{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,28]],"date-time":"2024-09-28T06:10:16Z","timestamp":1727503816866},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,27]],"date-time":"2024-10-27T00:00:00Z","timestamp":1729987200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,27]],"date-time":"2024-10-27T00:00:00Z","timestamp":1729987200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,27]]},"DOI":"10.1109\/icip51287.2024.10647522","type":"proceedings-article","created":{"date-parts":[[2024,9,27]],"date-time":"2024-09-27T18:34:45Z","timestamp":1727462085000},"page":"1302-1308","source":"Crossref","is-referenced-by-count":0,"title":["Improving Self-Supervised Vision Transformers for Visual Control"],"prefix":"10.1109","author":[{"given":"Wonil","family":"Song","sequence":"first","affiliation":[{"name":"Yonsei University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kwanghoon","family":"Sohn","sequence":"additional","affiliation":[{"name":"Yonsei University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongbo","family":"Min","sequence":"additional","affiliation":[{"name":"Ewha Womans University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref2","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref4","article-title":"Masked visual pre-training for motor control","author":"Xiao","year":"2022","journal-title":"arXiv:2203.06173"},{"key":"ref5","article-title":"Training data-efficient image transformers & distillation through attention","author":"Touvron","year":"2021","journal-title":"ICML"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref7","article-title":"End-toend object detection with transformers","author":"Carion","year":"2020","journal-title":"ECCV"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"ref9","article-title":"Intriguing properties of vision transformers","author":"Naseer","year":"2021","journal-title":"NeurIPS"},{"key":"ref10","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","author":"Kostrikov","year":"2020","journal-title":"arXiv:2004.13649"},{"key":"ref11","article-title":"Evaluating vision transformer methods for deep reinforcement learning from pixels","author":"Tao","year":"2022","journal-title":"arXiv:2204.04905"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref13","article-title":"Beit: Bert pre-training of image transformers","author":"Bao","year":"2021","journal-title":"arXiv:2106.08254"},{"key":"ref14","article-title":"Curl: Contrastive unsupervised representations for reinforcement learning","author":"Laskin","year":"2020","journal-title":"ICML"},{"key":"ref15","article-title":"Data-efficient reinforcement learning with self-predictive representations","author":"Schwarzer","year":"2020","journal-title":"arXiv:2007.05929"},{"key":"ref16","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref17","article-title":"Pretraining representations for data-efficient reinforcement learning","author":"Schwarzer","year":"2021","journal-title":"NeurIPS"},{"key":"ref18","article-title":"Decoupling representation learning from reinforcement learning","author":"Stooke","year":"2021","journal-title":"ICML"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.07.006"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref21","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020","journal-title":"ICML"},{"key":"ref22","article-title":"Deepmind control suite","author":"Tassa","year":"2018","journal-title":"arXiv:1801.00690"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref24","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref25","article-title":"Gaussian error linear units (gelus)","author":"Hendrycks","year":"2016","journal-title":"arXiv:1606.08415"},{"key":"ref26","article-title":"Data-efficient image recognition with contrastive predictive coding","author":"Henaff","year":"2020","journal-title":"ICML"},{"key":"ref27","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"Haarnoja","year":"2018","journal-title":"ICML"},{"key":"ref28","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref29","article-title":"Reinforcement learning with augmented data","author":"Laskin","year":"2020","journal-title":"NeurIPS"},{"key":"ref30","article-title":"Mastering visual continuous control: Improved dataaugmented reinforcement learning","author":"Yarats","year":"2021","journal-title":"arXiv:2107.09645"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17276"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref33","article-title":"When to use parametric models in reinforcement learning?","author":"Van Hasselt","year":"2019","journal-title":"NeurIPS"},{"key":"ref34","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref35","article-title":"Model-based reinforcement learning for atari","author":"Kaiser","year":"2019","journal-title":"arXiv:1903.00374"},{"article-title":"Do recent advancements in model-based deep reinforcement learning really improve data efficiency?","year":"2020","author":"Kielak","key":"ref36"},{"key":"ref37","article-title":"Bootstrap your own latent-a new approach to self-supervised learning","author":"Grill","year":"2020","journal-title":"NeurIPS"}],"event":{"name":"2024 IEEE International Conference on Image Processing (ICIP)","start":{"date-parts":[[2024,10,27]]},"location":"Abu Dhabi, United Arab Emirates","end":{"date-parts":[[2024,10,30]]}},"container-title":["2024 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10647221\/10647122\/10647522.pdf?arnumber=10647522","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,28]],"date-time":"2024-09-28T05:36:20Z","timestamp":1727501780000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10647522\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,27]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icip51287.2024.10647522","relation":{},"subject":[],"published":{"date-parts":[[2024,10,27]]}}}