{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T03:59:03Z","timestamp":1777003143962,"version":"3.51.4"},"reference-count":68,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,2,18]],"date-time":"2025-02-18T00:00:00Z","timestamp":1739836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,2,18]],"date-time":"2025-02-18T00:00:00Z","timestamp":1739836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["(Grant No. 2021A1515011867)"],"award-info":[{"award-number":["(Grant No. 2021A1515011867)"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1007\/s00530-025-01677-w","type":"journal-article","created":{"date-parts":[[2025,2,18]],"date-time":"2025-02-18T15:07:42Z","timestamp":1739891262000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Region attention and label embedding for facial action unit detection"],"prefix":"10.1007","volume":"31","author":[{"given":"Wei","family":"Song","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,2,18]]},"reference":[{"key":"1677_CR1","volume-title":"Facial Action Coding System: A Technique for the Measurement of Facial Movement","author":"P Ekman","year":"1978","unstructured":"Ekman, P., Friesen, W.: Facial Action Coding System: A Technique for the Measurement of Facial Movement, vol. 12. Consulting Psychologists Press, Palo Alto (1978)"},{"key":"1677_CR2","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1007\/s00530-022-00984-w","volume":"29","author":"R Adyapady","year":"2023","unstructured":"Adyapady, R., Annappa, B.: A comprehensive review of facial expression recognition techniques. Multimed. Syst. 29, 73\u2013103 (2023)","journal-title":"Multimed. Syst."},{"issue":"9","key":"1677_CR3","doi-asserted-by":"publisher","first-page":"947","DOI":"10.1016\/0006-3223(92)90120-O","volume":"31","author":"DR Rubinow","year":"1992","unstructured":"Rubinow, D.R., Post, R.M.: Impaired recognition of affect in facial expression in depressed patients. Biol. Psychiatry 31(9), 947\u2013953 (1992)","journal-title":"Biol. Psychiatry"},{"key":"1677_CR4","doi-asserted-by":"publisher","first-page":"1449","DOI":"10.1109\/TSMCB.2004.825931","volume":"34","author":"M Pantic","year":"2004","unstructured":"Pantic, M., Rothkrantz, L.: Facial action recognition for facial expression analysis from static face images. IEEE Trans. Syst. Man Cybern. Part B Cybern. 34, 1449\u20131461 (2004)","journal-title":"IEEE Trans. Syst. Man Cybern. Part B Cybern."},{"key":"1677_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00530-023-01081-2","volume":"29","author":"C Vilchis","year":"2023","unstructured":"Vilchis, C., Perez-Guerrero, C., Mendez-Ruiz, M., Gonzalez-Mendoza, M.: A survey on the pipeline evolution of facial capture and tracking for digital humans. Multimed. Syst. 29, 1\u201324 (2023)","journal-title":"Multimed. Syst."},{"key":"1677_CR6","doi-asserted-by":"publisher","first-page":"847","DOI":"10.1007\/s11571-021-09761-3","volume":"16","author":"X Fan","year":"2022","unstructured":"Fan, X., Jiang, M., Shahid, A., Yan, H.: Hierarchical scale convolutional neural network for facial expression recognition. Cogn. Neurodyn. 16, 847\u2013858 (2022)","journal-title":"Cogn. Neurodyn."},{"key":"1677_CR7","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1016\/j.patrec.2022.09.010","volume":"162","author":"X Fan","year":"2022","unstructured":"Fan, X., Shahid, A., Yan, H.: Edge-aware motion based facial micro-expression generation with attention mechanism. Pattern Recogn. Lett. 162, 97\u2013104 (2022)","journal-title":"Pattern Recogn. Lett."