{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T04:30:59Z","timestamp":1793334659689,"version":"4.5.0"},"reference-count":49,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2027,1]]},"DOI":"10.1016\/j.eswa.2026.133764","type":"journal-article","created":{"date-parts":[[2026,7,26]],"date-time":"2026-07-26T22:07:07Z","timestamp":1785103627000},"page":"133764","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["Evidential gating mixture-of-experts based on spatial and temporal transformers for uncertainty-aware engagement estimation"],"prefix":"10.1016","volume":"333","author":[{"given":"Zhengrui","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongqiang","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juncheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0790-6492","authenticated-orcid":false,"given":"Zhaohong","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"3","key":"10.1016\/j.eswa.2026.133764_b0005","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1080\/10447318.2021.1938389","article-title":"Understanding learner continuance intention: A comparison of live video learning, pre-recorded video learning and hybrid video learning in COVID-19 pandemic","volume":"38","author":"Wang","year":"2022","journal-title":"International Journal of Human-Computer Interaction"},{"key":"10.1016\/j.eswa.2026.133764_b0010","doi-asserted-by":"crossref","first-page":"452","DOI":"10.1007\/s12528-018-9179-z","article-title":"Online learning in higher education: Exploring advantages and disadvantages for engagement","volume":"30","author":"Dumford","year":"2018","journal-title":"Journal of Computing in Higher Education"},{"key":"10.1016\/j.eswa.2026.133764_b0015","article-title":"Multimodal engagement analysis from facial videos in the classroom","author":"S\u00fcmer","year":"2021","journal-title":"IEEE Transactions on Affective Computing"},{"key":"10.1016\/j.eswa.2026.133764_b0020","doi-asserted-by":"crossref","unstructured":"A. Abedi and S. S. Khan, \u201cImproving state-of-the-art in detecting student engagement with resnet and tcn hybrid network,\u201d in Proceedings of the 2021 18th Conference on Robots and Vision (CRV), 2021: IEEE, pp. 151-157.","DOI":"10.1109\/CRV52889.2021.00028"},{"key":"10.1016\/j.eswa.2026.133764_b0025","series-title":"in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"6546","article-title":"Can spatiotemporal 3d cnns retrace the history of 2d cnns and imagenet?","author":"Hara","year":"2018"},{"key":"10.1016\/j.eswa.2026.133764_b0030","doi-asserted-by":"crossref","unstructured":"H. Zhang, X. Xiao, T. Huang, S. Liu, Y. Xia, and J. Li, \u201cAn novel end-to-end network for automatic student engagement recognition,\u201d in 2019 IEEE 9th International Conference on Electronics Information and Emergency Communication (ICEIEC), 2019: IEEE, pp. 342-345.","DOI":"10.1109\/ICEIEC.2019.8784507"},{"key":"10.1016\/j.eswa.2026.133764_b0035","doi-asserted-by":"crossref","unstructured":"J. Yu, K. Lu, J. Zhao, Z. Wei, I.-H. Chu, and P. Chang, \u201cDialogue cross-enhanced central engagement attention model for real-time Engagement estimation,\u201d in Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, Jeju, Korea, 2024, p. Article 353, doi: 10.24963\/ijcai.2024\/353.","DOI":"10.24963\/ijcai.2024\/353"},{"key":"10.1016\/j.eswa.2026.133764_b0040","series-title":"in Proceedings of the 31st ACM International Conference on Multimedia","first-page":"9496","article-title":"Sliding Window Seq2seq Modeling for Engagement Estimation","author":"Yu","year":"2023"},{"key":"10.1016\/j.eswa.2026.133764_b0045","series-title":"in 31st ACM International Conference on Multimedia","first-page":"9521","article-title":"DCTM: Dilated Convolutional Transformer Model for Multimodal Engagement Estimation in conversation","author":"Tu","year":"2023"},{"key":"10.1016\/j.eswa.2026.133764_b0050","doi-asserted-by":"crossref","unstructured":"H. He, D. Wang, M. R. Hasan, T. Gedeon, and M. Z. Hossain, \u201cTCA-NET: Triplet Concatenated-Attentional Network For Multimodal Engagement Estimation,\u201d in Proceedings of the IEEE International Conference on Image Processing (ICIP), 2024.","DOI":"10.1109\/ICIP51287.2024.10647692"},{"key":"10.1016\/j.eswa.2026.133764_b0055","article-title":"Evidential deep learning to quantify classification uncertainty","volume":"31","author":"Sensoy","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.133764_b0060","unstructured":"A. Jsang, Subjective Logic: A formalism for reasoning under uncertainty. Springer Publishing Company, Incorporated, 2018."