{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T12:29:07Z","timestamp":1777984147618,"version":"3.51.4"},"reference-count":86,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100017622","name":"Key-Area Research and Development Program of Guangdong Province","doi-asserted-by":"publisher","award":["2023B0909040001"],"award-info":[{"award-number":["2023B0909040001"]}],"id":[{"id":"10.13039\/501100017622","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019014","name":"Shenzhen Science and Technology Program","doi-asserted-by":"publisher","award":["KCXFZ20240903093911016"],"award-info":[{"award-number":["KCXFZ20240903093911016"]}],"id":[{"id":"10.13039\/501100019014","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1109\/tits.2025.3569706","type":"journal-article","created":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T13:29:06Z","timestamp":1750685346000},"page":"13466-13476","source":"Crossref","is-referenced-by-count":2,"title":["BEVMamba: Time Sequence Dense Bird\u2019s-Eye-View Perception Modeling With State Space Model"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8242-8127","authenticated-orcid":false,"given":"Xiao","family":"Liu","sequence":"first","affiliation":[{"name":"School of Mechanical Engineering, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5701-1720","authenticated-orcid":false,"given":"Jiaru","family":"Zhong","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9324-0892","authenticated-orcid":false,"given":"Chao","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref2","article-title":"NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles","author":"Caesar","year":"2021","journal-title":"arXiv:2106.11810"},{"key":"ref3","article-title":"MonoScene: Monocular 3D semantic scene completion","author":"Cao","year":"2021","journal-title":"arXiv:2112.00726"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3283021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2025.105438"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01211"},{"key":"ref9","volume-title":"OpenScene: The Largest Up-to-date 3D Occupancy Prediction Benchmark in Autonomous Driving","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_14"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02067"},{"key":"ref13","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv:2312.00752"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00314"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3401172"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610625"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01499"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref21","article-title":"Fast-BEV: Towards real-time on-vehicle bird\u2019s-eye view perception","author":"Huang","year":"2023","journal-title":"arXiv:2301.07870"},{"key":"ref22","article-title":"BEVDet4D: Exploit temporal cues in multi-camera 3D object detection","author":"Huang","year":"2022","journal-title":"arXiv:2203.17054"},{"key":"ref23","article-title":"BEVPoolv2: A cutting-edge implementation of BEVDet toward deployment","author":"Huang","year":"2022","journal-title":"arXiv:2211.17111"},{"key":"ref24","article-title":"BEVDet: High-performance multi-camera 3D object detection in bird-eye-view","author":"Huang","year":"2021","journal-title":"arXiv:2112.11790"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00398"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01885"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00890"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25185"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00103"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_14"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812383"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73414-4_5"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25234"},{"key":"ref34","first-page":"18442","article-title":"Unifying voxel-based representation with transformer for 3D object detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3414835"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01901"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref39","first-page":"10421","article-title":"BEVFusion: A simple and robust LiDAR-camera fusion framework","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liang"},{"key":"ref40","article-title":"Sparse4D: Multi-view 3D object detection with sparse spatial\u2013temporal fusion","author":"Lin","year":"2022","journal-title":"arXiv:2211.10581"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01703"},{"key":"ref42","article-title":"VMamba: Visual state space model","author":"Liu","year":"2024","journal-title":"arXiv:2401.10166"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00302"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_8"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02030"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01884"},{"key":"ref49","article-title":"Vision-centric BEV perception: A survey","author":"Ma","year":"2022","journal-title":"arXiv:2208.02797"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01790-1"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00313"},{"key":"ref53","article-title":"Time will tell: New outlooks and a baseline for temporal multi-view 3D object detection","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Park"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref55","first-page":"652","article-title":"PointNet: Deep learning on point sets for 3D classification and segmentation","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Qi"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58526-6_6"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01489"},{"key":"ref58","article-title":"Occ3D: A large-scale 3D occupancy prediction benchmark for autonomous driving","author":"Tian","year":"2023","journal-title":"arXiv:2304.14365"},{"key":"ref59","first-page":"64318","article-title":"Occ3d: A large-scale 3D occupancy prediction benchmark for autonomous driving","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Tian"},{"key":"ref60","first-page":"8406","article-title":"Scene as occupancy","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Sima"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3332608"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00335"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01636"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01624"},{"key":"ref66","first-page":"180","article-title":"DETR3D: 3D object detection from multi-view images via 3D-to-2D queries","volume-title":"Proc. Conf. Robot Learn.","volume":"164","author":"Wang"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635875"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00351"},{"key":"ref69","article-title":"STS: Surround-view temporal stereo for multi-view 3D detection","author":"Wang","year":"2022","journal-title":"arXiv:2208.10145"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01986"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72973-7_22"},{"key":"ref72","article-title":"M2BEV: Multi-camera joint 3D detection and segmentation with unified birds-eye view representation","author":"Xie","year":"2022","journal-title":"arXiv:2204.05088"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102671"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2024.3519178"},{"key":"ref75","first-page":"989","article-title":"CoBEVT: Cooperative bird\u2019s eye view semantic segmentation with sparse transformers","volume-title":"Proc. Conf. Robot Learn.","author":"Xu"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01710"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.33040"},{"key":"ref78","article-title":"FlashOcc: Fast and memory-efficient occupancy prediction via channel-to-height plugin","author":"Yu","year":"2023","journal-title":"arXiv:2311.12058"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00865"},{"key":"ref80","article-title":"BEVerse: Unified perception and prediction in birds-eye-view for vision-centric autonomous driving","author":"Zhang","year":"2022","journal-title":"arXiv:2205.09743"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC58415.2024.10920140"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref83","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024","journal-title":"arXiv:2401.09417"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/IV55156.2024.10588419"},{"key":"ref85","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv:2010.04159"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00350"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6979\/11178161\/11048669.pdf?arnumber=11048669","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T12:20:34Z","timestamp":1759234834000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11048669\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":86,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tits.2025.3569706","relation":{"has-preprint":[{"id-type":"doi","id":"10.36227\/techrxiv.172236567.72239502\/v1","asserted-by":"object"}]},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9]]}}}