{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T02:13:54Z","timestamp":1769825634140,"version":"3.49.0"},"reference-count":66,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,1,3]],"date-time":"2024-01-03T00:00:00Z","timestamp":1704240000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,3]],"date-time":"2024-01-03T00:00:00Z","timestamp":1704240000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,1,3]]},"DOI":"10.1109\/wacv57701.2024.00673","type":"proceedings-article","created":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T17:36:09Z","timestamp":1712684169000},"page":"6864-6874","source":"Crossref","is-referenced-by-count":17,"title":["Limited Data, Unlimited Potential: A Study on ViTs Augmented by Masked Autoencoders"],"prefix":"10.1109","author":[{"given":"Srijan","family":"Das","sequence":"first","affiliation":[{"name":"UNC Charlotte"}]},{"given":"Tanmay","family":"Jain","sequence":"additional","affiliation":[{"name":"Delhi Technological University"}]},{"given":"Dominick","family":"Reilly","sequence":"additional","affiliation":[{"name":"UNC Charlotte"}]},{"given":"Pranav","family":"Balaji","sequence":"additional","affiliation":[{"name":"BITS Pilani Hyderabad"}]},{"given":"Soumyajit","family":"Karmakar","sequence":"additional","affiliation":[{"name":"Indian Institute of Information Technology Guwahati"}]},{"given":"Shyam","family":"Marjit","sequence":"additional","affiliation":[{"name":"Indian Institute of Information Technology Guwahati"}]},{"given":"Xiang","family":"Li","sequence":"additional","affiliation":[{"name":"Stony Brook University"}]},{"given":"Abhijit","family":"Das","sequence":"additional","affiliation":[{"name":"BITS Pilani Hyderabad"}]},{"given":"Michael S.","family":"Ryoo","sequence":"additional","affiliation":[{"name":"Stony Brook University"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/info11020125"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01567"},{"key":"ref6","article-title":"Self-supervised vision transformers learn visual concepts in histopathology","author":"Chen","year":"2022"},{"key":"ref7","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International conference on machine learning","author":"Chen"},{"key":"ref8","article-title":"Per-pixel classification is not all you need for semantic segmentation","author":"Cheng","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-06433-3_19"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01941"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/FG52635.2021.9667026"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref13","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref15","article-title":"How to train vision transformer on small-scale datasets?","author":"Gani","year":"2022"},{"key":"ref16","article-title":"Convmae: Masked convolution meets masked autoencoders","author":"Gao","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref18","article-title":"Transformer in transformer","author":"Han","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01553"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01172"},{"key":"ref24","article-title":"Cd-net: Histopathology representation learning using pyramidal context-detail network","author":"Kapse","year":"2022"},{"key":"ref25","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref26","article-title":"Quantifying the carbon emissions of machine learning","author":"Lacoste","year":"2019"},{"key":"ref27","first-page":"5639","article-title":"Curl: Contrastive unsupervised representations for reinforcement learning","author":"Laskin","year":"2020","journal-title":"Int. Conf. on Mach. Learn"},{"key":"ref28","article-title":"Vision transformer for small-size datasets","author":"Lee","year":"2021","journal-title":"CoRR"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_7"},{"key":"ref30","article-title":"Crossway diffusion: Improving diffusion-based visuomotor policy via self-supervised learning","author":"Li","year":"2023"},{"key":"ref31","article-title":"Does self-supervised learning really improve reinforcement learning from pixels?","author":"Li","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref32","article-title":"Uniform masking: Enabling mae pre-training for pyramid-based vision transformers with locality","author":"Li","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref34","article-title":"Efficient training of visual transformers with small datasets","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Liu"},{"key":"ref35","first-page":"10012","article-title":"Swin transformer: Hierarchical vision transformer using shifted windows","author":"Liu","year":"2021","journal-title":"CVPR"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00320"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.2118\/18761-MS"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref39","first-page":"17390","article-title":"Blurs behave like ensembles: Spatial smoothings to improve accuracy, uncertainty, and robustness","volume-title":"Proceedings of the 39th International Conference on Machine Learning","volume":"162","author":"Park"},{"key":"ref40","article-title":"How do vision transformers work?","author":"Park","year":"2022"},{"key":"ref41","article-title":"What do self-supervised vision transformers learn?","volume-title":"International Conference on Learning Representations","author":"Park"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00149"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00021"},{"key":"ref44","first-page":"416","article-title":"Real-world robot learning with masked visual pre-training","volume-title":"Conference on Robot Learning","author":"Radosavovic"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00289"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00009"},{"key":"ref47","article-title":"TokenLearner: Adaptive Space-Time Tokenization for Videos","volume":"34","author":"Ryoo","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref48","author":"Seferbekov","year":"2020","journal-title":"Dfdc 1st place solution"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref50","article-title":"Learning viewpoint-agnostic visual representations by recovering tokens in 3d space","author":"Shang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/wacv56688.2023.00611"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.97"},{"key":"ref53","article-title":"Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training","author":"Tong","year":"2022"},{"key":"ref54","first-page":"10347","article-title":"Training data-efficient image transformers: Distillation through attention","volume":"139","author":"Touvron","year":"2021","journal-title":"Int. Conf. on Mach. Learn"},{"key":"ref55","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87237-3_18"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref60","article-title":"Segformer: Simple and efficient design for semantic segmentation with transformers","author":"Xie","year":"2021"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01721-8"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref64","article-title":"Deepvit: Towards deeper vision transformer","author":"Zhou","year":"2021"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3125459"},{"key":"ref66","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020"}],"event":{"name":"2024 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Waikoloa, HI, USA","start":{"date-parts":[[2024,1,3]]},"end":{"date-parts":[[2024,1,8]]}},"container-title":["2024 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10483279\/10483282\/10484258.pdf?arnumber=10484258","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,10]],"date-time":"2024-04-10T05:46:48Z","timestamp":1712728008000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10484258\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,3]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/wacv57701.2024.00673","relation":{},"subject":[],"published":{"date-parts":[[2024,1,3]]}}}