},{"key":"10.1016\/j.eswa.2026.133764_b0065","unstructured":"A. Gupta, A. D'Cunha, K. Awasthi, and V. Balasubramanian, \u201cDaisee: Towards user engagement recognition in the wild,\u201d arXiv preprint arXiv:1609.01885, 2016."},{"key":"10.1016\/j.eswa.2026.133764_b0070","doi-asserted-by":"crossref","DOI":"10.1016\/j.sasc.2022.200039","article-title":"DMCNet: Diversified model combination network for understanding engagement from video screengrabs","volume":"4","author":"Batra","year":"2022","journal-title":"Systems and Soft Computing"},{"issue":"1","key":"10.1016\/j.eswa.2026.133764_b0075","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1109\/TAFFC.2014.2316163","article-title":"The faces of engagement: Automatic recognition of student engagementfrom facial expressions","volume":"5","author":"Whitehill","year":"2014","journal-title":"IEEE Transactions on Affective Computing"},{"key":"10.1016\/j.eswa.2026.133764_b0080","doi-asserted-by":"crossref","unstructured":"A. Dhall, G. Sharma, R. Goecke, and T. Gedeon, \u201cEmotiw 2020: Driver gaze, group emotion, student engagement and physiological signal based challenges,\u201d in Proceedings of the 2020 International Conference on Multimodal Interaction (ICMI), 2020, pp. 784-789.","DOI":"10.1145\/3382507.3417973"},{"key":"10.1016\/j.eswa.2026.133764_b0085","doi-asserted-by":"crossref","unstructured":"L. Geng, M. Xu, Z. Wei, and X. Zhou, \u201cLearning deep spatiotemporal feature for engagement recognition of online courses,\u201d in Proceedings of the 2019 IEEE Symposium Series on Computational Intelligence (SSCI), 2019: IEEE, pp. 442-447.","DOI":"10.1109\/SSCI44817.2019.9002713"},{"key":"10.1016\/j.eswa.2026.133764_b0090","doi-asserted-by":"crossref","unstructured":"A. Kaur, A. Mustafa, L. Mehta, and A. Dhall, \u201cPrediction and localization of student engagement in the wild,\u201d in Proceedings of 2018 Digital Image Computing: Techniques and Applications, 2018: IEEE, pp. 1-8.","DOI":"10.1109\/DICTA.2018.8615851"},{"issue":"2","key":"10.1016\/j.eswa.2026.133764_b0095","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1080\/00461520.2017.1281747","article-title":"Advanced, analytic, automated (AAA) measurement of engagement during learning","volume":"52","author":"D'Mello","year":"2017","journal-title":"Educational Psychologist"},{"key":"10.1016\/j.eswa.2026.133764_b0100","article-title":"EEG-based emotion recognition via channel-wise attention and self attention","author":"Tao","year":"2020","journal-title":"IEEE Transactions on Affective Computing"},{"issue":"3","key":"10.1016\/j.eswa.2026.133764_b0105","doi-asserted-by":"crossref","first-page":"532","DOI":"10.1109\/TAFFC.2018.2817622","article-title":"EEG emotion recognition using dynamical graph convolutional neural networks","volume":"11","author":"Song","year":"2018","journal-title":"IEEE Transactions on Affective Computing"},{"key":"10.1016\/j.eswa.2026.133764_b0110","doi-asserted-by":"crossref","unstructured":"A. Dhall, G. Sharma, R. Goecke, and T. Gedeon, \u201cEmotiw 2020: Driver gaze, group emotion, student engagement and physiological signal based challenges,\u201d in Proceedings of the 2020 International Conference on Multimodal Interaction, 2020, pp. 784-789.","DOI":"10.1145\/3382507.3417973"},{"key":"10.1016\/j.eswa.2026.133764_b0115","doi-asserted-by":"crossref","unstructured":"P. M\u00fcller et al., \u201cMultiMediate '23: Engagement Estimation and Bodily Behaviour Recognition in Social Interactions,\u201d in