},{"key":"1677_CR8","doi-asserted-by":"crossref","unstructured":"Shahid, A.: A Survey on Facial Expression Recognition: Modality, Methodologies, Challenges and Emerging Topics. Authorea Preprints (2023)","DOI":"10.36227\/techrxiv.23531241"},{"key":"1677_CR9","doi-asserted-by":"crossref","unstructured":"Eleftheriadis, S., Rudovic, O., Pantic, M.: Multi-conditional latent variable model for joint facial action unit detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3792\u20133800 (2015)","DOI":"10.1109\/ICCV.2015.432"},{"issue":"11","key":"1677_CR10","doi-asserted-by":"publisher","first-page":"1940","DOI":"10.1109\/TPAMI.2010.50","volume":"32","author":"S Koelstra","year":"2010","unstructured":"Koelstra, S., Pantic, M., Patras, I.: A dynamic texture-based approach to recognition of facial actions and their temporal models. IEEE Trans. Pattern Anal. Mach. Intell. 32(11), 1940\u20131954 (2010)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1677_CR11","doi-asserted-by":"crossref","unstructured":"Chu, W.-S., De la Torre, F., Cohn, J.F.: Selective transfer machine for personalized facial action unit detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3515\u20133522 (2013)","DOI":"10.1109\/CVPR.2013.451"},{"key":"1677_CR12","doi-asserted-by":"crossref","unstructured":"Zhao, K., Chu, W.-S., De\u00a0la Torre, F., Cohn, J. F., Zhang, H.: Joint patch and multi-label learning for facial action unit detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2207\u20132216 (2015)","DOI":"10.1109\/CVPR.2015.7298833"},{"key":"1677_CR13","doi-asserted-by":"crossref","unstructured":"Zhao, K., Chu, W.-S., Zhang, H.: Deep region and multi-label learning for facial action unit detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3391\u20133399 (2016)","DOI":"10.1109\/CVPR.2016.369"},{"key":"1677_CR14","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.patrec.2024.03.022","volume":"181","author":"Z Shao","year":"2024","unstructured":"Shao, Z., Zhou, Y., Li, F., Zhu, H., Liu, B.: Joint facial action unit recognition and self-supervised optical flow estimation. Pattern Recogn. Lett. 181, 70\u201376 (2024)","journal-title":"Pattern Recogn. Lett."},{"key":"1677_CR15","doi-asserted-by":"crossref","unstructured":"Chang, Y., Wang, S.: Knowledge-driven self-supervised representation learning for facial action unit recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20417\u201320426 (2022)","DOI":"10.1109\/CVPR52688.2022.01977"},{"key":"1677_CR16","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1007\/s44267-024-00037-y","volume":"2","author":"W Zhao","year":"2024","unstructured":"Zhao, W., Xu, L.: Weakly supervised target detection based on spatial attention. Vis. Intell. 2, 2 (2024)","journal-title":"Vis. Intell."},{"key":"1677_CR17","doi-asserted-by":"crossref","unstructured":"Fan, X., Chen, X., Jiang, M., Shahid, A., Yan, H.: SelfME: self-supervised motion learning for micro-expression recognition. In: Proceedings of the IEEE\/CVF Conference On Computer Vision And Pattern Recognition, pp. 13834\u201313843 (2023)","DOI":"10.1109\/CVPR52729.2023.01329"},{"key":"1677_CR18","doi-asserted-by":"publisher","first-page":"5284","DOI":"10.1109\/TIP.2024.3459626","volume":"33","author":"J Gao","year":"2024","unstructured":"Gao, J., Ma, X.,  Xu, C.: Learning transferable conceptual prototypes for interpretable unsupervised domain adaptation. IEEE Trans. Image. Process. 33, 5284\u20135297 (2024)","journal-title":"IEEE Trans. Image. Process."},{"issue":"11","key":"1677_CR19","doi-asserted-by":"publisher","first-page":"2583","DOI":"10.1109\/TPAMI.2018.2791608","volume":"40","author":"W Li","year":"2018","unstructured":"Li, W., Abtahi, F., Zhu, Z., Yin, L.: Eac-net: deep nets with enhancing and cropping for facial action unit detection. IEEE Trans. Pattern Anal. Mach. Intell. 40(11), 2583\u20132596 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"2","key":"1677_CR20","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1007\/s11263-020-01378-z","volume":"129","author":"Z Shao","year":"2021","unstructured":"Shao, Z., Liu, Z., Cai, J., Ma, L.: Jaa-net: joint facial action unit detection and face alignment via adaptive attention. Int. J. Comput. Vis. 129(2), 321\u2013340 (2021)","journal-title":"Int. J. Comput. Vis."