{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T11:15:17Z","timestamp":1788434117198,"version":"build-2803163510"},"reference-count":73,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T00:00:00Z","timestamp":1784851200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T00:00:00Z","timestamp":1784851200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62203290"],"award-info":[{"award-number":["62203290"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1007\/s00371-026-04637-1","type":"journal-article","created":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T13:03:45Z","timestamp":1784898225000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Easr: expression aware supervision and refinement for in-the-wild facial expression recognition"],"prefix":"10.1007","volume":"42","author":[{"given":"Xuantao","family":"Nie","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zixiang","family":"Fei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yukun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenju","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minrui","family":"Fei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xia","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,24]]},"reference":[{"issue":"3","key":"4637_CR1","doi-asserted-by":"publisher","first-page":"1195","DOI":"10.1109\/TAFFC.2020.2981446","volume":"13","author":"S Li","year":"2020","unstructured":"Li, S., Deng, W.: Deep facial expression recognition: A survey. IEEE Trans. Affect. Comput. 13(3), 1195\u20131215 (2020). https:\/\/doi.org\/10.1109\/TAFFC.2020.2981446","journal-title":"IEEE Trans. Affect. Comput."},{"issue":"9","key":"4637_CR2","doi-asserted-by":"publisher","first-page":"4204","DOI":"10.3390\/s23094204","volume":"23","author":"J Liao","year":"2023","unstructured":"Liao, J., Lin, Y., Ma, T., et al.: Facial expression recognition methods in the wild based on fusion feature of attention mechanism and lbp. Sensors 23(9), 4204 (2023). https:\/\/doi.org\/10.3390\/s23094204","journal-title":"Sensors"},{"key":"4637_CR3","doi-asserted-by":"publisher","unstructured":"Li, S., Deng, W., Du, J.: Reliable crowdsourcing and deep locality-preserving learning for expression recognition in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2852\u20132861 (2017). https:\/\/doi.org\/10.1109\/cvpr.2017.277","DOI":"10.1109\/cvpr.2017.277"},{"issue":"1","key":"4637_CR4","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/taffc.2017.2740923","volume":"10","author":"A Mollahosseini","year":"2017","unstructured":"Mollahosseini, A., Hasani, B., Mahoor, M.H.: Affectnet: a database for facial expression, valence, and arousal computing in the wild. IEEE Trans. Affect. Comput. 10(1), 18\u201331 (2017). https:\/\/doi.org\/10.1109\/taffc.2017.2740923","journal-title":"IEEE Trans. Affect. Comput."},{"key":"4637_CR5","doi-asserted-by":"publisher","unstructured":"Gera, D., Balasubramanian, S.: Noisy annotations robust consensual collaborative affect expression recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3585\u20133592 (2021). https:\/\/doi.org\/10.1109\/iccvw54120.2021.00399","DOI":"10.1109\/iccvw54120.2021.00399"},{"key":"4637_CR6","doi-asserted-by":"publisher","unstructured":"Chen, S., Wang, Z., Geng, X.: Label distribution learning on auxiliary label space graphs for facial expression recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10120\u201310129 (2020). https:\/\/doi.org\/10.1109\/cvpr42600.2020.01400","DOI":"10.1109\/cvpr42600.2020.01400"},{"key":"4637_CR7","doi-asserted-by":"publisher","unstructured":"She, J., Hu, Y., Shi, H., et\u00a0al.: Dive into ambiguity: Latent distribution mining and pairwise uncertainty estimation for facial expression recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6248\u20136257 (2021). https:\/\/doi.org\/10.1109\/cvpr46437.2021.00618","DOI":"10.1109\/cvpr46437.2021.00618"},{"key":"4637_CR8","doi-asserted-by":"publisher","unstructured":"Barsoum, E., Zhang, C., Ferrer, C.C., et\u00a0al.: Training deep networks for facial expression recognition with crowd-sourced label distribution. In: Proceedings of the 18th ACM International Conference on Multimodal Interaction, pp. 279\u2013283 (2016). https:\/\/doi.org\/10.1145\/2993148.2993165","DOI":"10.1145\/2993148.2993165"},{"key":"4637_CR9","doi-asserted-by":"publisher","unstructured":"Goodfellow, I.J., Erhan, D., Carrier, P.L., et\u00a0al.: Challenges in representation learning: a report on three machine learning contests. In: International Conference on Neural Information Processing, pp 117\u2013124. Springer (2013). https:\/\/doi.org\/10.1016\/j.neunet.2014.09.005","DOI":"10.1016\/j.neunet.2014.09.005"},{"key":"4637_CR10","doi-asserted-by":"publisher","unstructured":"Le, N., Nguyen, K., Tran, Q., et\u00a0al.: Uncertainty-aware label distribution learning for facial expression recognition. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 6088\u20136097 (2023). https:\/\/doi.org\/10.1109\/wacv56688.2023.00603","DOI":"10.1109\/wacv56688.2023.00603"},{"key":"4637_CR11","doi-asserted-by":"publisher","unstructured":"Wang, K., Peng, X., Yang, J., et\u00a0al.: Suppressing uncertainties for large-scale facial expression recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6897\u20136906 (2020). https:\/\/doi.org\/10.1109\/cvpr42600.2020.00693","DOI":"10.1109\/cvpr42600.2020.00693"},{"key":"4637_CR12","doi-asserted-by":"publisher","unstructured":"Zeng, J., Shan, S., Chen, X.: Facial expression recognition with inconsistently annotated datasets. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 222\u2013237 (2018). https:\/\/doi.org\/10.1007\/978-3-030-01261-8_14","DOI":"10.1007\/978-3-030-01261-8_14"},{"key":"4637_CR13","doi-asserted-by":"publisher","unstructured":"Lee, J., Choi, Y., Kim, H, et\u00a0al.: Navigating label ambiguity for facial expression recognition in the wild. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 4517\u20134525 (2025). https:\/\/doi.org\/10.1609\/aaai.v39i4.32476","DOI":"10.1609\/aaai.v39i4.32476"},{"key":"4637_CR14","doi-asserted-by":"publisher","unstructured":"Gera, D., Vikas, G. N., Balasubramanian, S.: Handling ambiguous annotations for facial expression recognition in the wild. In: Proceedings of the Twelfth Indian Conference on Computer Vision, Graphics and Image Processing, pp. 1\u20139 (2021). https:\/\/doi.org\/10.1145\/3490035.3490289","DOI":"10.1145\/3490035.3490289"},{"key":"4637_CR15","doi-asserted-by":"publisher","DOI":"10.5555\/3327757.3327944","author":"B Han","year":"2018","unstructured":"Han, B., Yao, Q., Yu, X., et al.: Co-teaching: Robust training of deep neural networks with extremely noisy labels. Adv. Neural. Inf. Process. Syst. (2018). https:\/\/doi.org\/10.5555\/3327757.3327944","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4637_CR16","doi-asserted-by":"publisher","unstructured":"Jiang, L., Zhou, Z., Leung, T.: Mentornet: Learning data-driven curriculum for very deep neural networks on corrupted labels. In: International Conference on Machine Learning, PMLR, pp. 2304\u20132313. (2018). https:\/\/doi.org\/10.48550\/pmlr.v80.jiang18c","DOI":"10.48550\/pmlr.v80.jiang18c"},{"key":"4637_CR17","unstructured":"Zhang, Y., Wang, C., Deng, W.: Relative uncertainty learning for facial expression recognition. Adva. Neural Inf. Process. Syst. 34:17616\u201317627 (2021). https:\/\/doi.org\/10.48550\/arXiv.2109.10455"},{"key":"4637_CR18","doi-asserted-by":"publisher","unstructured":"Wu, Z., Cui, J.: La-net: Landmark-aware learning for reliable facial expression recognition under label noise. