{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T08:31:26Z","timestamp":1772181086588,"version":"3.50.1"},"reference-count":63,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100004607","name":"Guangxi Natural Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004607","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62366006"],"award-info":[{"award-number":["62366006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62366005"],"award-info":[{"award-number":["62366005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62106054"],"award-info":[{"award-number":["62106054"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Visual Communication and Image Representation"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1016\/j.jvcir.2026.104728","type":"journal-article","created":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T14:03:49Z","timestamp":1769004229000},"page":"104728","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Global\u2013local co-regularization network for facial action unit detection"],"prefix":"10.1016","volume":"116","author":[{"given":"Yumei","family":"Tan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haiying","family":"Xia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0280-2640","authenticated-orcid":false,"given":"Shuxiang","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"issue":"2","key":"10.1016\/j.jvcir.2026.104728_b1","first-page":"5","article-title":"Facial action coding system: a technique for the measurement of facial movement","volume":"3","author":"Friesen","year":"1978","journal-title":"Palo Alto"},{"key":"10.1016\/j.jvcir.2026.104728_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2020.106172","article-title":"Deep reinforcement learning for robust emotional classification in facial expression recognition","volume":"204","author":"Li","year":"2020","journal-title":"Knowl.-Based Syst."},{"issue":"1","key":"10.1016\/j.jvcir.2026.104728_b3","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1007\/s00530-022-00984-w","article-title":"A comprehensive review of facial expression recognition techniques","volume":"29","author":"Adyapady","year":"2023","journal-title":"Multimedia Syst."},{"key":"10.1016\/j.jvcir.2026.104728_b4","article-title":"Learning informative and discriminative semantic features for robust facial expression recognition","volume":"98","year":"2024","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.jvcir.2026.104728_b5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.jvcir.2017.05.002","article-title":"A joint dictionary learning and regression model for intensity estimation of facial AUs","volume":"47","year":"2017","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.jvcir.2026.104728_b6","article-title":"A recent survey on perceived group sentiment analysis","volume":"97","year":"2023","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.jvcir.2026.104728_b7","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1016\/j.patrec.2023.06.004","article-title":"MMA-net: Multi-view mixed attention mechanism for facial action unit detection","volume":"172","author":"Shang","year":"2023","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.jvcir.2026.104728_b8","article-title":"Detecting facial action units from global-local fine-grained expressions","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"8","key":"10.1016\/j.jvcir.2026.104728_b9","doi-asserted-by":"crossref","first-page":"3931","DOI":"10.1109\/TIP.2016.2570550","article-title":"Joint patch and multi-label learning for facial action unit and holistic expression recognition","volume":"25","author":"Zhao","year":"2016","journal-title":"IEEE Trans. Image Process."},{"issue":"2","key":"10.1016\/j.jvcir.2026.104728_b10","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1007\/s11263-020-01378-z","article-title":"JAA-Net: Joint facial action unit detection and face alignment via adaptive attention","volume":"129","author":"Shao","year":"2021","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.jvcir.2026.104728_b11","doi-asserted-by":"crossref","unstructured":"X. Niu, H. Han, S. Yang, Y. Huang, S. Shan, Local relationship learning with person-specific shape regularization for facial action unit detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 11917\u201311926.","DOI":"10.1109\/CVPR.2019.01219"},{"key":"10.1016\/j.jvcir.2026.104728_b12","doi-asserted-by":"crossref","DOI":"10.1109\/TAFFC.2024.3367015","article-title":"Facial