{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:45:06Z","timestamp":1777567506491,"version":"3.51.4"},"reference-count":141,"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":[{"name":"Apple Scholars in AI\/ML Ph.D. Fellowship Program"},{"DOI":"10.13039\/100031931","name":"Shanghai Artificial Intelligence Laboratory","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100031931","id-type":"DOI","asserted-by":"publisher"}]},{"name":"PJ-PRJ24DMX001 Program"},{"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/tpami.2025.3617126","type":"journal-article","created":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T17:39:25Z","timestamp":1759426765000},"page":"1291-1308","source":"Crossref","is-referenced-by-count":3,"title":["LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Driving"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3884-2185","authenticated-orcid":false,"given":"Lingdong","family":"Kong","sequence":"first","affiliation":[{"name":"School of Computing, Department of Computer Science, National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4505-0912","authenticated-orcid":false,"given":"Xiang","family":"Xu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1625-4318","authenticated-orcid":false,"given":"Youquan","family":"Liu","sequence":"additional","affiliation":[{"name":"Hochschule Bremerhaven, Bremerhaven, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7578-7667","authenticated-orcid":false,"given":"Jun","family":"Cen","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8832-9016","authenticated-orcid":false,"given":"Runnan","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2748-4514","authenticated-orcid":false,"given":"Wenwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1821-4296","authenticated-orcid":false,"given":"Liang","family":"Pan","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"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"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Megatron-LM: Training multi-billion parameter language models using model parallelism","author":"Shoeybi"},{"key":"ref2","first-page":"30","article-title":"Training compute-optimal large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Hoffmann","year":"2022"},{"key":"ref3","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang"},{"key":"ref4","article-title":"GPT-4 technical report"},{"issue":"240","key":"ref5","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01451"},{"key":"ref8","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":"ref9","article-title":"An empirical study of training state-of-the-art LiDAR segmentation models","author":"Sun"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IVWorkshops54471.2021.9669228"},{"key":"ref11","article-title":"Analyzing deep learning representations of point clouds for real-time in-vehicle LiDAR perception","author":"Uecker"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3390\/technologies10040090"},{"key":"ref13","first-page":"34980","article-title":"Is your LiDAR placement optimized for 3D scene understanding?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Li","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1177\/02783649211006735"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00272"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02079"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00903"},{"key":"ref18","first-page":"1","article-title":"Coarse3D: Class-prototypes for contrastive learning in weakly-supervised 3D point cloud segmentation","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Li","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3076844"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3262786"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3535960"},{"key":"ref22","first-page":"21298","article-title":"Robodepth: Robust out-of-distribution depth estimation under corruptions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Kong","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0706"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6224570"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00258"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610896"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196512"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00100"},{"key":"ref29","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":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00966"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00686"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.120"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00494"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01112"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00651"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3083288"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/wacv56688.2023.00135"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00313"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967762"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_1"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IV47402.2020.9304631"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636385"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859693"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00028"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3550011"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00962"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01299"},{"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":"10.1109\/CVPR46437.2021.01289"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3349304"},{"key":"ref52","article-title":"Amvnet: Assertion-based multi-view fusion network for LiDAR semantic segmentation","author":"Liong"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_41"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01572"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01597"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01236"},{"key":"ref57","first-page":"1","article-title":"GFNET: Geometric flow network for 3D point cloud semantic segmentation","volume":"1","author":"Qiu","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3535625"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_35"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01154"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_3"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_5"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_15"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3264102"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01262"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3159589"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160410"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00702"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_33"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00134"},{"key":"ref71","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":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref73","first-page":"1","article-title":"DINOV2: Learning robust visual features without supervision","volume":"1","author":"Oquab","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00110"},{"key":"ref75","first-page":"12962","article-title":"Self-supervised deep learning on point clouds by reconstructing space","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Sauder","year":"2019"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/3DV50981.2020.00112"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58526-6_37"},{"key":"ref78","article-title":"SERP: Self-supervised representation learning using perturbed point clouds","author":"Garg"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26319-4_25"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_32"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00678"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01230"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_38"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02060"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_32"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"ref89","article-title":"Unsupervised representation learning by predicting image rotations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Gidaris","year":"2018"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref92","article-title":"Improved baselines with momentum contrastive learning","author":"Chen"},{"key":"ref93","first-page":"4182","article-title":"Data-efficient image recognition with contrastive predictive coding","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Henaff","year":"2020"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00990"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00993"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref99","first-page":"35946","article-title":"Masked autoencoders as spatiotemporal learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Feichtenhofer","year":"2022"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00107"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01293"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00017"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_34"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01009"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3142440"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_4"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00536"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341614"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC57777.2023.10421941"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2025.3543302"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01388"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00939"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00601"},{"key":"ref117","article-title":"Unidrive: Towards universal driving perception across camera configurations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li","year":"2025"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2025.3546784"},{"key":"ref119","article-title":"Learning from 2D: Contrastive pixel-to-point knowledge transfer for 3D pretraining","author":"Liu"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00252"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1145\/358669.358692"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.5555\/3001460.3001507"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3148457"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref125","first-page":"1","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2020"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00506"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01883"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01981-w"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02033"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561251"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/IV47402.2020.9304596"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00905"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20183"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3298706"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01830"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.3390\/s18103337"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00328"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01170"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00464"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11345188\/11190062.pdf?arnumber=11190062","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:00:58Z","timestamp":1768255258000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11190062\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":141,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3617126","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":[[2026,2]]}}}