{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T20:03:24Z","timestamp":1784664204746,"version":"3.55.0"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Institute of Information & Communications Technology Planning & Evaluation"},{"name":"Korea government","award":["RS-2021-II211341"],"award-info":[{"award-number":["RS-2021-II211341"]}]},{"name":"Artificial Intelligent Graduate School Program"},{"name":"Korea Research Institute for defense Technology planning and advancement through Defense Innovation Vanguard Enterprise"},{"DOI":"10.13039\/501100003626","name":"Defense Acquisition Program Administration","doi-asserted-by":"crossref","award":["R230106"],"award-info":[{"award-number":["R230106"]}],"id":[{"id":"10.13039\/501100003626","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Technological Innovation R&D Program","award":["RS-2024-00488442"],"award-info":[{"award-number":["RS-2024-00488442"]}]},{"name":"Ministry of SMEs and Startup"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3701015","type":"journal-article","created":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T19:52:56Z","timestamp":1780948376000},"page":"87364-87376","source":"Crossref","is-referenced-by-count":0,"title":["PLuG: Pairwise Logit Gating for Expressive Attention Modulation in Vision Transformers"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-4871-6194","authenticated-orcid":false,"given":"Dongheon","family":"Lee","sequence":"first","affiliation":[{"name":"Chung-Ang University","place":["Seoul, South Korea"],"department":["Department of Artificial Intelligence"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7344-7639","authenticated-orcid":false,"given":"Sangwoo","family":"Yoon","sequence":"additional","affiliation":[{"name":"Chung-Ang University","place":["Seoul, South Korea"],"department":["Department of Image"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seongsu","family":"Kim","sequence":"additional","affiliation":[{"name":"Chung-Ang University","place":["Seoul, South Korea"],"department":["Department of Artificial Intelligence"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8593-7155","authenticated-orcid":false,"given":"Joonki","family":"Paik","sequence":"additional","affiliation":[{"name":"Chung-Ang University","place":["Seoul, South Korea"],"department":["Department of Artificial Intelligence"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref3","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref4","article-title":"An image is worth 16$\\times$\n16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref5","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref8","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv:2010.04159"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref12","first-page":"1","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"25","author":"Krizhevsky"},{"key":"ref13","article-title":"Talking-heads attention","author":"Shazeer","year":"2020","journal-title":"arXiv:2003.02436"},{"key":"ref14","first-page":"10183","article-title":"Synthesizer: Rethinking self-attention for transformer models","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Tay"},{"key":"ref15","article-title":"Forgetting transformer: Softmax attention with a forget gate","author":"Lin","year":"2025","journal-title":"arXiv:2503.02130"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0353"},{"key":"ref17","article-title":"Selective attention improves transformer","author":"Leviathan","year":"2024","journal-title":"arXiv:2410.02703"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1063\/5.0246927"},{"key":"ref19","first-page":"9099","article-title":"Transformer quality in linear time","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hua"},{"key":"ref20","article-title":"Mega: Moving average equipped gated attention","author":"Ma","year":"2022","journal-title":"arXiv:2209.10655"},{"key":"ref21","article-title":"Gated linear attention transformers with hardware-efficient training","author":"Yang","year":"2023","journal-title":"arXiv:2312.06635"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00718"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3710"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02440"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00343"},{"key":"ref26","first-page":"1","article-title":"Gated attention for large language models: Non-linearity, sparsity, and attention-sink-free","volume-title":"Proc. 39th Annu. Conf. Neural Inf. Process. Syst.","author":"Qiu"},{"issue":"1","key":"ref27","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref28","first-page":"1","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref30","volume-title":"PyTorch image models","author":"Wightman","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_5"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00063"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref35","first-page":"12633","article-title":"Global context vision transformers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hatamizadeh"},{"key":"ref36","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":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342025"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00062"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00044"},{"key":"ref40","volume-title":"Fast-DiT: Fast Diffusion Models With Transformers","author":"Jin","year":"2024"},{"key":"ref41","article-title":"ImageNet-21K pretraining for the masses","author":"Ridnik","year":"2021","journal-title":"arXiv:2104.10972"},{"key":"ref42","first-page":"3519","article-title":"Similarity of neural network representations revisited","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kornblith"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.385"},{"key":"ref44","article-title":"ALBERT: A lite BERT for self-supervised learning of language representations","author":"Lan","year":"2019","journal-title":"arXiv:1909.11942"},{"issue":"140","key":"ref45","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"ref47","article-title":"Customizing the inductive biases of softmax attention using structured matrices","author":"Kuang","year":"2025","journal-title":"arXiv:2509.07963"},{"key":"ref48","article-title":"Chronos: Learning the language of time series","author":"Fatir Ansari","year":"2024","journal-title":"arXiv:2403.07815"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11554332.pdf?arnumber=11554332","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T19:09:31Z","timestamp":1784660971000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11554332\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3701015","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}