{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T14:44:35Z","timestamp":1784645075999,"version":"3.55.0"},"reference-count":135,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100011501","name":"Qinghai Provincial Department of Science and Technology through the Applied Basic Research Project","doi-asserted-by":"publisher","award":["2021-ZJ-717"],"award-info":[{"award-number":["2021-ZJ-717"]}],"id":[{"id":"10.13039\/501100011501","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3323383","type":"journal-article","created":{"date-parts":[[2023,10,11]],"date-time":"2023-10-11T17:49:06Z","timestamp":1697046546000},"page":"113560-113579","source":"Crossref","is-referenced-by-count":25,"title":["Masked Autoencoders in Computer Vision: A Comprehensive Survey"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5948-2102","authenticated-orcid":false,"given":"Zexian","family":"Zhou","sequence":"first","affiliation":[{"name":"Department of Computer Technology and Application, Qinghai University, Xining, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5571-4735","authenticated-orcid":false,"given":"Xiaojing","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Technology and Application, Qinghai University, Xining, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref57","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2018","journal-title":"arXiv 1807 03748"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.202"},{"key":"ref59","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015","journal-title":"ArXiv 1503 02531"},{"key":"ref58","article-title":"Exploring target representations for masked autoencoders","author":"liu","year":"2022","journal-title":"arXiv 2209 03917"},{"key":"ref53","article-title":"Exploring the role of mean teachers in self-supervised masked auto-encoders","author":"lee","year":"2023","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s00591-010-0080-8"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref54","article-title":"Contrastive masked autoencoders are stronger vision learners","author":"huang","year":"2022","journal-title":"arXiv 2207 13532"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19821-2_9"},{"key":"ref50","article-title":"(certified!!) adversarial robustness for free!","author":"carlini","year":"2022","journal-title":"arXiv 2206 10550"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"ref48","article-title":"IBOT: Image BERT pre-training with online tokenizer","author":"zhou","year":"2021","journal-title":"arXiv 2111 07832"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref42","first-page":"10347","article-title":"Training data-efficient image transformers and distillation through attention","author":"touvron","year":"2021","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref41","first-page":"21271","article-title":"Bootstrap your own latent—A new approach to self-supervised learning","volume":"33","author":"grill","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref44","article-title":"BEiT: BERT pre-training of image transformers","author":"bao","year":"2021","journal-title":"arXiv 2106 08254"},{"key":"ref43","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref49","article-title":"Semantic understanding of scenes through the ADE20K dataset","author":"zhou","year":"2016","journal-title":"arXiv 1608 05442"},{"key":"ref8","article-title":"A survey on masked autoencoder for self-supervised learning in vision and beyond","author":"zhang","year":"2022","journal-title":"arXiv 2208 00173"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1002\/stc.3096"},{"key":"ref9","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"arXiv 2010 11929"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2022.3227547"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.11.151"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/en15103592"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/INDIN51773.2022.9976158"},{"key":"ref100","article-title":"Solution for SnakeCLEF 2022 by tackling long-tailed categorization","author":"yang","year":"2022","journal-title":"Proc Working Notes (CLEF)"},{"key":"ref101","first-page":"2253","article-title":"Transfer learning with self-supervised vision transformer for large-scale plant identification","author":"xu","year":"2022","journal-title":"Proc Int Conf Cross-Lang Eval Forum Eur Lang"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_13"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_7"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/S0001-2998(78)80014-2"},{"key":"ref37","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv 1810 04805"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref33","article-title":"Fine-tuning can distort pretrained features and underperform out-of-distribution","author":"kumar","year":"0","journal-title":"ICLRE"},{"key":"ref32","first-page":"551","article-title":"Computer vision","author":"quinn","year":"2020","journal-title":"Dive into Deep Learning Tools for Engagement"},{"key":"ref39","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"Proc IEEE Int Conf (ICML)"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-020-09548-1"},{"key":"ref24","article-title":"The kinetics human action video dataset","author":"kay","year":"2017","journal-title":"arXiv 1705 06950"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_15"},{"key":"ref22","article-title":"Denoising masked autoencoders help robust classification","author":"wu","year":"2023","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref21","first-page":"14290","article-title":"SemMAE: Semantic-guided masking for learning masked autoencoders","volume":"35","author":"li","year":"2022","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref27","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"soomro","year":"2012","journal-title":"arXiv 1212 0402"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.107037"},{"key":"ref128","article-title":"MGAE: Masked autoencoders for self-supervised learning on graphs","author":"tan","year":"2022","journal-title":"arXiv 2201 02534"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3199228"},{"key":"ref129","article-title":"Masked autoencoders are robust data augmentors","author":"xu","year":"2022","journal-title":"arXiv 2206 04846"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.3390\/s22218331"},{"key":"ref126","article-title":"Occupancy-MAE: Self-supervised pre-training large-scale LiDAR point clouds with masked occupancy autoencoders","author":"min","year":"2022","journal-title":"arXiv 2206 09900"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00150"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539321"},{"key":"ref11","article-title":"How to understand masked autoencoders","author":"cao","year":"2022","journal-title":"arXiv 2202 03670"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.3390\/ani12213055"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_38"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00765"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/SECON55815.2022.9918549"},{"key":"ref125","first-page":"27061","article-title":"Point-M2AE: Multi-scale masked autoencoders for hierarchical point cloud