{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T15:15:11Z","timestamp":1780413311663,"version":"3.54.1"},"reference-count":86,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"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":"crossref","award":["62225208"],"award-info":[{"award-number":["62225208"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62171431"],"award-info":[{"award-number":["62171431"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61836012"],"award-info":[{"award-number":["61836012"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"Strategic Priority Research Program of Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["XDA27000000"],"award-info":[{"award-number":["XDA27000000"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1109\/tcsvt.2024.3393474","type":"journal-article","created":{"date-parts":[[2024,4,25]],"date-time":"2024-04-25T17:59:38Z","timestamp":1714067978000},"page":"8779-8793","source":"Crossref","is-referenced-by-count":2,"title":["Generic-to-Specific Distillation of Masked Autoencoders"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8899-0069","authenticated-orcid":false,"given":"Wei","family":"Huang","sequence":"first","affiliation":[{"name":"School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6643-9329","authenticated-orcid":false,"given":"Zhiliang","family":"Peng","sequence":"additional","affiliation":[{"name":"School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3083-7170","authenticated-orcid":false,"given":"Li","family":"Dong","sequence":"additional","affiliation":[{"name":"Microsoft Research, BeiJing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Furu","family":"Wei","sequence":"additional","affiliation":[{"name":"Microsoft Research, BeiJing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1215-6259","authenticated-orcid":false,"given":"Qixiang","family":"Ye","sequence":"additional","affiliation":[{"name":"School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0454-3929","authenticated-orcid":false,"given":"Jianbin","family":"Jiao","sequence":"additional","affiliation":[{"name":"School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref5","first-page":"1","article-title":"BEiT: BERT pre-training of image transformers","volume-title":"Proc. ICLR","author":"Bao"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref7","article-title":"HiViT: Hierarchical vision transformer meets masked image modeling","author":"Zhang","year":"2022","journal-title":"arXiv:2205.14949"},{"key":"ref8","article-title":"BEiT v2: Masked image modeling with vector-quantized visual tokenizers","author":"Peng","year":"2022","journal-title":"arXiv:2208.06366"},{"key":"ref9","article-title":"Context autoencoder for self-supervised representation learning","author":"Chen","year":"2022","journal-title":"arXiv:2202.03026"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"ref11","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","author":"Baevski","year":"2022","journal-title":"arXiv:2202.03555"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref13","article-title":"FitNets: Hints for thin deep nets","author":"Romero","year":"2014","journal-title":"arXiv:1412.6550"},{"key":"ref14","article-title":"Training data-efficient image transformers & distillation through attention","author":"Touvron","year":"2020","journal-title":"arXiv:2012.12877"},{"key":"ref15","article-title":"TinyBERT: Distilling BERT for natural language understanding","author":"Jiao","year":"2019","journal-title":"arXiv:1909.10351"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3243048"},{"key":"ref22","article-title":"Integrally migrating pre-trained transformer encoder\u2013decoders for visual object detection","author":"Liu","year":"2022","journal-title":"arXiv:2205.09613"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2203.16527"},{"key":"ref24","first-page":"23296","article-title":"Intriguing properties of vision transformers","volume-title":"Proc. NIPS","volume":"34","author":"Naseer"},{"key":"ref25","article-title":"MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer","author":"Mehta","year":"2021","journal-title":"arXiv:2110.02178"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_5"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01174"},{"key":"ref28","first-page":"3396","article-title":"Cross-architecture knowledge distillation","volume-title":"Proc. ACCV","author":"Liu"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref30","article-title":"Rethinking knowledge distillation via cross-entropy","author":"Yang","year":"2022","journal-title":"arXiv:2208.10139"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00497"},{"key":"ref32","first-page":"3030","article-title":"Learning what and where to transfer","volume-title":"Proc. ICML","author":"Jang"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00145"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00511"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3250031"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3222013"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3090902"},{"key":"ref39","article-title":"ViTKD: Practical guidelines for ViT feature knowledge distillation","author":"Yang","year":"2022","journal-title":"arXiv:2209.02432"},{"key":"ref40","article-title":"Learning efficient vision transformers via fine-grained manifold distillation","author":"Hao","year":"2021","journal-title":"arXiv:2107.01378"},{"key":"ref41","article-title":"Meta knowledge distillation","author":"Liu","year":"2022","journal-title":"arXiv:2202.07940"},{"key":"ref42","first-page":"24031","article-title":"Self-supervised models are good teaching assistants for vision transformers","volume-title":"Proc. ICML","author":"Wu"},{"key":"ref43","first-page":"5213","article-title":"Distilling object detectors with feature richness","volume-title":"Proc. NeurIPS","author":"Du"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00526"},{"key":"ref45","first-page":"1","article-title":"SEED: Self-supervised distillation for visual representation","volume-title":"Proc. ICLR","author":"Fang"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_14"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00359"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref49","first-page":"10078","article-title":"VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume-title":"Proc. NeurIPS","author":"Tong"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00961"},{"key":"ref51","article-title":"IBOT: Image BERT pre-training with online tokenizer","author":"Zhou","year":"2021","journal-title":"arXiv:2111.07832"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref53","article-title":"Masked autoencoders enable efficient knowledge distillers","author":"Bai","year":"2022","journal-title":"arXiv:2208.12256"},{"key":"ref54","article-title":"VanillaKD: Revisit the power of vanilla knowledge distillation from small scale to large scale","author":"Hao","year":"2023","journal-title":"arXiv:2305.15781"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref57","article-title":"ResNet strikes back: An improved training procedure in timm","author":"Wightman","year":"2021","journal-title":"arXiv:2110.00476"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref59","first-page":"1","article-title":"Designing BERT for convolutional networks: Sparse and hierarchical masked modeling","volume-title":"Proc. ICLR","author":"Tian"},{"key":"ref60","article-title":"Exploring simple Siamese representation learning","author":"Chen","year":"2020","journal-title":"arXiv:2011.10566"},{"key":"ref61","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020","journal-title":"arXiv:2003.04297"},{"key":"ref62","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020","journal-title":"arXiv:2002.05709"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref64","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. NIPS","author":"Caron"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00938"},{"key":"ref66","article-title":"Vision transformer adapter for dense predictions","author":"Chen","year":"2022","journal-title":"arXiv:2205.08534"},{"key":"ref67","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. ICLR","author":"Loshchilov"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1710.09412"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00565"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00611"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01345"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01003"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.188"},{"key":"ref80","article-title":"Similarity of neural network representations revisited","author":"Kornblith","year":"2019","journal-title":"arXiv:1905.00414"},{"key":"ref81","article-title":"Understanding masked image modeling via learning occlusion invariant feature","author":"Kong","year":"2022","journal-title":"arXiv:2208.04164"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref84","first-page":"10506","article-title":"Learning robust global representations by penalizing local predictive power","volume-title":"Proc. NeurIPS","author":"Wang"},{"key":"ref85","first-page":"5389","article-title":"Do ImageNet classifiers generalize to ImageNet?","volume-title":"Proc. ICML","author":"Recht"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.385"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10700029\/10508550.pdf?arnumber=10508550","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T05:53:53Z","timestamp":1727762033000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10508550\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":86,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3393474","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9]]}}}