{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T23:42:40Z","timestamp":1783381360418,"version":"3.54.6"},"reference-count":111,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tpami.2025.3535625","type":"journal-article","created":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T18:39:09Z","timestamp":1738089549000},"page":"3748-3765","source":"Crossref","is-referenced-by-count":38,"title":["Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Driving"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3884-2185","authenticated-orcid":false,"given":"Lingdong","family":"Kong","sequence":"first","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1950-5976","authenticated-orcid":false,"given":"Jiawei","family":"Ren","sequence":"additional","affiliation":[{"name":"S-Lab, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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":[{"vocabulary":"crossref","role":"author"}]},{"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":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8994-1736","authenticated-orcid":false,"given":"Wei Tsang","family":"Ooi","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3086804"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3142440"},{"key":"ref4","article-title":"Forging vision foundation models for autonomous driving: Challenges, methodologies, and opportunities","author":"Yan","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/machines5010006"},{"key":"ref6","article-title":"RoboDepth: Robust out-of-distribution depth estimation under corruptions","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kong"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00272"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_35"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160410"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02079"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00903"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_5"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3076844"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3226029"},{"key":"ref15","first-page":"5050","article-title":"MixMatch: A holistic approach to semi-supervised learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Berthelot"},{"key":"ref16","article-title":"FixMatch: Simplifying semi-supervised learning with consistency and confidence","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sohn"},{"key":"ref17","article-title":"RemixMatch: Semi-supervised learning with distribution alignment and augmentation anchoring","author":"Berthelot","year":"2019"},{"key":"ref18","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Tarvainen"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01269"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_26"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00264"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00636"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_22"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00607"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02281"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00939"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3390\/s21062140"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3200245"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01830"},{"key":"ref32","article-title":"RoboBEV: Towards robust bird\u2019s eye view perception under corruptions","author":"Xie","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00981"},{"key":"ref34","first-page":"26871","article-title":"PolarStream: Streaming LiDAR object detection and segmentation with polar pillars","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-64559-5_16"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636385"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00962"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3148457"},{"key":"ref39","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967762"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_41"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3207665"},{"key":"ref43","article-title":"Calib3D: Calibrating model preferences for reliable 3D scene understanding","author":"Kong","year":"2024"},{"key":"ref44","article-title":"Optimizing LiDAR placements for robust driving perception in adverse conditions","author":"Li","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561251"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2886133"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_1"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00028"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00507"},{"key":"ref50","article-title":"FRNet: Frustum-range networks for scalable LiDAR segmentation","author":"Xu","year":"2023"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01299"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3349304"},{"key":"ref54","article-title":"AMVNet: Assertion-based multi-view fusion network for LiDAR semantic segmentation","author":"Liong","year":"2020"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01572"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01980"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01523"},{"key":"ref58","article-title":"Box2Seg: Learning semantics of 3D point clouds with box-level supervision","author":"Liu","year":"2022"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2919741"},{"key":"ref60","first-page":"1","article-title":"Temporal ensembling for semi-supervised learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Laine"},{"key":"ref61","first-page":"1","article-title":"Semi-supervised semantic segmentation needs strong, high-dimensional perturbations","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"French"},{"key":"ref62","first-page":"1","article-title":"PseudoSeg: Designing pseudo labels for semantic segmentation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zou"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00422"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00812"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00141"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_46"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_18"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00423"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/3DV50981.2020.00052"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0281-9"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/icra46639.2022.9811904"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16200"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01533"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01485"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00051"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00966"},{"key":"ref77","article-title":"Segment any point cloud sequences by distilling vision foundation models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02033"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01262"},{"key":"ref80","article-title":"Visual foundation models boost cross-modal unsupervised domain adaptation for 3D semantic segmentation","author":"Xu","year":"2024"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3159589"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00678"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref84","article-title":"Towards label-free scene understanding by vision foundation models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01388"},{"key":"ref86","first-page":"529","article-title":"Semi-supervised learning by entropy minimization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Grandvalet"},{"key":"ref87","first-page":"1","article-title":"mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01112"},{"key":"ref90","article-title":"Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks","volume-title":"Proc. Int. Conf. Mach. Learn. Workshop","author":"Lee"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref92","first-page":"8430","article-title":"Objects365: A large-scale, high-quality dataset for object detection","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Zhang"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00100"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01451"},{"key":"ref98","article-title":"Segment everything everywhere all at once","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zou"},{"key":"ref99","first-page":"1067","article-title":"360$^\\circ$\u2218 from a single camera: A few-shot approach for LiDAR segmentation","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis. Workshop","author":"Reichardt"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00022"},{"key":"ref102","first-page":"11035","article-title":"PolarMix: A general data augmentation technique for LiDAR point clouds","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Xiao"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_34"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01009"},{"key":"ref105","article-title":"Learning from 2D: Contrastive pixel-to-point knowledge transfer for 3D pretraining","author":"Liu","year":"2021"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00686"},{"key":"ref107","article-title":"MMDetection3D: OpenMMLab next-generation platform for general 3D object detection","author":"Contributors","year":"2020"},{"key":"ref108","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1117\/12.2520589"},{"key":"ref110","first-page":"3239","article-title":"Realistic evaluation of deep semi-supervised learning algorithms","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Oliver"},{"key":"ref111","article-title":"Improved regularization of convolutional neural networks with cutout","author":"DeVries","year":"2017"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10958761\/10856442.pdf?arnumber=10856442","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T17:32:15Z","timestamp":1747243935000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10856442\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":111,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3535625","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":[[2025,5]]}}}