{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T01:30:05Z","timestamp":1773106205639,"version":"3.50.1"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376153"],"award-info":[{"award-number":["62376153"]}],"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":["62402318"],"award-info":[{"award-number":["62402318"]}],"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":["24Z990200676"],"award-info":[{"award-number":["24Z990200676"]}],"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":["62271237"],"award-info":[{"award-number":["62271237"]}],"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":["U24A20220"],"award-info":[{"award-number":["U24A20220"]}],"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":["62132006"],"award-info":[{"award-number":["62132006"]}],"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":["62311530101"],"award-info":[{"award-number":["62311530101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010251","name":"Science Foundation of Jiangxi Province of China","doi-asserted-by":"publisher","award":["20242BAB26014"],"award-info":[{"award-number":["20242BAB26014"]}],"id":[{"id":"10.13039\/501100010251","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/tcsvt.2025.3600527","type":"journal-article","created":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T18:17:54Z","timestamp":1755627474000},"page":"2177-2190","source":"Crossref","is-referenced-by-count":1,"title":["CMF-IoU: Multi-Stage Cross-Modal Fusion 3D Object Detection With IoU Joint Prediction"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-0287-888X","authenticated-orcid":false,"given":"Zhiwei","family":"Ning","sequence":"first","affiliation":[{"name":"School of Automation and Intelligent Sensing and Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, Shanghai, China"}]},{"given":"Zhaojiang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Automation and Intelligent Sensing and Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6169-7493","authenticated-orcid":false,"given":"Xuanang","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Automation and Intelligent Sensing and Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4980-7211","authenticated-orcid":false,"given":"Yifan","family":"Zuo","sequence":"additional","affiliation":[{"name":"School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics, Nanchang, Jiangxi, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4801-7162","authenticated-orcid":false,"given":"Jie","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Automation and Intelligent Sensing, Institute of Image Processing and Pattern Recognition, and Institute of Medical Robotics, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6946-3586","authenticated-orcid":false,"given":"Yuming","family":"Fang","sequence":"additional","affiliation":[{"name":"School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics, Nanchang, Jiangxi, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6351-9019","authenticated-orcid":false,"given":"Wei","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Automation and Intelligent Sensing, Institute of Image Processing and Pattern Recognition, and Institute of Medical Robotics, Shanghai Jiao Tong University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01790-1"},{"key":"ref2","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":"ref3","first-page":"5105","article-title":"PointNet+: Deep hierarchical feature learning on point sets in a metric space","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Qi"},{"key":"ref4","article-title":"PointMamba: A simple state space model for point cloud analysis","author":"Liang","year":"2024","journal-title":"arXiv:2402.10739"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.691"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref9","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":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"ref11","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":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02074"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01675"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00466"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_3"},{"key":"ref17","first-page":"16494","article-title":"Multimodal virtual point 3D detection","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Yin"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00534"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16207"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108684"},{"key":"ref21","article-title":"3D IoU-net: IoU guided 3D object detector for point clouds","author":"Li","year":"2020","journal-title":"arXiv:2004.04962"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107816"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3396870"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00086"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3260115"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2977026"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00274"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3272734"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00608"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00890"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3202810"},{"key":"ref32","article-title":"BEVDet: High-performance multi-camera 3D object detection in bird-eye-view","author":"Huang","year":"2021","journal-title":"arXiv:2112.11790"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref34","article-title":"STS: Surround-view temporal stereo for multi-view 3D detection","author":"Wang","year":"2022","journal-title":"arXiv:2208.10145"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00311"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_48"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475314"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3203163"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2018.11.566"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561035"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02076"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01372"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01255"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561423"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3392783"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3306361"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01681"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25380"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01327"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19980"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00826"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/116"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00535"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00771"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01299"},{"key":"ref61","first-page":"53076","article-title":"HEDNet: A hierarchical encoder\u2013decoder network for 3D object detection in point clouds","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Zhang"},{"key":"ref62","article-title":"FUTR3D: A unified sensor fusion framework for 3D detection","author":"Chen","year":"2022","journal-title":"arXiv:2203.10642"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1911.08287"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00662"},{"key":"ref66","article-title":"Multi-class object detection using adaptive non-maximum suppression in dense images","author":"Lee","year":"2022","journal-title":"Authorea Preprints"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.533"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2881123"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11392768\/11129877.pdf?arnumber=11129877","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T21:02:20Z","timestamp":1770930140000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11129877\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":68,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3600527","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}