},{"key":"1677_CR21","unstructured":"Jacob, G. M., Stenger, B.: Facial action unit detection with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7680\u20137689 (2021)"},{"key":"1677_CR22","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1016\/j.patrec.2023.06.004","volume":"172","author":"Z Shang","year":"2023","unstructured":"Shang, Z., Du, C., Li, B., Yan, Z., Yu, L.: MMA-Net: Multi-view mixed attention mechanism for facial action unit detection. Pattern. Recogn. Lett. 172, 165-171 (2023)","journal-title":"Pattern. Recogn. Lett."},{"key":"1677_CR23","doi-asserted-by":"crossref","unstructured":"Lakshminarayana, N., Setlur, S., Govindaraju, V.: Learning guided attention masks for facial action unit recognition. In: 2020 15th IEEE International Conference On Automatic Face And Gesture Recognition (FG 2020), pp. 465\u2013472 (2020)","DOI":"10.1109\/FG47880.2020.00128"},{"key":"1677_CR24","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/s44267-024-00054-x","volume":"2","author":"S Peng","year":"2024","unstructured":"Peng, S., Zhu, X., Yi, D., Qian, C., Lei, Z.: Formulating facial mesh tracking as a differentiable optimization problem: a backpropagation-based solution. Vis. Intell. 2, 21 (2024)","journal-title":"Vis. Intell."},{"key":"1677_CR25","doi-asserted-by":"publisher","first-page":"110451","DOI":"10.1016\/j.knosys.2023.110451","volume":"269","author":"A Shahid","year":"2023","unstructured":"Shahid, A., Yan, H.: SqueezExpNet: dual-stage convolutional neural network for accurate facial expression recognition with attention mechanism. Knowled.-Based Syst. 269, 110451 (2023)","journal-title":"Knowled.-Based Syst."},{"issue":"3","key":"1677_CR26","first-page":"1274","volume":"13","author":"Z Shao","year":"2019","unstructured":"Shao, Z., Liu, Z., Cai, J., Wu, Y., Ma, L.: Facial action unit detection using attention and relation learning. IEEE Trans. Affect. Comput. 13(3), 1274\u20131289 (2019)","journal-title":"Affect. Comput."},{"key":"1677_CR27","doi-asserted-by":"publisher","first-page":"3354","DOI":"10.1109\/TIP.2023.3277794","volume":"32","author":"Z Shao","year":"2023","unstructured":"Shao, Z., Zhou, Y., Cai, J., Zhu, H., Yao, R.: Facial action unit detection via adaptive attention and relation. IEEE Trans. Image. Process. 32, 3354-3366 (2023)","journal-title":"IEEE Trans. Image. Process."},{"key":"1677_CR28","doi-asserted-by":"crossref","unstructured":"You, R., Guo, Z., Cui, L., Long, X., Bao, Y., Wen, S.: Cross-modality attention with semantic graph embedding for multi-label classification. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034(07), pp. 12709\u201312716 (2020)","DOI":"10.1609\/aaai.v34i07.6964"},{"key":"1677_CR29","doi-asserted-by":"crossref","unstructured":"Qin, J., Wu, J., Yan, P., Li, M., Yuxi, R., Xiao, X., Wang, Y., Wang, R., Wen, S., Pan, X.: Others Freeseg: unified, universal and open-vocabulary image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision And Pattern Recognition, pp. 19446\u201319455 (2023)","DOI":"10.1109\/CVPR52729.2023.01863"},{"key":"1677_CR30","doi-asserted-by":"crossref","unstructured":"He, S., Guo, T., Dai, T., Qiao, R., Shu, X., Ren, B., Xia, S.-T.: Open-vocabulary multi-label classification via multi-modal knowledge transfer. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37(1), pp. 808\u2013816 (2023)","DOI":"10.1609\/aaai.v37i1.25159"},{"key":"1677_CR31","doi-asserted-by":"crossref","unstructured":"Xu, W., Xian, Y., Wang, J., Schiele, B., Akata Z.: VGSE: visually-grounded semantic embeddings for zero-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9316\u20139325 (2022)","DOI":"10.1109\/CVPR52688.2022.00910"},{"key":"1677_CR32","doi-asserted-by":"crossref","unstructured":"Yin, Y., Chang, D., Song, G., Sang, S., Zhi, T., Liu, J., Luo, L., Soleymani, M.: Fg-net: facial action unit detection with generalizable pyramidal features. In: Proceedings of The IEEE\/CVF Winter Conference On Applications Of Computer Vision, pp. 6099-6108 (2024)","DOI":"10.1109\/WACV57701.2024.00599"},{"key":"1677_CR33","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1007\/s00530-024-01385-x","volume":"30","author":"Z Liang","year":"2024","unstructured":"Liang, Z., Xia, H., Tan, Y., Song, S.: Hard semantic mask strategy for automatic facial action unit recognition with teacher-student model. Multimed. Syst. 30, 183 (2024)","journal-title":"Multimed. Syst."