{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T15:08:37Z","timestamp":1776784117671,"version":"3.51.2"},"reference-count":46,"publisher":"Tech Science Press","issue":"1","license":[{"start":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T00:00:00Z","timestamp":1729382400000},"content-version":"vor","delay-in-days":293,"URL":"https:\/\/doi.org\/10.32604\/TSP-CROSSMARKPOLICY"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["CMC"],"published-print":{"date-parts":[[2024]]},"DOI":"10.32604\/cmc.2024.054982","type":"journal-article","created":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T08:36:42Z","timestamp":1726043802000},"page":"369-391","update-policy":"https:\/\/doi.org\/10.32604\/tsp-crossmarkpolicy","source":"Crossref","is-referenced-by-count":2,"title":["Re-Distributing Facial Features for Engagement Prediction with ModernTCN"],"prefix":"10.32604","volume":"81","author":[{"given":"Xi","family":"Li","sequence":"first","affiliation":[]},{"given":"Weiwei","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Qian","family":"Li","sequence":"additional","affiliation":[]},{"given":"Changhui","family":"Hou","sequence":"additional","affiliation":[]},{"given":"Yaozong","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"17807","published-online":{"date-parts":[[2024]]},"reference":[{"key":"ref1","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/978-3-030-46133-1_17","author":"Mohamad Nezami","year":"2020","journal-title":"Machine Learning and Knowledge Discovery in Databases"},{"key":"ref2","series-title":"Proc. 20th ACM Int. Conf. Multimodal Interact.","first-page":"594","article-title":"Deep recurrent multi-instance learning with spatio-temporal features for engagement intensity prediction","author":"Yang","year":"Oct. 16\u201320, 2018"},{"key":"ref3","unstructured":"P. Guhan, M. Agarwal, N. Awasthi, G. Reeves, D. Manocha and A. Bera, \u201cABC-Net: Semi-supervised multimodal GAN-based engagement detection using an affective, behavioral and cognitive model,\u201d 2020, arXiv:2011.08690."},{"key":"ref4","series-title":"2017 2nd Int. Conf. Educ., Sports, Arts Manag. Eng. (ICESAME 2017)","first-page":"1508","article-title":"Visualization analysis of learning attention based on single-image PnP head pose estimation","author":"Li","year":"Apr. 29\u201330, 2017"},{"key":"ref5","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\u2019Mello","year":"2017","journal-title":"Educ. Psychol."},{"key":"ref6","first-page":"1163","article-title":"Student engagement recognition network integrating facial appearance and multi-behavior features","volume":"12","author":"Lu","year":"2022","journal-title":"Comput. Sci. Appl."},{"key":"ref7","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":"Appl. Intell."},{"key":"ref8","series-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","first-page":"22","article-title":"CvT: Introducing convolutions to vision transformers","author":"Wu","year":"Oct. 11\u201317, 2021"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"1499","DOI":"10.1109\/LSP.2016.2603342","article-title":"Joint face detection and alignment using multitask cascaded convolutional networks","volume":"23","author":"Zhang","year":"2016","journal-title":"IEEE Signal Process. Lett."},{"key":"ref10","series-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recogn.","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"Jun. 27\u201330, 2016"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"733","DOI":"10.1007\/s41095-023-0364-2","article-title":"Visual attention network","volume":"9","author":"Guo","year":"2023","journal-title":"Comput. Vis. Media"},{"key":"ref12","series-title":"Twelfth Int. Conf. Learn. Represent.","first-page":"25","article-title":"ModernTCN: A modern pure convolution structure for general time series analysis","author":"Luo","year":"Apr. 2024"},{"key":"ref13","unstructured":"A. Gupta, A. D\u2019Cunha, K. Awasthi, and V. Balasubramanian, \u201cDAiSEE: Towards user engagement recognition in the wild,\u201d 2016, arXiv:1609.01885."},{"key":"ref14","doi-asserted-by":"crossref","first-page":"49641","DOI":"10.1007\/s11042-023-17534-9","article-title":"Automatic student engagement measurement using machine learning techniques: A literature study of data and methods","volume":"83","author":"Mandia","year":"2023","journal-title":"Multimed. Tools Appl."