{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:31Z","timestamp":1777865371437,"version":"3.51.4"},"reference-count":55,"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":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376222"],"award-info":[{"award-number":["62376222"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010097","name":"CAST","doi-asserted-by":"publisher","award":["2023QNRC001"],"award-info":[{"award-number":["2023QNRC001"]}],"id":[{"id":"10.13039\/100010097","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\/iccv51701.2025.00661","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"7037-7047","source":"Crossref","is-referenced-by-count":0,"title":["Open-Vocabulary Octree-Graph for 3D Scene Understanding"],"prefix":"10.1109","author":[{"given":"Zhigang","family":"Wang","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifei","family":"Su","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenhui","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuelong","family":"Li","sequence":"additional","affiliation":[{"name":"TeleAI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_25"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3511401"},{"key":"ref4","article-title":"Lowis3d: Language-driven open-world instance-level 3d scene understanding","author":"Ding","year":"2023","journal-title":"CoRR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00677"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref7","article-title":"Conceptgraphs: Open-vocabulary 3d scene graphs for perception and planning","author":"Gu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","volume-title":"The Tenth International Conference on Learning Representations, ICLR 2022","author":"Gu","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSSC.1968.300136"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01868"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-012-9321-0"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_10"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00689"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.066"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02011"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01807"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00098"},{"key":"ref20","article-title":"Language-driven semantic segmentation","volume-title":"The Tenth International Conference on Learning Representations, ICLR 2022","author":"Li","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00594"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref23","article-title":"Beyond bare queries: Openvocabulary object retrieval with 3d scene graph","author":"Linok","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref25","article-title":"Ovir-3d: Open-vocabulary 3d instance retrieval without training on 3d data","volume-title":"7th Annual Conference on Robot Learning","author":"Lu","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2528"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3451395"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00385"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_19"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00374"},{"key":"ref33","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML","author":"Radford","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00549"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_8"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_8"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3068335"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160590"},{"key":"ref39","article-title":"The replica dataset: A digital replica of indoor spaces","author":"Straub","year":"2019","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2989"},{"key":"ref41","first-page":"944","article-title":"Integrating grid-based and topological maps for mobile robot navigation","volume-title":"Proceedings of the Thirteenth National Conference on Artificial Intelligence and Eighth Innovative Applications of Artificial Intelligence Conference, AAAI 96, IAAI 96","volume":"2","author":"Thrun"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01302"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02254"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.077"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00477"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610193"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02671"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01874"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3257"},{"key":"ref51","article-title":"Sam3d: Segment anything in 3d scenes","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/7682201"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00317"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00570"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00645"}],"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\/11444976.pdf?arnumber=11444976","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:21:53Z","timestamp":1777530113000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444976\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00661","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}