{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T16:22:46Z","timestamp":1783700566421,"version":"3.55.0"},"reference-count":79,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2021YFA0717700"],"award-info":[{"award-number":["2021YFA0717700"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476011"],"award-info":[{"award-number":["62476011"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CCF-Ant Research Fund","award":["CCF-AFSG RF20230403"],"award-info":[{"award-number":["CCF-AFSG RF20230403"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tcsvt.2024.3523049","type":"journal-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:40:00Z","timestamp":1735155600000},"page":"5109-5122","source":"Crossref","is-referenced-by-count":5,"title":["BEVUDA++: Geometric-Aware Unsupervised Domain Adaptation for Multi-View 3D Object Detection"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9174-1765","authenticated-orcid":false,"given":"Rongyu","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Electronic Science and Engineering, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaming","family":"Liu","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoqi","family":"Li","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6559-4378","authenticated-orcid":false,"given":"Xiaowei","family":"Chi","sequence":"additional","affiliation":[{"name":"Academy of Interdisciplinary Studies, The Hong Kong University of Science and Technology, Hung Hom, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0921-2726","authenticated-orcid":false,"given":"Dan","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2687-6978","authenticated-orcid":false,"given":"Li","family":"Du","sequence":"additional","affiliation":[{"name":"School of Electronic Science and Engineering, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5316-619X","authenticated-orcid":false,"given":"Yuan","family":"Du","sequence":"additional","affiliation":[{"name":"School of Electronic Science and Engineering, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4047-3526","authenticated-orcid":false,"given":"Shanghang","family":"Zhang","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1686","article-title":"Towards optimal strategies for training self-driving perception models in simulation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Acuna"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2892405"},{"key":"ref3","article-title":"Monocular 3D object detection via geometric reasoning on keypoints","author":"Barabanau","year":"2019","journal-title":"arXiv:1905.05618"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564553"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-009-5152-4"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2017.1285773"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00938"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01172"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6618"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3293954"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2025.105438"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.236"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.691"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00352"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01169"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3268849"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3348795"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045502"},{"key":"ref22","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ganin"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.5555\/2946645.2946704"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","article-title":"BEVDet4D: Exploit temporal cues in multi-camera 3D object detection","author":"Huang","year":"2022","journal-title":"arXiv:2203.17054"},{"key":"ref27","article-title":"BEVDet: High-performance multi-camera 3D object detection in bird-eye-view","author":"Huang","year":"2021","journal-title":"arXiv:2112.11790"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00398"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00890"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25185"},{"key":"ref31","first-page":"1","article-title":"What uncertainties do we need in Bayesian deep learning for computer vision?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Kendall"},{"key":"ref32","article-title":"BEVStereo: Enhancing depth estimation in multi-view 3D object detection with dynamic temporal stereo","author":"Li","year":"2022","journal-title":"arXiv:2209.10248"},{"key":"ref33","article-title":"Unifying voxel-based representation with transformer for 3D object detection","author":"Li","year":"2022","journal-title":"arXiv:2206.00630"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"ref35","article-title":"Towards model generalization for monocular 3D object detection","author":"Li","year":"2022","journal-title":"arXiv:2205.11664"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_15"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00281"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610511"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610096"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"ref42","article-title":"PETRv2: A unified framework for 3D perception from multi-camera images","author":"Liu","year":"2022","journal-title":"arXiv:2206.01256"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01535"},{"key":"ref44","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00874"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00217"},{"key":"ref47","article-title":"BEV-seg: Bird\u2019s eye view semantic segmentation using geometry and semantic point cloud","author":"Ng","year":"2020","journal-title":"arXiv:2006.11436"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3396870"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3253554"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00712"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1072-8"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01059"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00404"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3359543"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00208"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref59","first-page":"1","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Tarvainen"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3332353"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3192135"},{"key":"ref62","article-title":"Barnes-Hut-SNE","author":"van der Maaten","year":"2013","journal-title":"arXiv:1301.3342"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3394550"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3366664"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00706"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475317"},{"key":"ref68","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":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01174"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01237"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_37"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681135"},{"key":"ref73","article-title":"Decomposing the neurons: Activation sparsity via mixture of experts for continual test time adaptation","author":"Zhang","year":"2024","journal-title":"arXiv:2405.16486"},{"key":"ref74","article-title":"Unimodal training-multimodal prediction: Cross-modal federated learning with hierarchical aggregation","author":"Zhang","year":"2023","journal-title":"arXiv:2303.15486"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i15.29622"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00670"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00330"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3028503"},{"key":"ref79","article-title":"Class-balanced grouping and sampling for point cloud 3D object detection","author":"Zhu","year":"2019","journal-title":"arXiv:1908.09492"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10989278\/10816404.pdf?arnumber=10816404","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,7]],"date-time":"2025-05-07T04:21:09Z","timestamp":1746591669000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10816404\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":79,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3523049","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}