{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T18:09:58Z","timestamp":1790878198756,"version":"4.1.0"},"reference-count":50,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>\n                    Facial expression recognition is an important task in real-time human-computer interaction, but its practical application is still limited by partial facial occlusion, high computational cost, and the lack of fine-grained emotion representation. To address these issues, this paper proposes OQ-FERNet, an occlusion-aware quantitative facial expression recognition network. The proposed network adopts MobileNetV4-Conv-S as a lightweight facial expression feature extraction backbone to obtain compact and discriminative representations with low computational cost. On this basis, an Occlusion-aware Regional Reweighting module is designed to divide the feature map into upper-face, middle-face, and lower-face regions, and adaptively adjust their contributions according to regional reliability. This design suppresses occluded or less informative facial areas while enhancing visible expression-related cues. Furthermore, a Quantitative Emotion Prediction Head is introduced to jointly perform discrete expression classification and emotion intensity estimation, enabling the model to provide both categorical and fine-grained affective outputs. Experiments are conducted on RAF-DB and AffectNet-7. The results show that OQ-FERNet achieves competitive classification performance, improved robustness under different occlusion conditions, and effective quantitative emotion prediction. Specifically, OQ-FERNet obtains 93.12% accuracy on RAF-DB and 68.32% accuracy on AffectNet-7, while achieving an MAE of 0.246, an MSE of 0.101, and an RMSE of 0.318 for quantitative emotion prediction on AffectNet-7. In addition, the model contains only 4.18M parameters and 0.26G FLOPs, with an inference speed of 356 FPS. These results indicate that OQ-FERNet provides an effective and efficient solution for lightweight, occlusion-robust, and fine-grained facial expression recognition in real-time human-computer interaction scenarios. The source code is publicly available at:\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/jiahao001-j\/OQ-FERNet\" xlink:type=\"simple\">https:\/\/github.com\/jiahao001-j\/OQ-FERNet<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1371\/journal.pone.0359554","type":"journal-article","created":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T17:45:49Z","timestamp":1790876749000},"page":"e0359554","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["OQ-FERNet: An occlusion-aware quantitative facial expression recognition network for real-time human-computer interaction"],"prefix":"10.1371","volume":"21","author":[{"given":"Lianfei","family":"Gao","sequence":"first","affiliation":[{"name":"Shandong Huitong Financial Leasing Co., Ltd.","place":["Jinan, Shandong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junfeng","family":"Tan","sequence":"additional","affiliation":[{"name":"Shandong Huitong Financial Leasing Co., Ltd.","place":["Jinan, Shandong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6405-2980","authenticated-orcid":true,"given":"Jiahao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shandong Huitong Financial Leasing Co., Ltd.","place":["Jinan, Shandong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,10,1]]},"reference":[{"key":"pone.0359554.ref001","doi-asserted-by":"crossref","unstructured":"Gaya-Morey FX, Buades-Rubio JM, Palanque P, Lacuesta R, Manresa-Yee C. Deep learning-based facial expression recognition for the elderly: A systematic review. 2025.","DOI":"10.1016\/j.eswa.2026.132709"},{"key":"pone.0359554.ref002","doi-asserted-by":"crossref","first-page":"110951","DOI":"10.1016\/j.patcog.2024.110951","article-title":"POSTER++: A simpler and stronger facial expression recognition network","volume":"157","author":"J Mao","year":"2025","journal-title":"Pattern Recognition"},{"key":"pone.0359554.ref003","doi-asserted-by":"crossref","unstructured":"Cui F-Q, Tong A, Huang J, Zhang J, Guo D, Liu Z, et al. Learning from heterogeneity: Generalizing dynamic facial expression recognition via distributionally robust optimization. In: Proceedings of the 33rd ACM International conference on multimedia. 2025. 