{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T16:38:06Z","timestamp":1757608686752,"version":"3.44.0"},"reference-count":58,"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\/icra55743.2025.11127282","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"7577-7584","source":"Crossref","is-referenced-by-count":0,"title":["Map-SemNav: Advancing Zero-Shot Continuous Vision-and-Language Navigation Through Visual Semantics and Map Integration"],"prefix":"10.1109","author":[{"given":"Shuai","family":"Wu","sequence":"first","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University,Tianjin,China"}],"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"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhibo","family":"Pang","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology,Stockholm,Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.524"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-023-09217-1"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00254"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00689"},{"key":"ref7","article-title":"Vilbert: Pretraining taskagnostic visiolinguistic representations for vision-and-language tasks","volume":"32","author":"Lu","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref8","first-page":"7685","article-title":"Language and visual entity relationship graph for agent navigation","volume":"33","author":"Hong","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00166"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_37"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01103"},{"key":"ref13","article-title":"Clip-nav: Using clip for zero-shot vision-and-language navigation","author":"Dorbala","year":"2022","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/tce.2025.3601582"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.529"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28597"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687470"},{"key":"ref18","article-title":"A2 nav: Action-aware zero-shot robot navigation by exploiting vision-and-language ability of foundation models","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01497"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/204"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01003"},{"key":"ref22","article-title":"Self-monitoring navigation agent via auxiliary progress estimation","author":"Ma","year":"2019","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01315"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01498"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1159"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3092686"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref29","article-title":"Rethinking the spatial route prior in vision-and-language navigation","author":"Zhou","year":"2021","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01432"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01500"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01502"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446850"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956561"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00998"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01488"},{"key":"ref37","article-title":"Mlanet: Multilevel attention network with sub-instruction for continuous vision-andlanguage navigation","author":"He","year":"2023","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00450"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00101"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20887-5_34"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69535-4_10"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.29007\/mx3z"},{"key":"ref43","article-title":"Zero-shot semantic segmentation","volume":"32","author":"Bucher","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00172"},{"key":"ref45","first-page":"32340","article-title":"Zson: Zero-shot object-goal navigation using multimodal goal embeddings","volume":"35","author":"Majumdar","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref46","article-title":"Zeroshot object goal visual navigation with class-independent relationship network","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02219"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161289"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01652"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73254-6_10"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812423"},{"key":"ref52","article-title":"Learning to map for active semantic goal navigation","author":"Georgakis","year":"2021","journal-title":"arXiv preprint"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref54","article-title":"Dd-ppo: Learning near-perfect pointgoal navigators from 2.5 billion frames","author":"Wijmans","year":"2019","journal-title":"arXiv preprint"},{"key":"ref55","article-title":"On evaluation of embodied navigation agents","author":"Anderson","year":"2018","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref57","article-title":"Language-aligned waypoint (law) supervision for vision-andlanguage navigation in continuous environments","author":"Raychaudhuri","year":"2021","journal-title":"arXiv preprint"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.079"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2025,5,19]]},"location":"Atlanta, GA, USA","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\/11127282.pdf?arnumber=11127282","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:12:04Z","timestamp":1756879924000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127282\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127282","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}