{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T04:39:34Z","timestamp":1784349574368,"version":"3.55.0"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Key Research and Development Program of Shaanxi Province","award":["2021GY-025"],"award-info":[{"award-number":["2021GY-025"]}]},{"name":"Key Research and Development Program of Shaanxi Province","award":["2021GXLH-Z-097"],"award-info":[{"award-number":["2021GXLH-Z-097"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tcsvt.2024.3430904","type":"journal-article","created":{"date-parts":[[2024,7,19]],"date-time":"2024-07-19T17:43:00Z","timestamp":1721410980000},"page":"12158-12170","source":"Crossref","is-referenced-by-count":9,"title":["PTM: Torus Masking for 3D Representation Learning Guided by Robust and Trusted Teachers"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8723-9924","authenticated-orcid":false,"given":"Haozhe","family":"Cheng","sequence":"first","affiliation":[{"name":"School of Software, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3081-8781","authenticated-orcid":false,"given":"Jihua","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Software, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2048-3375","authenticated-orcid":false,"given":"Naiwen","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Software, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6295-7850","authenticated-orcid":false,"given":"Jinqian","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Software, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9884-9923","authenticated-orcid":false,"given":"Wenbiao","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Software, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3251395"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3272741"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3169469"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3284493"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00967"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.111217"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"ref12","article-title":"Autoencoders as cross-modal teachers: Can pretrained 2D image transformers help 3D representation learning?","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Dong"},{"key":"ref13","first-page":"28223","article-title":"Contrast with reconstruct: Contrastive 3D representation learning guided by generative pretraining","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Qi"},{"key":"ref14","article-title":"Self-supervised adversarial masking for 3D point cloud representation learning","author":"Szachniewicz","year":"2023","journal-title":"arXiv:2307.05325"},{"key":"ref15","first-page":"79226","article-title":"Bridging the domain gap: Self-supervised 3D scene understanding with foundation models","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Chen"},{"key":"ref16","article-title":"Contrastive representation distillation","author":"Tian","year":"2019","journal-title":"arXiv:1910.10699"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01165"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"ref20","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. (NeurIPS)","author":"Zhang"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_38"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/88"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02085"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00836"},{"key":"ref28","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":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00249"},{"key":"ref30","article-title":"Visual recognition with deep nearest centroids","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Wang"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00261"},{"key":"ref32","first-page":"46419","article-title":"Unified 3D segmenter as prototypical classifiers","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Qin"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27944"},{"key":"ref34","volume-title":"Bayesian Learning for Neural Networks","volume":"118","author":"Neal","year":"2012"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.3.448"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045502"},{"key":"ref37","first-page":"6402","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Lakshminarayanan"},{"key":"ref38","first-page":"3183","article-title":"Evidential deep learning to quantify classification uncertainty","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Sensoy"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3171983"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-44792-4_3"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1515\/9780691214696"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_30"},{"key":"ref43","article-title":"Fusion is not enough: Single-modal attacks to compromise fusion models in autonomous driving","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Cheng"},{"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. (NeurIPS)","author":"Qi"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2021.104239"},{"key":"ref46","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":"ref47","article-title":"Rethinking network design and local geometry in point cloud: A simple residual MLP framework","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Ma"},{"key":"ref48","first-page":"23192","article-title":"PointNext: Revisiting PointNet++ with improved training and scaling strategies","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Qian"},{"key":"ref49","first-page":"14388","article-title":"P2P: Tuning pre-trained image models for point cloud analysis with point-to-pixel prompting","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Wang"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02025"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612106"},{"key":"ref52","article-title":"ShapeNet: An information-rich 3D model repository","author":"Chang","year":"2015","journal-title":"arXiv:1512.03012"},{"key":"ref53","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Dosovitskiy"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.170"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00939"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00167"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298801"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00174"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00964"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00719"},{"key":"ref64","first-page":"29667","article-title":"PointGPT: Auto-regressively generative pre-training from point clouds","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Chen"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00290"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00981"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_41"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10811772\/10604912.pdf?arnumber=10604912","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T20:14:35Z","timestamp":1736453675000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10604912\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":67,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3430904","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}