{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T18:29:59Z","timestamp":1775068199778,"version":"3.50.1"},"reference-count":61,"publisher":"Springer Science and Business Media LLC","issue":"17","license":[{"start":{"date-parts":[[2025,3,17]],"date-time":"2025-03-17T00:00:00Z","timestamp":1742169600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,3,17]],"date-time":"2025-03-17T00:00:00Z","timestamp":1742169600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["19DZ2252600"],"award-info":[{"award-number":["19DZ2252600"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Service Industry Development Fund","award":["06162021592"],"award-info":[{"award-number":["06162021592"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1007\/s00521-025-11139-z","type":"journal-article","created":{"date-parts":[[2025,3,17]],"date-time":"2025-03-17T11:45:23Z","timestamp":1742211923000},"page":"11399-11420","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Multi-scale feature fusion for facial expression recognition"],"prefix":"10.1007","volume":"37","author":[{"given":"Jiatao","family":"Guo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junjie","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yansong","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zesu","family":"Cai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuhua","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,3,17]]},"reference":[{"issue":"6","key":"11139_CR1","doi-asserted-by":"publisher","first-page":"1113","DOI":"10.1109\/TPAMI.2014.2366127","volume":"37","author":"E Sariyanidi","year":"2015","unstructured":"Sariyanidi E, Gunes H, Cavallaro A (2015) Automatic analysis of facial affect: a survey of registration, representation, and recognition. IEEE Trans Pattern Anal Mach Intell 37(6):1113\u20131133. https:\/\/doi.org\/10.1109\/TPAMI.2014.2366127","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"1\u20132","key":"11139_CR2","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1016\/S1071-5819(03)00051-X","volume":"59","author":"CL Lisetti","year":"2003","unstructured":"Lisetti CL, Nasoz F, LeRouge C, Ozyer O, Alvarez K (2003) Developing multimodal intelligent affective interfaces for tele-home health care. Int J Hum Comput Stud 59(1\u20132):245\u2013255. https:\/\/doi.org\/10.1016\/S1071-5819(03)00051-X","journal-title":"Int J Hum Comput Stud"},{"issue":"4","key":"11139_CR3","doi-asserted-by":"publisher","first-page":"2132","DOI":"10.1109\/TAFFC.2022.3188390","volume":"13","author":"AV Savchenko","year":"2022","unstructured":"Savchenko AV, Savchenko LV, Makarov I (2022) Classifying emotions and engagement in online learning based on a single facial expression recognition neural network. IEEE Trans Affect Comput 13(4):2132\u20132143. https:\/\/doi.org\/10.1109\/TAFFC.2022.3188390","journal-title":"IEEE Trans Affect Comput"},{"issue":"1","key":"11139_CR4","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1109\/79.911197","volume":"18","author":"R Cowie","year":"2001","unstructured":"Cowie R, Douglas-Cowie E, Tsapatsoulis N, Votsis GN, Kollias SD, Fellenz WA, Taylor JG (2001) Emotion recognition in human-computer interaction. IEEE Signal Process Mag 18(1):32\u201380. https:\/\/doi.org\/10.1109\/79.911197","journal-title":"IEEE Signal Process Mag"},{"issue":"6","key":"11139_CR5","doi-asserted-by":"publisher","first-page":"487","DOI":"10.1016\/J.SPECOM.2008.03.012","volume":"50","author":"C Clavel","year":"2008","unstructured":"Clavel C, Vasilescu I, Devillers L, Richard G, Ehrette T (2008) Fear-type emotion recognition for future audio-based surveillance systems. Speech Commun 50(6):487\u2013503. https:\/\/doi.org\/10.1016\/J.SPECOM.2008.03.012","journal-title":"Speech