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 20698\u201320707 (2023). https:\/\/doi.org\/10.1109\/iccv51070.2023.01892","DOI":"10.1109\/iccv51070.2023.01892"},{"key":"4637_CR19","doi-asserted-by":"publisher","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., et\u00a0al.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.308","DOI":"10.1109\/CVPR.2016.308"},{"key":"4637_CR20","doi-asserted-by":"publisher","unstructured":"Kuiry, S., Das, A., Nasipuri, M., et\u00a0al.: Regularizing cnns using confusion penalty based label smoothing for histopathology images. In: International Conference on Computational Intelligence in Communications and Business Analytics, pp. 257\u2013269. Springer (2024). https:\/\/doi.org\/10.1007\/978-3-031-81339-9_22","DOI":"10.1007\/978-3-031-81339-9_22"},{"issue":"4","key":"4637_CR21","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.13517","volume":"41","author":"X Zhang","year":"2024","unstructured":"Zhang, X., Fu, X., Qi, G., et al.: A multi-scale feature fusion convolutional neural network for facial expression recognition. Expert. Syst. 41(4), e13517 (2024). https:\/\/doi.org\/10.1111\/exsy.13517","journal-title":"Expert. Syst."},{"key":"4637_CR22","doi-asserted-by":"publisher","unstructured":"Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: European Conference on Computer Vision, pp. 818\u2013833., Springer (2014). https:\/\/doi.org\/10.1007\/978-3-319-10590-1_53","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"4637_CR23","doi-asserted-by":"publisher","first-page":"6544","DOI":"10.1109\/tip.2021.3093397","volume":"30","author":"Z Zhao","year":"2021","unstructured":"Zhao, Z., Liu, Q., Wang, S.: Learning deep global multi-scale and local attention features for facial expression recognition in the wild. IEEE Trans. Image Process. 30, 6544\u20136556 (2021). https:\/\/doi.org\/10.1109\/tip.2021.3093397","journal-title":"IEEE Trans. Image Process."},{"key":"4637_CR24","doi-asserted-by":"publisher","unstructured":"Ezati, A., Dezyani, M., Rana, R., et\u00a0al.: A lightweight attention-based deep network via multi-scale feature fusion for multi-view facial expression recognition. arXiv preprint arXiv:2403.14318 (2024). https:\/\/doi.org\/10.48550\/arXiv.2403.14318","DOI":"10.48550\/arXiv.2403.14318"},{"key":"4637_CR25","doi-asserted-by":"publisher","first-page":"1250706","DOI":"10.3389\/fnbot.2023.1250706","volume":"17","author":"Y Chen","year":"2023","unstructured":"Chen, Y., Liu, S., Zhao, D., et al.: Occlusion facial expression recognition based on feature fusion residual attention network. Front. Neurorobot. 17, 1250706 (2023). https:\/\/doi.org\/10.3389\/fnbot.2023.1250706","journal-title":"Front. Neurorobot."},{"key":"4637_CR26","doi-asserted-by":"publisher","unstructured":"Guo J, Peng J, Huang Y, et\u00a0al.: Multi-scale feature fusion for facial expression recognition. In: Neural Computing and Applications, pp. 1\u201322 (2025). https:\/\/doi.org\/10.1007\/s00521-025-11139-z","DOI":"10.1007\/s00521-025-11139-z"},{"key":"4637_CR27","doi-asserted-by":"publisher","unstructured":"Jarrett, K., Kavukcuoglu, K., Ranzato, M., et\u00a0al.: What is the best multi-stage architecture for object recognition? In: 2009 IEEE 12th International Conference on Computer Vision, pp. 2146\u20132153. IEEE (2009). https:\/\/doi.org\/10.1109\/iccv.2009.5459469","DOI":"10.1109\/iccv.2009.5459469"},{"key":"4637_CR28","doi-asserted-by":"publisher","unstructured":"Wang, B., Zhang, L., Dai, Y., et\u00a0al.: Progressive feature polishing network for salient object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 12128\u201312135 (2020). https:\/\/doi.org\/10.1609\/aaai.v34i07.6892","DOI":"10.1609\/aaai.v34i07.6892"},{"key":"4637_CR29","doi-asserted-by":"publisher","unstructured":"Xue, F., Tan, Z., Zhu, Y., et\u00a0al.: Coarse-to-fine cascaded networks with smooth predicting for video facial expression recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2412\u20132418 (2022). https:\/\/doi.org\/10.1109\/cvprw56347.2022.00269","DOI":"10.1109\/cvprw56347.2022.00269"},{"key":"4637_CR30","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1016\/j.neunet.2023.11.033","volume":"170","author":"H Tao","year":"2024","unstructured":"Tao, H., Duan, Q.: Hierarchical attention network with progressive feature fusion for facial expression recognition. Neural Netw. 170, 337\u2013348 (2024). https:\/\/doi.org\/10.1016\/j.neunet.2023.11.033","journal-title":"Neural Netw."},{"issue":"5","key":"4637_CR31","doi-asserted-by":"publisher","first-page":"2439","DOI":"10.1109\/tip.2018.2886767","volume":"28","author":"Y Li","year":"2018","unstructured":"Li, Y., Zeng, J., Shan, S., et al.: Occlusion aware facial expression recognition using cnn with attention mechanism. IEEE Trans. Image Process. 28(5), 2439\u20132450 (2018). https:\/\/doi.org\/10.1109\/tip.2018.2886767","journal-title":"IEEE Trans. Image Process."},{"key":"4637_CR32","doi-asserted-by":"publisher","first-page":"4057","DOI":"10.1109\/tip.2019.2956143","volume":"29","author":"K Wang","year":"2020","unstructured":"Wang, K., Peng, X., Yang, J., et al.: Region attention networks for pose and occlusion robust facial expression recognition. IEEE Trans. Image Process. 29, 4057\u20134069 (2020). https:\/\/doi.org\/10.1109\/tip.2019.2956143","journal-title":"IEEE Trans. Image Process."},{"issue":"2","key":"4637_CR33","doi-asserted-by":"publisher","first-page":"199","DOI":"10.3390\/biomimetics8020199","volume":"8","author":"Z Wen","year":"2023","unstructured":"Wen, Z., Lin, W., Wang, T., et al.: Distract your attention: multi-head cross attention network for facial expression recognition. Biomimetics 8(2), 199 (2023). https:\/\/doi.org\/10.3390\/biomimetics8020199","journal-title":"Biomimetics"},{"key":"4637_CR34","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.2266","volume":"10","author":"W Wang","year":"2024","unstructured":"Wang, W., Jia, M.: A facial expression recognition network based on attention double branch enhanced fusion. PeerJ Comput. Sci. 10, e2266 (2024). https:\/\/doi.org\/10.7717\/peerj-cs.2266","journal-title":"PeerJ Comput. Sci."},{"key":"4637_CR35","doi-asserted-by":"publisher","unstructured":"Zheng, C., Mendieta, M., Chen, C.: Poster: A pyramid cross-fusion transformer network for facial expression recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops (2023). https:\/\/doi.org\/10.1109\/ICCVW60793.2023.00339","DOI":"10.1109\/ICCVW60793.2023.00339"},{"key":"4637_CR36","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1109\/cvpr.2018.00745","DOI":"10.1109\/cvpr.2018.00745"},{"key":"4637_CR37","doi-asserted-by":"publisher","unstructured":"Woo, S., Park, J., Lee, J.Y., et\u00a0al.: Cbam: convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3\u201319 (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_1","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"4637_CR38","doi-asserted-by":"publisher","unstructured":"Dai, J., Qi, H., Xiong, Y., et\u00a0al.: Deformable convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 764\u2013773 (2017). https:\/\/doi.org\/10.1109\/iccv.2017.89","DOI":"10.1109\/iccv.2017.89"},{"key":"4637_CR39","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.129323","volume":"622","author":"Z Fei","year":"2025","unstructured":"Fei, Z., Zhang, B., Zhou, W., et al.: Global multi-scale extraction and local mixed multi-head attention for facial expression recognition in the wild. Neurocomputing 622, 129323 (2025). https:\/\/doi.org\/10.1016\/j.neucom.2024.129323","journal-title":"Neurocomputing"},{"issue":"15","key":"4637_CR40","doi-asserted-by":"publisher","first-page":"6471","DOI":"10.3390\/app14156471","volume":"14","author":"Y Tian","year":"2024","unstructured":"Tian, Y., Zhu, J., Yao, H., et al.: Facial expression recognition based on vision transformer with hybrid local attention. Appl. Sci. 14(15), 6471 (2024). https:\/\/doi.org\/10.3390\/app14156471","journal-title":"Appl. Sci."},{"key":"4637_CR41","doi-asserted-by":"publisher","unstructured":"Huang, Q., Chen, J.: xlstm-fer: Enhancing student expression recognition with extended vision long short-term memory network. In: Asia-Pacific Web (APWeb) and Web-Age Information Management (WAIM) Joint International Conference on Web and Big Data, pp. 249\u2013259. Springer (2024) https:\/\/doi.org\/10.1007\/978-981-96-0055-7_21","DOI":"10.1007\/978-981-96-0055-7_21"},{"key":"4637_CR42","doi-asserted-by":"publisher","unstructured":"Deng, J., Guo, J., Ververas, E., et\u00a0al.: Retinaface: Single-shot multi-level face localisation in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5203\u20135212 (2020). https:\/\/doi.org\/10.1109\/cvpr42600.2020.00525","DOI":"10.1109\/cvpr42600.2020.00525"},{"key":"4637_CR43","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1016\/j.neucom.2020.06.014","volume":"411","author":"J Li","year":"2020","unstructured":"Li, J., Jin, K., Zhou, D., et al.: Attention mechanism-based cnn for facial expression recognition. Neurocomputing 411, 340\u2013350 (2020). https:\/\/doi.org\/10.1016\/j.neucom.2020.06.014","journal-title":"Neurocomputing"},{"key":"4637_CR44","doi-asserted-by":"publisher","unstructured":"Zhang, Y., Wang, C., Ling, X., et\u00a0al.: Learn from all: Erasing attention consistency for noisy label facial expression recognition. In: European Conference on Computer Vision, pp. 418\u2013434. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-19809-0_24","DOI":"10.1007\/978-3-031-19809-0_24"},{"key":"4637_CR45","doi-asserted-by":"publisher","unstructured":"Farzaneh, A.H., Qi, X.: Facial expression recognition in the wild via deep attentive center loss. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2402\u20132411 (2021). https:\/\/doi.org\/10.1109\/wacv48630.2021.00245","DOI":"10.1109\/wacv48630.2021.00245"},{"key":"4637_CR46","doi-asserted-by":"publisher","unstructured":"Liu, S., Xu. Y., Wan, T., et\u00a0al.: A dual-branch adaptive distribution fusion framework for real-world facial expression recognition. In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135. IEEE (2023). https:\/\/doi.org\/10.1109\/icassp49357.2023.10097033","DOI":"10.1109\/icassp49357.2023.10097033"},{"key":"4637_CR47","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., et\u00a0al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/cvpr.2016.90","DOI":"10.1109\/cvpr.2016.90"},{"key":"4637_CR48","doi-asserted-by":"publisher","unstructured":"Guo, Y., Zhang, L., Hu, Y., et\u00a0al.: Ms-celeb-1m: a dataset and benchmark for large-scale face recognition. In: European Conference on Computer Vision, pp. 