{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T05:11:44Z","timestamp":1776057104794,"version":"3.50.1"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"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":["62101032"],"award-info":[{"award-number":["62101032"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Young Elite Scientist Sponsorship Program of China Association for Science and Technology","award":["YESS20220448"],"award-info":[{"award-number":["YESS20220448"]}]},{"name":"Young Elite Scientist Sponsorship Program of Beijing Association for Science and Technology","award":["BYESS2022167"],"award-info":[{"award-number":["BYESS2022167"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1109\/tpami.2023.3345880","type":"journal-article","created":{"date-parts":[[2023,12,22]],"date-time":"2023-12-22T19:32:19Z","timestamp":1703273539000},"page":"3736-3752","source":"Crossref","is-referenced-by-count":21,"title":["MsSVT++: Mixed-Scale Sparse Voxel Transformer With Center Voting for 3D Object Detection"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6936-9485","authenticated-orcid":false,"given":"Jianan","family":"Li","sequence":"first","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6152-9299","authenticated-orcid":false,"given":"Shaocong","family":"Dong","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1976-9496","authenticated-orcid":false,"given":"Lihe","family":"Ding","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5452-2662","authenticated-orcid":false,"given":"Tingfa","family":"Xu","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"11615","article-title":"MsSVT: Mixed-scale sparse voxel transformer for 3D object detection on point clouds","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dong"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353481"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00315"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00827"},{"key":"ref8","first-page":"27378","article-title":"Understanding the robustness in vision transformers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhou"},{"key":"ref9","article-title":"How do vision transformers work?","author":"Park","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00937"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3390\/s18103337"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref15","article-title":"Argoverse 2: Next generation datasets for self-driving perception and forecasting","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Wilson"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.691"},{"key":"ref17","first-page":"146","article-title":"HDNET: Exploiting HD maps for 3D object detection","volume-title":"Proc. Conf. Robot Learn.","author":"Yang"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00798"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.114"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2016.XII.042"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594049"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00118"},{"key":"ref24","first-page":"29975","article-title":"CAGroup3D: Class-aware grouping for 3D object detection on point clouds","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3104172"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_3"},{"key":"ref28","first-page":"77","article-title":"PointNet: Deep learning on point sets for 3D classification and segmentation","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Qi"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00334"},{"key":"ref30","first-page":"21224","article-title":"Every view counts: Cross-view consistency in 3D object detection with hybrid-cylindrical-spherical voxelization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref31","first-page":"286","article-title":"Reconfigurable voxels: A new representation for LiDAR-based point clouds","volume-title":"Proc. Conf. Robot Learn.","author":"Wang"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3390\/s20030704"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref34","article-title":"Pillar in pillar: Multi-scale and dynamic feature extraction for 3D object detection in point clouds","author":"Tian","year":"2019"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00746"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01710-9"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00274"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00761"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3063611"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_2"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_42"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19-1423"},{"key":"ref44","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01058"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-021-0229-5"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref49","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":"ref50","article-title":"PVT: Point-voxel transformer for 3D deep learning","author":"Zhang","year":"2021"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01644"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00823"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00073"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3390\/rs15071839"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_25"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00446"},{"key":"ref57","first-page":"351","article-title":"Fully sparse 3D object detection","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Fan"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00988"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00835"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref62","article-title":"Openpcdet: An open-source toolbox for 3D object detection from point clouds","year":"2020"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00567"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2977026"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16207"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00828"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_29"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_38"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01681"},{"key":"ref71","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00086"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3286409"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10490207\/10371785.pdf?arnumber=10371785","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:46:12Z","timestamp":1725903972000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10371785\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":74,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3345880","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":[[2024,5]]}}}