Commun"},{"issue":"12","key":"11139_CR6","doi-asserted-by":"publisher","first-page":"1743","DOI":"10.1016\/J.IMAVIS.2008.11.007","volume":"27","author":"A Vinciarelli","year":"2009","unstructured":"Vinciarelli A, Pantic M, Bourlard H (2009) Social signal processing: survey of an emerging domain. Image Vis Comput 27(12):1743\u20131759. https:\/\/doi.org\/10.1016\/J.IMAVIS.2008.11.007","journal-title":"Image Vis Comput"},{"key":"11139_CR7","unstructured":"Vural E, \u00c7etin M, Er\u00e7il A, Littlewort G, Bartlett M, Movellan J (2008) Automated drowsiness detection for improved driving safety"},{"issue":"6","key":"11139_CR8","doi-asserted-by":"publisher","first-page":"915","DOI":"10.1109\/TPAMI.2007.1110","volume":"29","author":"G Zhao","year":"2007","unstructured":"Zhao G, Pietik\u00e4inen M (2007) Dynamic texture recognition using local binary patterns with an application to facial expressions. IEEE Trans Pattern Anal Mach Intell 29(6):915\u2013928. https:\/\/doi.org\/10.1109\/TPAMI.2007.1110","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11139_CR9","doi-asserted-by":"publisher","unstructured":"Zhong L, Liu Q, Yang P, Liu B, Huang J, Metaxas DN (2012) Learning active facial patches for expression analysis. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA, June 16-21, pp. 2562\u20132569. https:\/\/doi.org\/10.1109\/CVPR.2012.6247974","DOI":"10.1109\/CVPR.2012.6247974"},{"issue":"1","key":"11139_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40064-015-1427-3","volume":"4","author":"P Carcagn\u00ec","year":"2015","unstructured":"Carcagn\u00ec P, Del Coco M, Leo M, Distante C (2015) Facial expression recognition and histograms of oriented gradients: a comprehensive study. SpringerPlus 4(1):1\u201325. https:\/\/doi.org\/10.1186\/s40064-015-1427-3","journal-title":"SpringerPlus"},{"issue":"11","key":"11139_CR11","doi-asserted-by":"publisher","first-page":"1021","DOI":"10.1007\/S00371-011-0611-X","volume":"27","author":"S Berretti","year":"2011","unstructured":"Berretti S, Amor BB, Daoudi M, Bimbo AD (2011) 3d facial expression recognition using SIFT descriptors of automatically detected keypoints. Vis Comput 27(11):1021\u20131036. https:\/\/doi.org\/10.1007\/S00371-011-0611-X","journal-title":"Vis Comput"},{"key":"11139_CR12","doi-asserted-by":"publisher","unstructured":"Shan C, Gong S, McOwan PW (2005) Robust facial expression recognition using local binary patterns. In: Proceedings of the 2005 International Conference on Image Processing, ICIP 2005, Genoa, Italy, September 11-14, 2005, pp. 370\u2013373 . https:\/\/doi.org\/10.1109\/ICIP.2005.1530069","DOI":"10.1109\/ICIP.2005.1530069"},{"key":"11139_CR13","doi-asserted-by":"publisher","unstructured":"Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005), 20-26 June 2005, San Diego, CA, USA, pp. 886\u2013893 . https:\/\/doi.org\/10.1109\/CVPR.2005.177","DOI":"10.1109\/CVPR.2005.177"},{"issue":"6","key":"11139_CR14","doi-asserted-by":"publisher","first-page":"803","DOI":"10.1016\/J.IMAVIS.2008.08.005","volume":"27","author":"C Shan","year":"2009","unstructured":"Shan C, Gong S, McOwan PW (2009) Facial expression recognition based on local binary patterns: a comprehensive study. Image Vis Comput 27(6):803\u2013816. https:\/\/doi.org\/10.1016\/J.IMAVIS.2008.08.005","journal-title":"Image Vis Comput"},{"issue":"2","key":"11139_CR15","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91\u2013110. https:\/\/doi.org\/10.1023\/B:VISI.0000029664.99615.94","journal-title":"Int J Comput Vis"},{"key":"11139_CR16","doi-asserted-by":"publisher","unstructured":"Wang K, Peng X, Yang J, Lu S, Qiao Y (2020) Suppressing uncertainties for large-scale facial expression recognition. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, June 13-19, 2020, pp. 6896\u20136905 . https:\/\/doi.org\/10.1109\/CVPR42600.2020.00693","DOI":"10.1109\/CVPR42600.2020.00693"},{"key":"11139_CR17","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, Meng D, Qiao Y (2020) Region attention networks for pose and occlusion robust facial expression recognition. IEEE Trans Image Process 29:4057\u20134069. https:\/\/doi.org\/10.1109\/TIP.2019.2956143","journal-title":"IEEE Trans Image Process"},{"key":"11139_CR18","doi-asserted-by":"publisher","first-page":"2016","DOI":"10.1109\/TIP.2021.3049955","volume":"30","author":"H Li","year":"2021","unstructured":"Li H, Wang N, Ding X, Yang X, Gao X (2021) Adaptively learning facial expression representation via C-F labels and distillation. IEEE Trans Image Process 30:2016\u20132028. https:\/\/doi.org\/10.1109\/TIP.2021.3049955","journal-title":"IEEE Trans Image Process"},{"key":"11139_CR19","doi-asserted-by":"publisher","unstructured":"Liu T, Li J, Wu J, Zhang L, Zhao S, Chang J, Wan J (2023) Cross-domain facial expression recognition via disentangling identity representation. In: Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJCAI 2023, 19th-25th August 2023, Macao, SAR, China, pp. 1213\u20131221 . https:\/\/doi.org\/10.24963\/IJCAI.2023\/135","DOI":"10.24963\/IJCAI.2023\/135"},{"issue":"10","key":"11139_CR20","doi-asserted-by":"publisher","first-page":"1499","DOI":"10.1109\/LSP.2016.2603342","volume":"23","author":"K Zhang","year":"2016","unstructured":"Zhang K, Zhang Z, Li Z, Qiao Y (2016) Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Process Lett 23(10):1499\u20131503. https:\/\/doi.org\/10.1109\/LSP.2016.2603342","journal-title":"IEEE Signal Process Lett"},{"key":"11139_CR21","unstructured":"Hazourli AR, Djeghri A, Salam H, Othmani A (2020) Deep multi-facial patches aggregation network for facial expression recognition. CoRR arXiv:abs\/2002.09298"},{"key":"11139_CR22","doi-asserted-by":"publisher","unstructured":"Bulat A, Tzimiropoulos G (2017) How far are we from solving the 2d & 3d face alignment problem? (and a dataset of 230, 000 3d facial landmarks). In: IEEE International Conference on Computer Vision, ICCV 2017, Venice, Italy, October 22-29, 2017, pp. 1021\u20131030 . https:\/\/doi.org\/10.1109\/ICCV.2017.116","DOI":"10.1109\/ICCV.2017.116"},{"key":"11139_CR23","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1109\/TIP.2020.3032029","volume":"30","author":"J Wan","year":"2021","unstructured":"Wan J, Lai Z, Liu J, Zhou J, Gao C (2021) Robust face alignment by multi-order high-precision hourglass network. IEEE Trans Image Process 30:121\u2013133. https:\/\/doi.org\/10.1109\/TIP.2020.3032029","journal-title":"IEEE Trans Image Process"},{"key":"11139_CR24","doi-asserted-by":"publisher","first-page":"1966","DOI":"10.1109\/TIP.2023.3261749","volume":"32","author":"J Wan","year":"2023","unstructured":"Wan J, Liu J, Zhou J, Lai Z, Shen L, Sun H, Xiong P, Min W (2023) Precise facial landmark detection by reference heatmap transformer. IEEE Trans Image Process 32:1966\u20131977. https:\/\/doi.org\/10.1109\/TIP.2023.3261749","journal-title":"IEEE Trans Image Process"},{"issue":"5","key":"11139_CR25","doi-asserted-by":"publisher","first-page":"2439","DOI":"10.1109\/TIP.2018.2886767","volume":"28","author":"Y Li","year":"2019","unstructured":"Li Y, Zeng J, Shan S, Chen X (2019) Occlusion aware facial expression recognition using CNN with attention mechanism. IEEE Trans Image Process 28(5):2439\u20132450. https:\/\/doi.org\/10.1109\/TIP.2018.2886767","journal-title":"IEEE Trans Image Process"},{"issue":"1","key":"11139_CR26","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1109\/TAFFC.2020.3031602","volume":"14","author":"Y Li","year":"2023","unstructured":"Li Y, Lu G, Li J, Zhang Z, Zhang D (2023) Facial expression recognition in the wild using multi-level features and attention mechanisms. IEEE Trans Affect