87\u2013102. Springer (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_6","DOI":"10.1007\/978-3-319-46487-9_6"},{"key":"4637_CR49","doi-asserted-by":"publisher","unstructured":"Loshchilov, I., Hutter, F.: Decoupled Weight Decay Regularization. arXiv preprint arXiv:1711.05101, (2017). https:\/\/doi.org\/10.48550\/arXiv.1711.05101","DOI":"10.48550\/arXiv.1711.05101"},{"key":"4637_CR50","unstructured":"Paszke, A., Gross, S., Massa, F., et al.: Pytorch: An imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, vol. 32 (2019). https:\/\/doi.org\/10.48550\/arXiv.1912.01703"},{"issue":"9","key":"4637_CR51","doi-asserted-by":"publisher","first-page":"6253","DOI":"10.1109\/tcsvt.2022.3165321","volume":"32","author":"H Liu","year":"2022","unstructured":"Liu, H., Cai, H., Lin, Q., et al.: Adaptive multilayer perceptual attention network for facial expression recognition. IEEE Trans. Circuits Syst. Video Technol. 32(9), 6253\u20136266 (2022). https:\/\/doi.org\/10.1109\/tcsvt.2022.3165321","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"3","key":"4637_CR52","doi-asserted-by":"publisher","first-page":"2035","DOI":"10.1007\/s00371-023-02900-3","volume":"40","author":"H Xia","year":"2024","unstructured":"Xia, H., Lu, L., Song, S.: Feature fusion of multi-granularity and multi-scale for facial expression recognition. Vis. Comput. 40(3), 2035\u20132047 (2024). https:\/\/doi.org\/10.1007\/s00371-023-02900-3","journal-title":"Vis. Comput."},{"key":"4637_CR53","doi-asserted-by":"publisher","first-page":"781","DOI":"10.1016\/j.ins.2022.11.068","volume":"619","author":"C Liu","year":"2023","unstructured":"Liu, C., Hirota, K., Dai, Y.: Patch attention convolutional vision transformer for facial expression recognition with occlusion. Inf. Sci. 619, 781\u2013794 (2023). https:\/\/doi.org\/10.1016\/j.ins.2022.11.068","journal-title":"Inf. Sci."},{"key":"4637_CR54","doi-asserted-by":"publisher","unstructured":"Lee, I., Lee, E., Yoo, S.B.: Latent-ofer: Detect, mask, and reconstruct with latent vectors for occluded facial expression recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1536\u20131546 (2023). https:\/\/doi.org\/10.1109\/iccv51070.2023.00148","DOI":"10.1109\/iccv51070.2023.00148"},{"key":"4637_CR55","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.120962","volume":"677","author":"D Li","year":"2024","unstructured":"Li, D., Xiong, W., Luo, T., et al.: 3waus: A novel three-way adaptive uncertainty-suppressing model for facial expression recognition. Inf. Sci. 677, 120962 (2024). https:\/\/doi.org\/10.1016\/j.ins.2024.120962","journal-title":"Inf. Sci."},{"key":"4637_CR56","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2024.104062","volume":"98","author":"Y Tan","year":"2024","unstructured":"Tan, Y., Xia, H., Song, S.: Learning informative and discriminative semantic features for robust facial expression recognition. J. Vis. Commun. Image Represent. 98, 104062 (2024). https:\/\/doi.org\/10.1016\/j.jvcir.2024.104062","journal-title":"J. Vis. Commun. Image Represent."},{"issue":"12","key":"4637_CR57","doi-asserted-by":"publisher","first-page":"10175","DOI":"10.1007\/s00521-022-07016-8","volume":"34","author":"W Gong","year":"2022","unstructured":"Gong, W., Fan, Y., Qian, Y.: Effective attention feature reconstruction loss for facial expression recognition in the wild. Neural Comput. Appl. 34(12), 10175\u201310187 (2022). https:\/\/doi.org\/10.1007\/s00521-022-07016-8","journal-title":"Neural Comput. Appl."