},{"key":"ref15","series-title":"Int. Conf. Tech. Innov. Learn., Teach. Educ.","first-page":"52","article-title":"Student engagement detection using emotion analysis, eye tracking and head movement with machine learning","author":"Sharma","year":"Jun. 25, 2022"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"731","DOI":"10.3390\/electronics12030731","article-title":"Student-engagement detection in classroom using machine learning algorithm","volume":"12","author":"Alruwais","year":"2023","journal-title":"Electronics"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"107113","DOI":"10.1016\/j.patcog.2019.107113","article-title":"Deformable face net for pose invariant face recognition","volume":"100","author":"He","year":"2020","journal-title":"Pattern Recognit."},{"key":"ref18","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 Trans. Affect. Comput."},{"key":"ref19","doi-asserted-by":"crossref","first-page":"106561","DOI":"10.1016\/j.knosys.2020.106561","article-title":"Deep face clustering using residual graph convolutional network","volume":"211","author":"Qi","year":"2021","journal-title":"Knowl. Based Syst."},{"key":"ref20","doi-asserted-by":"crossref","first-page":"15693","DOI":"10.1007\/s11042-014-2356-9","article-title":"3D face pose estimation by a robust real time tracking of facial features","volume":"75","author":"Chun","year":"2016","journal-title":"Multimed. Tools Appl."},{"key":"ref21","series-title":"Proc. 2020 Int. Conf. Multimodal Interact.","first-page":"777","article-title":"Advanced multi-instance learning method with multi-features engineering and conservative optimization for engagement intensity prediction","author":"Wu","year":"Nov. 9, 2020"},{"key":"ref22","series-title":"2018 Dig. Image Comput.: Tech. App. (DICTA)","first-page":"1","article-title":"Prediction and localization of student engagement in the wild","author":"Kaur","year":"Dec. 3\u20135, 2018"},{"key":"ref23","series-title":"2020 7th IEEE Int. Conf. Cyber Secur. Cloud Comput. (CSCloud)\/2020 6th IEEE Int. Conf. Edge Comput. Scal. Cloud (EdgeCom)","first-page":"270","article-title":"Automated student engagement monitoring and evaluation during learning in the wild","author":"Wang","year":"Jul. 6\u20138, 2020"},{"key":"ref24","series-title":"Proc. Eur. Conf. Comput. Vis. (ECCV) Workshops","article-title":"The 2nd YouTube-8M large-scale video understanding challenge","author":"Lee","year":"Sep. 8\u201314, 2018"},{"key":"ref25","series-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recogn.","first-page":"2625","article-title":"Long-term recurrent convolutional networks for visual recognition and description","author":"Donahue","year":"Jun. 7\u201312, 2015"},{"key":"ref26","series-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recogn.","first-page":"2818","article-title":"Rethinking the inception architecture for computer vision","author":"Szegedy","year":"Jun. 27\u201330, 2016"},{"key":"ref27","series-title":"Proc. IEEE Int. Conf. Comput. Vis.","first-page":"4489","article-title":"Learning spatiotemporal features with 3D convolutional networks","author":"Tran","year":"Dec. 7\u201313, 2015"},{"key":"ref28","series-title":"2019 IEEE Symp. Series Computat. Intell. (SSCI)","first-page":"442","article-title":"Learning deep spatiotemporal feature for engagement recognition of online courses","author":"Geng","year":"Dec. 6\u20139, 2019"},{"key":"ref29","series-title":"2019 IEEE 9th Int. Conf. Electron. Inf. Emerg. Commun. (ICEIEC)","first-page":"342","article-title":"An novel end-to-end network for automatic student engagement recognition","author":"Zhang","year":"Jun. 21\u201323, 2019"},{"key":"ref30","series-title":"2019 IEEE 9th Int. Conf. Electron. Inf. Emerg. Commun. (ICEIEC)","first-page":"338","article-title":"Fine-grained engagement recognition in online learning environment","author":"Huang","year":"Jan. 20\u201322, 2019"},{"key":"ref31","series-title":"2016 IEEE Winter Conf. App. Comput. Vis. (WACV)","first-page":"1","article-title":"OpenFace: An open source facial behavior analysis