{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T09:04:05Z","timestamp":1765357445170,"version":"3.37.3"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,8]],"date-time":"2023-10-08T00:00:00Z","timestamp":1696723200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,8]],"date-time":"2023-10-08T00:00:00Z","timestamp":1696723200000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,8]]},"DOI":"10.1109\/icip49359.2023.10222606","type":"proceedings-article","created":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T17:58:31Z","timestamp":1694455111000},"page":"2490-2494","source":"Crossref","is-referenced-by-count":2,"title":["Attention-Guided Contrastive Masked Image Modeling for Transformer-Based Self-Supervised Learning"],"prefix":"10.1109","author":[{"given":"Yucheng","family":"Zhan","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}]},{"given":"Yucheng","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}]},{"given":"Chong","family":"Luo","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia,Beijing,China"}]},{"given":"Yueyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}]},{"given":"Xiaoyan","family":"Sun","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International conference on machine learning","author":"Chen"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00828"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01000"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"article-title":"Self-supervised learning with swin transformers","year":"2021","author":"Xie","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/355161a0"},{"article-title":"Beit: Bert pre-training of image transformers","volume-title":"International Conference on Learning Representations","author":"Bao","key":"ref11"},{"article-title":"Image bert pre-training with online tokenizer","volume-title":"International Conference on Learning Representations","author":"Zhou","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00944"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25130"},{"article-title":"Semantic-aware generation for self-supervised visual representation learning","year":"2021","author":"Tian","key":"ref18"},{"key":"ref19","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"International Conference on Machine Learning","author":"Touvron"}],"event":{"name":"2023 IEEE International Conference on Image Processing (ICIP)","start":{"date-parts":[[2023,10,8]]},"location":"Kuala Lumpur, Malaysia","end":{"date-parts":[[2023,10,11]]}},"container-title":["2023 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10221937\/10221892\/10222606.pdf?arnumber=10222606","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T20:36:01Z","timestamp":1709325361000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10222606\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,8]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icip49359.2023.10222606","relation":{},"subject":[],"published":{"date-parts":[[2023,10,8]]}}}