action unit detection and intensity estimation from self-supervised representation","author":"Ma","year":"2024","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.jvcir.2026.104728_b13","doi-asserted-by":"crossref","unstructured":"Z. Shao, Z. Liu, J. Cai, L. Ma, Deep adaptive attention for joint facial action unit detection and face alignment, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 705\u2013720.","DOI":"10.1007\/978-3-030-01261-8_43"},{"key":"10.1016\/j.jvcir.2026.104728_b14","doi-asserted-by":"crossref","unstructured":"Y. Yin, D. Chang, G. Song, S. Sang, T. Zhi, J. Liu, L. Luo, M. Soleymani, FG-Net: Facial Action Unit Detection with Generalizable Pyramidal Features, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2024, pp. 6099\u20136108.","DOI":"10.1109\/WACV57701.2024.00599"},{"key":"10.1016\/j.jvcir.2026.104728_b15","article-title":"PAttNet: Patch-attentive deep network for action unit detection","volume":"vol. 114","author":"Ertugrul","year":"2019"},{"key":"10.1016\/j.jvcir.2026.104728_b16","first-page":"1","article-title":"Learning facial expression-aware global-to-local representation for robust action unit detection","author":"An","year":"2024","journal-title":"Appl. Intell."},{"key":"10.1016\/j.jvcir.2026.104728_b17","article-title":"Multi-label co-regularization for semi-supervised facial action unit recognition","volume":"32","author":"Niu","year":"2019"},{"key":"10.1016\/j.jvcir.2026.104728_b18","doi-asserted-by":"crossref","unstructured":"T. Song, Z. Cui, W. Zheng, Q. Ji, Hybrid message passing with performance-driven structures for facial action unit detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 6267\u20136276.","DOI":"10.1109\/CVPR46437.2021.00620"},{"key":"10.1016\/j.jvcir.2026.104728_b19","first-page":"5993","article-title":"Uncertain graph neural networks for facial action unit detection","volume":"vol. 35","author":"Song","year":"2021"},{"key":"10.1016\/j.jvcir.2026.104728_b20","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.jvcir.2026.104728_b21","series-title":"International Conference on Learning Representations","article-title":"CrossFormer: A versatile vision transformer hinging on cross-scale attention","author":"Wang","year":"2022"},{"key":"10.1016\/j.jvcir.2026.104728_b22","doi-asserted-by":"crossref","unstructured":"Y. Zhang, T. Xiang, T.M. Hospedales, H. Lu, Deep mutual learning, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 4320\u20134328.","DOI":"10.1109\/CVPR.2018.00454"},{"key":"10.1016\/j.jvcir.2026.104728_b23","series-title":"European Conference on Computer Vision","first-page":"151","article-title":"Feature disentangling machine-a novel approach of feature selection and disentangling in facial expression analysis","author":"Liu","year":"2014"},{"key":"10.1016\/j.jvcir.2026.104728_b24","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"3391","article-title":"Deep region and multi-label learning for facial action unit detection","author":"Zhao","year":"2016"},{"key":"10.1016\/j.jvcir.2026.104728_b25","series-title":"2016 IEEE Winter Conference on Applications of Computer Vision","first-page":"1","article-title":"Deep learning the dynamic appearance and shape of facial action units","author":"Jaiswal","year":"2016"},{"key":"10.1016\/j.jvcir.2026.104728_b26","series-title":"2017 12th IEEE International Conference on Automatic Face & Gesture Recognition","first-page":"103","article-title":"Eac-net: A region-based deep enhancing and cropping approach for facial action unit detection","author":"Li","year":"2017"},{"key":"10.1016\/j.jvcir.2026.104728_b27","article-title":"Facial action unit detection using attention and relation learning","author":"Shao","year":"2019"},{"key":"10.1016\/j.jvcir.2026.104728_b28","unstructured":"G.M. Jacob, B. Stenger, Facial action unit detection with transformers, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 7680\u20137689."