5587\u201396. https:\/\/doi.org\/10.1145\/3746027.3755036","DOI":"10.1145\/3746027.3755036"},{"issue":"1","key":"pone.0359554.ref004","first-page":"120","article-title":"Emotion recognition from facial expressions using CNNs","volume":"8","author":"A Akula","year":"2026","journal-title":"Int J Eng Ext Technol Res"},{"issue":"1","key":"pone.0359554.ref005","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1109\/TAFFC.2025.3611173","article-title":"STRFLNet: Spatio-temporal representation fusion learning network for EEG-based emotion recognition","volume":"17","author":"F Hu","year":"2026","journal-title":"IEEE Trans Affective Comput"},{"key":"pone.0359554.ref006","doi-asserted-by":"crossref","unstructured":"Zhang M, Zhu T, Gong H, Yang W, Wei F, Yao L. SFML-Net: spatial feature-guided motion learning network for micro-expression recognition. J King Saud Univ Comp Inform Sci. 2026.","DOI":"10.1007\/s44443-026-00498-9"},{"issue":"2","key":"pone.0359554.ref007","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3737456","article-title":"Facial expression analysis and its potentials in IoT systems: A contemporary survey","volume":"58","author":"Z Shangguan","year":"2025","journal-title":"ACM Comput Surv"},{"issue":"3","key":"pone.0359554.ref008","article-title":"A fusion framework for micro-expression recognition using hierarchical transformer network with DEAC","volume":"18","author":"S Bhukya","year":"2025","journal-title":"Inter J Intelligent Eng Systems"},{"key":"pone.0359554.ref009","doi-asserted-by":"crossref","unstructured":"Jiang H, Lyu J, Lan X, Xue J. Continuous action unit intensity modeling for micro-expression recognition. In: 2025 IEEE International Conference on Image Processing (ICIP), 2025. 941\u20136. https:\/\/doi.org\/10.1109\/icip55913.2025.11084479","DOI":"10.1109\/ICIP55913.2025.11084479"},{"issue":"6","key":"pone.0359554.ref010","doi-asserted-by":"crossref","first-page":"981","DOI":"10.1080\/01969722.2024.2343988","article-title":"An optimal modified bidirectional generative adversarial network for security authentication in cloud environment","volume":"57","author":"N Subramanian","year":"2024","journal-title":"Cybernetics and Systems"},{"issue":"40","key":"pone.0359554.ref011","doi-asserted-by":"crossref","first-page":"48651","DOI":"10.1007\/s11042-025-21059-8","article-title":"Enhancing facial expression recognition using coordinate attention mechanism and MobileNetV3","volume":"84","author":"MS Bendelhoum","year":"2025","journal-title":"Multimed Tools Appl"},{"key":"pone.0359554.ref012","unstructured":"Arman SE, Abdullah HM, Sakib SN, Saiem R, Asha SN, Hasan MM, et al. SugarcaneShuffleNet: A Very Fast, Lightweight Convolutional Neural Network for Diagnosis of 15 Sugarcane Leaf Diseases. 2025. https:\/\/doi.org\/arXiv:250817107"},{"key":"pone.0359554.ref013","doi-asserted-by":"crossref","unstructured":"Sharma S, Avasthi S, Malik I. Lightweight facial expressions analysis with MobileNet. In: 2025 3rd International Conference on Advancement in Computation Computer Technologies (InCACCT), 2025. 444\u20139. https:\/\/doi.org\/10.1109\/incacct65424.2025.11011401","DOI":"10.1109\/InCACCT65424.2025.11011401"},{"issue":"1","key":"pone.0359554.ref014","doi-asserted-by":"crossref","DOI":"10.1007\/s00138-024-01641-0","article-title":"Twinned attention network for occlusion-aware facial expression recognition","volume":"36","author":"G Devasena","year":"2024","journal-title":"Machine Vision Appl"},{"issue":"3","key":"pone.0359554.ref015","doi-asserted-by":"crossref","first-page":"1277","DOI":"10.1109\/TAFFC.2025.3544677","article-title":"Progressive masking oriented self-taught learning for occluded facial expression recognition","volume":"16","author":"B Kang","year":"2025","journal-title":"IEEE Trans Affective Comput"},{"issue":"9","key":"pone.0359554.ref016","doi-asserted-by":"crossref","first-page":"5139","DOI":"10.3390\/app15095139","article-title":"Occlusion-robust facial expression recognition based on multi-angle feature extraction","volume":"15","author":"Y Li","year":"2025","journal-title":"Appl Sci"},{"key":"pone.0359554.ref017","doi-asserted-by":"crossref","first-page":"105365","DOI":"10.1016\/j.imavis.2024.105365","article-title":"Information gap based knowledge distillation for occluded facial expression recognition","volume":"154","author":"Y Zhang","year":"2025","journal-title":"Image Vision Comp"},{"issue":"9","key":"pone.0359554.ref018","doi-asserted-by":"crossref","DOI":"10.1007\/s11760-025-04278-2","article-title":"Attention-augmented squeeze-and-excitation enhanced mobile network for occluded facial expression recognition in resource-constrained environments","volume":"19","author":"A