{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T20:17:40Z","timestamp":1783455460461,"version":"3.55.0"},"reference-count":89,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"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":["2022ZD0160900"],"award-info":[{"award-number":["2022ZD0160900"]}]},{"name":"Basic Research Program of Jiangsu","award":["BK20250009"],"award-info":[{"award-number":["BK20250009"]}]},{"name":"Collaborative Innovation Center of Novel Software Technology and Industrialization"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1109\/tpami.2026.3679808","type":"journal-article","created":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T20:12:30Z","timestamp":1775074350000},"page":"9748-9764","source":"Crossref","is-referenced-by-count":0,"title":["SparseBEV: A Fully Sparse Framework for Multi-View 3D Object Detection"],"prefix":"10.1109","volume":"48","author":[{"given":"Yang","family":"Chen","sequence":"first","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haisong","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3674-7718","authenticated-orcid":false,"given":"Limin","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref3","article-title":"Group DETR: Fast training convergence with decoupled one-to-many label assignment","author":"Chen","year":"2022"},{"key":"ref4","article-title":"Scaling up kernels in 3D CNNs","author":"Chen","year":"2022"},{"key":"ref5","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00360"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00529"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0084"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3401172"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_9"},{"key":"ref13","article-title":"BEVDet4D: Exploit temporal cues in multi-camera 3D object detection","author":"Huang","year":"2022"},{"key":"ref14","article-title":"BEVPoolv2: A cutting-edge implementation of BEVDet toward deployment","author":"Huang","year":"2022"},{"key":"ref15","article-title":"BEVDet: High-performance multi-camera 3D object detection in bird-eye-view","author":"Huang","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02001"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01887"},{"key":"ref18","first-page":"667","article-title":"Dynamic filter networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jia"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28033"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25185"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28037"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01392"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00615"},{"key":"ref28","article-title":"DualBEV: CNN is all you need in view transformation","author":"Li","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1340"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25234"},{"key":"ref31","article-title":"BEVDepth: Acquisition of reliable depth for multi-view 3D object detection","author":"Li","year":"2022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01901"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00637"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref37","article-title":"Sparse4D: Multi-view 3D object detection with sparse spatial-temporal fusion","author":"Lin","year":"2022"},{"key":"ref38","article-title":"Sparse4D v2: Recurrent temporal fusion with sparse model","author":"Lin","year":"2023"},{"key":"ref39","first-page":"200","article-title":"Ray denoising: Depth-aware hard negative sampling for multi-view 3D object detection","volume-title":"Proc. 18th Eur. Conf. Comput. Vis.","author":"Liu"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00570"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01703"},{"key":"ref42","article-title":"Fully sparse 3D occupancy prediction","author":"Liu","year":"2024"},{"key":"ref43","article-title":"DAB-DETR: Dynamic anchor boxes are better queries for DETR","author":"Liu","year":"2022"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00302"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00506"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref49","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00113"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3004325"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00313"},{"key":"ref54","article-title":"Time will tell: New outlooks and a baseline for temporal multi-view 3D object detection","author":"Park","year":"2022"},{"key":"ref55","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00592"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"ref59","article-title":"Orthographic feature transform for monocular 3D object detection","author":"Roddick","year":"2018"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00331"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00605"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref65","first-page":"24261","article-title":"MLP-mixer: An all-MLP architecture for vision","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tolstikhin"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2023.3332608"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00335"},{"key":"ref69","article-title":"MV-FCOS3D: Multi-view camera-only 4D object detection with pretrained monocular backbones","author":"Wang","year":"2022"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01385"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00864"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20158"},{"key":"ref74","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":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00351"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00114"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02066"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01710"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680807"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00719"},{"key":"ref82","article-title":"DINO: DETR with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00310"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00840"},{"key":"ref85","article-title":"A simple baseline for multi-camera 3D object detection","author":"Zhang","year":"2022"},{"key":"ref86","article-title":"Class-balanced grouping and sampling for point cloud 3D object detection","author":"Zhu","year":"2019"},{"key":"ref87","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00350"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00621"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11595778\/11460277.pdf?arnumber=11460277","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T19:44:53Z","timestamp":1783453493000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11460277\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":89,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3679808","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":[[2026,8]]}}}