{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:14:12Z","timestamp":1777889652399,"version":"3.51.4"},"reference-count":54,"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\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62206315,92470202,U21A20471"],"award-info":[{"award-number":["62206315,92470202,U21A20471"]}],"id":[{"id":"10.13039\/501100001809","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\/iccv51701.2025.00884","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"9477-9486","source":"Crossref","is-referenced-by-count":0,"title":["monoVLN: Bridging the Observation Gap between Monocular and Panoramic Vision and Language Navigation"],"prefix":"10.1109","author":[{"given":"Renjie","family":"Lu","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Cheng","sequence":"additional","affiliation":[{"name":"Hunan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingke","family":"Meng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei-Shi","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475282"},{"key":"ref2","article-title":"Bevbert: Multimodal map pre-training for language-guided navigation","author":"An","year":"2023","journal-title":"ICCV"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3386695"},{"key":"ref4","article-title":"Chang, Devendra Singh Chaplot, Alexey Dosovitskiy, Saurabh Gupta, Vladlen Koltun, Jana Kosecka, Jitendra Malik, Roozbeh Mottaghi, Manolis Savva, and Amir R","author":"Anderson","year":"2018","journal-title":"Zamir. On evaluation of embodied navigation agents. CoRR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref6","article-title":"Sim-to-real transfer for vision-and-language navigation","author":"Anderson","year":"2020","journal-title":"CoRL"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01112"},{"key":"ref9","article-title":"Weaklysupervised multi-granularity map learning for vision-andlanguage navigation","author":"Chen","year":"2022","journal-title":"NeurIPS"},{"key":"ref10","article-title":"History aware multimodal transformer for vision-and-language navigation","author":"Chen","year":"2021","journal-title":"NeurIPS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref12","article-title":"An image is worth $16\\times 16$ words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref13","article-title":"Speaker-follower models for vision-and-language navigation","author":"Fried","year":"2018","journal-title":"NeurIPS"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01432"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01502"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00166"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01315"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0193"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00169"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01500"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"ref23","article-title":"General evaluation for instruction conditioned navigation using dynamic time warping","volume-title":"NeurIPS Workshop","author":"Ilharco","year":"2019"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01041"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00690"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_34"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01488"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01497"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00167"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01544"},{"key":"ref33","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019","journal-title":"I C L R"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72848-8_5"},{"key":"ref35","article-title":"Selfmonitoring navigation agent via auxiliary progress estimation","author":"Ma","year":"2019","journal-title":"ICLR"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_16"},{"key":"ref37","author":"Oquab","year":"2023","journal-title":"Dinov2: Learning robust visual features without supervision. CoRR"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01498"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3234243"},{"key":"ref40","article-title":"Habitat-matterport 3d dataset (HM3D): 1000 large-scale 3d environments for embodied AI","author":"Kumar Ramakrishnan","year":"2021","journal-title":"NeurIPS"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.328"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00835"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01499"},{"key":"ref46","article-title":"g3d-lf: Generalizable 3dlanguage feature fields for embodied tasks","author":"Wang","year":"2024","journal-title":"CoRR"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01103"},{"key":"ref48","article-title":"Bootstrapping language-guided navigation learning with self-refining data flywheel","author":"Wang","year":"2024","journal-title":"CoRR"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01305"},{"key":"ref50","article-title":"Sim-to-real transfer via 3d feature fields for vision-and-language navigation","author":"Wang","year":"2024","journal-title":"CoRL"},{"key":"ref51","article-title":"Faster segment anything: Towards lightweight sam for mobile applications","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.079"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02048"},{"key":"ref54","article-title":"Objects as points","author":"Zhou","year":"2019","journal-title":"CoRR"}],"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\/11445895.pdf?arnumber=11445895","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:15:11Z","timestamp":1777612511000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445895\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00884","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}