{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T16:41:14Z","timestamp":1792082474311,"version":"4.4.0"},"reference-count":51,"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\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3598917","type":"journal-article","created":{"date-parts":[[2025,8,14]],"date-time":"2025-08-14T18:48:28Z","timestamp":1755197308000},"page":"144689-144698","source":"Crossref","is-referenced-by-count":10,"title":["Enhancing Vision Transformers for Facial Expression Recognition"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-5190-4747","authenticated-orcid":false,"given":"Ali Mohammad","family":"Pazandeh","sequence":"first","affiliation":[{"name":"Electrical Engineering Department, Sharif University of Technology, Tehran, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5017-7136","authenticated-orcid":false,"given":"Emad","family":"Fatemizadeh","sequence":"additional","affiliation":[{"name":"Electrical Engineering Department, Sharif University of Technology, Tehran, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Learning vision transformer with squeeze and excitation for facial expression recognition","author":"Aouayeb","year":"2021","journal-title":"arXiv:2107.03107"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2993165"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.10882"},{"key":"ref4","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chu"},{"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\/ACCESS.2024.3496506"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.2988264"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3156598"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00245"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/2868\/1\/012036"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-42051-1_16"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01172"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2021.08.043"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/info15060321"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119640"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747322"},{"key":"ref17","article-title":"Facial emotion recognition: State of the art performance on FER2013","author":"Khaireddin","year":"2021","journal-title":"arXiv:2105.03588"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3390\/s22103729"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00541"},{"key":"ref20","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"25","author":"Krizhevsky"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3049955"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.2981446"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.277"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3165321"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref26","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3122146"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3390\/s21093046"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2740923"},{"key":"ref30","article-title":"Mini-ResEmoteNet: Leveraging knowledge distillation for human-centered design","author":"Murtada","year":"2025","journal-title":"arXiv:2501.18538"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3407108"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00043"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvcm4g18.8"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3390\/info13090419"},{"key":"ref35","article-title":"Learning to amend facial expression representation via De-albino and affinity","author":"Shi","year":"2021","journal-title":"arXiv:2103.10189"},{"key":"ref36","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6037"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ATEE52255.2021.9425073"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00693"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3390\/biomimetics8020199"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110530"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00358"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2997639"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2830595"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_24"},{"key":"ref49","first-page":"317","article-title":"Feature selection mechanism in CNNs for facial expression recognition","volume-title":"Proc. BMVC","volume":"12","author":"Zhao"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00339"},{"key":"ref51","article-title":"DeepViT: Towards deeper vision transformer","author":"Zhou","year":"2021","journal-title":"arXiv:2103.11886"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11124874.pdf?arnumber=11124874","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:01:53Z","timestamp":1755910913000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11124874\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3598917","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}