},{"issue":"6","key":"4637_CR58","doi-asserted-by":"publisher","first-page":"2277","DOI":"10.1007\/s00371-022-02413-5","volume":"39","author":"X Liang","year":"2023","unstructured":"Liang, X., Xu, L., Zhang, W., et al.: A convolution-transformer dual branch network for head-pose and occlusion facial expression recognition. Vis. Comput. 39(6), 2277\u20132290 (2023). https:\/\/doi.org\/10.1007\/s00371-022-02413-5","journal-title":"Vis. Comput."},{"issue":"2","key":"4637_CR59","doi-asserted-by":"publisher","first-page":"1236","DOI":"10.1109\/taffc.2021.3122146","volume":"14","author":"F Ma","year":"2021","unstructured":"Ma, F., Sun, B., Li, S.: Facial expression recognition with visual transformers and attentional selective fusion. IEEE Trans. Affect. Comput. 14(2), 1236\u20131248 (2021). https:\/\/doi.org\/10.1109\/taffc.2021.3122146","journal-title":"IEEE Trans. Affect. Comput."},{"issue":"15","key":"4637_CR60","doi-asserted-by":"publisher","first-page":"6799","DOI":"10.3390\/s23156799","volume":"23","author":"H Yao","year":"2023","unstructured":"Yao, H., Yang, X., Chen, D., et al.: Facial expression recognition based on fine-tuned channel-spatial attention transformer. Sensors 23(15), 6799 (2023). https:\/\/doi.org\/10.3390\/s23156799","journal-title":"Sensors"},{"key":"4637_CR61","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2023.108583","volume":"107","author":"N Sun","year":"2023","unstructured":"Sun, N., Song, Y., Liu, J., et al.: Appearance and geometry transformer for facial expression recognition in the wild. Comput. Electr. Eng. 107, 108583 (2023). https:\/\/doi.org\/10.1016\/j.compeleceng.2023.108583","journal-title":"Comput. Electr. Eng."},{"issue":"2","key":"4637_CR62","doi-asserted-by":"publisher","first-page":"1236","DOI":"10.1109\/TAFFC.2021.3122146","volume":"14","author":"F Ma","year":"2023","unstructured":"Ma, F., Sun, B., Li, S.: Facial expression recognition with visual transformers and attentional selective fusion. IEEE Trans. Affect. Comput. 14(2), 1236\u20131248 (2023). https:\/\/doi.org\/10.1109\/TAFFC.2021.3122146","journal-title":"IEEE Trans. Affect. Comput."},{"key":"4637_CR63","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3598917","author":"AM Pazandeh","year":"2025","unstructured":"Pazandeh, A.M., Fatemizadeh, E.: Enhancing vision transformers for facial expression recognition. IEEE Access (2025). https:\/\/doi.org\/10.1109\/ACCESS.2025.3598917","journal-title":"IEEE Access"},{"issue":"1","key":"4637_CR64","doi-asserted-by":"publisher","first-page":"15","DOI":"10.2352\/J.ImagingSci.Technol.2025.69.1.010410","volume":"69","author":"J Wang","year":"2025","unstructured":"Wang, J., Hu, Y., Huang, A.: Efficient facial expression recognition transformer with additively comprised class attention encoder. J. Imaging Sci. Technol. 69(1), 15 (2025). https:\/\/doi.org\/10.2352\/J.ImagingSci.Technol.2025.69.1.010410","journal-title":"J. Imaging Sci. Technol."},{"issue":"12","key":"4637_CR65","doi-asserted-by":"publisher","first-page":"1626","DOI":"10.3390\/brainsci12121626","volume":"12","author":"Y Fan","year":"2022","unstructured":"Fan, Y., Wang, H., Zhu, X., et al.: FER-PCVT: facial expression recognition with patch-convolutional vision transformer for stroke patients. Brain Sci. 12(12), 1626 (2022). https:\/\/doi.org\/10.3390\/brainsci12121626","journal-title":"Brain Sci."},{"issue":"12","key":"4637_CR66","doi-asserted-by":"publisher","first-page":"11823","DOI":"10.1109\/TII.2023.3253188","volume":"19","author":"M Sun","year":"2023","unstructured":"Sun, M., Cui, W., Zhang, Y., et al.: Attention-rectified and texture-enhanced cross-attention transformer feature fusion network for facial expression recognition. IEEE Trans. Ind. Inf. 19(12), 11823\u201311832 (2023). https:\/\/doi.org\/10.1109\/TII.2023.3253188","journal-title":"IEEE Trans. Ind. Inf."