{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T21:31:41Z","timestamp":1775251901908,"version":"3.50.1"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Institute of Information and Communications Technology Planning and Evaluation (IITP) and the Information Technology Research Center (ITRC) Grant"},{"name":"Korea Government","award":["IITP-2025-RS-2022-00156295"],"award-info":[{"award-number":["IITP-2025-RS-2022-00156295"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3628323","type":"journal-article","created":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T18:45:59Z","timestamp":1762195559000},"page":"190093-190107","source":"Crossref","is-referenced-by-count":3,"title":["Batch Transformer: Look for Attention in Batch"],"prefix":"10.1109","volume":"13","author":[{"given":"Myungbeom","family":"Her","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Seoul National University of Science and Technology, Seoul, South Korea"}]},{"given":"Jisu","family":"Jeong","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Seoul National University of Science and Technology, Seoul, South Korea"}]},{"given":"Hojoon","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Seoul National University of Science and Technology, Seoul, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8391-6898","authenticated-orcid":false,"given":"Ji-Hyeong","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Seoul National University of Science and Technology, Seoul, South Korea"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Expression, affect, action unit recognition: Aff-wild2, multi-task learning and ArcFace","author":"Kollias","year":"2019","journal-title":"arXiv:1910.04855"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3010018"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16465"},{"key":"ref4","article-title":"Distribution matching for heterogeneous multi-task learning: A large-scale face study","author":"Kollias","year":"2021","journal-title":"arXiv:2105.03790"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3156598"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110951"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00358"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3226473"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00339"},{"key":"ref10","article-title":"ARBEx: Attentive feature extraction with reliability balancing for robust facial expression learning","author":"Wasi","year":"2023","journal-title":"arXiv:2305.01486"},{"key":"ref11","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":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01521-4"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8545853"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-01476-3"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107678"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2010.5543262"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.3451524"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2005.1521424"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1037\/h0030377"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2008.08.005"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkg509"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.005"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2740923"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.277"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00693"},{"key":"ref29","first-page":"17616","article-title":"Relative uncertainty learning for facial expression recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Zhang"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_24"},{"key":"ref31","first-page":"12633","article-title":"Global context vision transformers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hatamizadeh"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.55730\/1300-0632.4121"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2024.3415000"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.55730\/1300-0632.4120"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.106959"},{"key":"ref36","article-title":"Learning vision transformer with squeeze and excitation for facial expression recognition","author":"Aouayeb","year":"2021","journal-title":"arXiv:2107.03107"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2913372"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3122146"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3390\/biomimetics8020199"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref41","volume-title":"Pytorch Face Landmark: A Fast and Accurate Facial Landmark Detector. 2021","author":"Chen","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2956143"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2011.07.002"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.05.081"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00027"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_6"},{"key":"ref47","article-title":"Sharpness-aware minimization for efficiently improving generalization","author":"Foret","year":"2020","journal-title":"arXiv:2010.01412"},{"key":"ref48","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref49","article-title":"An exponential learning rate schedule for deep learning","author":"Li","year":"2019","journal-title":"arXiv:1910.07454"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2025.3567966"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3049955"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00618"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00757"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3093397"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.3390\/computation12100201"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3453443"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2917266"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9411919"},{"key":"ref59","article-title":"Facial expression recognition with deep learning","author":"Khanzada","year":"2020","journal-title":"arXiv:2004.11823"},{"key":"ref60","article-title":"Facial emotion recognition: State of the art performance on FER2013","author":"Khaireddin","year":"2021","journal-title":"arXiv:2105.03588"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.3390\/info13090419"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s41870-023-01184-z"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3085744"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3165321"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3237006"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3234312"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.11.033"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00020"},{"issue":"86","key":"ref69","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00245"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3237817"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.11.068"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3304724"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11224489.pdf?arnumber=11224489","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T05:55:36Z","timestamp":1762840536000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11224489\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3628323","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}