{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T21:04:24Z","timestamp":1775682264074,"version":"3.50.1"},"reference-count":94,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFC3015801"],"award-info":[{"award-number":["2024YFC3015801"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Science Fund of China","award":["U24A20330"],"award-info":[{"award-number":["U24A20330"]}]},{"name":"National Science Fund of China","award":["62361166670"],"award-info":[{"award-number":["62361166670"]}]},{"name":"National Science Fund of China","award":["62276144"],"award-info":[{"award-number":["62276144"]}]},{"name":"National Science Fund of China","award":["62306238"],"award-info":[{"award-number":["62306238"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3671587","type":"journal-article","created":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T19:54:15Z","timestamp":1774986855000},"page":"3566-3580","source":"Crossref","is-referenced-by-count":0,"title":["Learning 3D Representation From Auto-Labeled 2D Object Boxes"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0998-6788","authenticated-orcid":false,"given":"Qian","family":"Deng","sequence":"first","affiliation":[{"name":"College of Computer Science, Nankai University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0851-6805","authenticated-orcid":false,"given":"Le","family":"Hui","sequence":"additional","affiliation":[{"name":"School of Electronics and Information, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4800-832X","authenticated-orcid":false,"given":"Jian","family":"Yang","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology and the School of Intelligence Science and Technology, Nanjing University, Suzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9157-838X","authenticated-orcid":false,"given":"Jin","family":"Xie","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology and the School of Intelligence Science and Technology, Nanjing University, Suzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01450"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01980"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00342"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-021-0229-5"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.26599\/cvm.2025.9450383"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00463"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01683"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01849"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3372449"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3072214"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3372446"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3205208"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3190709"},{"key":"ref15","article-title":"COARSE3D: Class-prototypes for contrastive learning in weakly-supervised 3D point cloud segmentation","author":"Li","year":"2022","journal-title":"arXiv:2210.01784"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_3"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00272"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_15"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_5"},{"key":"ref20","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"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01690"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02079"},{"key":"ref23","first-page":"1","article-title":"Semi-supervised LiDAR semantic segmentation with spatial consistency training","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kong"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00903"},{"key":"ref25","first-page":"1","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"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3279660"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00966"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00686"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00678"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3315"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1617"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_4"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-0969-7_2"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01981-w"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02549"},{"key":"ref36","article-title":"LargeAD: Large-scale cross-sensor data pretraining for autonomous driving","author":"Kong","year":"2025","journal-title":"arXiv:2501.04005"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.691"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2016.XII.042"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.114"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00939"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561171"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1602.07360"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_1"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00962"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_41"},{"key":"ref48","first-page":"33330","article-title":"Point transformer v2: Grouped vector attention and partition-based pooling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Wu"},{"key":"ref49","article-title":"Submanifold sparse convolutional networks","author":"Graham","year":"2017","journal-title":"arXiv:1706.01307"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.28"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353481"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00959"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01154"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_34"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01009"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3142440"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3286981"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3345353"},{"key":"ref60","article-title":"Learning from 2D: Contrastive pixel-to-point knowledge transfer for 3D pretraining","author":"Liu","year":"2021","journal-title":"arXiv:2104.04687"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3584625"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.120"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00506"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01451"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00100"},{"key":"ref67","first-page":"19769","article-title":"Segment everything everywhere all at once","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Zou"},{"key":"ref68","article-title":"Is contrastive distillation enough for learning comprehensive 3D representations?","author":"Zhang","year":"2024","journal-title":"arXiv:2412.08973"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4078"},{"key":"ref70","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref73","article-title":"Language-driven semantic segmentation","author":"Li","year":"2022","journal-title":"arXiv:2201.03546"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_26"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_7"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01076"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02250"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00083"},{"key":"ref83","first-page":"15946","article-title":"Multi-modal classifiers for open-vocabulary object detection","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kaul"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref85","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv:2304.07193"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01883"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3535625"},{"key":"ref93","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11459399.pdf?arnumber=11459399","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T20:09:19Z","timestamp":1775678959000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11459399\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":94,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3671587","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}