{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T16:03:45Z","timestamp":1770739425336,"version":"3.49.0"},"reference-count":106,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"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":["U24B20155"],"award-info":[{"award-number":["U24B20155"]}],"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":["62506175"],"award-info":[{"award-number":["62506175"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research and Development Program of Jiangsu Province","award":["BE2023016-3"],"award-info":[{"award-number":["BE2023016-3"]}]},{"DOI":"10.13039\/501100001459","name":"Ministry of Education - Singapore","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001459","id-type":"DOI","asserted-by":"publisher"}]},{"name":"MOE AcRF Tier 2","award":["MOET2EP20221-0012"],"award-info":[{"award-number":["MOET2EP20221-0012"]}]},{"name":"MOE AcRF Tier 2","award":["MOE-T2EP20223-0002"],"award-info":[{"award-number":["MOE-T2EP20223-0002"]}]},{"name":"NTU S-Lab and industry partne"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tpami.2025.3640589","type":"journal-article","created":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:37:55Z","timestamp":1764959875000},"page":"3819-3834","source":"Crossref","is-referenced-by-count":0,"title":["Enhanced Spatiotemporal Consistency for Image-to-LiDAR Data Pretraining"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4505-0912","authenticated-orcid":false,"given":"Xiang","family":"Xu","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3884-2185","authenticated-orcid":false,"given":"Lingdong","family":"Kong","sequence":"additional","affiliation":[{"name":"School of Computing, Department of Computer Science, National University of Singapore, and CNRS@CREATE, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8840-5069","authenticated-orcid":false,"given":"Hui","family":"Shuai","sequence":"additional","affiliation":[{"name":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2748-4514","authenticated-orcid":false,"given":"Wenwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}]},{"given":"Liang","family":"Pan","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}]},{"given":"Kai","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4220-5958","authenticated-orcid":false,"given":"Ziwei","family":"Liu","sequence":"additional","affiliation":[{"name":"S-Lab, Nanyang Technological University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5512-6984","authenticated-orcid":false,"given":"Qingshan","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113816"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/technologies10040090"},{"key":"ref3","article-title":"An empirical study of training state-of-the-art LiDAR segmentation models","author":"Sun","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3076844"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3394735"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3032227"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3262786"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01934-3"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3031549"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00966"},{"key":"ref13","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020"},{"key":"ref14","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00686"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01981-w"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02549"},{"key":"ref18","first-page":"37193","article-title":"Segment any point cloud sequences by distilling vision foundation models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Liu","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3617126"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02033"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00939"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00505"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00508"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_4"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00100"},{"key":"ref27","first-page":"19769","article-title":"Segment everything everywhere all at once","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Zou","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01830"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00905"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_34"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01009"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW58289.2023.00039"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00335"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00134"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01293"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00647"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00017"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01883"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IVWorkshops54471.2021.9669228"},{"key":"ref41","article-title":"Analyzing deep learning representations of point clouds for real-time in-vehicle lidar perception","author":"Uecker","year":"2022"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00494"},{"key":"ref43","first-page":"652","article-title":"PointNet: Deep learning on point sets for 3D classification and segmentation","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Qi","year":"2017"},{"key":"ref44","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.","volume":"30","author":"Qi","year":"2017"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01112"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00651"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3073660"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00981"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_41"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01289"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00962"},{"key":"ref53","first-page":"26871","article-title":"PolarStream: Streaming LiDAR object detection and segmentation with polar pillars","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chen","year":"2021"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01299"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967762"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_1"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-64559-5_16"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3550011"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00028"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01572"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01236"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2023.3328603"},{"key":"ref63","article-title":"AMVNet: Assertion-based multi-view fusion network for LiDAR semantic segmentation","author":"Liong","year":"2020"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01980"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160410"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01154"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_35"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00272"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_5"},{"key":"ref70","first-page":"48444","article-title":"Annotator: A generic active learning baseline for LiDAR semantic segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Xie","year":"2023"},{"key":"ref71","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Tarvainen","year":"2017"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02079"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3535625"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00548"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3349304"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00463"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/3DV50981.2020.00088"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01514"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00062"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01520"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01694"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_32"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/358669.358692"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3093009"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.5555\/3001460.3001507"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.120"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01451"},{"key":"ref88","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3148457"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref91","article-title":"Learning from 2D: Contrastive pixel-to-point knowledge transfer for 3D pretraining","author":"Liu","year":"2021"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00506"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3584625"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.3390\/s18103337"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00328"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561251"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/IV47402.2020.9304596"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20183"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3298706"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_33"},{"key":"ref103","article-title":"MMDetection3D: OpenMMLab next-generation platform for general 3D object detection","author":"Contributors","year":"2020"},{"key":"ref104","article-title":"PCSeg: An open source point cloud segmentation codebase","author":"Liu","year":"2023"},{"key":"ref105","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Loshchilov","year":"2019"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1117\/12.2520589"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11372200\/11278787.pdf?arnumber=11278787","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:06:19Z","timestamp":1770671179000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11278787\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":106,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3640589","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":[[2026,3]]}}}