{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T02:48:10Z","timestamp":1792464490043,"version":"4.5.0"},"reference-count":93,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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":["IEEE Trans. Affective Comput."],"published-print":{"date-parts":[[2023,10,1]]},"DOI":"10.1109\/taffc.2022.3226473","type":"journal-article","created":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T18:14:05Z","timestamp":1670264045000},"page":"3244-3256","source":"Crossref","is-referenced-by-count":168,"title":["Vision Transformer With Attentive Pooling for Robust Facial Expression Recognition"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1848-2322","authenticated-orcid":false,"given":"Fanglei","family":"Xue","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0416-8778","authenticated-orcid":false,"given":"Qiangchang","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8501-4123","authenticated-orcid":false,"given":"Zichang","family":"Tan","sequence":"additional","affiliation":[{"name":"Institute of Deep Learning, Baidu Research, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4322-033X","authenticated-orcid":false,"given":"Zhongsong","family":"Ma","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9583-0055","authenticated-orcid":false,"given":"Guodong","family":"Guo","sequence":"additional","affiliation":[{"name":"Institute of Deep Learning, Baidu Research, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","article-title":"MViT: Mask vision transformer for facial expression recognition in the wild","author":"li","year":"2021"},{"key":"ref57","article-title":"Expression, affect, action unit recognition: Aff-wild2, multi-task learning and arcface","author":"kollias","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3122146"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2019.2907628"},{"key":"ref15","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":"ref59","article-title":"Emotion recognition with incomplete labels using modified multi-task learning technique","author":"thinh","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.248"},{"key":"ref53","first-page":"117","article-title":"Challenges in representation learning: A report on three machine learning contests","author":"goodfellow","year":"2013","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00408"},{"key":"ref11","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020"},{"key":"ref55","article-title":"Acted facial expressions in the wild database","author":"dhall","year":"2011"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00358"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3049955"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2919199"},{"key":"ref16","first-page":"10750","article-title":"Dropblock: A regularization method for convolutional networks","author":"ghiasi","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref19","article-title":"DeepViT: Towards deeper vision transformer","author":"zhou","year":"2021"},{"key":"ref18","article-title":"Conditional positional encodings for vision transformers","author":"chu","year":"2021"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"ref92","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1055-1"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130508"},{"key":"ref91","article-title":"A multi-modal and multi-task learning method for action unit and expression recognition","author":"jin","year":"0"},{"key":"ref90","first-page":"3539","article-title":"Prior aided streaming network for multi-task affective recognitionat the 2nd ABAW2 Competition","author":"zhang","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis Workshops"},{"key":"ref46","article-title":"Learning vision transformer with squeeze and excitation for facial expression recognition","author":"aouayeb","year":"2021"},{"key":"ref45","first-page":"9992","article-title":"Swin transformer: Hierarchical vision transformer using shifted windows","author":"liu","year":"2021","journal-title":"Proc IEEE\/CVF Int Conf Comput Vis"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.600"},{"key":"ref48","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","author":"zagoruyko","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00835"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.97"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00396"},{"key":"ref41","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"zhu","year":"2020"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00402"},{"key":"ref44","first-page":"2286","article-title":"ConViT: Improving vision transformers with soft convolutional inductive biases","author":"d\u2019ascoli","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref43","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"2020"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2014.03.024"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2993165"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2956143"},{"key":"ref7","first-page":"222","article-title":"Facial expression recognition with inconsistently annotated datasets","author":"zeng","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.2988264"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.277"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2740923"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2886767"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00051"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2921241"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-019-1176-9"},{"key":"ref40","first-page":"213","article-title":"End-to-End object detection with transformers","author":"carion","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00401"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00394"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412554"},{"key":"ref35","first-page":"2562","article-title":"Learning active facial patches for expression analysis","author":"zhong","year":"2012","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref79","article-title":"Distract your attention: Multi-head cross attention network for facial expression recognition","author":"wen","year":"2021"},{"key":"ref34","first-page":"29","volume":"1","author":"duchenne","year":"1862","journal-title":"Mécanisme de la physionomie humaine ou analyse électro-physiologique de ses différents modes de l'expression"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00194"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3093397"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.03.019"},{"key":"ref31","first-page":"3282","article-title":"Processing megapixel images with deep attention-sampling models","author":"katharopoulos","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240578"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1155\/2014\/408953"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2018.2880201"},{"key":"ref33","article-title":"Efficient video transformers with spatial-temporal token selection","author":"wang","year":"2021"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.12.076"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00238"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2830590"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2008.08.005"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780195112719.001.0001"},{"key":"ref39","article-title":"Attention is all you need","author":"vaswani","year":"2017"},{"key":"ref38","first-page":"3","article-title":"CBAM: Convolutional block attention module","author":"woo","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3131621"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00757"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2017.120"},{"key":"ref72","first-page":"499","article-title":"A discriminative feature learning approach for deep face recognition","author":"wen","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00525"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16465"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00245"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2002.999679"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3156920"},{"key":"ref20","first-page":"18590","article-title":"All tokens matter: Token labeling for training better vision transformers","author":"jiang","year":"2021","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00077"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01400"},{"key":"ref22","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00669"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00693"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2386334"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkg509"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3390\/s130607714"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref62","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"loshchilov","year":"2016","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref61","first-page":"87","article-title":"MS-celeb-1M: A dataset and benchmark for large-scale face recognition","author":"guo","year":"2016","journal-title":"Proc Eur Conf Comput Vis"}],"container-title":["IEEE Transactions on Affective Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5165369\/10330166\/09969878.pdf?arnumber=9969878","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T18:14:47Z","timestamp":1701281687000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9969878\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":93,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/taffc.2022.3226473","relation":{},"ISSN":["1949-3045","2371-9850"],"issn-type":[{"value":"1949-3045","type":"electronic"},{"value":"2371-9850","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,1]]}}}