{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:23:50Z","timestamp":1777890230246,"version":"3.51.4"},"reference-count":67,"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\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2022ZD0160305"],"award-info":[{"award-number":["2022ZD0160305"]}],"id":[{"id":"10.13039\/501100012166","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\/iccv51701.2025.00322","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"3367-3377","source":"Crossref","is-referenced-by-count":0,"title":["AutoOcc: Automatic Open-Ended Semantic Occupancy Annotation via Vision-Language Guided Gaussian Splatting"],"prefix":"10.1109","author":[{"given":"Xiaoyu","family":"Zhou","sequence":"first","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingqi","family":"Wang","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongtao","family":"Wang","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yufei","family":"Wei","sequence":"additional","affiliation":[{"name":"Chongqing Changan Automobile Co., Ltd"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nan","family":"Dong","sequence":"additional","affiliation":[{"name":"Chongqing Changan Automobile Co., Ltd"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming-Hsuan","family":"Yang","sequence":"additional","affiliation":[{"name":"University of California,Merced"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.385"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00939"},{"key":"ref3","article-title":"Langocc: Self-supervised open vocabulary occupancy estimation via volume rendering","author":"Boeder","year":"2024","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Occflownet: Towards self-supervised occupancy estimation via differentiable rendering and occupancy flow","author":"Boeder","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00396"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01439"},{"key":"ref7","first-page":"13086","article-title":"Seal: Selfsupervised embodied active learning using exploration and 3d consistency","volume-title":"NIPS","volume":"34","author":"Singh Chaplot","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02076"},{"key":"ref9","article-title":"Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks","volume-title":"CVPR","author":"Chen","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.264"},{"key":"ref12","article-title":"Dy-namic 3d gaussian fields for urban areas","author":"Fischer","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Gaussianocc: Fully self-supervised and efficient 3d occupancy estimation with gaussian splatting","volume-title":"arXiv e-prints","author":"Gan","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3403134"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160831"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00890"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01885"},{"key":"ref18","article-title":"Segment anything in high quality","volume-title":"NIPS","volume":"36","author":"Ke","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref21","article-title":"F-vlm: Open-vocabulary object detection upon frozen vision and language models","author":"Kuo","year":"2022","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref23","first-page":"18442","article-title":"Unifying voxel-based representation with transformer for 3d object detection","volume-title":"NIPS","volume":"35","author":"Li","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00119"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3414835"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref27","article-title":"Fb-occ: 3d occupancy prediction based on forward-backward view transformation","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01324"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2223"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref32","first-page":"1610","article-title":"Ovir-3d: Open-vocabulary 3d instance retrieval without training on 3d data","volume-title":"Conference on Robot Learning","author":"Lu","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02103"},{"key":"ref34","article-title":"Uniocc: Unifying vision-centric 3d occupancy prediction with geometric and semantic rendering","author":"Pan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611537"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00963"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01895"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_24"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01437-z"},{"key":"ref40","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"Grounded sam: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","first-page":"1757","article-title":"Toward open set recognition","volume-title":"TPAMI","author":"Scheirer","year":"2012"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73030-6_5"},{"key":"ref44","article-title":"Ovo: Open-vocabulary occupancy","author":"Tan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32793"},{"key":"ref46","article-title":"Occ3d: A large-scale 3d occupancy prediction benchmark for autonomous driving","volume-title":"NIPS","volume":"36","author":"Tian","year":"2024"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00772"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636333"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01636"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01624"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01986"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3361862"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.370"},{"key":"ref54","article-title":"Sampro3d: Locating sam prompts in 3d for zero-shot scene segmentation","author":"Xu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref56","article-title":"Flashocc: Fast and memory-efficient occupancy prediction via channel-to-height plugin","author":"Yu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01839"},{"key":"ref58","article-title":"Faster segment anything: Towards lightweight sam for mobile applications","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref59","first-page":"arXiv-2312","article-title":"Occnerf: Selfsupervised multi-camera occupancy prediction with neural radiance fields","author":"Zhang","year":"2023","journal-title":"arXiv e-prints"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-023-3943-6"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00100"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00865"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3277281"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2020.2966034"},{"key":"ref65","article-title":"Fast segment anything","author":"Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref66","first-page":"92","article-title":"Veon: Vocabularyenhanced occupancy prediction","volume-title":"ECCV","author":"Zheng","year":"2025"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02044"}],"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\/11445202.pdf?arnumber=11445202","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:31:41Z","timestamp":1777613501000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445202\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00322","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}