Comput 14(1):451\u2013462. https:\/\/doi.org\/10.1109\/TAFFC.2020.3031602","journal-title":"IEEE Trans Affect Comput"},{"key":"11139_CR27","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 (2021) Learning deep global multi-scale and local attention features for facial expression recognition in the wild. IEEE Trans Image Process 30:6544\u20136556. https:\/\/doi.org\/10.1109\/TIP.2021.3093397","journal-title":"IEEE Trans Image Process"},{"key":"11139_CR28","doi-asserted-by":"publisher","unstructured":"Zhao Z, Liu Q, Zhou F (2021) Robust lightweight facial expression recognition network with label distribution training. In: Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, February 2-9, 2021, pp. 3510\u20133519 . https:\/\/doi.org\/10.1609\/AAAI.V35I4.16465","DOI":"10.1609\/AAAI.V35I4.16465"},{"issue":"4","key":"11139_CR29","doi-asserted-by":"publisher","first-page":"1834","DOI":"10.1109\/TCSVT.2021.3083326","volume":"32","author":"C Wang","year":"2022","unstructured":"Wang C, Xue J, Lu K, Yan Y (2022) Light attention embedding for facial expression recognition. IEEE Trans Circuits Syst Video Technol 32(4):1834\u20131847. https:\/\/doi.org\/10.1109\/TCSVT.2021.3083326","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"11139_CR30","doi-asserted-by":"publisher","unstructured":"Ma X, Ma Y (2023) Relation-aware network for facial expression recognition. In: 17th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2023, Waikoloa Beach, HI, USA, January 5-8, 2023, pp. 1\u20137. https:\/\/doi.org\/10.1109\/FG57933.2023.10042525","DOI":"10.1109\/FG57933.2023.10042525"},{"issue":"1","key":"11139_CR31","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1109\/TIP.2018.2868382","volume":"28","author":"S Li","year":"2019","unstructured":"Li S, Deng W (2019) Reliable crowdsourcing and deep locality-preserving learning for unconstrained facial expression recognition. IEEE Trans Image Process 28(1):356\u2013370. https:\/\/doi.org\/10.1109\/TIP.2018.2868382","journal-title":"IEEE Trans Image Process"},{"issue":"1","key":"11139_CR32","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/TAFFC.2017.2740923","volume":"10","author":"A Mollahosseini","year":"2019","unstructured":"Mollahosseini A, Hassani B, Mahoor MH (2019) Affectnet: a database for facial expression, valence, and arousal computing in the wild. IEEE Trans Affect Comput 10(1):18\u201331. https:\/\/doi.org\/10.1109\/TAFFC.2017.2740923","journal-title":"IEEE Trans Affect Comput"},{"key":"11139_CR33","doi-asserted-by":"publisher","unstructured":"Barsoum E, Zhang C, Canton-Ferrer C, Zhang Z (2016) Training deep networks for facial expression recognition with crowd-sourced label distribution. In: Nakano, Y.I., Andr\u00e9, E., Nishida, T., Morency, L., Busso, C., Pelachaud, C. (eds.) Proceedings of the 18th ACM International Conference on Multimodal Interaction, ICMI 2016, Tokyo, Japan, November 12-16, 2016, pp. 279\u2013283 . https:\/\/doi.org\/10.1145\/2993148.2993165","DOI":"10.1145\/2993148.2993165"},{"key":"11139_CR34","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1016\/J.NEUCOM.2020.12.076","volume":"432","author":"H Li","year":"2021","unstructured":"Li H, Wang N, Yu Y, Yang X, Gao X (2021) LBAN-IL: a novel method of high discriminative representation for facial expression recognition. Neurocomputing 432:159\u2013169. https:\/\/doi.org\/10.1016\/J.NEUCOM.2020.12.076","journal-title":"Neurocomputing"},{"key":"11139_CR35","doi-asserted-by":"publisher","unstructured":"Li H, Wang N, Yang X, Wang X, Gao X (2022) Towards semi-supervised deep facial expression recognition with an adaptive confidence margin. