{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:03:02Z","timestamp":1777888982187,"version":"3.51.4"},"reference-count":45,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02378","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"25639-25648","source":"Crossref","is-referenced-by-count":0,"title":["Semantic-Guided Camera Ray Regression for Visual Localization"],"prefix":"10.1109","author":[{"given":"Yesheng","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Automation and Intelligent Sensing, Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Automation and Intelligent Sensing, Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_40"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00762"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3070754"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00488"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3487503"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01953"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref8","article-title":"Vision transformers need registers","volume-title":"In The Twelfth International Conference on Learning Representations","author":"Darcet"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01085"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/358669.358692"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73113-6_19"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511811685"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01672"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01077"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487679"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.694"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.336"},{"key":"ref18","article-title":"Unleashing the power of data synthesis in visual localization","volume-title":"arXiv preprint","author":"Li","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01616"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73404-5_17"},{"key":"ref21","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019","journal-title":"ICLR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ITNEC60942.2024.10733333"},{"key":"ref23","article-title":"Matrix3d: Large photogrammetry model all-inone","author":"Lu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01556"},{"key":"ref26","author":"Oquab","year":"2023","journal-title":"Dinov2: Learning robust visual features without supervision"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73661-2_4"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01476"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01300"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00326"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33718-5_54"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2611662"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00261"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00273"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1117\/12.2520589"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00564"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00881"},{"key":"ref40","first-page":"7537","article-title":"Fourier features let networks learn high frequency functions in low dimensional domains","volume":"33","author":"Tancik","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02037"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02047"},{"key":"ref43","article-title":"se(3) equivariant ray embeddings for implicit multi-view depth estimation","volume-title":"In The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Xu"},{"key":"ref44","article-title":"Cameras as rays: Pose estimation via ray diffusion","volume-title":"In International Conference on Learning Representations (ICLR)","author":"Zhang","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01911"}],"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\/11445429.pdf?arnumber=11445429","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:04:21Z","timestamp":1777611861000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445429\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02378","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}