{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T15:40:32Z","timestamp":1785512432975,"version":"3.56.0"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100019635","name":"IITP","doi-asserted-by":"publisher","award":["IITP-2025-RS-2020-II201819,IITP-2025-RS-2024-00436857,RS-202400398115,IITP-2025-RS-2025-02263754,IITP-2025-RS-2025-02304828,RS-2021-II212068"],"award-info":[{"award-number":["IITP-2025-RS-2020-II201819,IITP-2025-RS-2024-00436857,RS-202400398115,IITP-2025-RS-2025-02263754,IITP-2025-RS-2025-02304828,RS-2021-II212068"]}],"id":[{"id":"10.13039\/100019635","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00797","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"8514-8523","source":"Crossref","is-referenced-by-count":1,"title":["DialNav: Multi-Turn Dialog Navigation with a Remote Guide"],"prefix":"10.1109","author":[{"given":"Leekyeung","family":"Han","sequence":"first","affiliation":[{"name":"Korea University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyunji","family":"Min","sequence":"additional","affiliation":[{"name":"Korea University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gyeom","family":"Hwangbo","sequence":"additional","affiliation":[{"name":"University of Seoul"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonghyun","family":"Choi","sequence":"additional","affiliation":[{"name":"Seoul National University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul Hongsuck","family":"Seo","sequence":"additional","affiliation":[{"name":"Korea University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref2","first-page":"1384","article-title":"The robotslang benchmark: Dialog-guided robot localization and navigation","volume-title":"Conference on Robot Learning","author":"Banerjee","year":"2021"},{"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":"10.1007\/978-3-031-19842-7_37"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i03.5627"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00008"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2003.1238654"},{"key":"ref9","author":"de Vries","year":"2018","journal-title":"Talk the walk: Navigating new york city through grounded dialogue"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.190"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.915"},{"key":"ref12","article-title":"Speaker-follower models for vision-and-language navigation","volume":"31","author":"Fried","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3193254"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.aacl-short.36"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.59"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01315"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1181"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.106"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01560"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1537"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1063"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01281"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20097"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN57019.2023.10309343"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"ref28","article-title":"Rmm: A recursive mental model for dialog navigation","author":"Roman Roman","year":"2020","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1180"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1218"},{"key":"ref31","first-page":"394","article-title":"Vision-and-dialog navigation","volume-title":"Conference on Robot Learning","author":"Thomason","year":"2020"},{"key":"ref32","author":"Touvron","year":"2023","journal-title":"Llama 2: Open foundation and fine-tuned chat models"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01503"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01246"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01499"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01826"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01103"},{"key":"ref38","author":"Yan","year":"2024","journal-title":"Instrugen: Automatic instruction generation for vision-and-language navigation via large multimodal models"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01196"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01250"},{"key":"ref41","article-title":"Multimodal text style transfer for outdoor vision-and-language navigation","author":"Zhu","year":"2020","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00162"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445960.pdf?arnumber=11445960","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:05:02Z","timestamp":1777611902000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445960\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00797","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}