{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T13:32:50Z","timestamp":1773840770449,"version":"3.50.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746526","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"2614-2618","source":"Crossref","is-referenced-by-count":12,"title":["Vision Transformer Equipped With Neural Resizer On Facial Expression Recognition Task"],"prefix":"10.1109","author":[{"given":"Hyeonbin","family":"Hwang","sequence":"first","affiliation":[{"name":"KAIST,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Soyeon","family":"Kim","sequence":"additional","affiliation":[{"name":"KAIST,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei-Jin","family":"Park","sequence":"additional","affiliation":[{"name":"ACRYL,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiho","family":"Seo","sequence":"additional","affiliation":[{"name":"ACRYL,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyungtae","family":"Ko","sequence":"additional","affiliation":[{"name":"ACRYL,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyeon","family":"Yeo","sequence":"additional","affiliation":[{"name":"KAIST,Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3010018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref12","article-title":"Learning imbalanced datasets with label-distribution-aware margin loss","author":"cao","year":"2019","journal-title":"arXiv preprint arXiv 1906 02415"},{"key":"ref13","article-title":"Learning vision transformer with squeeze and excitation for facial expression recognition","author":"aouayeb","year":"2021"},{"key":"ref14","article-title":"Mvt: Mask vision transformer for facial expression recognition in the wild","author":"li","year":"2021"},{"key":"ref15","article-title":"Robust facial expression recognition with convolutional visual transformers","author":"ma","year":"2021"},{"key":"ref16","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_25"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00055"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2993165"},{"key":"ref3","article-title":"Learning from noisy labels with deep neural networks: A survey","author":"song","year":"2020","journal-title":"arXiv preprint arXiv 2007 09948"},{"key":"ref6","article-title":"Region attention networks for pose and occlusion robust facial expression recognition","author":"wang","year":"2019"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2019.8756625"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3390\/s20092639"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00693"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.277"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00945"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.2981446"},{"key":"ref20","article-title":"Training data-efficient image transformers distillation through attention","author":"touvron","year":"2021"},{"key":"ref22","article-title":"Xcit: Cross-covariance image transformers","author":"el-nouby","year":"2021"},{"key":"ref21","article-title":"Convit: Improving vision transformers with soft convolutional inductive biases","author":"d\u2019ascoli","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33712-3_49"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00561"},{"key":"ref26","first-page":"ii","article-title":"Robust facial expression recognition using local binary patterns","volume":"2","author":"shan","year":"0","journal-title":"IEEE International Conference on Image Processing 2005"},{"key":"ref25","article-title":"Spatial transformer networks","author":"jaderberg","year":"2016"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746526.pdf?arnumber=9746526","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:11:46Z","timestamp":1661199106000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746526\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746526","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}