{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:20Z","timestamp":1777491920197,"version":"3.51.4"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea (NRF) Grant funded by Korean Government","doi-asserted-by":"publisher","award":["NRF-2021R1A5A1032937"],"award-info":[{"award-number":["NRF-2021R1A5A1032937"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3394539","type":"journal-article","created":{"date-parts":[[2024,4,29]],"date-time":"2024-04-29T17:43:07Z","timestamp":1714412587000},"page":"72598-72606","source":"Crossref","is-referenced-by-count":13,"title":["FSwin Transformer: Feature-Space Window Attention Vision Transformer for Image Classification"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-0299-4857","authenticated-orcid":false,"given":"Dayeon","family":"Yoo","sequence":"first","affiliation":[{"name":"Graduate School of Automotive Engineering, Kookmin University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeesu","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Cogno-Mechatronics Engineering, Pusan National University, Busan, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1025-3784","authenticated-orcid":false,"given":"Jinwoo","family":"Yoo","sequence":"additional","affiliation":[{"name":"Department of Automobile and IT Convergence, Kookmin University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Krizhevsky"},{"key":"ref2","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref5","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref7","article-title":"BOAT: Bilateral local attention vision transformer","author":"Yu","year":"2022","journal-title":"arXiv:2201.13027"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1807.06521"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1080\/01431160600746456"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/rs14133087"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01739-w"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LifeTech52111.2021.9391844"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref18","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00119"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20176"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_27"},{"key":"ref23","first-page":"30008","article-title":"Focal attention for long-range interactions in vision transformers","volume-title":"Proc. NeurIPS","author":"Yang"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00599"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00207"},{"key":"ref26","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst.","author":"Chu"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102417"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"ref31","first-page":"28522","article-title":"ViTAE: Vision transformer advanced by exploring intrinsic inductive bias","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Xu"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_12"},{"key":"ref33","article-title":"BAM: Bottleneck attention module","author":"Park","year":"2018","journal-title":"arXiv:1807.06514"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01168"},{"key":"ref39","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","author":"Zagoruyko","year":"2016","journal-title":"arXiv:1612.03928"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref43","first-page":"15908","article-title":"Transformer in transformer","volume-title":"Proc. NIPS","author":"Han"},{"key":"ref44","article-title":"Shuffle transformer: Rethinking spatial shuffle for vision transformer","author":"Huang","year":"2021","journal-title":"arXiv:2106.03650"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01175"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10380310\/10509828.pdf?arnumber=10509828","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,28]],"date-time":"2024-05-28T04:25:38Z","timestamp":1716870338000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10509828\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3394539","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}