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18-24, 2022, pp. 4156\u20134165 . https:\/\/doi.org\/10.1109\/CVPR52688.2022.00413","DOI":"10.1109\/CVPR52688.2022.00413"},{"issue":"1","key":"11139_CR36","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1109\/TAFFC.2023.3263886","volume":"15","author":"H Li","year":"2024","unstructured":"Li H, Wang N, Yang X, Wang X, Gao X (2024) Unconstrained facial expression recognition with no-reference de-elements learning. IEEE Trans Affect Comput 15(1):173\u2013185. https:\/\/doi.org\/10.1109\/TAFFC.2023.3263886","journal-title":"IEEE Trans Affect Comput"},{"key":"11139_CR37","doi-asserted-by":"publisher","unstructured":"Savchenko AV (2021) Facial expression and attributes recognition based on multi-task learning of lightweight neural networks. In: 19th IEEE International Symposium on Intelligent Systems and Informatics, SISY 2021, Subotica, Serbia, September 16-18, 2021, pp. 119\u2013124 . https:\/\/doi.org\/10.1109\/SISY52375.2021.9582508","DOI":"10.1109\/SISY52375.2021.9582508"},{"key":"11139_CR38","doi-asserted-by":"publisher","first-page":"4637","DOI":"10.1109\/TIP.2022.3186536","volume":"31","author":"H Li","year":"2022","unstructured":"Li H, Wang N, Yang X, Gao X (2022) CRS-CONT: a well-trained general encoder for facial expression analysis. IEEE Trans Image Process 31:4637\u20134650. https:\/\/doi.org\/10.1109\/TIP.2022.3186536","journal-title":"IEEE Trans Image Process"},{"key":"11139_CR39","doi-asserted-by":"publisher","first-page":"2514","DOI":"10.1109\/TIP.2024.3378459","volume":"33","author":"W Xie","year":"2024","unstructured":"Xie W, Peng Z, Shen L, Lu W, Zhang Y, Song S (2024) Cross-layer contrastive learning of latent semantics for facial expression recognition. IEEE Trans Image Process 33:2514\u20132529. https:\/\/doi.org\/10.1109\/TIP.2024.3378459","journal-title":"IEEE Trans Image Process"},{"issue":"2","key":"11139_CR40","doi-asserted-by":"publisher","first-page":"1613","DOI":"10.1109\/TAFFC.2021.3133429","volume":"14","author":"G Chen","year":"2023","unstructured":"Chen G, Peng J, Zhang W, Huang K, Cheng F, Yuan H, Huang Y (2023) A region group adaptive attention model for subtle expression recognition. IEEE Trans Affect Comput 14(2):1613\u20131626. https:\/\/doi.org\/10.1109\/TAFFC.2021.3133429","journal-title":"IEEE Trans Affect Comput"},{"key":"11139_CR41","doi-asserted-by":"publisher","unstructured":"Zhang Y, Wang C, Ling X, Deng W (2022) Learn from all: Erasing attention consistency for noisy label facial expression recognition. In: Avidan, S., Brostow, G.J., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022 - 17th European Conference, Tel Aviv, Israel, October 23-27, Proceedings, Part XXVI. Lecture Notes in Computer Science, vol. 13686, pp. 418\u2013434. https:\/\/doi.org\/10.1007\/978-3-031-19809-0_24","DOI":"10.1007\/978-3-031-19809-0_24"},{"issue":"2","key":"11139_CR42","doi-asserted-by":"publisher","first-page":"882","DOI":"10.1109\/TCSVT.2023.3237006","volume":"34","author":"C Li","year":"2024","unstructured":"Li C, Li X, Wang X, Huang D, Liu Z, Liao L (2024) FG-AGR: fine-grained associative graph representation for facial expression recognition in the wild. IEEE Trans Circuits Syst Video Technol 34(2):882\u2013896. https:\/\/doi.org\/10.1109\/TCSVT.2023.3237006","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"issue":"2","key":"11139_CR43","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 (2023) Facial expression recognition with visual transformers and attentional selective fusion. IEEE Trans Affect Comput 14(2):1236\u20131248. https:\/\/doi.org\/10.1109\/TAFFC.2021.3122146","journal-title":"IEEE Trans Affect Comput"},{"key":"11139_CR44","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 (2023) Patch attention convolutional vision transformer for facial expression recognition with occlusion. Inf Sci 619:781\u2013794. https:\/\/doi.org\/10.1016\/J.INS.2022.11.068","journal-title":"Inf