{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T03:59:07Z","timestamp":1778903947433,"version":"3.51.4"},"reference-count":90,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00864","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"9252-9262","source":"Crossref","is-referenced-by-count":3,"title":["3D Gaussian Map with Open-Set Semantic Grouping for Vision-Language Navigation"],"prefix":"10.1109","author":[{"given":"Jianzhe","family":"Gao","sequence":"first","affiliation":[{"name":"Zhejiang University,The State Key Lab of Brain-Machine Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Liu","sequence":"additional","affiliation":[{"name":"Zhejiang University,The State Key Lab of Brain-Machine Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenguan","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University,The State Key Lab of Brain-Machine Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Bevbert: Multimodal map pre-training for language-guided navigation","author":"An","year":"2023","journal-title":"ICCV"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3386695"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.170"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref6","article-title":"Object goal navigation using goal-oriented semantic exploration","author":"Singh Chaplot","year":"2020","journal-title":"NeurIPS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01289"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01840"},{"key":"ref9","article-title":"A survey on 3d gaussian splatting","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2078"},{"key":"ref11","article-title":"Weaklysupervised multi-granularity map learning for vision-andlanguage navigation","author":"Chen","year":"2022","journal-title":"NeurIPS"},{"key":"ref12","article-title":"History aware multimodal transformer for vision-and-language navigation","author":"Chen","year":"2021","journal-title":"NeurIPS"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref16","article-title":"Evolving graphical planner: Contextual global planning for vision-and-language navigation","author":"Deng","year":"2020","journal-title":"NeurIPS"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01404"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1232"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01547"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_21"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00647"},{"key":"ref22","article-title":"Speaker-follower models for vision-and-language navigation","author":"Fried","year":"2018","journal-title":"NeurIPS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00042"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00566"},{"issue":"2","key":"ref25","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2023.3326851","article-title":"Room-object entity prompting and reasoning for embodied referring expression","volume":"46","author":"Gao","year":"2023","journal-title":"IEEE TPAMI"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01502"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00166"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00497"},{"key":"ref29","article-title":"Language and visual entity relationship graph for agent navigation","author":"Hong","year":"2020","journal-title":"NeurIPS"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00169"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00284"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1181"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01866"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00709"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02018"},{"key":"ref36","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019","journal-title":"NAACL"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref38","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015","journal-title":"ICLR"},{"key":"ref39","article-title":"Controllable navigation instruction generation with chain of thought prompting","author":"Kong","year":"2024","journal-title":"ECCV"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00878"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01497"},{"key":"ref42","article-title":"3d neural scene representations for visuomotor control","author":"Li","year":"2022","journal-title":"CoRL"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00877"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00623"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00696"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00167"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01007"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3436"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01544"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00572"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref52","article-title":"Soat: A scene-and object-aware transformer for vision-and-language navigation","author":"Moudgil","year":"2021","journal-title":"NeurIPS"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_30"},{"key":"ref54","article-title":"Neural map: Structured memory for deep reinforcement learning","author":"Parisotto","year":"2018","journal-title":"ICLR"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01018"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01498"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2021.3058599"},{"key":"ref59","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_24"},{"key":"ref61","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref62","author":"Ross","year":"2011","journal-title":"Gordon"},{"issue":"7","key":"ref63","first-page":"1757","article-title":"Toward open set recognition","volume":"35","author":"Walter","year":"2012","journal-title":"IEEE TPAMI"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00510"},{"key":"ref65","article-title":"Snerl: Semantic-aware neural radiance fields for reinforcement learning","author":"Shim","year":"2023","journal-title":"ICML"},{"key":"ref66","article-title":"Sequence to sequence learning with neural networks","author":"Sutskever","year":"2014","journal-title":"NeurIPS"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_19"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00835"},{"key":"ref70","article-title":"Towards versatile embodied navigation","author":"Wang","year":"2022","journal-title":"NeurIPS"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01503"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00998"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01721-6"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00679"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01826"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref77","article-title":"Gridmm: Grid memory map for vision-andlanguage navigation","author":"Wang","year":"2023","journal-title":"ICCV"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01305"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00921"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01893"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_10"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3286184"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548281"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01554"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73464-9_9"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00546"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00651"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02016"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02048"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01003"}],"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\/11445640.pdf?arnumber=11445640","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:56:40Z","timestamp":1777611400000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445640\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":90,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00864","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}