{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:32:09Z","timestamp":1777865529556,"version":"3.51.4"},"reference-count":70,"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\/501100001827","name":"University of Amsterdam","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001827","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\/iccv51701.2025.00472","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"4961-4972","source":"Crossref","is-referenced-by-count":0,"title":["SceneSplat: Gaussian Splatting-Based Scene Understanding with Vision-Language Pretraining"],"prefix":"10.1109","author":[{"given":"Yue","family":"Li","sequence":"first","affiliation":[{"name":"University of Amsterdam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Ma","sequence":"additional","affiliation":[{"name":"ETH Zürich"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Runyi","family":"Yang","sequence":"additional","affiliation":[{"name":"Sofia University “St. Kliment Ohridski”,INSAIT"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huapeng","family":"Li","sequence":"additional","affiliation":[{"name":"ETH Zürich"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengjiao","family":"Ma","sequence":"additional","affiliation":[{"name":"Sofia University “St. Kliment Ohridski”,INSAIT"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Ren","sequence":"additional","affiliation":[{"name":"Sofia University “St. Kliment Ohridski”,INSAIT"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nikola","family":"Popovic","sequence":"additional","affiliation":[{"name":"Sofia University “St. Kliment Ohridski”,INSAIT"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicu","family":"Sebe","sequence":"additional","affiliation":[{"name":"University of Trento"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ender","family":"Konukoglu","sequence":"additional","affiliation":[{"name":"ETH Zürich"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Theo","family":"Gevers","sequence":"additional","affiliation":[{"name":"University of Amsterdam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luc","family":"Van Gool","sequence":"additional","affiliation":[{"name":"Sofia University “St. Kliment Ohridski”,INSAIT"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin R.","family":"Oswald","sequence":"additional","affiliation":[{"name":"University of Amsterdam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Danda Pani","family":"Paudel","sequence":"additional","affiliation":[{"name":"Sofia University “St. Kliment Ohridski”,INSAIT"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Arkitscenes: A diverse real-world dataset for 3d indoor scene understanding using mobile rgb-d data","author":"Baruch","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref2","article-title":"Matterport3d: Learning from \\operatorname{rgb}-{d} data in indoor environments","author":"Chang","year":"2017","journal-title":"arXiv preprint arXiv"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref4","article-title":"Occam\u2019s lgs: A simple approach for language gaussian splatting","author":"Cheng","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref6","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00677"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00677"},{"key":"ref9","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations (ICLR)","author":"Dosovitskiy","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2026.3675320"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW58289.2023.00039"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73223-2_24"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72673-6_16"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02011"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01807"},{"key":"ref18","first-page":"80965","article-title":"3d gaussian splatting as markov chain monte carlo","volume":"37","author":"Kheradmand","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","volume-title":"Auto-encoding variational bayes","author":"Kingma","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01315"},{"key":"ref22","article-title":"Pointcnn: Convolution on x-transformed points","author":"Li","year":"2018","journal-title":"Advances in neural information processing systems, 31"},{"key":"ref23","volume-title":"Neural manifold clustering and embedding","author":"Li","year":"2022"},{"key":"ref24","first-page":"32653","article-title":"Pointmamba: A simple state space model for point cloud analysis","volume":"37","author":"Liang","year":"2025","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_3"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00019"},{"key":"ref28","volume-title":"Implicit-zoo: A large-scale dataset of neural implicit functions for 2d images and 3d scenes","author":"Ma","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802241"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73242-3_8"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref32","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref35","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":"ref36","first-page":"28223","article-title":"Contrast with reconstruct: Contrastive 3d representation learning guided by generative pretraining","volume-title":"International Conference on Machine Learning","author":"Qi","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01895"},{"key":"ref38","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":"ref39","article-title":"Language embedded radiance fields for zero-shot task-oriented grasping","volume-title":"7th Annual Conference on Robot Learning","author":"Rashid","year":"2023"},{"key":"ref40","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01952"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-0963-5_4"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01073"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_8"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00510"},{"key":"ref46","article-title":"The replica dataset: A digital replica of indoor spaces","author":"Straub","year":"2019","journal-title":"arXiv preprint arXiv"},{"key":"ref47","article-title":"Siglip 2: Multilingual vision-language encoders with improved semantic understanding, localization, and dense features","author":"Tschannen","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref48","volume-title":"Attention is all you need","author":"Vaswani","year":"2023"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00775"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2415"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00463"},{"key":"ref52","article-title":"Simplifying dino via coding rate regularization","author":"Wu","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01874"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.26599\/cvm.2025.9450383"},{"issue":"34","key":"ref56","first-page":"1","article-title":"gsplat: An open-source library for gaussian splatting","volume":"26","author":"Ye","year":"2025","journal-title":"Journal of Machine Learning Research"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01839"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02664"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3789201"},{"key":"ref62","article-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1962"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00836"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_30"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3432348"},{"key":"ref68","volume-title":"ibot: Image bert pre-training with online tokenizer","author":"Zhou"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02048"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00249"}],"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\/11445351.pdf?arnumber=11445351","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:46:44Z","timestamp":1777531604000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445351\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00472","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}