},{"key":"4637_CR67","doi-asserted-by":"publisher","unstructured":"Li, H., Xu, Y., Yao, J., et\u00a0al.: Knowledge-Enhanced Facial Expression Recognition with Emotional-to-Neutral Transformation. arXiv preprint arXiv:2409.08598, (2024). https:\/\/doi.org\/10.1109\/TMM.2025.3604916","DOI":"10.1109\/TMM.2025.3604916"},{"key":"4637_CR68","doi-asserted-by":"publisher","unstructured":"Yang, M.: Landmark-guided visual-language models for facial emotion recognition in university students. In: 2025 IEEE 3rd International Conference on Computer, Vision and Intelligent Technology (ICCVIT), pp. 1\u20135. IEEE (2025). https:\/\/doi.org\/10.1109\/ICCVIT67848.2025.11391408","DOI":"10.1109\/ICCVIT67848.2025.11391408"},{"key":"4637_CR69","doi-asserted-by":"publisher","first-page":"370","DOI":"10.1016\/j.ins.2023.02.056","volume":"630","author":"Z Zhang","year":"2023","unstructured":"Zhang, Z., Tian, X., Zhang, Y., et al.: Enhanced discriminative global-local feature learning with priority for facial expression recognition. Inf. Sci. 630, 370\u2013384 (2023). https:\/\/doi.org\/10.1016\/j.ins.2023.02.056","journal-title":"Inf. Sci."},{"issue":"2","key":"4637_CR70","doi-asserted-by":"publisher","first-page":"1236","DOI":"10.1109\/TAFFC.2021.3122146","volume":"14","author":"F Ma","year":"2023","unstructured":"Ma, F., Sun, B., Li, S.: Facial expression recognition with visual transformers and attentional selective fusion. IEEE Trans. Affect. Comput. 14(2), 1236\u20131248 (2023). https:\/\/doi.org\/10.1109\/TAFFC.2021.3122146","journal-title":"IEEE Trans. Affect. Comput."},{"key":"4637_CR71","doi-asserted-by":"crossref","unstructured":"Li, D., Wang, Y., Funakoshi, K.: Joyful: Joint modality fusion and graph contrastive learning for multimodal emotion recognition. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 16051\u201316069. Association for Computational Linguistics, Singapore (2023). https:\/\/doi.org\/10.18653\/v1\/2023.emnlp-main.996","DOI":"10.18653\/v1\/2023.emnlp-main.996"},{"key":"4637_CR72","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103809","author":"J Xiang","year":"2025","unstructured":"Xiang, J., Zhu, X., Cambria, E.: Integrating audio-visual text generation with contrastive learning for enhanced multimodal emotion analysis. Inf. Fusion (2025). https:\/\/doi.org\/10.1016\/j.inffus.2025.103809","journal-title":"Inf. Fusion"},{"key":"4637_CR73","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108580","volume":"244","author":"AI Middya","year":"2022","unstructured":"Middya, A.I., Nag, B., Roy, S.: Deep learning based multimodal emotion recognition using model-level fusion of audio-visual modalities. Knowl. Based Syst. 244, 108580 (2022). https:\/\/doi.org\/10.1016\/j.knosys.2022.108580","journal-title":"Knowl. Based Syst."}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-026-04637-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-026-04637-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-026-04637-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T10:24:13Z","timestamp":1788431053000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-026-04637-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,24]]},"references-count":73,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2026,8]]}},"alternative-id":["4637"],"URL":"https:\/\/doi.org\/10.1007\/s00371-026-04637-1","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,24]]},"assertion":[{"value":"13 February 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no conflict of interest.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"431"}}