{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T18:02:41Z","timestamp":1775066561375,"version":"3.50.1"},"reference-count":33,"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":[{"name":"Postdoctoral Fellowship Program of CPSF","award":["GZC20232676"],"award-info":[{"award-number":["GZC20232676"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/lsp.2024.3458792","type":"journal-article","created":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T19:35:18Z","timestamp":1725996918000},"page":"2615-2619","source":"Crossref","is-referenced-by-count":2,"title":["Improving Visual Representations of Masked Autoencoders With Artifacts Suppression"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5326-3790","authenticated-orcid":false,"given":"Zhengwei","family":"Miao","sequence":"first","affiliation":[{"name":"National Key Laboratory of Optical Field Manipulation Science and Technology, Chinese Academy of Sciences, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6698-5576","authenticated-orcid":false,"given":"Hui","family":"Luo","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Optical Field Manipulation Science and Technology, Chinese Academy of Sciences, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0691-4025","authenticated-orcid":false,"given":"Dongxu","family":"Liu","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Optical Field Manipulation Science and Technology, Chinese Academy of Sciences, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5284-2942","authenticated-orcid":false,"given":"Jianlin","family":"Zhang","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Optical Field Manipulation Science and Technology, Chinese Academy of Sciences, Chengdu, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3238277"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3044544"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3342719"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3337538"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3150258"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3337727"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref9","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2014"},{"key":"ref10","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"NAACL-HCT","author":"Devlin","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3336525"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref14","article-title":"Vision transformers need registers","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Darcet","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref16","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref19","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":"ref20","article-title":"BEiT: BERT pre-training of image transformers","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Bao","year":"2022"},{"key":"ref21","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01852-4"},{"key":"ref23","first-page":"14290","article-title":"SEMMAE: Semantic-guided masking for learning masked autoencoders","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Li","year":"2022"},{"key":"ref24","article-title":"IBOT: Image bert pre-training with online tokenizer","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Zhou","year":"2022"},{"key":"ref25","article-title":"Masked frequency modeling for self-supervised visual pre-training","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Xie","year":"2023"},{"key":"ref26","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Dosovitskiy","year":"2021"},{"key":"ref27","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Loshchilov","year":"2019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref30","first-page":"13165","article-title":"MST: Masked self-supervised transformer for visual representation","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_18"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01000"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01001"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/97\/10380231\/10675434.pdf?arnumber=10675434","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T06:02:37Z","timestamp":1727935357000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10675434\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/lsp.2024.3458792","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}