},{"key":"1677_CR34","unstructured":"Yang, H., Yin, L., Zhou, Y., Gu, J.: Exploiting semantic embedding and visual feature for facial action unit detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10\u00a0482\u201310\u00a0491 (2021)"},{"issue":"3","key":"1677_CR35","doi-asserted-by":"publisher","first-page":"1274","DOI":"10.1109\/TAFFC.2019.2948635","volume":"13","author":"Z Shao","year":"2019","unstructured":"Shao, Z., Liu, Z., Cai, J., Wu, Y., Ma, L.: Facial action unit detection using attention and relation learning. IEEE Trans. Affect. Comput. 13(3), 1274\u20131289 (2019)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"1677_CR36","doi-asserted-by":"publisher","first-page":"7955","DOI":"10.1109\/TPAMI.2021.3119334","volume":"44","author":"W Liu","year":"2021","unstructured":"Liu, W., Wang, H., Shen, X., Tsang, I.: The emerging trends of multi-label learning. IEEE Trans. Pattern Anal. Mach. Intell. 44, 7955\u20137974 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1677_CR37","doi-asserted-by":"publisher","first-page":"1425","DOI":"10.1109\/TPAMI.2015.2487986","volume":"38","author":"Z Akata","year":"2015","unstructured":"Akata, Z., Perronnin, F., Harchaoui, Z., Schmid, C.: Label-embedding for image classification. IEEE Trans. Pattern Anal. Mach. Intell. 38, 1425\u20131438 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1677_CR38","doi-asserted-by":"publisher","unstructured":"Luo, C., Song, S., Xie, W., Shen, L. & Gunes, H.: Learning multi-dimensional edge feature-based AU relation graph for facial action unit recognition. In: Proceedings Of The Thirty-First International Joint Conference On Artificial Intelligence, IJCAI-22, pp. 1239-1246 (2022), https:\/\/doi.org\/10.24963\/ijcai.2022\/173, Main Track","DOI":"10.24963\/ijcai.2022\/173"},{"key":"1677_CR39","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"1677_CR40","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference On Computer Vision And Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"1677_CR41","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J., Kweon, I.: Cbam: Convolutional block attention module. In: Proceedings of the European Conference On Computer Vision (ECCV), pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"1677_CR42","doi-asserted-by":"crossref","unstructured":"Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., Wei, Y.: Deformable convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 764\u2013773 (2017)","DOI":"10.1109\/ICCV.2017.89"},{"key":"1677_CR43","first-page":"6000","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A., Kaiser, L., Polosukhin, I.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30, 6000\u20136010 (2017)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"1677_CR44","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: Bert: Pre-Training of Deep Bidirectional Transformers for Language Understanding. ArXiv Preprint arXiv:1810.04805 (2018)"},{"issue":"10","key":"1677_CR45","doi-asserted-by":"publisher","first-page":"692","DOI":"10.1016\/j.imavis.2014.06.002","volume":"32","author":"X Zhang","year":"2014","unstructured":"Zhang, X., Yin, L., Cohn, J.F., Canavan, S., Reale, M., Horowitz, A., Liu, P., Girard, J.M.: Bp4d-spontaneous: a high-resolution spontaneous 3d dynamic facial expression database. Image and Vis. Comput. 32(10), 692\u2013706 (2014)","journal-title":"Image and Vis. Comput."