{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T03:12:59Z","timestamp":1779246779520,"version":"3.51.4"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"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":["U20B2052"],"award-info":[{"award-number":["U20B2052"]}],"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":["61936011"],"award-info":[{"award-number":["61936011"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Okawa Foundation Research Award"},{"name":"Ant Group Research Fund"},{"name":"Kunpeng & Ascend Center of Excellence"},{"DOI":"10.13039\/501100007937","name":"Peking University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007937","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1109\/tpami.2024.3490776","type":"journal-article","created":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T18:36:00Z","timestamp":1730745360000},"page":"1013-1027","source":"Crossref","is-referenced-by-count":5,"title":["Evolved Hierarchical Masking for Self-Supervised Learning"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-0071-454X","authenticated-orcid":false,"given":"Zhanzhou","family":"Feng","sequence":"first","affiliation":[{"name":"State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9053-9314","authenticated-orcid":false,"given":"Shiliang","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","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"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref5","first-page":"13165","article-title":"MST: Masked self-supervised transformer for visual representation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_18"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01499"},{"key":"ref8","article-title":"SemMAE: Semantic-guided masking for learning masked autoencoders","author":"Li","year":"2022"},{"key":"ref9","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383172"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587635"},{"key":"ref14","article-title":"BEiT: BERT pre-training of image transformers","author":"Bao","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00304"},{"key":"ref19","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01615"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref22","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Caron"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref25","article-title":"Unsupervised representation learning by predicting image rotations","author":"Gidaris","year":"2018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref28","first-page":"1691","article-title":"Generative pretraining from pixels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"ref31","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref32","article-title":"Masked frequency modeling for self-supervised visual pre-training","author":"Xie","year":"2022"},{"key":"ref33","article-title":"iBOT: Image BERT pre-training with online tokenizer","author":"Zhou","year":"2021"},{"key":"ref34","first-page":"20026","article-title":"Adversarial masking for self-supervised learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Shi"},{"key":"ref35","article-title":"Judging LLM-as-a-judge with MT-bench and chatbot arena","author":"Zheng","year":"2023"},{"key":"ref36","article-title":"Visual instruction tuning","author":"Liu","year":"2023"},{"key":"ref37","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref38","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"ref39","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01001"},{"key":"ref41","first-page":"249","article-title":"Learning linear Bayesian networks with latent variables","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Anandkumar"},{"key":"ref42","first-page":"5549","article-title":"Latent hierarchical causal structure discovery with rank constraints","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Huang"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00765"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01557"},{"key":"ref45","first-page":"3859","article-title":"Dynamic routing between capsules","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sabour"},{"key":"ref46","article-title":"BIVA: A very deep hierarchy of latent variables for generative modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Maal\u00f8e"},{"key":"ref47","first-page":"19667","article-title":"NVAE: A deep hierarchical variational autoencoder","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vahdat"},{"key":"ref48","article-title":"Learning hierarchical features from generative models","author":"Zhao","year":"2017"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"ref51","article-title":"What makes for good visual tokenizers for large language models?","author":"Wang","year":"2023"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00265"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_43"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref56","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref60","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jaegle"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref62","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01852-4"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00211"},{"key":"ref65","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref67","article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","author":"Frankle","year":"2018"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10835210\/10742293.pdf?arnumber=10742293","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,10]],"date-time":"2025-01-10T20:26:39Z","timestamp":1736540799000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10742293\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":67,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3490776","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2]]}}}