{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T15:06:10Z","timestamp":1781622370844,"version":"3.54.5"},"reference-count":78,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"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":["62441232"],"award-info":[{"award-number":["62441232"]}],"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":["62306092"],"award-info":[{"award-number":["62306092"]}],"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":["U21B2038"],"award-info":[{"award-number":["U21B2038"]}],"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":["62476068"],"award-info":[{"award-number":["62476068"]}],"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":["62236008"],"award-info":[{"award-number":["62236008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province, China","doi-asserted-by":"publisher","award":["ZR2024QF066"],"award-info":[{"award-number":["ZR2024QF066"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province, China","doi-asserted-by":"publisher","award":["ZR2023QF052"],"award-info":[{"award-number":["ZR2023QF052"]}],"id":[{"id":"10.13039\/501100007129","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":[[2025,12]]},"DOI":"10.1109\/tcsvt.2025.3578474","type":"journal-article","created":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T13:54:59Z","timestamp":1749563699000},"page":"12410-12425","source":"Crossref","is-referenced-by-count":2,"title":["VPA: Multi-Modal Virtual Point Augmentation for 3D Object Detection"],"prefix":"10.1109","volume":"35","author":[{"given":"Jianping","family":"Zhong","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Weihai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9196-9818","authenticated-orcid":false,"given":"Zhaobo","family":"Qi","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Weihai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8663-7429","authenticated-orcid":false,"given":"Kaiwen","family":"Duan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanrong","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Weihai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0042-7074","authenticated-orcid":false,"given":"Weigang","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Weihai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7542-296X","authenticated-orcid":false,"given":"Qingming","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/s18103337"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.691"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00641"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00466"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00119"},{"key":"ref6","first-page":"16494","article-title":"Multimodal virtual point 3D detection","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Yin"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02073"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3194044"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3257546"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01675"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16207"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3296583"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3297620"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19897"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01838"},{"key":"ref20","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":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01412"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3202810"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3248656"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3595916.3626385"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3306361"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3272734"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3366664"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"ref32","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":"ref33","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":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25186"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3246792"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref41","article-title":"BEVFusion4D: Learning LiDAR-camera fusion under Bird\u2019s-Eye-View via cross-modality guidance and temporal aggregation","author":"Cai","year":"2023","journal-title":"arXiv:2303.17099"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_36"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01613"},{"key":"ref44","article-title":"EA-LSS: Edge-aware Lift-splat-shot framework for 3D BEV object detection","author":"Hu","year":"2023","journal-title":"arXiv:2303.17895"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01299"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0435"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564951"},{"key":"ref48","first-page":"1992","article-title":"DeepInteraction: 3D object detection via modality interaction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02076"},{"key":"ref50","article-title":"FusionFormer: A multi-sensory fusion in Bird\u2019s-Eye-View and temporal consistent transformer for 3D object detection","author":"Hu","year":"2023","journal-title":"arXiv:2309.05257"},{"key":"ref51","article-title":"Voxel mamba: Group-free state space models for point cloud based 3D object detection","author":"Zhang","year":"2024","journal-title":"arXiv:2406.10700"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2977026"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01426"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00828"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00987"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01437"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00086"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_3"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_43"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3228806"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01392"},{"key":"ref64","article-title":"Probabilistic two-stage detection","author":"Zhou","year":"2021","journal-title":"arXiv:2103.07461"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3181116"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123564"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_10"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00325"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01615"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01656"},{"key":"ref75","article-title":"ContrastAlign: Toward robust BEV feature alignment via contrastive learning for multi-modal 3D object detection","author":"Song","year":"2024","journal-title":"arXiv:2405.16873"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00105"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00107"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11278843\/11029206.pdf?arnumber=11029206","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T18:42:47Z","timestamp":1765219367000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11029206\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":78,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3578474","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}