},{"issue":"2","key":"1677_CR46","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1109\/T-AFFC.2013.4","volume":"4","author":"SM Mavadati","year":"2013","unstructured":"Mavadati, S.M., Mahoor, M.H., Bartlett, K., Trinh, P., Cohn, J.F.: Disfa: a spontaneous facial action intensity database. IEEE Trans. Affect. Comput. 4(2), 151\u2013160 (2013)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"1677_CR47","doi-asserted-by":"crossref","unstructured":"Ridnik, T., Ben-Baruch, E., Zamir, N., Noy, A., Friedman, I., Protter, M., Zelnik-Manor, L.: Asymmetric loss for multi-label classification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 82\u201391 (2021)","DOI":"10.1109\/ICCV48922.2021.00015"},{"key":"1677_CR48","doi-asserted-by":"crossref","unstructured":"M\u00fcller, S., Hutter, F.: Trivialaugment: tuning-free yet state-of-the-art data augmentation. In: Proceedings Of The IEEE\/CVF International Conference On Computer Vision, pp. 774\u2013782 (2021)","DOI":"10.1109\/ICCV48922.2021.00081"},{"key":"1677_CR49","first-page":"1871","volume":"9","author":"R-E Fan","year":"2008","unstructured":"Fan, R.-E., Chang, K.-W., Hsieh, C.-J., Wang, X.-R., Lin, C.-J.: Liblinear: a library for large linear classification. J. Mach. Learn. Res. 9, 1871\u20131874 (2008)","journal-title":"J. Mach. Learn. Res."},{"issue":"8","key":"1677_CR50","doi-asserted-by":"publisher","first-page":"3931","DOI":"10.1109\/TIP.2016.2570550","volume":"25","author":"K Zhao","year":"2016","unstructured":"Zhao, K., Chu, W.S., De la Torre, F., Cohn, J.F., Zhang, H.: Joint patch and multi-label learning for facial action unit and holistic expression recognition. IEEE Trans. Image Process. 25(8), 3931\u20133946 (2016)","journal-title":"IEEE Trans. Image Process."},{"key":"1677_CR51","unstructured":"Niu, X., Han, H., Yang, S., Huang, Y., Shan, S.: Local relationship learning with person-specific shape regularization for facial action unit detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 11\u00a0917\u201311\u00a0926 (2019)"},{"key":"1677_CR52","doi-asserted-by":"crossref","unstructured":"Corneanu, C., Madadi, M., Escalera, S.: Deep structure inference network for facial action unit recognition. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 298\u2013313 (2018)","DOI":"10.1007\/978-3-030-01258-8_19"},{"key":"1677_CR53","doi-asserted-by":"crossref","unstructured":"Li, G., Zhu, X., Zeng, Y., Wang, Q., Lin, L.: Semantic relationships guided representation learning for facial action unit recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8594\u20138601 (2019)","DOI":"10.1609\/aaai.v33i01.33018594"},{"key":"1677_CR54","doi-asserted-by":"crossref","unstructured":"Liu, Z., Dong, J., Zhang, C., Wang, L., Dang, J.: Relation modeling with graph convolutional networks for facial action unit detection. In: International Conference on Multimedia Modeling. Springer, Berlin, pp. 489\u2013501 (2020)","DOI":"10.1007\/978-3-030-37734-2_40"},{"key":"1677_CR55","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1016\/j.neucom.2019.03.082","volume":"355","author":"C Ma","year":"2019","unstructured":"Ma, C., Chen, L., Yong, J.: Au R-CNN: encoding expert prior knowledge into R-CNN for action unit detection. Neurocomputing 355, 35\u201347 (2019)","journal-title":"Neurocomputing"},{"key":"1677_CR56","doi-asserted-by":"crossref","unstructured":"Chen, Z.-M., Wei, X.