{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T17:33:49Z","timestamp":1758476029172,"version":"3.28.2"},"reference-count":49,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,6]],"date-time":"2024-10-06T00:00:00Z","timestamp":1728172800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,6]],"date-time":"2024-10-06T00:00:00Z","timestamp":1728172800000},"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":[[2024,10,6]]},"DOI":"10.1109\/dsaa61799.2024.10722789","type":"proceedings-article","created":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T17:23:54Z","timestamp":1729790634000},"page":"1-10","source":"Crossref","is-referenced-by-count":1,"title":["Masked Contrastive Representation Learning for Self-Supervised Visual Pre-Training"],"prefix":"10.1109","author":[{"given":"Yuchong","family":"Yao","sequence":"first","affiliation":[{"name":"The University of Melbourne,Department of Electrical and Electronic Engineering,Melbourne,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nandakishor","family":"Desai","sequence":"additional","affiliation":[{"name":"The University of Melbourne,Department of Electrical and Electronic Engineering,Melbourne,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marimuthu","family":"Palaniswami","sequence":"additional","affiliation":[{"name":"The University of Melbourne,Department of Electrical and Electronic Engineering,Melbourne,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref3","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Beit: Bert pre-training of image transformers","author":"Bao","year":"2021","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref8","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International conference on machine learning","author":"Chen","year":"2020"},{"journal-title":"Improving language understanding by generative pre-training","year":"2018","author":"Radford","key":"ref9"},{"key":"ref10","first-page":"1691","article-title":"Generative pretraining from pixels","volume-title":"International conference on machine learning","author":"Chen","year":"2020"},{"key":"ref11","first-page":"16000","article-title":"Masked au-toencoders are scalable vision learners","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"He","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548173"},{"key":"ref13","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume":"33","author":"Caron","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref16","first-page":"22243","article-title":"Big self-supervised models are strong semi-supervised learners","volume":"33","author":"Chen","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref19","first-page":"12310","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","volume-title":"International Conference on Machine Learning","author":"Zbontar","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref22","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"International Conference on Machine Learning","author":"Ramesh","year":"2021"},{"key":"ref23","article-title":"Sit: Self-supervised vision trans-former","author":"Atito","year":"2021","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref26","article-title":"Corrupted image modeling for self-supervised visual pre-training","author":"Fang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01852-4"},{"key":"ref28","first-page":"27 127","article-title":"How mask matters: Towards theoretical understandings of masked autoencoders","volume":"35","author":"Zhang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref29","article-title":"Siamese image modeling for self-supervised vision representation learning","author":"Tao","year":"2022","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"A simple, efficient and scalable contrastive masked autoencoder for learning visual representations","author":"Mishra","year":"2022","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01607"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19821-2_26"},{"key":"ref33","first-page":"30392","article-title":"Early convolutions help transformers see better","volume":"34","author":"Xiao","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref34","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv preprint"},{"key":"ref35","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume-title":"International conference on machine learning","author":"Ioffe","year":"2015"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.29007\/1mjd"},{"key":"ref37","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"International Conference on Machine Learning","author":"Touvron","year":"2021"},{"key":"ref38","article-title":"Context autoencoder for self-supervised representation learning","author":"Chen","year":"2022","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00212"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"7","key":"ref41","first-page":"3","article-title":"Tiny imagenet visual recognition challenge","volume":"7","author":"Le","year":"2015","journal-title":"CS 231N"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3390\/INFOo11020108"},{"journal-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref43"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"journal-title":"Fixing weight decay regularization in adam","year":"2018","author":"Loshchilov","key":"ref45"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"ref48","article-title":"Au-toaugment: Learning augmentation policies from data","author":"Cubuk","year":"2018","journal-title":"arXiv preprint"},{"key":"ref49","article-title":"Improved regularization of convolutional neural networks with cutout","author":"DeVries","year":"2017","journal-title":"arXiv preprint"}],"event":{"name":"2024 IEEE 11th International Conference on Data Science and Advanced Analytics (DSAA)","start":{"date-parts":[[2024,10,6]]},"location":"San Diego, CA, USA","end":{"date-parts":[[2024,10,10]]}},"container-title":["2024 IEEE 11th International Conference on Data Science and Advanced Analytics (DSAA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10722027\/10722766\/10722789.pdf?arnumber=10722789","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T02:27:28Z","timestamp":1732674448000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10722789\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,6]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/dsaa61799.2024.10722789","relation":{},"subject":[],"published":{"date-parts":[[2024,10,6]]}}}