{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T13:37:58Z","timestamp":1758893878802,"version":"3.37.3"},"reference-count":53,"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 (NRF) Grant","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003621","name":"Korea Government","doi-asserted-by":"publisher","award":["RS-2022-00166109","2022M3J6A1084845"],"award-info":[{"award-number":["RS-2022-00166109","2022M3J6A1084845"]}],"id":[{"id":"10.13039\/501100003621","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.2024.3356064","type":"journal-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:48:56Z","timestamp":1705690136000},"page":"13626-13633","source":"Crossref","is-referenced-by-count":2,"title":["Strengthening Dynamic Convolution With Attention and Residual Connection in Kernel Space"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4147-9750","authenticated-orcid":false,"given":"Seokju","family":"Yun","sequence":"first","affiliation":[{"name":"Department of Artificial Intelligence, Machine Intelligence Laboratory, University of Seoul, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0661-9192","authenticated-orcid":false,"given":"Youngmin","family":"Ro","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, Machine Intelligence Laboratory, University of Seoul, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","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":"ref2","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/ICCV48922.2021.00986"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/ICCV48922.2021.00061"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/CVPR52688.2022.00520"},{"key":"ref6","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv:1704.04861"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/CVPR.2018.00474"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/ICCV.2019.00140"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/CVPR.2018.00716"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref11","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref12","first-page":"1307","article-title":"CondConv: Conditionally parameterized convolutions for efficient inference","volume":"32","author":"Yang","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/CVPR42600.2020.01104"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/CVPR46437.2021.00797"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1007\/978-3-030-58555-6_46"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1007\/978-3-030-58452-8_17"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/CVPR46437.2021.00042"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/CVPR.2009.5206848"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1007\/978-3-319-10602-1_48"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/ICCV.2017.324"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref24","article-title":"How do vision transformers work?","author":"Park","year":"2022","journal-title":"arXiv:2202.06709"},{"key":"ref25","article-title":"Inception transformer","author":"Si","year":"2022","journal-title":"arXiv:2205.12956"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"ref27","first-page":"3965","article-title":"CoAtNet: Marrying convolution and attention for all data sizes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Dai"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1109\/ICCV48922.2021.00983"},{"key":"ref29","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":"ref30","article-title":"Conditional positional encodings for vision transformers","author":"Chu","year":"2021","journal-title":"arXiv:2102.10882"},{"key":"ref31","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jaegle"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1007\/978-3-030-58529-7_21"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.1109\/CVPR.2018.00745"},{"doi-asserted-by":"publisher","key":"ref34","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref35","article-title":"Revisiting dynamic convolution via matrix decomposition","author":"Li","year":"2021","journal-title":"arXiv:2103.08756"},{"key":"ref36","article-title":"Omni-dimensional dynamic convolution","author":"Li","year":"2022","journal-title":"arXiv:2209.07947"},{"key":"ref37","article-title":"MicroNet: Towards image recognition with extremely low FLOPs","author":"Li","year":"2020","journal-title":"arXiv:2011.12289"},{"doi-asserted-by":"publisher","key":"ref38","DOI":"10.1109\/CVPR52729.2023.01548"},{"doi-asserted-by":"publisher","key":"ref39","DOI":"10.1007\/978-3-031-20083-0_18"},{"doi-asserted-by":"publisher","key":"ref40","DOI":"10.1007\/978-3-031-25082-8_1"},{"key":"ref41","article-title":"ConTNet: Why not use convolution and transformer at the same time?","author":"Yan","year":"2021","journal-title":"arXiv:2104.13497"},{"key":"ref42","article-title":"EfficientViT: Multi-scale linear attention for high-resolution dense prediction","author":"Cai","year":"2022","journal-title":"arXiv:2205.14756"},{"doi-asserted-by":"publisher","key":"ref43","DOI":"10.1109\/CVPR52688.2022.00714"},{"key":"ref44","article-title":"MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer","author":"Mehta","year":"2021","journal-title":"arXiv:2110.02178"},{"key":"ref45","first-page":"10096","article-title":"EfficientNetV2: Smaller models and faster training","volume-title":"Proc. 38th Int. Conf. Mach. Learn. (ICML)","author":"Tan"},{"doi-asserted-by":"publisher","key":"ref46","DOI":"10.1109\/CVPR52688.2022.01167"},{"doi-asserted-by":"publisher","key":"ref47","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"ref48","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref49","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016","journal-title":"arXiv:1608.03983"},{"doi-asserted-by":"publisher","key":"ref50","DOI":"10.1609\/aaai.v34i07.7000"},{"doi-asserted-by":"publisher","key":"ref51","DOI":"10.1109\/CVPRW50498.2020.00359"},{"doi-asserted-by":"publisher","key":"ref52","DOI":"10.1007\/s41095-022-0274-8"},{"doi-asserted-by":"publisher","key":"ref53","DOI":"10.1109\/ICCV.2017.322"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10380310\/10409154.pdf?arnumber=10409154","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T13:29:12Z","timestamp":1706794152000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10409154\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3356064","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2024]]}}}