{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T16:56:36Z","timestamp":1775667396217,"version":"3.50.1"},"reference-count":78,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276200"],"award-info":[{"award-number":["62276200"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62036006"],"award-info":[{"award-number":["62036006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Basic Research Plan in Shaanxi Province of China","award":["2022JM-327"],"award-info":[{"award-number":["2022JM-327"]}]},{"name":"CAAI-Huawei MINDSPORE Academic Open Fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3317998","type":"journal-article","created":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T18:24:08Z","timestamp":1695666248000},"page":"3897-3908","source":"Crossref","is-referenced-by-count":12,"title":["Inter-Modal Masked Autoencoder for Self-Supervised Learning on Point Clouds"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-9699-1987","authenticated-orcid":false,"given":"Jiaming","family":"Liu","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3459-5079","authenticated-orcid":false,"given":"Yue","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0415-8556","authenticated-orcid":false,"given":"Maoguo","family":"Gong","sequence":"additional","affiliation":[{"name":"School of Electronic Engineering, Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3517-9556","authenticated-orcid":false,"given":"Zhixiao","family":"Liu","sequence":"additional","affiliation":[{"name":"Yantai Research Institute, Harbin Engineering University, Yantai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6766-8310","authenticated-orcid":false,"given":"Qiguang","family":"Miao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8872-2195","authenticated-orcid":false,"given":"Wenping","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, Xidian University, Xi'an, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Devlin","year":"2018"},{"key":"ref2","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown","year":"2020"},{"issue":"140","key":"ref3","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref6","first-page":"1691","article-title":"Generative pretraining from pixels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3056238"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2017.06.011"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW58289.2023.00039"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6859"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00967"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3029008"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-021-0229-5"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3116304"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3198318"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00831"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01150"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3198011"},{"key":"ref25","article-title":"Unsupervised representation learning by predicting image rotations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gidaris","year":"2018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3140070"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref31","first-page":"40","article-title":"Learning representations and generative models for 3D point clouds","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Achlioptas","year":"2018"},{"key":"ref32","article-title":"Self-supervised deep learning on point clouds by reconstructing space","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"32","author":"Sauder","year":"2019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_34"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00964"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01009"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01533"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00815"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3206664"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01336"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20040"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3073265"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3284591"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00692"},{"key":"ref45","first-page":"638","article-title":"Image2point: 3D point-cloud understanding with pretrained 2D convnets","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Xu","year":"2021"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00637"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3237328"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3271757"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3286943"},{"key":"ref50","article-title":"Discrete variational autoencoders","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Rolfe","year":"2016"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_38"},{"key":"ref53","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.","author":"Zhang","year":"2022"},{"key":"ref54","first-page":"492","article-title":"Disn: Deep implicit surface network for high-quality single-view 3D reconstruction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2019"},{"key":"ref55","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.","author":"Qi","year":"2017"},{"key":"ref56","first-page":"77","article-title":"PointNet: Deep learning on point sets for 3D classification and segmentation","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Qi","year":"2017"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref58","article-title":"ShapeNet: An information-rich 3D model repository","author":"Chang","year":"2015"},{"key":"ref59","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2017"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298801"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00167"},{"key":"ref62","first-page":"820","article-title":"PointCNN: Convolution on x-transformed points","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2018"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00985"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00651"},{"key":"ref65","first-page":"23192","article-title":"Pointnext: Revisiting pointnet with improved training and scaling strategies","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Qian","year":"2022"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00319"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00095"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3074240"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01519"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01837"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506426"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1002\/int.23073"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_6"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2980238"},{"issue":"11","key":"ref75","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref76","article-title":"3D feature prediction for masked-autoencoder-based point cloud pretraining","author":"Yan","year":"2023"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01302"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02082"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10262210.pdf?arnumber=10262210","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T06:28:32Z","timestamp":1709360912000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10262210\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":78,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3317998","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}