{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T18:27:50Z","timestamp":1784399270020,"version":"3.55.0"},"reference-count":90,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2022ZD0161300"],"award-info":[{"award-number":["2022ZD0161300"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372223"],"award-info":[{"award-number":["62372223"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206172"],"award-info":[{"award-number":["62206172"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376134"],"award-info":[{"award-number":["62376134"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U24A20330"],"award-info":[{"award-number":["U24A20330"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key R&D Project","award":["SQ2024YFE0201271"],"award-info":[{"award-number":["SQ2024YFE0201271"]}]},{"name":"Oriental Leading Talent Project","award":["LJ2023034"],"award-info":[{"award-number":["LJ2023034"]}]},{"name":"China Mobile Zijin Innovation Institute","award":["NR2310J7M"],"award-info":[{"award-number":["NR2310J7M"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tpami.2024.3515454","type":"journal-article","created":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T01:16:11Z","timestamp":1733879771000},"page":"2020-2036","source":"Crossref","is-referenced-by-count":227,"title":["BEVFormer: Learning Bird\u2019s-Eye-View Representation From LiDAR-Camera via Spatiotemporal Transformers"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7041-0748","authenticated-orcid":false,"given":"Zhiqi","family":"Li","sequence":"first","affiliation":[{"name":"National Key Lab for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2418-3134","authenticated-orcid":false,"given":"Wenhai","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9110-5534","authenticated-orcid":false,"given":"Hongyang","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6890-1049","authenticated-orcid":false,"given":"Enze","family":"Xie","sequence":"additional","affiliation":[{"name":"NVIDIA Research, Sheung Wan, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6350-4116","authenticated-orcid":false,"given":"Chonghao","family":"Sima","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7051-5347","authenticated-orcid":false,"given":"Tong","family":"Lu","sequence":"additional","affiliation":[{"name":"National Key Lab for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1889-2567","authenticated-orcid":false,"given":"Qiao","family":"Yu","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6785-0785","authenticated-orcid":false,"given":"Jifeng","family":"Dai","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2892405"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10160968"},{"key":"ref5","article-title":"BEVFusion: A simple and robust LiDAR-camera fusion framework","author":"Liang","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00466"},{"key":"ref7","article-title":"DeepInteraction: 3D object detection via modality interaction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw59228.2023.00022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/116"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01162"},{"key":"ref12","article-title":"Leveraging vision-centric multi-modal expertise for 3D object detection","author":"Huang","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_9"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3346386"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00376"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00607"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.95"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref20","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00134"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00938"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.597"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00249"},{"key":"ref29","article-title":"Objects as points","author":"Zhou","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref32","first-page":"180","article-title":"DETR3D: 3D object detection from multi-view images via 3D-to-2D queries","volume-title":"Proc. Conf. Robot Learn.","author":"Wang"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00302"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00864"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"ref37","article-title":"BEVDet: High-performance multi-camera 3D object detection in bird-eye-view","author":"Huang","year":"2021"},{"key":"ref38","article-title":"BEVDet4D: Exploit temporal cues in multi-camera 3D object detection","author":"Huang","year":"2022"},{"key":"ref39","article-title":"Orthographic feature transform for monocular 3D object detection","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Roddick"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00133"},{"key":"ref41","article-title":"M $^{2}$2 BEV: Multi-camera joint 3D detection and segmentation with unified birds-eye view representation","author":"Xie","year":"2022"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"ref43","article-title":"BEVStereo: Enhancing depth estimation in multi-view 3D object detection with dynamic temporal stereo","author":"Li","year":"2022"},{"key":"ref44","article-title":"Time will tell: New outlooks and a baseline for temporal multi-view 3D object detection","author":"Park","year":"2022"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00335"},{"key":"ref46","article-title":"Sparse4D v2: Recurrent temporal fusion with sparse model","author":"Lin","year":"2023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00086"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00204"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"ref51","first-page":"16494","article-title":"Multimodal virtual point 3D detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yin"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564951"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01667"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref56","first-page":"1243","article-title":"Convolutional sequence to sequence learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gehring"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01499"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811901"},{"key":"ref59","article-title":"Understanding bird\u2019s-eye view semantic HD-maps using an onboard monocular camera","author":"Can","year":"2020"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_38"},{"key":"ref61","article-title":"MapTR: Structured modeling and learning for online vectorized HD map construction","author":"Liao","year":"2022"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00637"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00637"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.441"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00103"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_8"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00535"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00255"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"ref73","first-page":"1475","article-title":"Probabilistic and geometric depth: Detecting objects in perspective","volume-title":"Proc. Conf. Robot Learn.","author":"Wang"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19-1021"},{"key":"ref77","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00532"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3168781"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00500"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9562072"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636498"},{"key":"ref83","article-title":"Unifying voxel-based representation with transformer for 3D object detection","author":"Li","year":"2022"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00865"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00890"},{"key":"ref86","article-title":"Fully sparse 3D panoptic occupancy prediction","author":"Liu","year":"2023"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3004325"},{"key":"ref88","first-page":"22352","article-title":"VectorMapNet: End-to-end vectorized HD map learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01408"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00313"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10873290\/10791908.pdf?arnumber=10791908","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T06:00:21Z","timestamp":1738821621000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10791908\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":90,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3515454","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}