Agarwal","year":"2025","journal-title":"SIViP"},{"issue":"1","key":"pone.0359554.ref019","doi-asserted-by":"crossref","DOI":"10.1002\/jdn.10391","article-title":"Improving facial expression recognition for autism with IDenseNet-RCAformer under occlusions","volume":"85","author":"S Selvi","year":"2025","journal-title":"Int J Dev Neurosci"},{"key":"pone.0359554.ref020","doi-asserted-by":"crossref","first-page":"129323","DOI":"10.1016\/j.neucom.2024.129323","article-title":"Global multi-scale extraction and local mixed multi-head attention for facial expression recognition in the wild","volume":"622","author":"Z Fei","year":"2025","journal-title":"Neurocomputing"},{"issue":"3","key":"pone.0359554.ref021","doi-asserted-by":"crossref","first-page":"2352","DOI":"10.1109\/TAFFC.2025.3561139","article-title":"Continual facial features transfer for facial expression recognition","volume":"16","author":"RS Maharjan","year":"2025","journal-title":"IEEE Trans Affective Comput"},{"key":"pone.0359554.ref022","doi-asserted-by":"crossref","unstructured":"Jia J, Zhang H, Liang J. Bridging discrete and continuous: a multimodal strategy for complex emotion detection. In: 2025 IEEE 35th International workshop on machine learning for signal processing (MLSP), 2025. 1\u20136. https:\/\/doi.org\/10.1109\/mlsp62443.2025.11204253","DOI":"10.1109\/MLSP62443.2025.11204253"},{"issue":"21","key":"pone.0359554.ref023","doi-asserted-by":"crossref","first-page":"24059","DOI":"10.1007\/s11042-024-19924-z","article-title":"Gaussian-filtered Local Difference Pattern with kernel representation for person-independent facial expression recognition robust to noise and resolution","volume":"84","author":"M Najmabadi","year":"2024","journal-title":"Multimed Tools Appl"},{"issue":"1","key":"pone.0359554.ref024","doi-asserted-by":"crossref","DOI":"10.1007\/s44196-024-00729-9","article-title":"Real-time facial expression recognition based on image processing in virtual reality","volume":"18","author":"Q Gong","year":"2025","journal-title":"Int J Comput Intell Syst"},{"key":"pone.0359554.ref025","doi-asserted-by":"crossref","first-page":"708","DOI":"10.1201\/9781003530190-100","article-title":"Facial emotion detection and recognition in images using convolutional neural networks","volume-title":"Intelligent computing and communication techniques","author":"A Dagur","year":"2025"},{"key":"pone.0359554.ref026","doi-asserted-by":"crossref","unstructured":"Babu AR, Mohebbanaaz, Chandrika S, Rajeswari G, Pavani UV. Face emotion recognition using Deep Neural Network (DNN). In: 2025 IEEE 14th International Conference on Communication Systems and Network Technologies (CSNT). 2025. 547\u201351. https:\/\/doi.org\/10.1109\/csnt64827.2025.10967857","DOI":"10.1109\/CSNT64827.2025.10967857"},{"issue":"10","key":"pone.0359554.ref027","doi-asserted-by":"crossref","first-page":"7363","DOI":"10.1007\/s00521-025-10974-4","article-title":"Enhancing facial expression recognition in uncontrolled environment: a lightweight CNN approach with pre-processing","volume":"37","author":"R Grover","year":"2025","journal-title":"Neural Comput & Applic"},{"issue":"23","key":"pone.0359554.ref028","doi-asserted-by":"crossref","first-page":"7264","DOI":"10.3390\/s25237264","article-title":"Lightweight convolutional neural network with efficient channel attention mechanism for real-time facial emotion recognition in embedded systems","volume":"25","author":"JA Ramirez-Quintana","year":"2025","journal-title":"Sensors (Basel)"},{"issue":"1","key":"pone.0359554.ref029","doi-asserted-by":"crossref","first-page":"19","DOI":"10.62762\/TACS.2024.974479","article-title":"Prediction of coronavirus inhibitors in drug discovery through deep learning","volume":"1","author":"T Khan","year":"2025","journal-title":"ICCK Trans Adv Comput Syst"},{"issue":"8","key":"pone.0359554.ref030","doi-asserted-by":"crossref","first-page":"473","DOI":"10.3390\/a18080473","article-title":"A novel lightweight facial expression recognition network based on deep shallow network fusion and attention mechanism","volume":"18","author":"Q Yang","year":"2025","journal-title":"Algorithms"},{"issue":"4","key":"pone.0359554.ref031","doi-asserted-by":"crossref","first-page":"2721","DOI":"10.1109\/TAFFC.2025.3566773","article-title":"Lightweight spatio-temporal convolutional neural network for audio-visual emotion recognition","volume":"16","author":"SY Ding","year":"2025","journal-title":"IEEE Trans Affective Comput"},{"key":"pone.0359554.ref032","doi-asserted-by":"crossref","first-page":"129656","DOI":"10.1016\/j.neucom.2025.129656","article-title":"Lightweight