{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T17:18:08Z","timestamp":1787937488306,"version":"build-2784847793"},"reference-count":69,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","award":["202006180033"],"award-info":[{"award-number":["202006180033"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Project of Gansu","award":["24JRRA388"],"award-info":[{"award-number":["24JRRA388"]}]},{"name":"Science Foundation of Zhejiang Sci-Tech University","award":["22062338-Y"],"award-info":[{"award-number":["22062338-Y"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2024.3521788","type":"journal-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:32:25Z","timestamp":1735155145000},"page":"2412-2422","source":"Crossref","is-referenced-by-count":36,"title":["FER-Former: Multimodal Transformer for Facial Expression Recognition"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9972-8020","authenticated-orcid":false,"given":"Yande","family":"Li","sequence":"first","affiliation":[{"name":"School of Information Science and Engineering, Lanzhou University, Lanzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingjie","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Science, Zhejiang Sci-Tech University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5820-5381","authenticated-orcid":false,"given":"Minglun","family":"Gong","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Guelph, Guelph, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8926-2039","authenticated-orcid":false,"given":"Yonggang","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Lanzhou University, Lanzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4776-5292","authenticated-orcid":false,"given":"Li","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Big Data and Software Engineering, Chongqing University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106217"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.06.087"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3096068"},{"key":"ref4","article-title":"Induced disgust, happiness and surprise: An addition to the MMI facial expression database","volume-title":"Proc. 3rd Intern. Workshop Emotion (Satell. LREC): Corpora Res. Emotion Affect","author":"Valstar","year":"2010"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2010.5543262"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2011.07.002"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108290"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01559"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3055613"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2522848.2531745"},{"key":"ref11","article-title":"Deep learning using linear support vector machines","author":"Tang","year":"2013"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2956143"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2886767"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3093397"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3121547"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.compind.2019.01.012"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACPR.2017.7"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref19","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref20","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01178"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3144158"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00525"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00568"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00358"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01471"},{"key":"ref27","article-title":"Label distribution amendment with emotional semantic correlations for facial expression recognition","author":"Mao","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16465"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01400"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00618"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547960"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00693"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00413"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548005"},{"key":"ref35","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00444"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00381"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351049"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413773"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2972114"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3072786"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00062"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"ref47","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2021"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"ref49","article-title":"SimVLM: Simple visual language model pretraining with weak supervision","author":"Wang","year":"2021"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00147"},{"key":"ref51","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim","year":"2021"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref53","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia","year":"2021"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_6"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2868382"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2993165"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-42051-1_16"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130508"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3197761"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3237006"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3049955"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00669"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3186536"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00077"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00051"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_14"},{"issue":"11","key":"ref69","first-page":"2579","article-title":"Visualizing data using T-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10814686.pdf?arnumber=10814686","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T17:47:54Z","timestamp":1747158474000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10814686\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3521788","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}