is worth 16  16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref73","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":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/11071855.pdf?arnumber=11071855","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T12:24:16Z","timestamp":1759235056000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11071855\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3586105","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}