},{"key":"10.1016\/j.jvcir.2026.104728_b29","doi-asserted-by":"crossref","unstructured":"H. Yang, L. Yin, Y. Zhou, J. Gu, Exploiting semantic embedding and visual feature for facial action unit detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 10482\u201310491.","DOI":"10.1109\/CVPR46437.2021.01034"},{"key":"10.1016\/j.jvcir.2026.104728_b30","first-page":"14338","article-title":"Knowledge augmented deep neural networks for joint facial expression and action unit recognition","volume":"33","author":"Cui","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jvcir.2026.104728_b31","series-title":"2021 16th IEEE International Conference on Automatic Face and Gesture Recognition","first-page":"01","article-title":"Emotion-aware contrastive learning for facial action unit detection","author":"Sun","year":"2021"},{"issue":"9","key":"10.1016\/j.jvcir.2026.104728_b32","doi-asserted-by":"crossref","first-page":"2900","DOI":"10.1109\/TCSVT.2020.2984241","article-title":"Learned 3D shape representations using fused geometrically augmented images: Application to facial expression and action unit detection","volume":"30","author":"Taha","year":"2020","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.jvcir.2026.104728_b33","article-title":"Semantic learning for facial action unit detection","author":"Wang","year":"2022","journal-title":"IEEE Trans. Comput. Soc. Syst."},{"key":"10.1016\/j.jvcir.2026.104728_b34","article-title":"Meta auxiliary learning for facial action unit detection","author":"Li","year":"2021","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.jvcir.2026.104728_b35","series-title":"2019 IEEE International Conference on Image Processing","first-page":"56","article-title":"Multi-task learning of emotion recognition and facial action unit detection with adaptively weights sharing network","author":"Wang","year":"2019"},{"key":"10.1016\/j.jvcir.2026.104728_b36","doi-asserted-by":"crossref","unstructured":"K. Zhao, W.-S. Chu, A.M. Martinez, Learning facial action units from web images with scalable weakly supervised clustering, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 2090\u20132099.","DOI":"10.1109\/CVPR.2018.00223"},{"key":"10.1016\/j.jvcir.2026.104728_b37","doi-asserted-by":"crossref","unstructured":"Y. Chang, S. Wang, Knowledge-Driven Self-Supervised Representation Learning for Facial Action Unit Recognition, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 20417\u201320426.","DOI":"10.1109\/CVPR52688.2022.01977"},{"key":"10.1016\/j.jvcir.2026.104728_b38","doi-asserted-by":"crossref","unstructured":"G. Peng, S. Wang, Weakly supervised facial action unit recognition through adversarial training, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 2188\u20132196.","DOI":"10.1109\/CVPR.2018.00233"},{"key":"10.1016\/j.jvcir.2026.104728_b39","first-page":"8827","article-title":"Dual semi-supervised learning for facial action unit recognition","volume":"vol. 33","author":"Peng","year":"2019"},{"key":"10.1016\/j.jvcir.2026.104728_b40","series-title":"International Conference on Multimedia Modeling","first-page":"489","article-title":"Relation modeling with graph convolutional networks for facial action unit detection","author":"Liu","year":"2020"},{"key":"10.1016\/j.jvcir.2026.104728_b41","series-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016"},{"key":"10.1016\/j.jvcir.2026.104728_b42","series-title":"Temporal Reasoning Graph for Activity Recognition","first-page":"5491","volume":"vol. 29","author":"Zhang","year":"2020"},{"key":"10.1016\/j.jvcir.2026.104728_b43","first-page":"8594","article-title":"Semantic relationships guided representation learning for facial action unit recognition","volume":"vol. 33","author":"Li","year":"2019"},{"key":"10.1016\/j.jvcir.2026.104728_b44","series-title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","first-page":"1239","article-title":"Learning multi-dimensional edge feature-based AU relation graph for facial action unit recognition","author":"Luo","year":"2022"},{"key":"10.1016\/j.jvcir.2026.104728_b45","volume":"vol. 2","author":"Hinton","year":"2015"},{"key":"10.1016\/j.jvcir.2026.104728_b46","doi-asserted-by":"crossref","unstructured":"S. Qiao, W. Shen, Z. Zhang, B. Wang, A. Yuille, Deep co-training for semi-supervised image recognition, in: Proceedings of the European Conference on Computer Vision, Eccv, 2018, pp. 135\u2013152.","DOI":"10.1007\/978-3-030-01267-0_9"},{"key":"10.1016\/j.jvcir.2026.104728_b47","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2020.106124","article-title":"Self-adaptive feature learning based on a priori knowledge for facial expression recognition","volume":"204","author":"Sun","year":"2020","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.jvcir.2026.104728_b48","article-title":"Deep modality assistance co-training network for semi-supervised multi-label semantic