Sci"},{"issue":"10","key":"11139_CR45","doi-asserted-by":"publisher","first-page":"5962","DOI":"10.1109\/TPAMI.2021.3087709","volume":"44","author":"J Deng","year":"2022","unstructured":"Deng J, Guo J, Yang J, Xue N, Kotsia I, Zafeiriou S (2022) Arcface: additive angular margin loss for deep face recognition. IEEE Trans Pattern Anal Mach Intell 44(10):5962\u20135979. https:\/\/doi.org\/10.1109\/TPAMI.2021.3087709","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11139_CR46","doi-asserted-by":"publisher","unstructured":"Yu F, Koltun V (2016) Multi-scale context aggregation by dilated convolutions. In: Bengio, Y., LeCun, Y. (eds.) 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2-4, 2016, Conference Track Proceedings . https:\/\/doi.org\/10.48550\/arXiv.1511.07122","DOI":"10.48550\/arXiv.1511.07122"},{"key":"11139_CR47","unstructured":"Li Z, Arora S (2020) An exponential learning rate schedule for deep learning. In: 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020 . https:\/\/openreview.net\/forum?id=rJg8TeSFDH"},{"key":"11139_CR48","doi-asserted-by":"publisher","unstructured":"Xue F, Wang Q, Guo G (2021) Transfer: Learning relation-aware facial expression representations with transformers. In: 2021 IEEE\/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, October 10-17, 2021, pp. 3581\u20133590 . https:\/\/doi.org\/10.1109\/ICCV48922.2021.00358","DOI":"10.1109\/ICCV48922.2021.00358"},{"key":"11139_CR49","doi-asserted-by":"publisher","unstructured":"Farzaneh AH, Qi X (2021) Facial expression recognition in the wild via deep attentive center loss. In: IEEE Winter Conference on Applications of Computer Vision, WACV 2021, Waikoloa, HI, USA, January 3-8, 2021, pp. 2401\u20132410 . https:\/\/doi.org\/10.1109\/WACV48630.2021.00245","DOI":"10.1109\/WACV48630.2021.00245"},{"key":"11139_CR50","doi-asserted-by":"publisher","unstructured":"Le N, Nguyen K, Tran QD, Tjiputra E, Le B, Nguyen A (2023) Uncertainty-aware label distribution learning for facial expression recognition. In: IEEE\/CVF Winter Conference on Applications of Computer Vision, WACV 2023, Waikoloa, HI, USA, January 2-7, 2023, pp. 6077\u20136086 . https:\/\/doi.org\/10.1109\/WACV56688.2023.00603","DOI":"10.1109\/WACV56688.2023.00603"},{"key":"11139_CR51","doi-asserted-by":"crossref","unstructured":"Lee I, Lee E, Yoo SB (2023) 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","DOI":"10.1109\/ICCV51070.2023.00148"},{"key":"11139_CR52","doi-asserted-by":"publisher","unstructured":"Guo Y, Zhang L, Hu Y, He X, Gao J (2016) Ms-celeb-1m: A dataset and benchmark for large-scale face recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) Computer Vision - ECCV 2016 - 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part III. Lecture Notes in Computer Science, vol. 9907, pp. 87\u2013102 . https:\/\/doi.org\/10.1007\/978-3-319-46487-9_6","DOI":"10.1007\/978-3-319-46487-9_6"},{"key":"11139_CR53","doi-asserted-by":"publisher","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, June 27-30, 2016, pp. 770\u2013778 . https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"11139_CR54","unstructured":"Touvron H, Cord M, Douze M, Massa F, Sablayrolles A, J\u00e9gou H (2021) Training data-efficient image transformers & distillation through attention. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event. Proceedings of Machine Learning Research, vol. 139, pp. 10347\u201310357 . http:\/\/proceedings.mlr.press\/v139\/touvron21a.html"},{"key":"11139_CR55","doi-asserted-by":"publisher","unstructured":"Yan H, Gu Y, Zhang X, Wang Y, Ji Y, Ren F (2022) Mitigating label-noise for facial expression recognition in the wild. In: IEEE International Conference on Multimedia and Expo, ICME 2022, Taipei, Taiwan, July 18-22, 2022, pp. 1\u20136 . https:\/\/doi.org\/10.1109\/ICME52920.2022.9859818","DOI":"10.1109\/ICME52920.2022.9859818"},{"key":"11139_CR56","doi-asserted-by":"publisher","unstructured":"Zeng D, Lin Z, Yan X, Liu Y, Wang F, Tang B (2022) Face2exp: Combating data biases for facial expression recognition. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18-24, 2022, pp. 20259\u201320268 . https:\/\/doi.org\/10.1109\/CVPR52688.2022.01965","DOI":"10.1109\/CVPR52688.2022.01965"},{"key":"11139_CR57","first-page":"78","volume":"45","author":"P Ekman","year":"1978","unstructured":"Ekman P, Friesen WV (1978) Facial action coding system. Environ Psychol Nonverbal Behav 45:78","journal-title":"Environ Psychol Nonverbal Behav"},{"key":"11139_CR58","first-page":"12","volume":"9","author":"L Van der Maaten","year":"2008","unstructured":"Van der Maaten L, Hinton G (2008) Visualizing data using t-sne. J Mach Learn Res 9:12","journal-title":"J Mach Learn Res"},{"issue":"2","key":"11139_CR59","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1007\/S11263-019-01228-7","volume":"128","author":"RR Selvaraju","year":"2020","unstructured":"Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D (2020) Grad-cam: visual explanations from deep networks via gradient-based localization. Int J Comput Vis 128(2):336\u2013359. https:\/\/doi.org\/10.1007\/S11263-019-01228-7","journal-title":"Int J Comput Vis"},{"key":"11139_CR60","doi-asserted-by":"publisher","DOI":"10.1016\/J.MEDIA.2022.102447","volume":"79","author":"K Wang","year":"2022","unstructured":"Wang K, Zhan B, Zu C, Wu X, Zhou J, Zhou L, Wang Y (2022) Semi-supervised medical image segmentation via a tripled-uncertainty guided mean teacher model with contrastive learning. Med Image Anal 79:102447. https:\/\/doi.org\/10.1016\/J.MEDIA.2022.102447","journal-title":"Med Image Anal"},{"key":"11139_CR61","doi-asserted-by":"publisher","unstructured":"Zhuang P, Wang Y, Qiao Y (2020) Learning attentive pairwise interaction for fine-grained classification. In: The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI 2020, The Thirty-Second Innovative Applications of Artificial Intelligence Conference, IAAI 2020, The Tenth AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2020, New York, NY, USA, February 7-12, 2020, pp. 13130\u201313137 . https:\/\/doi.org\/10.1609\/AAAI.V34I07.7016","DOI":"10.1609\/AAAI.V34I07.7016"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-025-11139-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-025-11139-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-025-11139-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,31]],"date-time":"2025-05-31T09:15:54Z","timestamp":1748682954000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-025-11139-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,17]]},"references-count":61,"journal-issue":{"issue":"17","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["11139"],"URL":"https:\/\/doi.org\/10.1007\/s00521-025-11139-z","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,17]]},"assertion":[{"value":"30 December 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 February 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 March 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 declared that they have no conflict of interest to this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This article has never been submitted to more than one journal for simultaneous consideration. This article is original.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"The authors have approved this article before submission, including the names and order of authors.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"The authors agreed with the content and gave explicit consent to submit.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}]}}