{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T05:18:30Z","timestamp":1781846310322,"version":"3.54.5"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"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":["62473205"],"award-info":[{"award-number":["62473205"]}],"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":["U2013210"],"award-info":[{"award-number":["U2013210"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Young and Middle-Aged Leading Scholar in Oinglan Project by Jiangsu Province"},{"name":"Guangxi Key Laboratory of Machine Vision and Intelligent Control","award":["2022B09"],"award-info":[{"award-number":["2022B09"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1109\/tcsvt.2023.3268849","type":"journal-article","created":{"date-parts":[[2023,4,24]],"date-time":"2023-04-24T18:41:43Z","timestamp":1682361703000},"page":"8997-9009","source":"Crossref","is-referenced-by-count":34,"title":["HCPVF: Hierarchical Cascaded Point-Voxel Fusion for 3D Object Detection"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1627-9726","authenticated-orcid":false,"given":"Baojie","family":"Fan","sequence":"first","affiliation":[{"name":"College of Automation and College of Artificial Intelligence, Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8801-4497","authenticated-orcid":false,"given":"Kexin","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Automation and College of Artificial Intelligence, Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5027-1381","authenticated-orcid":false,"given":"Jiandong","family":"Tian","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561267"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9565009"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3202810"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3105685"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.691"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00798"},{"key":"ref7","first-page":"146","article-title":"HDNet: Exploiting HD maps for 3D object detection","volume-title":"Proc. Conf. Robot Learn.","author":"Yang"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475641"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/s18103337"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16207"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00272"},{"key":"ref13","article-title":"Dense voxel fusion for 3D object detection","author":"Mahmoud","year":"2022","journal-title":"arXiv:2203.00871"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00828"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20194"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01426"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00567"},{"key":"ref18","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":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"ref20","article-title":"PV-RCNN++: Point-voxel feature set abstraction with local vector representation for 3D object detection","author":"Shi","year":"2021","journal-title":"arXiv:2102.00463"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00086"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00746"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00204"},{"key":"ref26","first-page":"1","article-title":"PointNet++: Deep hierarchical feature learning on point sets in a metric space","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Qi"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475314"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3100848"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00235"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3102025"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3082763"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-021-0229-5"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00315"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00827"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00290"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00294"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00274"},{"key":"ref42","article-title":"CosFormer: Rethinking softmax in attention","author":"Qin","year":"2022","journal-title":"arXiv:2202.08791"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_3"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341791"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3189778"},{"key":"ref46","article-title":"3D object detection combining semantic and geometric features from point clouds","author":"Peng","year":"2021","journal-title":"arXiv:2110.04704"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00535"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108684"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref50","article-title":"EPNet++: Cascade bi-directional fusion for multi-modal 3D object detection","author":"Liu","year":"2021","journal-title":"arXiv:2112.11088"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_43"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00086"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3094562"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108684"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2977026"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19980"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10739868\/10107596.pdf?arnumber=10107596","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T20:13:46Z","timestamp":1736453626000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10107596\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":56,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3268849","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}