{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T11:14:43Z","timestamp":1756898083794,"version":"3.28.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,8,28]],"date-time":"2024-08-28T00:00:00Z","timestamp":1724803200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,28]],"date-time":"2024-08-28T00:00:00Z","timestamp":1724803200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100009122","name":"Ministry of Education","doi-asserted-by":"publisher","award":["2021RIS-003"],"award-info":[{"award-number":["2021RIS-003"]}],"id":[{"id":"10.13039\/100009122","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,8,28]]},"DOI":"10.1109\/iwis62722.2024.10706066","type":"proceedings-article","created":{"date-parts":[[2024,10,10]],"date-time":"2024-10-10T17:21:42Z","timestamp":1728580902000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Refining Attention Maps for Vision Transformer"],"prefix":"10.1109","author":[{"given":"Xuan-Thuy","family":"Vo","sequence":"first","affiliation":[{"name":"University of Ulsan,Department of Electrical, Electronic and Computer Engineering,Ulsan,South Korea,44610"}]},{"given":"Duy-Linh","family":"Nguyen","sequence":"additional","affiliation":[{"name":"University of Ulsan,Department of Electrical, Electronic and Computer Engineering,Ulsan,South Korea,44610"}]},{"given":"Adri","family":"Priadana","sequence":"additional","affiliation":[{"name":"University of Ulsan,Department of Electrical, Electronic and Computer Engineering,Ulsan,South Korea,44610"}]},{"given":"Kang-Hyun","family":"Jo","sequence":"additional","affiliation":[{"name":"University of Ulsan,Department of Electrical, Electronic and Computer Engineering,Ulsan,South Korea,44610"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref5","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"International conference on machine learning","author":"Touvron"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"ref11","first-page":"32097","article-title":"Peripheral vision transformer","volume":"35","author":"Min","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Conditional positional encodings for vision transformers","volume-title":"The Eleventh International Conference on Learning Representations","author":"Chu","key":"ref12"},{"key":"ref13","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision trans-formers","volume":"34","author":"Chu","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ISIE54533.2024.10595792"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00518"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_18"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00539"},{"key":"ref19","article-title":"Lightweight vision transformer with bidirectional interaction","volume":"36","author":"Fan","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref21","first-page":"36440","article-title":"Rest v2: simpler, faster and stronger","volume":"35","author":"Zhang","year":"2022","journal-title":"Ad-vances in Neural Information Processing Systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"article-title":"Mobilevit: Light-weight, general-purpose, and mobile- friendly vision transformer","volume-title":"International Conference on Learning Representations","author":"Mehta","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00764"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-06381-7_11"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00207"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01270"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01175"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_27"},{"key":"ref31","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for con-volutional neural networks","volume-title":"International conference on machine learning","author":"Tan"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00520"},{"article-title":"Moat: Alternating mobile convolution and attention brings strong vision models","volume-title":"The Eleventh International Conference on Learning Representations, 2022","author":"Yang","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00134"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01506"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00550"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20099"},{"article-title":"How do vision transformers work?","volume-title":"International Conference on Learning Representations","author":"Park","key":"ref38"},{"article-title":"Separable self-attention for mobile vision transformers","volume-title":"Transactions on Machine Learning Research, 2023","author":"Mehta","key":"ref39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20050-2_43"}],"event":{"name":"2024 International Workshop on Intelligent Systems (IWIS)","start":{"date-parts":[[2024,8,28]]},"location":"Ulsan, Korea, Republic of","end":{"date-parts":[[2024,8,30]]}},"container-title":["2024 International Workshop on Intelligent Systems (IWIS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10706037\/10706026\/10706066.pdf?arnumber=10706066","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,11]],"date-time":"2024-10-11T04:33:21Z","timestamp":1728621201000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10706066\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,28]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/iwis62722.2024.10706066","relation":{},"subject":[],"published":{"date-parts":[[2024,8,28]]}}}