{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T16:47:50Z","timestamp":1792169270334,"version":"4.4.0"},"reference-count":80,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Natural Science Fund","award":["62025304"],"award-info":[{"award-number":["62025304"]}]},{"name":"National Natural Science Fund","award":["62120106005"],"award-info":[{"award-number":["62120106005"]}]},{"name":"Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China","award":["JYB2025XDXM109"],"award-info":[{"award-number":["JYB2025XDXM109"]}]},{"name":"State Key Laboratory of General Artificial Intelligence (BIGAI) and Tsinghua University, Beijing, China"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tcsvt.2026.3675320","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T19:41:06Z","timestamp":1773862866000},"page":"9265-9277","source":"Crossref","is-referenced-by-count":24,"title":["Semantic Gaussians: Open-Vocabulary Scene Understanding With 3D Gaussian Splatting"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6626-4135","authenticated-orcid":false,"given":"Jun","family":"Guo","sequence":"first","affiliation":[{"name":"State Key Laboratory for General Artificial Intelligence, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5609-3822","authenticated-orcid":false,"given":"Xiaojian","family":"Ma","sequence":"additional","affiliation":[{"name":"State Key Laboratory for General Artificial Intelligence, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Fan","sequence":"additional","affiliation":[{"name":"State Key Laboratory for General Artificial Intelligence, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4042-6044","authenticated-orcid":false,"given":"Huaping","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1185-5365","authenticated-orcid":false,"given":"Qing","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory for General Artificial Intelligence, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"issue":"3","key":"ref1","first-page":"91","article-title":"Multi-view image-based 3D reconstruction in indoor scenes: A survey","volume":"22","author":"Lu","year":"2024","journal-title":"ZTE Commun."},{"key":"ref2","first-page":"643","article-title":"Semantic abstraction: Open-world 3D scene understanding from 2D vision-language models","volume-title":"Proc. CoRL","author":"Ha"},{"issue":"4","key":"ref3","first-page":"3","article-title":"Perceptual quality assessment for point clouds: A survey","volume":"21","author":"Zhou","year":"2023","journal-title":"ZTE Commun."},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2989"},{"issue":"3","key":"ref6","first-page":"71","article-title":"Key techniques and challenges in NeRF-based dynamic based dynamic 3D reconstruction D reconstruction","volume":"23","author":"Lu","year":"2025","journal-title":"ZTE Commun."},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2325"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01807"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3538684"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1694"},{"key":"ref12","article-title":"NeRF-SOS: Any-view self-supervised object segmentation on complex scenes","author":"Fan","year":"2022","journal-title":"arXiv:2209.08776"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00056"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3439737"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01895"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02048"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3746284"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02183-8"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00510"},{"key":"ref20","first-page":"19114","article-title":"OpenGaussian: Towards point-level 3D Gaussian-based open vocabulary understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cheng"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/3dv69130.2026.00157"},{"key":"ref22","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":"ref23","article-title":"Language-driven semantic segmentation","volume-title":"Proc. ICLR","author":"Li"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01417"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00883"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/3dv62453.2024.00044"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01554"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00572"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00566"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01018"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3544760"},{"key":"ref37","article-title":"4D Gaussian splatting for real-time dynamic scene rendering","author":"Wu","year":"2023","journal-title":"arXiv:2310.08528"},{"key":"ref38","article-title":"Real-time photorealistic dynamic scene representation and rendering with 4D Gaussian splatting","author":"Yang","year":"2023","journal-title":"arXiv:2310.10642"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01997"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3048"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00819"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3502257"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3557012"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02022"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_19"},{"key":"ref46","article-title":"DreamGaussian: Generative Gaussian splatting for efficient 3D content creation","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Tang"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00623"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00635"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3511342"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3540969"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref52","first-page":"23033","article-title":"SegCLIP: Patch aggregation with learnable centers for open-vocabulary semantic segmentation","volume-title":"Proc. ICML","author":"Luo"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02717"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.066"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00677"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00219"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00873"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0399"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref60","first-page":"22456","article-title":"ReferSplat: Referring segmentation in 3D Gaussian splatting","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"He"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3757377.3763926"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680852"},{"key":"ref63","article-title":"3D vision-language Gaussian splatting","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Peng"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/VISUAL.2001.964490"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref67","article-title":"Grounding DINO: Marrying DINO with grounded pre-training for open-set object detection","author":"Liu","year":"2023","journal-title":"arXiv:2303.05499"},{"key":"ref68","article-title":"Grounded SAM: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024","journal-title":"arXiv:2401.14159"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.381"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3354624"},{"key":"ref72","article-title":"LangSplatV2: High-dimensional 3D language Gaussian splatting with 450+ FPS","author":"Li","year":"2025","journal-title":"arXiv:2507.07136"},{"key":"ref73","article-title":"Spacetime Gaussian feature splatting for real-time dynamic view synthesis","author":"Li","year":"2023","journal-title":"arXiv:2312.16812"},{"key":"ref74","article-title":"Gaussian grouping: Segment and edit anything in 3D scenes","author":"Ye","year":"2023","journal-title":"arXiv:2312.00732"},{"key":"ref75","article-title":"Semantic anything in 3D Gaussians","author":"Hu","year":"2024","journal-title":"arXiv:2401.17857"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i2.32193"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00127"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01975"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02029"},{"key":"ref80","article-title":"Contrastive Gaussian clustering: Weakly supervised 3D scene segmentation","author":"Silva","year":"2024","journal-title":"arXiv:2404.12784"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11598845\/11442667.pdf?arnumber=11442667","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T19:46:06Z","timestamp":1783539966000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11442667\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":80,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3675320","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}