Proceedings of the 31st ACM International Conference on Multimedia, Ottawa ON, Canada, 2023: Association for Computing Machinery, pp. 9640\u20139645, doi: 10.1145\/3581783.3613851.","DOI":"10.1145\/3581783.3613851"},{"key":"10.1016\/j.eswa.2026.133764_b0120","series-title":"in Proceedings of the 32nd ACM International Conference on Multimedia","first-page":"11377","article-title":"MultiMediate'24: Multi-Domain Engagement Estimation","author":"M\u00fcller","year":"2024"},{"key":"10.1016\/j.eswa.2026.133764_b0125","doi-asserted-by":"crossref","unstructured":"A. Cafaro et al., \u201cThe NoXi database: multimodal recordings of mediated novice-expert interactions,\u201d in Proceedings of the 19th ACM International Conference on Multimodal Interaction, Glasgow, UK, 2017: Association for Computing Machinery, pp. 350\u2013359.","DOI":"10.1145\/3136755.3136780"},{"key":"10.1016\/j.eswa.2026.133764_b0130","doi-asserted-by":"crossref","unstructured":"C. Yang et al., \u201cMultiMediate 2023: Engagement Level Detection using Audio and Video Features,\u201d in Proceedings of the 31st ACM International Conference on Multimedia, 2023, pp. 9601-9605.","DOI":"10.1145\/3581783.3612873"},{"key":"10.1016\/j.eswa.2026.133764_b0135","series-title":"in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"1","article-title":"Going deeper with convolutions","author":"Szegedy","year":"2015"},{"key":"10.1016\/j.eswa.2026.133764_b0140","doi-asserted-by":"crossref","unstructured":"C. Lea, R. Vidal, A. Reiter, and G. D. Hager, \u201cTemporal convolutional networks: A unified approach to action segmentation,\u201d in Proceedings of the ECCV 2016 Workshops, 2016: Springer Verlag, pp. 47-54.","DOI":"10.1007\/978-3-319-49409-8_7"},{"key":"10.1016\/j.eswa.2026.133764_b0145","series-title":"in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"3202","article-title":"Video swin transformer","author":"Liu","year":"2022"},{"key":"10.1016\/j.eswa.2026.133764_b0150","unstructured":"J. Van Amersfoort, L. Smith, Y. W. Teh, and Y. Gal, \u201cUncertainty estimation using a single deep deterministic neural network,\u201d in Proceedings of the 37th International Conference on Machine Learning (ICML), 2020: PMLR, pp. 9690-9700."},{"key":"10.1016\/j.eswa.2026.133764_b0155","first-page":"23768","article-title":"Be confident! towards trustworthy graph neural networks via confidence calibration","volume":"34","author":"Wang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.133764_b0160","series-title":"in Proceedings of the International Conference on Learning Representations (ICLR)","article-title":"Beta-vae: Learning basic visual concepts with a constrained variational framework","author":"Higgins","year":"2016"},{"key":"10.1016\/j.eswa.2026.133764_b0165","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.133764_b0170","unstructured":"G. Bertasius, H. Wang, and L. Torresani, \u201cIs space-time attention all you need for video understanding?,\u201d in Proceedings of the 38th International Conference on Machine Learning (ICML), 2021, vol. 2, no. 3, p. 4."},{"key":"10.1016\/j.eswa.2026.133764_b0175","series-title":"in IEEE\/CVF International Conference on Computer Vision","first-page":"6836","article-title":"Vivit: A video vision transformer","author":"Arnab","year":"2021"},{"key":"10.1016\/j.eswa.2026.133764_b0180","unstructured":"N. M. Foteinopoulou and I. Patras, \u201cEmoCLIP: A Vision-Language Method for Zero-Shot Video Facial Expression Recognition,\u201d p. arXiv:2310.16640doi: 10.48550\/arXiv.2310.16640."},{"issue":"7","key":"10.1016\/j.eswa.2026.133764_b0185","doi-asserted-by":"crossref","first-page":"1235","DOI":"10.1162\/neco_a_01199","article-title":"A review of recurrent neural networks: LSTM cells and network architectures","volume":"31","author":"Yu","year":"2019","journal-title":"Neural Computation"},{"key":"10.1016\/j.eswa.2026.133764_b0190","article-title":"When does label smoothing help?","volume":"32","author":"M\u00fcller","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.133764_b0195","unstructured":"C. Guo, G. Pleiss, Y. Sun, and K. Q. Weinberger, \u201cOn calibration of modern neural networks,\u201d in Proceedings of the 34th International Conference on Machine Learning (ICML), 2017: PMLR, pp. 1321-1330."