{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T07:38:55Z","timestamp":1780385935132,"version":"3.54.1"},"reference-count":66,"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\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2024XKRC082"],"award-info":[{"award-number":["2024XKRC082"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["92470203"],"award-info":[{"award-number":["92470203"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L242022"],"award-info":[{"award-number":["L242022"]}],"id":[{"id":"10.13039\/501100004826","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\/iccv51701.2025.00444","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"4670-4680","source":"Crossref","is-referenced-by-count":2,"title":["CLIP-GS: Unifying Vision-Language Representation with 3D Gaussian Splatting"],"prefix":"10.1109","author":[{"given":"Siyu","family":"Jiao","sequence":"first","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoye","family":"Dong","sequence":"additional","affiliation":[{"name":"National University of Singapore,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuyang","family":"Yin","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zequn","family":"Jie","sequence":"additional","affiliation":[{"name":"Meituan,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yinlong","family":"Qian","sequence":"additional","affiliation":[{"name":"Meituan,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Humphrey","family":"Shi","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunchao","family":"Wei","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1554"},{"key":"ref4","article-title":"An image is worth $16 \\times 16$ words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00684"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-021-0229-5"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681173"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32353"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-38452-7_1"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/133994.134011"},{"key":"ref11","article-title":"Semantic anything in 3d gaussians","author":"Hu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"An embodied generalist agent in 3d world","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Huang","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02025"},{"key":"ref14","article-title":"Voxposer: Composable 3d value maps for robotic manipulation with language models","author":"Huang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref15","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International Conference on Machine Learning","author":"Jia","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1549"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73414-4_23"},{"key":"ref18","article-title":"Poisson surface reconstruction","volume-title":"Proceedings of the fourth Eurographics symposium on Geometry processing","author":"Kazhdan","year":"2006"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1088\/978-1-6270-5612-0"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref22","article-title":"3dmambacomplete: Exploring structured state space model for point cloud completion","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Pointmamba: A simple state space model for point cloud analysis","author":"Liang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3519"},{"key":"ref25","article-title":"Openshape: Scaling up 3d shape representation towards open-world understanding","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/280811.281026"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3198836"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3291"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00738"},{"key":"ref34","first-page":"652","article-title":"Pointnet: Deep learning on point sets for 3d classification and segmentation","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Qi","year":"2017"},{"key":"ref35","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","volume":"30","author":"Qi","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref36","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.43"},{"key":"ref38","article-title":"Eva-clip: Improved training techniques for clip at scale","author":"Sun","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01237"},{"key":"ref40","article-title":"Dreamgaussian: Generative gaussian splatting for efficient 3d content creation","author":"Tang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00964"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01868"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28376"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3374111"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298801"},{"key":"ref47","article-title":"Embodiedsam: Online segment any 3d thing in real time","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02558"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00563"},{"key":"ref51","article-title":"Street gaussians for modeling dynamic urban scenes","author":"Yan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_10"},{"key":"ref53","article-title":"4dgen: Grounded 4d content generation with spatial-temporal consistency","author":"Yin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1962"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00836"},{"key":"ref59","article-title":"Point could mamba: Point cloud learning via state space model","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref60","article-title":"Controlvideo: Training-free controllable text-to-video generation","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680709"},{"key":"ref63","article-title":"Uni3d: Exploring unified 3d representation at scale","volume-title":"International Conference on Learning Representations (ICLR)","author":"Zhou","year":"2024"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02044"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00249"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72784-9_11"}],"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\/11444607.pdf?arnumber=11444607","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:06:49Z","timestamp":1777612009000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444607\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00444","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}