decoding","author":"Li","year":"2021","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.jvcir.2026.104728_b49","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.jvcir.2026.104728_b50","first-page":"1858","article-title":"A new metric for probability distributions","volume":"49","author":"Endres","year":"2003"},{"key":"10.1016\/j.jvcir.2026.104728_b51","article-title":"Region attentive action unit intensity estimation with uncertainty weighted multi-task learning","author":"Chen","year":"2021","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.jvcir.2026.104728_b52","article-title":"Spatial transformer networks","volume":"28","author":"Jaderberg","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jvcir.2026.104728_b53","series-title":"International Conference on Machine Learning","first-page":"7354","article-title":"Self-attention generative adversarial networks","author":"Zhang","year":"2019"},{"key":"10.1016\/j.jvcir.2026.104728_b54","series-title":"International Conference on Learning Representations","article-title":"On the relationship between self-attention and convolutional layers","author":"Cordonnier","year":"2020"},{"key":"10.1016\/j.jvcir.2026.104728_b55","article-title":"Doing the best we can with what we have: Multi-label balancing with selective learning for attribute prediction","volume":"vol. 32","author":"Hand","year":"2018"},{"key":"10.1016\/j.jvcir.2026.104728_b56","series-title":"2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition","first-page":"1","article-title":"A high-resolution spontaneous 3d dynamic facial expression database","author":"Zhang","year":"2013"},{"issue":"2","key":"10.1016\/j.jvcir.2026.104728_b57","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1109\/T-AFFC.2013.4","article-title":"Disfa: A spontaneous facial action intensity database","volume":"4","author":"Mavadati","year":"2013","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.jvcir.2026.104728_b58","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2021.108355","article-title":"Geoconv: Geodesic guided convolution for facial action unit recognition","volume":"122","author":"Chen","year":"2022","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.jvcir.2026.104728_b59","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2023.126361","article-title":"Drop-relationship learning for semi-supervised facial action unit recognition","volume":"550","author":"Hu","year":"2023","journal-title":"Neurocomputing"},{"key":"10.1016\/j.jvcir.2026.104728_b60","doi-asserted-by":"crossref","first-page":"3354","DOI":"10.1109\/TIP.2023.3277794","article-title":"Facial action unit detection via adaptive attention and relation","volume":"32","author":"Shao","year":"2023","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.jvcir.2026.104728_b61","doi-asserted-by":"crossref","first-page":"268","DOI":"10.1016\/j.patrec.2022.11.010","article-title":"Heterogeneous spatio-temporal relation learning network for facial action unit detection","volume":"164","author":"Song","year":"2022","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.jvcir.2026.104728_b62","doi-asserted-by":"crossref","unstructured":"X. Li, X. Zhang, T. Wang, L. Yin, Knowledge-Spreader: Learning Semi-Supervised Facial Action Dynamics by Consistifying Knowledge Granularity, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 20979\u201320989.","DOI":"10.1109\/ICCV51070.2023.01918"},{"key":"10.1016\/j.jvcir.2026.104728_b63","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008"}],"container-title":["Journal of Visual Communication and Image Representation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320326000234?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320326000234?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T07:42:29Z","timestamp":1772178149000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1047320326000234"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":63,"alternative-id":["S1047320326000234"],"URL":"https:\/\/doi.org\/10.1016\/j.jvcir.2026.104728","relation":{},"ISSN":["1047-3203"],"issn-type":[{"value":"1047-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Global\u2013local co-regularization network for facial action unit detection","name":"articletitle","label":"Article Title"},{"value":"Journal of Visual Communication and Image Representation","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jvcir.2026.104728","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104728"}}