{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:55:49Z","timestamp":1777888549732,"version":"3.51.4"},"reference-count":77,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02564","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"27618-27629","source":"Crossref","is-referenced-by-count":0,"title":["Point Cloud Self-Supervised Learning via 3D to Multi-View Masked Learner"],"prefix":"10.1109","author":[{"given":"Zhimin","family":"Chen","sequence":"first","affiliation":[{"name":"Clemson University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuewei","family":"Chen","sequence":"additional","affiliation":[{"name":"Clemson University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Guo","sequence":"additional","affiliation":[{"name":"Michigan State University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingwei","family":"Li","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longlong","family":"Jing","sequence":"additional","affiliation":[{"name":"The City University of New York"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Yang","sequence":"additional","affiliation":[{"name":"The City University of New York"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bing","family":"Li","sequence":"additional","affiliation":[{"name":"Clemson University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00967"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_20"},{"key":"ref3","article-title":"Shapenet: An information-rich 3d model repository","author":"Chang","year":"2015","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00512"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1291"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.111154"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.5244\/c.35.217"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3467"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2638"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref12","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Autoencoders as cross-modal teachers: Can pretrained 2d image transformers help 3d representation learning?","author":"Dong","year":"2022","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00667"},{"key":"ref15","article-title":"Contrastive audio-visual masked autoencoder","author":"Gong","year":"2022","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02255-9"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/88"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00007"},{"key":"ref20","article-title":"Voint cloud: Multi-view point cloud representation for 3d understanding","author":"Hamdi","year":"2021","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref22","article-title":"Self-supervised modal and view invariant feature learning","author":"Jing","year":"2020","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS60139.2025.11246484"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_38"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01471"},{"key":"ref26","article-title":"Core knowledge deficits in multi-modal language models","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Beyond finite data: Towards data-free out-of-distribution generalization via extrapolation","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"M2iv: Towards efficient and fine-grained multimodal in-context learning in large visionlanguage models","author":"Li","year":"2025","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"Cama: Enhancing multimodal in-context learning with context-aware modulated attention","author":"Li","year":"2025","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.39"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_38"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00910"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00290"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01229"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102033"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.16"},{"key":"ref40","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","author":"Ruizhongtai Qi","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref41","first-page":"9277","article-title":"Deep hough voting for 3d object detection in point clouds","volume-title":"proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Charles","year":"2019"},{"key":"ref42","article-title":"Contrast with reconstruct: Contrastive 3d representation learning guided by generative pretraining","author":"Qi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Improving language understanding by generative pre-training","volume-title":"Proceedings of the 2019 3rd International Conference on Natural Language Processing and Information Retrieval","author":"Radford","year":"2019"},{"issue":"8","key":"ref44","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref45","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref46","author":"Ravi","year":"2020","journal-title":"Accelerating 3d deep learning with pytorch3d"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_32"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00104"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00445"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00549"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00966"},{"key":"ref52","article-title":"On learning multi-modal forgery representation for diffusion generated video detection","author":"Song","year":"2024","journal-title":"NeurIPS"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.114"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00241"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00167"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00167"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102871"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00519"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298801"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_34"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/IROS60139.2025.11247052"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2980238"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01871"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.107096"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755108"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3358850"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.111200"},{"key":"ref70","article-title":"Point-m2ae: multi-scale masked autoencoders for hierarchical point cloud pre-training","author":"Zhang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02085"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73223-2_22"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01009"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2024.3370762"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/tvt.2026.3679364"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3070828"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3063477"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444274.pdf?arnumber=11444274","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:49:38Z","timestamp":1777610978000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444274\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02564","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}