},{"issue":"2","key":"10.1016\/j.eswa.2026.133764_b0200","doi-asserted-by":"crossref","first-page":"2551","DOI":"10.1109\/TPAMI.2022.3171983","article-title":"Trusted multi-view classification with dynamic evidential fusion","volume":"45","author":"Han","year":"2022","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.eswa.2026.133764_b0205","unstructured":"H. Liu, M. Chaudhary, and H. Wang, \u201cTowards trustworthy and aligned machine learning: A data-centric survey with causality perspectives,\u201d arXiv preprint arXiv:2307.16851, 2023."},{"key":"10.1016\/j.eswa.2026.133764_b0210","doi-asserted-by":"crossref","unstructured":"C. Ju, T. Han, K. Zheng, Y. Zhang, and W. Xie, \u201cPrompting visual-language models for efficient video understanding,\u201d in Proceedings of European Conference on Computer Vision, 2022: Springer, pp. 105-124.","DOI":"10.1007\/978-3-031-19833-5_7"},{"issue":"12","key":"10.1016\/j.eswa.2026.133764_b0215","doi-asserted-by":"crossref","first-page":"13803","DOI":"10.1007\/s10489-022-03200-4","article-title":"Three-dimensional DenseNet self-attention neural network for automatic detection of student\u2019s engagement","volume":"52","author":"Mehta","year":"2022","journal-title":"Applied Intelligence"},{"issue":"1","key":"10.1016\/j.eswa.2026.133764_b0220","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1007\/s00530-023-01244-1","article-title":"Bag of states: A non-sequential approach to video-based engagement measurement","volume":"30","author":"Abedi","year":"2024","journal-title":"Multimedia Systems"},{"issue":"10","key":"10.1016\/j.eswa.2026.133764_b0225","doi-asserted-by":"crossref","first-page":"6609","DOI":"10.1007\/s10489-020-02139-8","article-title":"Deep facial spatiotemporal network for engagement prediction in online learning","volume":"51","author":"Liao","year":"2021","journal-title":"Applied Intelligence"},{"key":"10.1016\/j.eswa.2026.133764_b0230","doi-asserted-by":"crossref","unstructured":"R. Kosti, J. M. Alvarez, A. Recasens, and A. Lapedriza, \u201cEMOTIC: Emotions in Context Dataset,\u201d in 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 21-26 July 2017 2017, pp. 2309-2317, doi: 10.1109\/CVPRW.2017.285.","DOI":"10.1109\/CVPRW.2017.285"},{"key":"10.1016\/j.eswa.2026.133764_b0235","doi-asserted-by":"crossref","unstructured":"J. Lee, S. Kim, S. Kim, J. Park, and K. Sohn, \u201cContext-Aware Emotion Recognition Networks,\u201d in 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), 27 Oct.-2 Nov. 2019 2019, pp. 10142-10151, doi: 10.1109\/ICCV.2019.01024.","DOI":"10.1109\/ICCV.2019.01024"},{"key":"10.1016\/j.eswa.2026.133764_b0240","unstructured":"B. AI. \u201cBria RMBG 2.0 - image background removee.\u201d GitHub. https:\/\/github.com\/Bria-AI\/RMBG-2.0 accessed."},{"key":"10.1016\/j.eswa.2026.133764_b0245","doi-asserted-by":"crossref","unstructured":"P. Zheng et al., \u201cBilateral Reference for High-Resolution Dichotomous Image Segmentation,\u201d CAAI Artificial Intelligence Research, vol. 3, 2024, Art no. 9150038.","DOI":"10.26599\/AIR.2024.9150038"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426026722?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426026722?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T03:40:44Z","timestamp":1793331644000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426026722"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":49,"alternative-id":["S0957417426026722"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133764","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Evidential gating mixture-of-experts based on spatial and temporal transformers for uncertainty-aware engagement estimation","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133764","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"133764"}}