{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T16:01:01Z","timestamp":1784131261865,"version":"3.55.0"},"reference-count":60,"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\/iccv51701.2025.00809","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"8645-8655","source":"Crossref","is-referenced-by-count":1,"title":["AGO: Adaptive Grounding for Open World 3D Occupancy Prediction"],"prefix":"10.1109","author":[{"given":"Peizheng","family":"Li","sequence":"first","affiliation":[{"name":"Mercedes-Benz AG, Sindelfingen"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuxiao","family":"Ding","sequence":"additional","affiliation":[{"name":"Mercedes-Benz AG, Sindelfingen"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"You","family":"Zhou","sequence":"additional","affiliation":[{"name":"Mercedes-Benz AG, Sindelfingen"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingwen","family":"Zhang","sequence":"additional","affiliation":[{"name":"RPL, KTH Royal Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Onat","family":"Inak","sequence":"additional","affiliation":[{"name":"Mercedes-Benz AG, Sindelfingen"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Larissa","family":"Triess","sequence":"additional","affiliation":[{"name":"Mercedes-Benz AG, Sindelfingen"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Niklas","family":"Hanselmann","sequence":"additional","affiliation":[{"name":"Mercedes-Benz AG, Sindelfingen"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marius","family":"Cordts","sequence":"additional","affiliation":[{"name":"Mercedes-Benz AG, Sindelfingen"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Zell","sequence":"additional","affiliation":[{"name":"University of Tübingen"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s41064-024-00308-9"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00464"},{"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\/CVPR42600.2020.01164"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00396"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00861"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"ref10","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MFI49285.2020.9235240"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IV48863.2021.9575694"},{"key":"ref13","article-title":"Featup: A modelagnostic framework for features at any resolution","author":"Fu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"A simple attempt for 3d occupancy estimation in autonomous driving","author":"Gan","year":"2023","journal-title":"CoRR"},{"key":"ref15","author":"Gan","year":"2024","journal-title":"Gaussianocc: Fully self-supervised and efficient 3d occupancy estimation with gaussian splatting"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","article-title":"Bevdet: High-performance multi-camera 3d object detection in bird-eye-view","author":"Huang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00890"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01885"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01117"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25185"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref24","article-title":"Visualbert: A simple and performant baseline for vision and language","author":"Harold Li","year":"2019","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/120"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00877"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA240480"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref31","article-title":"Let occ flow: Selfsupervised 3d occupancy flow prediction","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume":"32","author":"Lu","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02030"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref36","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"ref38","article-title":"Grounded sam: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/3DV50981.2020.00021"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73030-6_5"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1514"},{"key":"ref42","article-title":"Ovo: Open-vocabulary occupancy","author":"Tan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2809"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00772"},{"key":"ref45","article-title":"Pop-3d: Open-vocabulary 3d occupancy prediction from images","volume":"36","author":"Vobecky","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01624"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01986"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01692"},{"key":"ref49","article-title":"Renderworld: World model with self-supervised 3d label","author":"Yan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01161"},{"key":"ref51","first-page":"2312","article-title":"Occnerf: Selfsupervised multi-camera occupancy prediction with neural radiance fields","author":"Zhang","year":"2023","journal-title":"arXiv e-prints"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610278"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_20"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00865"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3416798"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72949-2_6"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01339"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"}],"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\/11446007.pdf?arnumber=11446007","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:57:48Z","timestamp":1777611468000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446007\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00809","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}