{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T14:18:43Z","timestamp":1784211523395,"version":"3.55.0"},"reference-count":73,"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\/icra55743.2025.11128467","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"10607-10615","source":"Crossref","is-referenced-by-count":3,"title":["Na Vid-4D: Unleashing Spatial Intelligence in Egocentric RGB-D Videos for Vision-and-Language Navigation"],"prefix":"10.1109","author":[{"given":"Haoran","family":"Liu","sequence":"first","affiliation":[{"name":"School of Computer Science, Peking University,CFCS"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weikang","family":"Wan","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University,CFCS"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiqian","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minghan","family":"Li","sequence":"additional","affiliation":[{"name":"Galbot"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiazhao","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University,CFCS"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Zhao","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhibo","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Academy of Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhizheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Galbot"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"He","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University,CFCS"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref3","first-page":"671","article-title":"Sim-to-real transfer for vision-and-language navigation","volume-title":"Conference on Robot Learning","author":"Anderson","year":"2021"},{"key":"ref4","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":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref6","article-title":"Spatialbot: Precise spatial understanding with vision language models","author":"Cai","year":"2024","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01112"},{"key":"ref10","first-page":"38 149","article-title":"Weakly-supervised multi-granularity map learning for vision-and-language navigation","volume":"35","author":"Chen","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","article-title":"A2 Nav: Action-aware zero-shot robot navigation by exploiting vision-and-language ability of foun-dation models","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref12","first-page":"5834","article-title":"History aware multimodal transformer for vision-and-language navi-gation","volume":"34","author":"Chen","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref14","article-title":"Spatialrgpt: Grounded spatial reasoning in vision language model","author":"Cheng","year":"2024","journal-title":"arXiv preprint"},{"issue":"3","key":"ref15","first-page":"6","volume-title":"Vicuna: An open-source chat-bot impressing gpt-4 with 90%* chatgpt quality","volume":"2","author":"Chiang","year":"2023"},{"key":"ref16","article-title":"Instructblip: Towards general-purpose vision-language models with instruction tuning","volume":"36","author":"Dai","year":"2024","journal-title":"Advances in N eu-ral Information Processing Systems"},{"key":"ref17","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73337-6_9"},{"key":"ref19","article-title":"Threedworld: A platform for inter-active multi-modal physical simulation","author":"Gan","year":"2020","journal-title":"arXiv p rep rint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3193254"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01502"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.524"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610243"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TSSC.1968.300136"},{"key":"ref26","article-title":"Efficient multimodal learning from data-centric perspective","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01500"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00169"},{"key":"ref29","first-page":"20482","article-title":"3d-llm: Injecting the 3d world into large language models","volume":"36","author":"Hong","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3444912"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"ref32","article-title":"An embodied generalist agent in 3d world","author":"Huang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00690"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1002\/spe.4380210803"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01488"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_34"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01433"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"issue":"1908","key":"ref42","article-title":"Visualbert: A simple and perform ant baseline for vision and language. arxiv 2019","volume":"3","author":"Li","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref44","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref45","article-title":"Self-monitoring navigation agent via auxil-iary progress estimation","author":"Ma","year":"2019","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abm6074"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01560"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00156"},{"key":"ref50","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":"ref51","article-title":"Langnav: Language as a perceptual repre-sentation for navigation","author":"Pan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00168"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_18"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"ref55","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":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.328"},{"key":"ref57","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proceedings of the fourteenth international conference on artificial intelligence and statistics, JMLR Workshop and Conference Proceedings","author":"Ross","year":"2011"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"ref60","first-page":"492","article-title":"Lm-nav: Robotic navigation with large pre-trained models of language, vision, and action","volume-title":"Conference on robot learning","author":"Shah","year":"2023"},{"key":"ref61","volume-title":"Sharegpt","year":"2023"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01075"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_44"},{"key":"ref64","article-title":"Eva-clip: Improved training techniques for clip at scale","author":"Sun","year":"2023","journal-title":"arXiv preprint"},{"key":"ref65","first-page":"394","article-title":"Vision-and-dialog navigation","volume-title":"Conference on Robot Learning","author":"Thomason","year":"2020"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"ref67","article-title":"Chat-3d: Data-efficiently tuning large language model for univer-sal dialogue of 3d scenes","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref68","article-title":"Sim-to-real transfer via 3d feature fields for vision-and-language navigation","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01103"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.915"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00645"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.079"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28597"}],"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\/11128467.pdf?arnumber=11128467","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:07:48Z","timestamp":1756879668000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128467\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128467","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}