{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T22:06:12Z","timestamp":1778537172845,"version":"3.51.4"},"reference-count":57,"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\/iccv51701.2025.02371","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"25560-25570","source":"Crossref","is-referenced-by-count":2,"title":["Uniocc: a Unified Benchmark for Occupancy Forecasting and Prediction in Autonomous Driving"],"prefix":"10.1109","author":[{"given":"Yuping","family":"Wang","sequence":"first","affiliation":[{"name":"University of California,Riverside"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangyu","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Michigan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaokang","family":"Sun","sequence":"additional","affiliation":[{"name":"University of California,Riverside"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingxuan","family":"Yan","sequence":"additional","affiliation":[{"name":"University of California,Riverside"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuo","family":"Xing","sequence":"additional","affiliation":[{"name":"Texas A&M University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengzhong","family":"Tu","sequence":"additional","affiliation":[{"name":"Texas A&M University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiachen","family":"Li","sequence":"additional","affiliation":[{"name":"University of California,Riverside"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01373"},{"key":"ref2","article-title":"Dynamiccity: Large-scale occupancy generation from dynamic scenes","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Bian"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref4","article-title":"Covis: A collaborative framework for fine-grained graphic visual understanding","author":"Deng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","first-page":"1","article-title":"Carla: An open urban driving simulator","volume-title":"Conference on robot learning","author":"Dosovitskiy"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73254-6_7"},{"key":"ref7","article-title":"Airv2x: Unified air-ground vehicle-toeverything collaboration","author":"Gao","year":"2025","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00406"},{"key":"ref9","article-title":"Dome: Taming diffusion model into high-fidelity controllable occupancy world model","author":"Gu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICICML60161.2023.10424939"},{"key":"ref11","article-title":"Bevdet: High-performance multi-camera 3d object detection in bird-eye-view","author":"Huang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00890"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-9794-6_13"},{"key":"ref14","article-title":"Safeflow: A principled protocol for trustworthy and transactional autonomous agent systems","author":"Li","year":"2025","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01342"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3364"},{"key":"ref19","article-title":"A strong view-free baseline approach for singleview image guided point cloud completion","author":"Lin","year":"2025","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Strajnet: Occupancy flow prediction via multi-modal swin transformer","author":"Liu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160855"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-024-03608-8"},{"key":"ref23","first-page":"2895","article-title":"Let occ flow: Self-supervised 3d occupancy flow prediction","volume-title":"Proceedings of The 8th Conference on Robot Learning","author":"Liu"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02030"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW65960.2025.00114"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3151613"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.129"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01704"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01704"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2809"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00772"},{"key":"ref33","first-page":"A10","article-title":"Solving geometric problems with the rotating calipers","author":"Toussaint","year":"1983","journal-title":"Proc. IEEE Melecon"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref35","article-title":"Occsora: 4d occupancy generation models as world simulators for autonomous driving","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01636"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRAE59816.2023.10458643"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICECET58911.2023.10389246"},{"key":"ref39","article-title":"Generative ai for autonomous driving: Frontiers and opportunities","author":"Wang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3546862"},{"key":"ref41","article-title":"Occllama: An occupancy-language-action generative world model for autonomous driving","author":"Wei","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01986"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3188435"},{"key":"ref44","article-title":"Autotrust: Benchmarking trustworthiness in large vision language models for autonomous driving","author":"Xing","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Demystifying the visual quality paradox in multimodal large language models","author":"Xing","year":"2025","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW65960.2025.00113"},{"key":"ref47","article-title":"Can large vision language models read maps like a human?","author":"Xing","year":"2025","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.121"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812038"},{"key":"ref50","article-title":"Cobevt: Cooperative bird\u2019s eye view semantic segmentation with sparse transformers","volume-title":"Conference on Robot Learning (CoRL)","author":"Xu Xu"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73464-9_23"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3048658"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-024-40443-5"},{"key":"ref54","article-title":"Gps: A probabilistic distributional similarity with gumbel priors for set-to-set matching","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Zhang"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72624-8_4"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00862"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-emnlp.114"}],"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\/11444994.pdf?arnumber=11444994","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:18:31Z","timestamp":1777529911000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444994\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02371","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}