{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T02:58:50Z","timestamp":1782701930223,"version":"3.54.5"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of Chinax","award":["2023YFE0202700"],"award-info":[{"award-number":["2023YFE0202700"]}]},{"name":"National Key Research and Development Program of Chinax","award":["2021ZD0111501"],"award-info":[{"award-number":["2021ZD0111501"]}]},{"DOI":"10.13039\/501100001809","name":"NSFC for Key Program","doi-asserted-by":"publisher","award":["62237001"],"award-info":[{"award-number":["62237001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NSFC for Excellent Young Scholars","award":["62206064"],"award-info":[{"award-number":["62206064"]}]},{"name":"NSFC for Excellent Young Scholars","award":["62206061"],"award-info":[{"award-number":["62206061"]}]},{"name":"NSFC for Excellent Young Scholars","award":["62272298"],"award-info":[{"award-number":["62272298"]}]},{"name":"NSFC for Excellent Young Scholars","award":["62176066"],"award-info":[{"award-number":["62176066"]}]},{"name":"Guangdong International Technology Cooperation Project","award":["2022A0505050009"],"award-info":[{"award-number":["2022A0505050009"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1109\/tcsvt.2024.3405069","type":"journal-article","created":{"date-parts":[[2024,5,24]],"date-time":"2024-05-24T17:30:07Z","timestamp":1716571807000},"page":"9882-9897","source":"Crossref","is-referenced-by-count":15,"title":["PatchMixing Masked Autoencoders for 3D Point Cloud Self-Supervised Learning"],"prefix":"10.1109","volume":"34","author":[{"given":"Chengxing","family":"Lin","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Guangdong University of Technology (GDUT), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenju","family":"Xu","sequence":"additional","affiliation":[{"name":"Amazon, Palo Alto, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2551-2024","authenticated-orcid":false,"given":"Jian","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Guangdong University of Technology (GDUT), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8922-3205","authenticated-orcid":false,"given":"Yongwei","family":"Nie","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8972-167X","authenticated-orcid":false,"given":"Ruichu","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Guangdong University of Technology (GDUT), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8006-3663","authenticated-orcid":false,"given":"Xuemiao","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00939"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00761"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_31"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_42"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref9","first-page":"1","article-title":"Improving language understanding by generative pre-training","volume":"1","author":"Radford","year":"2018","journal-title":"OpenAI Blog"},{"issue":"8","key":"ref10","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref11","first-page":"1298","article-title":"data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Baevski"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00964"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"ref14","first-page":"27061","article-title":"Point-M2AE: Multi-scale masked autoencoders for hierarchical point cloud pre-training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Zhang"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref17","first-page":"1","article-title":"iBOT: Image BERT pre-training with online tokenizer","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhou"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_34"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3169145"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3169469"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3221611"},{"key":"ref22","first-page":"1","article-title":"Discrete variational autoencoders","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Rolfe"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00605"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02178"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-021-0229-5"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref30","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":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00290"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26319-4_20"},{"key":"ref33","first-page":"1","article-title":"BEiT: BERT pre-training of image transformers","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Bao"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01009"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02090"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_2"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_38"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02085"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/88"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00512"},{"key":"ref42","first-page":"29667","article-title":"PointGPT: Auto-regressively generative pre-training from point clouds","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Chen"},{"key":"ref43","first-page":"652","article-title":"PointNet: Deep learning on point sets for 3D classification and segmentation","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Qi"},{"key":"ref44","first-page":"5099","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Qi"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298801"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01336"},{"key":"ref48","first-page":"82","article-title":"Learning a probabilistic latent space of object shapes via 3D generative-adversarial modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Wu"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2976627"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00979"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00029"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01054"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018376"},{"key":"ref54","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"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00967"},{"key":"ref56","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016","journal-title":"arXiv:1606.08415"},{"key":"ref57","article-title":"ShapeNet: An information-rich 3D model repository","author":"Chang","year":"2015","journal-title":"arXiv:1512.03012"},{"key":"ref58","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Loshchilov"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00167"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"ref61","first-page":"820","article-title":"PointCNN: Convolution on X-transformed points","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Li"},{"key":"ref62","first-page":"23192","article-title":"PointNeXt: Revisiting PointNet ++ with improved training and scaling strategies","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Qian"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02089"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3171968"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3247506"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611767"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"ref68","first-page":"1","article-title":"Autoencoders as cross-modal teachers: Can pretrained 2D image transformers help 3D representation learning?","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dong"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3285803"},{"key":"ref70","first-page":"28223","article-title":"Contrast with reconstruct: Contrastive 3D representation learning guided by generative pretraining","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Qi"},{"key":"ref71","first-page":"1","article-title":"Rethinking network design and local geometry in point cloud: A simple residual MLP framework","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ma"},{"issue":"11","key":"ref72","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2980238"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.264"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10739869\/10538335.pdf?arnumber=10538335","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:22:20Z","timestamp":1732666940000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10538335\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":74,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3405069","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}