{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T05:34:11Z","timestamp":1772861651688,"version":"3.50.1"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"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":["62101290"],"award-info":[{"award-number":["62101290"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Major Key Project of PCL","doi-asserted-by":"publisher","award":["PCL2023A10-1"],"award-info":[{"award-number":["PCL2023A10-1"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tcsvt.2024.3439737","type":"journal-article","created":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T18:00:36Z","timestamp":1723053636000},"page":"12923-12936","source":"Crossref","is-referenced-by-count":17,"title":["OV-NeRF: Open-Vocabulary Neural Radiance Fields With Vision and Language Foundation Models for 3D Semantic Understanding"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5714-1926","authenticated-orcid":false,"given":"Guibiao","family":"Liao","sequence":"first","affiliation":[{"name":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China"}]},{"given":"Kaichen","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Oxford, Oxfordshire, Oxford, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1368-9364","authenticated-orcid":false,"given":"Zhenyu","family":"Bao","sequence":"additional","affiliation":[{"name":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6293-5464","authenticated-orcid":false,"given":"Kanglin","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Oxford, Oxfordshire, Oxford, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7816-9733","authenticated-orcid":false,"given":"Qing","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Oxford, Oxfordshire, Oxford, U.K."}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01804"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_20"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"ref6","article-title":"NeRF: Neural radiance field in 3D vision, a comprehensive review","author":"Gao","year":"2022","journal-title":"arXiv:2210.00379"},{"key":"ref7","first-page":"69532","article-title":"DynPoint: Dynamic neural point for view synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhou"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3300170"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3385360"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00494"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.2972974"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.066"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3079991"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3239541"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3273546"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01554"},{"key":"ref18","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":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref20","article-title":"Language-driven semantic segmentation","author":"Li","year":"2022","journal-title":"arXiv:2201.03546"},{"key":"ref21","first-page":"32215","article-title":"Convolutions die hard: Open-vocabulary segmentation with single frozen convolutional clip","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yu"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"ref24","article-title":"CLIPSelf: Vision transformer distills itself for open-vocabulary dense prediction","author":"Wu","year":"2023","journal-title":"arXiv:2310.01403"},{"key":"ref25","first-page":"23033","article-title":"SegCLIP: Patch aggregation with learnable centers for open-vocabulary semantic segmentation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Luo"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00100"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01807"},{"key":"ref30","first-page":"53433","article-title":"Weakly supervised 3D open-vocabulary segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref32","article-title":"The replica dataset: A digital replica of indoor spaces","author":"Straub","year":"2019","journal-title":"arXiv:1906.05797"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00581"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01786"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3202503"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3247082"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263464"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3305295"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/BF02310791"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00056"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref45","article-title":"NeRF-SOS: Any-view self-supervised object segmentation on complex scenes","author":"Fan","year":"2022","journal-title":"arXiv:2209.08776"},{"key":"ref46","first-page":"23311","article-title":"Decomposing NeRF for editing via feature field distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Kobayashi"},{"key":"ref47","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Alayrac"},{"key":"ref48","article-title":"Segment and track anything","author":"Cheng","year":"2023","journal-title":"arXiv:2305.06558"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-44824-z"},{"key":"ref50","first-page":"29914","article-title":"Segment anything in high quality","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ke"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3054739"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10811783\/10630553.pdf?arnumber=10630553","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,13]],"date-time":"2025-01-13T20:19:19Z","timestamp":1736799559000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10630553\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":52,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3439737","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}