{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:57:04Z","timestamp":1780765024029,"version":"3.54.1"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100013139","name":"Humanities and Social Science Fund of the Ministry of Education of the People\u2019s Republic of China","doi-asserted-by":"publisher","award":["22YJAZH036"],"award-info":[{"award-number":["22YJAZH036"]}],"id":[{"id":"10.13039\/501100013139","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tcsvt.2024.3436029","type":"journal-article","created":{"date-parts":[[2024,7,31]],"date-time":"2024-07-31T20:56:43Z","timestamp":1722459403000},"page":"12399-12410","source":"Crossref","is-referenced-by-count":8,"title":["A Self-Supervised Learning Network for Student Engagement Recognition From Facial Expressions"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-4689-4387","authenticated-orcid":false,"given":"Wen-Long","family":"Zhang","sequence":"first","affiliation":[{"name":"College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui-Sheng","family":"Jia","sequence":"additional","affiliation":[{"name":"College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1877-9150","authenticated-orcid":false,"given":"Hu","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2218-3053","authenticated-orcid":false,"given":"Cheng-Yue","family":"Che","sequence":"additional","affiliation":[{"name":"College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hong-Mei","family":"Sun","sequence":"additional","affiliation":[{"name":"College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jik.2022.100295"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijme.2023.100803"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02025"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref5","first-page":"2","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","volume":"1","author":"Kenton"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3285803"},{"key":"ref7","first-page":"10078","article-title":"VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Tong"},{"key":"ref8","first-page":"1691","article-title":"Generative pretraining from pixels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3265075"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1117\/12.2665871"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01898-4"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"ref13","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":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00222"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI44817.2019.9002713"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICEIEC.2019.8784507"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-03200-4"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3382507.3417959"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3382507.3417965"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-020-02139-8"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CRV52889.2021.00028"},{"key":"ref22","article-title":"Class-attention video transformer for engagement intensity prediction","author":"Ai","year":"2022","journal-title":"arXiv:2208.07216"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3304724"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01499"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00279"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01172"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.278"},{"key":"ref28","first-page":"1","article-title":"Generative adversarial nets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Goodfellow"},{"key":"ref29","article-title":"DAiSEE: Towards user engagement recognition in the wild","author":"Gupta","year":"2016","journal-title":"arXiv:1609.0188"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA.2018.8615851"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.sasc.2022.200039"},{"key":"ref32","article-title":"Accurate, large minibatch SGD: Training ImageNet in 1 hour","author":"Goyal","year":"2017","journal-title":"arXiv:1706.02677"},{"key":"ref33","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref34","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016","journal-title":"arXiv:1608.03983"},{"key":"ref35","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICEIEC.2019.8784559"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3390\/app12168007"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3340555.3355710"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20011"},{"key":"ref42","first-page":"35946","article-title":"Masked autoencoders as spatiotemporal learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Feichtenhofer"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.2981446"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.1188976"},{"key":"ref47","doi-asserted-by":"crossref","first-page":"334","DOI":"10.1016\/j.future.2020.02.075","article-title":"Affective database for e-learning and classroom environments using Indian students\u2019 faces, hand gestures and body postures","volume":"108","author":"Ashwin","year":"2020","journal-title":"Future Gener. Comput. Syst."},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803603"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66415-2_53"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3340555.3355719"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2997627"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01251-8"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3099900"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/184"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053415"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00464"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-249"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2019.8925444"},{"key":"ref60","article-title":"MSAF: Multimodal split attention fusion","author":"Su","year":"2020","journal-title":"arXiv:2012.07175"},{"key":"ref61","article-title":"A cross-modal fusion network based on self-attention and residual structure for multimodal emotion recognition","author":"Fu","year":"2021","journal-title":"arXiv:2111.02172"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01330"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2022.07.012"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09816-7"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2017.02.008"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2020.3005909"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3234312"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10811772\/10616120.pdf?arnumber=10616120","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,21]],"date-time":"2024-12-21T05:54:48Z","timestamp":1734760488000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10616120\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":67,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3436029","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}