{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T08:43:47Z","timestamp":1770194627339,"version":"3.49.0"},"reference-count":61,"publisher":"Tsinghua University Press","issue":"1","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62471168"],"award-info":[{"award-number":["62471168"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Comp. Visual. Med."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.26599\/cvm.2025.9450425","type":"journal-article","created":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:37:51Z","timestamp":1767638271000},"page":"141-158","source":"Crossref","is-referenced-by-count":0,"title":["BoostPoint: Boosting Point Cloud Backbones with Image Pre-Training for 3D Understanding"],"prefix":"10.26599","volume":"12","author":[{"given":"Honggu","family":"Zhou","sequence":"first","affiliation":[{"name":"School of Digital Media Technology, Hangzhou Dianzi University,Hangzhou,China,310018"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yakai","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Digital Media Technology, Hangzhou Dianzi University,Hangzhou,China,310018"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haohan","family":"Li","sequence":"additional","affiliation":[{"name":"School of Digital Media Technology, Hangzhou Dianzi University,Hangzhou,China,310018"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoling","family":"Gu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Hangzhou Dianzi University,Hangzhou,China,310018"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Zeng","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University,Xiamen,China,361005"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zizhao","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Digital Media Technology, Hangzhou Dianzi University,Hangzhou,China,310018"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"11138","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00494"},{"key":"ref2","author":"Chang","year":"2015","journal-title":"ShapeNet: An information-rich 3D model repository"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_36"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.114"},{"key":"ref5","author":"Wang","year":"2022","journal-title":"P2P: Tuning pre-trained image models for point cloud analysis with point-to-pixel prompting"},{"key":"ref6","author":"Goyal","year":"2021","journal-title":"Revisiting point cloud shape classification with a simple and effective baseline"},{"key":"ref7","author":"Yan","year":"2022","journal-title":"Let images give you more: Point cloud cross-modal training for shape analysis"},{"key":"ref8","author":"Liu","year":"2021","journal-title":"Learning from 2D: Contrastive pixel-to-point knowledge transfer for 3D pretraining"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00444"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20040"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00967"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3004555"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2010.2091281"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.463"},{"key":"ref15","author":"Vaswani","year":"2017","journal-title":"Attention is all you need"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/3dv62453.2024.00113"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2022.106004"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02312"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.16"},{"key":"ref20","author":"Qi","year":"2017","journal-title":"Pointriet-l+l-: Deep hierarchical feature learning on point sets in a metric space"},{"key":"ref21","author":"Ma","year":"2022","journal-title":"Rethinking network design and local geometry in point cloud: A simple residual MLP framework"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00910"},{"key":"ref24","author":"Li","year":"2018","journal-title":"PointCNN: Convolution on X-transformed points"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00985"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00563"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-021-0229-5"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00035"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2017.07.013"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.202"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25178"},{"key":"ref33","author":"Ma","year":"2023","journal-title":"Image as set of points"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref35","first-page":"492","article-title":"DISN: Deep implicit surface network for high-quality single-view 3D reconstruction","volume-title":"Proceedings of the 33rd International Conference on Neural Information Processing Systems","author":"Xu","year":"2019"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00651"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_20"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3074240"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16414"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_38"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"ref43","author":"Zhang","year":"2022","journal-title":"Point-M2AE: Multi-scale masked autoencoders for hierarchical point cloud pre-training"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28522"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02085"},{"key":"ref46","author":"Dong","year":"2022","journal-title":"Autoencoders as cross-modal teachers: Can pretrained 2D image transformers help 3D representation learning"},{"key":"ref47","author":"Qi","year":"2023","journal-title":"Contrast with reconstruct: Contrastive 3D representation learning guided by generative pretraining"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/88"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02085"},{"key":"ref50","author":"Qi","year":"2023","journal-title":"Contrast with reconstruct: Contrastive 3D representation learning guided by generative pretraining"},{"key":"ref51","author":"Zhang","year":"2023","journal-title":"Faster segment anything: Towards lightweight SAM for mobile applications"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298801"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00167"},{"key":"ref54","author":"Sauder","year":"2019","journal-title":"Self-supervised deep learning on point clouds by reconstructing space"},{"key":"ref55","first-page":"7212","article-title":"Self-supervised few-shot learning on point clouds","volume-title":"Proceedings of the 34th Conference on Neural Information Processing Systems","author":"Sharma","year":"2020"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00964"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00647"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3314973"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00120"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"}],"container-title":["Computational Visual Media"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10750449\/11370641\/11329128.pdf?arnumber=11329128","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T20:54:32Z","timestamp":1770152072000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11329128\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":61,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.26599\/cvm.2025.9450425","relation":{},"ISSN":["2096-0662","2096-0433"],"issn-type":[{"value":"2096-0662","type":"electronic"},{"value":"2096-0433","type":"print"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}