{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:31:25Z","timestamp":1776882685333,"version":"3.51.2"},"reference-count":64,"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":["61971383"],"award-info":[{"award-number":["61971383"]}],"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":["61827804"],"award-info":[{"award-number":["61827804"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key R&D Program of China","award":["2018AAA0102801"],"award-info":[{"award-number":["2018AAA0102801"]}]},{"name":"National Key R&D Program of China","award":["2018AAA0100405"],"award-info":[{"award-number":["2018AAA0100405"]}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2023M731964"],"award-info":[{"award-number":["2023M731964"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3306840","type":"journal-article","created":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T17:54:57Z","timestamp":1692640497000},"page":"3077-3087","source":"Crossref","is-referenced-by-count":11,"title":["Disjoint Masking With Joint Distillation for Efficient Masked Image Modeling"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1256-1767","authenticated-orcid":false,"given":"Xin","family":"Ma","sequence":"first","affiliation":[{"name":"School of Information and Communication Engineering, Communication University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6747-0646","authenticated-orcid":false,"given":"Chang","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6607-8209","authenticated-orcid":false,"given":"Chunyu","family":"Xie","sequence":"additional","affiliation":[{"name":"360 AI Research, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3562-5612","authenticated-orcid":false,"given":"Long","family":"Ye","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Communication University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2416-6913","authenticated-orcid":false,"given":"Yafeng","family":"Deng","sequence":"additional","affiliation":[{"name":"360 AI Research, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7333-9975","authenticated-orcid":false,"given":"Xiangyang","family":"Ji","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref2","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref4","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref9","article-title":"Efficient self-supervised vision transformers for representation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2022"},{"key":"ref10","article-title":"BEiT: BERT Pre-training of image transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bao","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25130"},{"key":"ref12","article-title":"Are large-scale datasets necessary for self-supervised pre-training?","author":"El-Nouby","year":"2021"},{"key":"ref13","article-title":"iBOT: Image BERT pre-training with online tokenizer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhou","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref18","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Keskar","year":"2016"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00815"},{"key":"ref20","article-title":"Drawing multiple augmentation samples per image during training efficiently decreases test error","author":"Fort","year":"2021"},{"key":"ref21","first-page":"35632","article-title":"ConvMAE: Masked convolution meets masked autoencoders","volume-title":"Proc. Adv. Neural Inf. Proc. Syst.","volume":"35","author":"Gao","year":"2022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref23","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh","year":"2021"},{"key":"ref24","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.","author":"Baevski","year":"2022"},{"key":"ref25","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_20"},{"key":"ref27","article-title":"BEiT v2: Masked image modeling with vector-quantized visual tokenizers","author":"Peng","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01838"},{"key":"ref29","article-title":"MILAN: Masked image pretraining on language assisted representation","author":"Hou","year":"2022"},{"key":"ref30","article-title":"CAE v2: Context autoencoder with CLIP target","author":"Zhang","year":"2022"},{"key":"ref31","first-page":"13165","article-title":"MST: Masked self-supervised transformer for visual representation","volume-title":"Proc. Adv. Neural Inf. Process. Syst","author":"Li","year":"2021"},{"key":"ref32","first-page":"20026","article-title":"Adversarial masking for self-supervised learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Shi","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_18"},{"key":"ref34","first-page":"14290","article-title":"SemMAE: Semantic-guided masking for learning masked autoencoders","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2022"},{"key":"ref35","article-title":"Accurate, large minibatch SGD: Training imagenet in 1 Hour","author":"Goyal","year":"2017"},{"key":"ref36","first-page":"1729","article-title":"Train longer, generalize better: Closing the generalization gap in large batch training of neural networks","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Hoffer","year":"2017"},{"key":"ref37","article-title":"Highly scalable deep learning training system with mixed-precision: Training ImageNet in four minutes","author":"Jia","year":"2018"},{"key":"ref38","article-title":"Image classification at supercomputer scale","author":"Ying","year":"2018"},{"key":"ref39","article-title":"Large batch training of convolutional networks","author":"You","year":"2017"},{"key":"ref40","article-title":"MultiGrain: A unified image embedding for classes and instances","author":"Berman","year":"2019"},{"key":"ref41","article-title":"Faster neural network training with data echoing","author":"Choi","year":"2019"},{"key":"ref42","article-title":"Uniform masking: Enabling MAE pre-training for pyramid-based vision transformers with locality","author":"Li","year":"2022"},{"key":"ref43","first-page":"19997","article-title":"Green hierarchical vision transformer for masked image modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Huang","year":"2022"},{"key":"ref44","article-title":"MixMIM: Mixed and masked image modeling for efficient visual representation learning","author":"Liu","year":"2022"},{"key":"ref45","article-title":"Efficient self-supervised vision pretraining with local masked reconstruction","author":"Chen","year":"2022"},{"key":"ref46","article-title":"FastMIM: Expediting masked image modeling pre-training for vision","author":"Guo","year":"2022"},{"key":"ref47","article-title":"ELECTRA: Pre-training text encoders as discriminators rather than generators","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Clark","year":"2020"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.217"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2912735"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3115335"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2759500"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3004963"},{"key":"ref53","article-title":"Contrastive learning rivals masked image modeling in fine-tuning via feature distillation","author":"Wei","year":"2022"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref55","article-title":"Layer normalization","author":"Lei Ba","year":"2016"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2844175"},{"key":"ref60","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref61","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2017"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01852-4"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_14"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_7"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10225408.pdf?arnumber=10225408","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T21:14:31Z","timestamp":1709327671000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10225408\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3306840","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}