pre-training","volume":"35","author":"zhang","year":"2022","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-17266-3_6"},{"key":"ref16","first-page":"1","article-title":"CoTMAE: Hybrid convolution-transformer pyramid network meets masked autoencoder","author":"li","year":"2022","journal-title":"Proc 9th Int Conf Asian Soc Precis Engg Nanotechnol (ASPEN)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref18","article-title":"Contrastive audio-visual masked autoencoder","author":"gong","year":"2023","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00555"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1016\/j.engstruct.2022.115158"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00271"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2022.107079"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3249566"},{"key":"ref131","first-page":"1","article-title":"Masked spectrogram modeling using masked autoencoders for learning general-purpose audio representation","author":"niizumi","year":"2022","journal-title":"Proc HEAR Holistic Eval Audio Represent"},{"key":"ref94","article-title":"Self pre-training with masked autoencoders for medical image analysis","author":"zhou","year":"2022","journal-title":"arXiv 2203 05573"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3211965"},{"key":"ref130","first-page":"28708","article-title":"Masked autoencoders that listen","volume":"35","author":"huang","year":"2022","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-8152-4_12"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-17027-0_11"},{"key":"ref89","article-title":"Masked autoencoders pre-training in multiple instance learning for whole slide image classification","author":"an","year":"2022","journal-title":"Proc Med Imag with Deep Learn (MIDL)"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICIST55546.2022.9926900"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548243"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00358"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2023.107827"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TCBB.2023.3246979"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2022.3228267"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01399"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01394"},{"key":"ref79","first-page":"35946","article-title":"Masked autoencoders as spatiotemporal learners","volume":"35","author":"feichtenhofer","year":"2022","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref108","first-page":"egu-2843","article-title":"Geography-aware masked autoencoders for change detection in remote sensing","author":"kondmann","year":"2023","journal-title":"Proc EGU Gen Assem Conf Abstr"},{"key":"ref78","first-page":"10078","article-title":"VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume":"35","author":"tong","year":"2022","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref109","first-page":"1287","article-title":"Automatic hiding method of sensitive targets in remote sensing images based on transformer structure","volume":"47","author":"li","year":"2022","journal-title":"Geomatics Inf Sci Wuhan Univ"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.3390\/rs14184656"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3201489"},{"key":"ref75","first-page":"679","article-title":"Multi-modal masked autoencoders for Medical vision-and-language pretraining","author":"chen","year":"2022","journal-title":"Proc Int Conf Med Image Comput Comput -Assist Intervent"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/SP46215.2023.10179379"},{"key":"ref74","article-title":"Multimodal masked autoencoders learn transferable representations","author":"geng","year":"2022","journal-title":"arXiv 2205 14204"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/IAECST54258.2021.9695735"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01003"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.13031\/aim.202200508"},{"key":"ref76","first-page":"24261","article-title":"MLP-mixer: An all-MLP architecture for vision","volume":"34","author":"tolstikhin","year":"2021","journal-title":"Proc 35th Conf Neural Inf Process Syst"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-21648-0_14"},{"key":"ref2","first-page":"5999","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Proc 31st Conf Neural Inf Process Syst"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_20"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00559"},{"key":"ref70","article-title":"Supmae: Supervised masked autoencoders are efficient vision learners","author":"liang","year":"2022","journal-title":"arXiv 2205 14540"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859873"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00201"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_22"},{"key":"ref110","first-page":"159","article-title":"Fire detection and verification using convolutional neural networks, masked autoencoder and transfer learning","volume":"16","author":"almoussawi","year":"2022","journal-title":"Majlesi J Electr Eng"},{"key":"ref68","article-title":"Uniform masking: Enabling mae pre-training for pyramid-based vision transformers with locality","author":"li","year":"2022","journal-title":"arXiv 2205 10063"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00512"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096209"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_3"},{"key":"ref69","first-page":"19997","article-title":"Green hierarchical vision transformer for masked image modeling","volume":"35","author":"huang","year":"2022","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02085"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref115","article-title":"DeepFakes: A new threat to face recognition? Assessment and detection","author":"korshunov","year":"2018","journal-title":"arXiv 1812 08685"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/CEI57409.2022.9950092"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02342"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/ICSES55317.2022.9914213"},{"key":"ref65","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"arXiv 1704 04861"},{"key":"ref114","article-title":"MaskViT: Masked visual pre-training for video prediction","author":"gupta","year":"2022","journal-title":"arXiv 2206 11894"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02323"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"ref62","first-page":"35632","article-title":"MCMAE: Masked convolution meets masked autoencoders","volume":"35","author":"gao","year":"2022","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/88"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3263288"},{"key":"ref121","article-title":"POS-BERT: Point cloud one-stage BERT pre-training","author":"fu","year":"2022","journal-title":"arXiv 2204 00989"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10278410.pdf?arnumber=10278410","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T19:57:45Z","timestamp":1699300665000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10278410\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":135,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3323383","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}