{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T06:01:41Z","timestamp":1779948101326,"version":"3.53.1"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:00:00Z","timestamp":1773964800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:00:00Z","timestamp":1773964800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,20]]},"DOI":"10.1109\/3dv69130.2026.00163","type":"proceedings-article","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T19:40:49Z","timestamp":1779910849000},"page":"1717-1727","source":"Crossref","is-referenced-by-count":0,"title":["GALA: Guided Attention with Language Alignment for Open Vocabulary Gaussian Splatting"],"prefix":"10.1109","author":[{"given":"Elena","family":"Alegret","sequence":"first","affiliation":[{"name":"Technical University of Munich"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kunyi","family":"Li","sequence":"additional","affiliation":[{"name":"Technical University of Munich"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sen","family":"Wang","sequence":"additional","affiliation":[{"name":"Technical University of Munich"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siyun","family":"Liang","sequence":"additional","affiliation":[{"name":"Technical University of Munich"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Niemeyer","sequence":"additional","affiliation":[{"name":"Google"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefano","family":"Gasperini","sequence":"additional","affiliation":[{"name":"Technical University of Munich"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nassir","family":"Navab","sequence":"additional","affiliation":[{"name":"Technical University of Munich"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Federico","family":"Tombari","sequence":"additional","affiliation":[{"name":"Technical University of Munich"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1130"},{"key":"ref5","article-title":"Scenear: Learning to reconstruct 3d indoor scenes for augmented reality","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Chen","year":"2023"},{"key":"ref6","article-title":"Occam\u2019s lgs: An efficient approach for language gaussian splatting","author":"Cheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657428"},{"key":"ref10","article-title":"Visual language maps for robot navigation","author":"Huang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241229725"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01319"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01807"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02034"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3538496"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01314"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10803056"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72761-0_25"},{"key":"ref21","article-title":"Supergseg: Open-vocabulary 3d segmentation with structured super-gaussians","author":"Liang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01952"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3451395"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/3DV66043.2025.00018"},{"key":"ref28","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Transactions on Machine Learning Research Journal"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i10.37787"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01895"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680852"},{"key":"ref33","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":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.chb.2022.107289"},{"key":"ref35","article-title":"Grounded sam: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01253"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00510"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00919"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_4"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01397"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0604"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00536"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_10"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01948"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01839"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02048"}],"event":{"name":"2026 International Conference on 3D Vision (3DV)","location":"Vancouver, BC, Canada","start":{"date-parts":[[2026,3,20]]},"end":{"date-parts":[[2026,3,23]]}},"container-title":["2026 International Conference on 3D Vision (3DV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11533157\/11533158\/11533233.pdf?arnumber=11533233","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T05:01:56Z","timestamp":1779944516000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11533233\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,20]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/3dv69130.2026.00163","relation":{},"subject":[],"published":{"date-parts":[[2026,3,20]]}}}