-S., Wang, P., Guo, Y.: Multi-label image recognition with graph convolutional networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5177\u20135186 (2019)","DOI":"10.1109\/CVPR.2019.00532"},{"key":"1677_CR57","doi-asserted-by":"crossref","unstructured":"Yang, L., Ertugrul, I. O., Cohn, J. F., Hammal, Z., Jiang, D., Sahli, H.: Facs3d-net: 3d convolution based spatiotemporal representation for action unit detection. In: 2019 8th International Conference on Affective Computing and Intelligent Interaction (ACII), pp. 538\u2013544 (2019)","DOI":"10.1109\/ACII.2019.8925514"},{"key":"1677_CR58","doi-asserted-by":"crossref","unstructured":"Song, T., Chen, L., Zheng, W., Ji, Q.: Uncertain graph neural networks for facial action unit detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a01 (2021)","DOI":"10.1609\/aaai.v35i7.16748"},{"key":"1677_CR59","doi-asserted-by":"crossref","unstructured":"Song, T., Cui, Z., Zheng, W., Ji, Q.: 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, pp. 6267\u20136276 (2021)","DOI":"10.1109\/CVPR46437.2021.00620"},{"key":"1677_CR60","doi-asserted-by":"publisher","first-page":"11","DOI":"10.3389\/fcomp.2019.00011","volume":"1","author":"I Onal Ertugrul","year":"2019","unstructured":"Onal Ertugrul, I., Yang, L., Jeni, L.A., Cohn, J.F.: D-pattnet: dynamic patch-attentive deep network for action unit detection. Front. Comput. Sci. 1, 11 (2019)","journal-title":"Front. Comput. Sci."},{"key":"1677_CR61","doi-asserted-by":"crossref","unstructured":"Chen, Y., Chen, D., Wang, T., Wang, Y., Liang, Y.: Causal intervention for subject-deconfounded facial action unit recognition. In: Proceedings of the AAAI Conference On Artificial Intelligence, vol. 36, pp. 374\u2013382 (2022)","DOI":"10.1609\/aaai.v36i1.19914"},{"key":"1677_CR62","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-resnet and the impact of residual connections on learning. In: Thirty-first AAAI Conference on Artificial Intelligence (2017)","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"1677_CR63","unstructured":"Tan, M., Le, Q.: Efficientnet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105\u20136114 (2019)"},{"key":"1677_CR64","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"1677_CR65","doi-asserted-by":"crossref","unstructured":"Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., Hu, Q.: ECA-Net: efficient channel attention for deep convolutional neural networks. In: Proceedings of the IEEE\/CVF Conference On Computer Vision And Pattern Recognition, pp. 11534\u201311542 (2020)","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"1677_CR66","unstructured":"Burkert, P., Trier, F., Afzal, M., Dengel, A., Liwicki, M.: Dexpression: Deep Convolutional Neural Network for Expression Recognition. ArXiv Preprint arXiv:1509.05371 (2015)"},{"key":"1677_CR67","doi-asserted-by":"publisher","first-page":"109036","DOI":"10.1016\/j.knosys.2022.109036","volume":"250","author":"S Umirzakova","year":"2022","unstructured":"Umirzakova, S., Whangbo, T.: Detailed feature extraction network-based fine-grained face segmentation. Knowled.-Based Syst. 250, 109036 (2022)","journal-title":"Knowled.-Based Syst."},{"key":"1677_CR68","doi-asserted-by":"publisher","first-page":"102949","DOI":"10.1016\/j.jvcir.2020.102949","volume":"73","author":"A Raza Shahid","year":"2020","unstructured":"Raza Shahid, A., Khan, S., Yan, H.: Contour and region harmonic features for sub-local facial expression recognition. J. Vis. Commun. Image Represent. 73, 102949 (2020)","journal-title":"J. Vis. Commun. Image Represent."}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-01677-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-025-01677-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-01677-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,21]],"date-time":"2025-04-21T19:35:27Z","timestamp":1745264127000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-025-01677-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,18]]},"references-count":68,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["1677"],"URL":"https:\/\/doi.org\/10.1007\/s00530-025-01677-w","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,18]]},"assertion":[{"value":"7 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 January 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 February 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no Conflict of interest","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"118"}}