{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:28:31Z","timestamp":1763191711252,"version":"3.45.0"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11228016","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-9","source":"Crossref","is-referenced-by-count":0,"title":["Symmetric masking strategy enhances the performance of Masked Image Modeling"],"prefix":"10.1109","author":[{"given":"Khanh Binh","family":"Nguyen","sequence":"first","affiliation":[{"name":"National Cancer Center,Cancer Big Data and Artificial Intelligence,Goyang,South Korea"}]},{"given":"Chae Jung","family":"Park","sequence":"additional","affiliation":[{"name":"National Cancer Center,Cancer Big Data and Artificial Intelligence,Goyang,South Korea"}]}],"member":"263","reference":[{"article-title":"Beit: Bert pre-training of image transformers","year":"2021","author":"Bao","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01852-4"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref5"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25130"},{"article-title":"Architecture-agnostic masked image modeling\u2013from vit back to cnn","year":"2022","author":"Li","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"ref13","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International conference on machine learning","author":"Chen"},{"article-title":"Representation learning with contrastive predictive coding","year":"2018","author":"Oord","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"article-title":"Improved baselines with momentum contrastive learning","year":"2020","author":"Chen","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00305"},{"key":"ref21","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"issue":"8","key":"ref22","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"issue":"12","key":"ref23","article-title":"Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion","volume":"11","author":"Vincent","year":"2010","journal-title":"Journal of machine learning research"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02178"},{"article-title":"Corrupted image modeling for self-supervised visual pre-training","year":"2022","author":"Fang","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_20"},{"article-title":"Multimodal masked autoencoders learn transferable representations","year":"2022","author":"Geng","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02240"},{"article-title":"Siamese masked autoencoders","year":"2023","author":"Gupta","key":"ref30"},{"article-title":"Masked image modeling with denoising contrast","volume-title":"International Conference on Learning Representations","author":"Yi","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref33","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"International Conference on Machine Learning","author":"Ramesh"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3190643"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00914"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"article-title":"How to train your vit? data, augmentation, and regularization in vision transformers","year":"2021","author":"Steiner","key":"ref38"},{"article-title":"Rethinking patch dependence for masked autoencoders","year":"2024","author":"Fu","key":"ref39"},{"article-title":"ibot: Image bert pre-training with online tokenizer","year":"2021","author":"Zhou","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"article-title":"Benchmarking detection transfer learning with vision transformers","year":"2021","author":"Li","key":"ref42"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00294"},{"article-title":"Decoupled weight decay regularization","year":"2017","author":"Loshchilov","key":"ref44"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11228016.pdf?arnumber=11228016","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:26:16Z","timestamp":1763191576000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11228016\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11228016","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}