toolkit","author":"Baltru\u0161aitis","year":"Mar. 7\u201310, 2016"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1007\/978-3-642-24797-2_4","author":"Graves","year":"2012","journal-title":"Supervised Sequence Labelling with Recurrent Neural Networks"},{"key":"ref33","first-page":"150","article-title":"Attention detection in online education based on spatiotemporal attention mechanism","volume":"23","author":"Liang","journal-title":"Softw. Guide"},{"key":"ref34","series-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","first-page":"783","article-title":"FcaNet: Frequency channel attention networks","author":"Qin","year":"Oct. 11\u201317, 2021"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1007\/s41095-022-0271-y","article-title":"Attention mechanisms in computer vision: A survey","volume":"8","author":"Guo","year":"2022","journal-title":"Computat. Vis. Media"},{"key":"ref36","series-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recogn.","first-page":"5659","article-title":"SCA-CNN: Spatial and channel-wise attention in convolutional networks for image captioning","author":"Chen","year":"Jul. 21\u201326, 2017"},{"key":"ref37","series-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recogn.","first-page":"1874","article-title":"Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network","author":"Shi","year":"Jun. 27\u201330, 2016"},{"key":"ref38","series-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recogn.","first-page":"2168","article-title":"Facial expression recognition by de-expression residue learning","author":"Yang","year":"Jun. 18\u201322, 2018"},{"key":"ref39","unstructured":"Y. Nie, N. H. Nguyen, P. Sinthong, and J. Kalagnanam, \u201cA time series is worth 64 words: Long-term forecasting with transformers,\u201d 2022, arXiv:2211.14730."},{"key":"ref40","unstructured":"S. Bai, J. Z. Kolter, and V. Koltun, \u201cAn empirical evaluation of generic convolutional and recurrent networks for sequence modeling,\u201d 2018, arXiv:1803.01271."},{"key":"ref41","first-page":"3","volume":"30","author":"Vaswani","year":"Dec. 4\u20139, 2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref42","series-title":"Proc. Eur. Conf. Comput. Vis. (ECCV)","first-page":"305","article-title":"Rethinking spatiotemporal feature learning: Speed-accuracy trade-offs in video classification","author":"Xie","year":"Sep. 8\u201314, 2018"},{"key":"ref43","series-title":"2021 18th Conf. Robots Vis. (CRV)","first-page":"151","article-title":"Improving state-of-the-art in detecting student engagement with Resnet and TCN hybrid network","author":"Abedi","year":"May 26\u201328, 2021"},{"key":"ref44","series-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recogn.","first-page":"3202","article-title":"Video swin transformer","author":"Liu","year":"Jun. 19\u201324, 2022"},{"key":"ref45","unstructured":"D. W. Romero, A. Kuzina, E. J. Bekkers, J. M. Tomczak, and M. Hoogendoorn, \u201cCKConv: Continuous kernel convolution for sequential data,\u201d 2021, arXiv:2102.02611."},{"key":"ref46","series-title":"Proc. IEEE Int. Conf. Comput. Vis.","first-page":"618","article-title":"Grad-CAM: Visual explanations from deep networks via gradient-based localization","author":"Selvaraju","year":"Oct. 22\u201329, 2017"}],"container-title":["Computers, Materials & Continua"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.techscience.com\/files\/cmc\/2024\/TSP_CMC-81-1\/TSP_CMC_54982\/TSP_CMC_54982.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T02:36:24Z","timestamp":1741314984000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.techscience.com\/cmc\/v81n1\/58326"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":46,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024]]},"published-print":{"date-parts":[[2024]]}},"URL":"https:\/\/doi.org\/10.32604\/cmc.2024.054982","relation":{},"ISSN":["1546-2226"],"issn-type":[{"value":"1546-2226","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"2024-06-13","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-08-22","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-10-15","order":2,"name":"published","label":"Published Online","group":{"name":"publication_history","label":"Publication History"}}]}}