{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T16:32:42Z","timestamp":1790353962366,"version":"4.1.0"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"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":"crossref","award":["62525309"],"award-info":[{"award-number":["62525309"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Zhejiang Key Laboratory of Advanced Intelligent Warehousing and Logistics Equipment","award":["2024E10007"],"award-info":[{"award-number":["2024E10007"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1109\/tcsvt.2026.3680794","type":"journal-article","created":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T19:55:41Z","timestamp":1775246141000},"page":"10943-10956","source":"Crossref","is-referenced-by-count":3,"title":["Open-Vocabulary SAM3D: Towards Training-Free Open-Vocabulary 3D Scene Understanding"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5017-2977","authenticated-orcid":false,"given":"Hanchen","family":"Tai","sequence":"first","affiliation":[{"name":"Zhejiang University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3203-0071","authenticated-orcid":false,"given":"Qingdong","family":"He","sequence":"additional","affiliation":[{"name":"YouTu Lab, Tencent","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yijie","family":"Qian","sequence":"additional","affiliation":[{"name":"Zhejiang University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5764-3096","authenticated-orcid":false,"given":"Xiaobin","family":"Hu","sequence":"additional","affiliation":[{"name":"YouTu Lab, Tencent","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0550-8247","authenticated-orcid":false,"given":"Xiangtai","family":"Li","sequence":"additional","affiliation":[{"name":"TikTok","place":["(ByteDance), Singapore"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4822-8939","authenticated-orcid":false,"given":"Yong","family":"Liu","sequence":"additional","affiliation":[{"name":"Zhejiang University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8891-6766","authenticated-orcid":false,"given":"Jiangning","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NIPS","author":"Brown"},{"issue":"140","key":"ref2","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref3","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref4","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"issue":"120","key":"ref5","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref6","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3361862"},{"key":"ref8","article-title":"Emergent abilities of large language models","author":"Wei","year":"2022","journal-title":"arXiv:2206.07682"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-05881-4"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1056\/aioa2300138"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00361"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-44824-z"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3514713"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3524543"},{"key":"ref16","article-title":"SAM3D: Segment anything in 3D scenes","author":"Yang","year":"2023","journal-title":"arXiv:2306.03908"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00116"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00317"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2989"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00385"},{"key":"ref22","article-title":"Recognize anything: A strong image tagging model","author":"Zhang","year":"2023","journal-title":"arXiv:2306.03514"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_8"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3474381"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_24"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3520734"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"ref31","article-title":"Tag2Text: Guiding vision-language model via image tagging","author":"Huang","year":"2023","journal-title":"arXiv:2303.05657"},{"key":"ref32","article-title":"SAM 3: Segment anything with concepts","author":"Carion","year":"2025","journal-title":"arXiv:2511.16719"},{"key":"ref33","article-title":"SAM 3D: 3Dfy anything in images","volume-title":"arXiv:2511.16624","author":"3D Team","year":"2025"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00831"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3526680"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3205208"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3190709"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01533"},{"key":"ref40","article-title":"Segment and track anything","author":"Cheng","year":"2023","journal-title":"arXiv:2305.06558"},{"key":"ref41","article-title":"Grounded SAM: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024","journal-title":"arXiv:2401.14159"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1130"},{"key":"ref43","article-title":"PointSeg: A training-free paradigm for 3D scene segmentation via foundation models","author":"He","year":"2024","journal-title":"arXiv:2403.06403"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000022288.19776.77"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00677"},{"key":"ref46","first-page":"812","article-title":"UniM-OV3D: Uni-modality open-vocabulary 3D scene understanding with fine-grained feature representation","volume-title":"Proc. IJCAI","author":"He"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref48","article-title":"Language-driven semantic segmentation","author":"Li","year":"2022","journal-title":"arXiv:2201.03546"},{"key":"ref49","article-title":"OpenIns3D: Snap and lookup for 3D open-vocabulary instance segmentation","author":"Huang","year":"2023","journal-title":"arXiv:2309.00616"},{"key":"ref50","first-page":"37146","article-title":"Look around and refer: 2D synthetic semantics knowledge distillation for 3D visual grounding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alsaedy"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_31"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160590"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref54","first-page":"1610","article-title":"OVIR-3D: Open-vocabulary 3D instance retrieval without training on 3D data","volume-title":"Proc. Conf. Robot Learn.","author":"Lu"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11643439\/11474625.pdf?arnumber=11474625","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T19:07:00Z","timestamp":1786993620000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11474625\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":54,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3680794","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8]]}}}