{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T10:40:06Z","timestamp":1774435206898,"version":"3.50.1"},"reference-count":111,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100022963","name":"Key Research and Development Program of Zhejiang Province","doi-asserted-by":"publisher","award":["2022C01011"],"award-info":[{"award-number":["2022C01011"]}],"id":[{"id":"10.13039\/100022963","id-type":"DOI","asserted-by":"publisher"}]},{"name":"2022 Key Artificial Intelligence Science and Technology Innovation Project of Hangzhou Science and Technology Office"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Affective Comput."],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1109\/taffc.2024.3367015","type":"journal-article","created":{"date-parts":[[2024,2,19]],"date-time":"2024-02-19T20:10:03Z","timestamp":1708373403000},"page":"1669-1683","source":"Crossref","is-referenced-by-count":16,"title":["Facial Action Unit Detection and Intensity Estimation From Self-Supervised Representation"],"prefix":"10.1109","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7538-3996","authenticated-orcid":false,"given":"Bowen","family":"Ma","sequence":"first","affiliation":[{"name":"Netease Fuxi AI Lab, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8575-8229","authenticated-orcid":false,"given":"Rudong","family":"An","sequence":"additional","affiliation":[{"name":"Netease Fuxi AI Lab, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5907-7342","authenticated-orcid":false,"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Netease Fuxi AI Lab, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1834-4429","authenticated-orcid":false,"given":"Yu","family":"Ding","sequence":"additional","affiliation":[{"name":"Netease Fuxi AI Lab, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7292-876X","authenticated-orcid":false,"given":"Zeng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Netease Fuxi AI Lab, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1248-2090","authenticated-orcid":false,"given":"Rongsheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Netease Fuxi AI Lab, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9858-809X","authenticated-orcid":false,"given":"Tangjie","family":"Lv","sequence":"additional","affiliation":[{"name":"Netease Fuxi AI Lab, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5420-0516","authenticated-orcid":false,"given":"Changjie","family":"Fan","sequence":"additional","affiliation":[{"name":"Netease Fuxi AI Lab, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4367-0816","authenticated-orcid":false,"given":"Zhipeng","family":"Hu","sequence":"additional","affiliation":[{"name":"Netease Fuxi AI Lab, Hangzhou, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1037\/t27734-000"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2010.2082525"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/VS-GAMES.2016.7590374"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.2974263"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3160061"},{"key":"ref6","first-page":"909","article-title":"Multi-label co-regularization for semi-supervised facial action unit recognition","volume-title":"Proc. Adva. Neural Inf. Process. Syst.","author":"Niu"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01977"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00394"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01471"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.2981446"},{"key":"ref11","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref12","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref13","article-title":"BEiT: Bert pre-training of image transformers","author":"Bao","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2006.85"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2011.5771416"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2354351"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.413"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3389\/fcomp.2019.00011"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2570550"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.369"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.03.082"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/FG52635.2021.9666961"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3643863"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1094"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01219"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_19"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-37734-2_40"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2017.136"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01378-z"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2019.2948635"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00759"},{"key":"ref34","first-page":"14338","article-title":"Knowledge augmented deep neural networks for joint facial expression and action unit recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cui"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01034"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00223"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00271"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00669"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19914"},{"key":"ref40","article-title":"Knowledge-spreader: Learning facial action unit dynamics with extremely limited labels","author":"Li","year":"2022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247983"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33868-7_26"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2721114"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.605"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54184-6_10"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.101"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00246"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00735"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00357"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3061605"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6963"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00082"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00896"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref55","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref56","article-title":"Learning deep representations by mutual information estimation and maximization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hjelm"},{"key":"ref57","first-page":"15535","article-title":"Learning representations by maximizing mutual information across views","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bachman"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref60","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref61","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475295"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-65414-6_9"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00264"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00949"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2771150"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2740923"},{"key":"ref69","article-title":"Learning face representation from scratch","author":"Yi","year":"2014"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0940-3"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00525"},{"key":"ref73","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2014.06.002"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.374"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2013.4"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1037\/\/0033-2909.86.2.420"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2791608"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018594"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i7.16748"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00620"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/173"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2019.8925514"},{"key":"ref84","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref85","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist.","author":"Glorot"},{"key":"ref86","article-title":"Accurate, large minibatch SGD: Training ImageNet in 1 hour","author":"Goyal","year":"2017"},{"key":"ref87","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016"},{"key":"ref88","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref93","article-title":"Averaging weights leads to wider optima and better generalization","author":"Izmailov","year":"2018"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2015.7284868"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.346"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/102"},{"key":"ref97","first-page":"137","article-title":"Re-net: A relation embedded deep model for au occurrence and intensity estimation","volume-title":"Proc. Asian Conf. Comput. Vis.","author":"Yang"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19778-9_7"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00245"},{"key":"ref100","article-title":"Learning to amend facial expression representation via de-albino and affinity","author":"Shi","year":"2021"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_24"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.3390\/biomimetics8020199"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00358"},{"key":"ref104","article-title":"Facial expression recognition using vanilla vit backbones with mae pretraining","author":"Li","year":"2022"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00339"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110951"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.277"},{"key":"ref108","article-title":"Resnet strikes back: An improved training procedure in timm","author":"Wightman","year":"2021"},{"key":"ref109","article-title":"How to train your vit? Data, augmentation, and regularization in vision transformers,","author":"Steiner","year":"2021"},{"key":"ref110","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"}],"container-title":["IEEE Transactions on Affective Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5165369\/10666803\/10439628.pdf?arnumber=10439628","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T18:02:16Z","timestamp":1725645736000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10439628\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":111,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/taffc.2024.3367015","relation":{},"ISSN":["1949-3045","2371-9850"],"issn-type":[{"value":"1949-3045","type":"electronic"},{"value":"2371-9850","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7]]}}}