{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:44:51Z","timestamp":1766061891284,"version":"3.48.0"},"reference-count":56,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","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\/iros60139.2025.11247697","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"858-865","source":"Crossref","is-referenced-by-count":0,"title":["A Coarse-to-Fine Approach to Multi-Modality 3D Occupancy Grounding"],"prefix":"10.1109","author":[{"given":"Zhan","family":"Shi","sequence":"first","affiliation":[{"name":"College of Software Technology, Zhejiang University"}]},{"given":"Song","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science, Zhejiang University,Hangzhou,China,310027"}]},{"given":"Junbo","family":"Chen","sequence":"additional","affiliation":[{"name":"Udeer.ai,Hangzhou,China,310000"}]},{"given":"Jianke","family":"Zhu","sequence":"additional","affiliation":[{"name":"College of Computer Science, Zhejiang University,Hangzhou,China,310027"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2892405"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref3","article-title":"Pop-3d: Open-vocabulary 3d occupancy prediction from images","author":"Vobecky","year":"2024","journal-title":"NeurIPS"},{"article-title":"Ovo: Open-vocabulary occupancy","year":"2023","author":"Tan","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01320"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00437"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28525"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01596"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00772"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_25"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1215"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128399"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91767-7_21"},{"key":"ref15","article-title":"Occ3d: A large-scale 3d occupancy prediction benchmark for autonomous driving","author":"Tian","year":"2024","journal-title":"NeurIPS"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.470"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00477"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2019.2911066"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00474"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00206"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00479"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859880"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01509"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6833"},{"key":"ref28","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","author":"Qi","year":"2017","journal-title":"NeurIPS"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00292"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475397"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_29"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01597"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00187"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_26"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01636"},{"article-title":"Occfusion: A straightforward and effective multi-sensor fusion framework for 3d occupancy prediction","year":"2024","author":"Ming","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IV55156.2024.10588696"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA240480"},{"key":"ref39","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"article-title":"Langocc: Self-supervised open vocabulary occupancy estimation via volume rendering","year":"2024","author":"Boeder","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2015.7280459"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01624"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref44","first-page":"2980","article-title":"Focal loss for dense object detection","author":"Ross","year":"2017","journal-title":"proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00464"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28033"},{"article-title":"Occdepth: A depth-aware method for 3d semantic scene completion","year":"2023","author":"Miao","key":"ref49"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00040"},{"article-title":"Occnerf: Self-supervised multi-camera occupancy prediction with neural radiance fields","year":"2023","author":"Zhang","key":"ref51"},{"article-title":"Deformable detr: Deformable transformers for end-to-end object detection","year":"2020","author":"Zhu","key":"ref52"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00396"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref55","article-title":"Roberta: A robustly optimized bert pretraining approach","volume":"364","author":"Liu","year":"2019"},{"article-title":"Gridmask data augmentation","year":"2020","author":"Chen","key":"ref56"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11247697.pdf?arnumber=11247697","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:40:13Z","timestamp":1766061613000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247697\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247697","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}