expression recognition combined attention fusion network with hybrid knowledge distillation for occluded e-learner facial images","volume":"628","author":"Y Chen","year":"2025","journal-title":"Neurocomputing"},{"issue":"3","key":"pone.0359554.ref033","doi-asserted-by":"crossref","first-page":"54","DOI":"10.23919\/JCC.ja.2023-0123","article-title":"Real-time facial expression recognition on Res-MobileNetV3","volume":"22","author":"L Beibei","year":"2025","journal-title":"China Commun"},{"key":"pone.0359554.ref034","doi-asserted-by":"crossref","first-page":"111315","DOI":"10.1016\/j.engappai.2025.111315","article-title":"Lightweight binary convolutional-transformers fusion network for facial expression recognition","volume":"158","author":"X Jin","year":"2025","journal-title":"Eng Appl Artificial Intellig"},{"issue":"12","key":"pone.0359554.ref035","doi-asserted-by":"crossref","first-page":"10027","DOI":"10.1007\/s11042-024-19012-2","article-title":"An integrated attention-guided deep convolutional neural network for facial expression recognition in the wild","volume":"84","author":"S Saurav","year":"2024","journal-title":"Multimed Tools Appl"},{"issue":"13","key":"pone.0359554.ref036","doi-asserted-by":"crossref","first-page":"7100","DOI":"10.3390\/app15137100","article-title":"A hyper-attentive multimodal transformer for real-time and robust facial expression recognition","volume":"15","author":"Z Tagmatova","year":"2025","journal-title":"Appl Sci"},{"issue":"4","key":"pone.0359554.ref037","doi-asserted-by":"crossref","first-page":"764","DOI":"10.3390\/electronics15040764","article-title":"Dynamic occlusion-aware facial expression recognition guided by AA-ViT","volume":"15","author":"X Mou","year":"2026","journal-title":"Electronics"},{"key":"pone.0359554.ref038","doi-asserted-by":"crossref","unstructured":"Sadiq M, Zhang Y, Zhou Y, Mahmud M, Azhar M, Durad M. A context-aware dropout-based occlusion-adaptive network for robust facial landmark and emotion detection. J King Saud Univ Comp Inform Sci. 2026.","DOI":"10.1007\/s44443-026-00705-7"},{"key":"pone.0359554.ref039","doi-asserted-by":"crossref","first-page":"8101","DOI":"10.1109\/TIP.2025.3637715","article-title":"A Perception CNN for facial expression recognition","volume":"34","author":"C Tian","year":"2025","journal-title":"IEEE Trans Image Process"},{"issue":"12","key":"pone.0359554.ref040","doi-asserted-by":"crossref","first-page":"3762","DOI":"10.3390\/s25123762","article-title":"Facial landmark-driven keypoint feature extraction for robust facial expression recognition","volume":"25","author":"J So","year":"2025","journal-title":"Sensors (Basel)"},{"key":"pone.0359554.ref041","doi-asserted-by":"crossref","unstructured":"Zhai H, Yang X, Ye Y, Li C, Fan B, Li C. Rethinking occlusion in FER: A semantic-aware perspective and go beyond. In: Proceedings of the 33rd ACM International conference on multimedia. 2025. 5567\u201376. https:\/\/doi.org\/10.1145\/3746027.3754978","DOI":"10.1145\/3746027.3754978"},{"key":"pone.0359554.ref042","first-page":"174","article-title":"MambaFER: A mamba-based dual-perception network for facial expression recognition in the wild","volume-title":"Lecture notes in computer science","author":"C Zhang","year":"2025"},{"key":"pone.0359554.ref043","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1016\/j.patrec.2026.01.007","article-title":"MM-Net: Facial expression recognition based on multi-level and multi-scale attention mechanisms","volume":"201","author":"D Wang","year":"2026","journal-title":"Pattern Recognition Letters"},{"issue":"2","key":"pone.0359554.ref044","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1007\/s11801-025-3293-8","article-title":"Robust facial expression recognition via lightweight reinforcement learning for rehabilitation robotics","volume":"21","author":"Y Chen","year":"2024","journal-title":"Optoelectron Lett"},{"key":"pone.0359554.ref045","doi-asserted-by":"crossref","unstructured":"Aisiri A, Naveen KH, Ramya B, Kumar A, Rishika M. Emotion-aware hotel feedback system using CNN-based facial expression recognition. In: 2025 International Conference on Communication, Computer, and Information Technology (IC3IT), 2025. 1\u20138.","DOI":"10.1109\/IC3IT66137.2025.11341745"},{"issue":"17","key":"pone.0359554.ref046","doi-asserted-by":"crossref","first-page":"11399","DOI":"10.1007\/s00521-025-11139-z","article-title":"Multi-scale feature fusion for facial expression recognition","volume":"37","author":"J Guo","year":"2025","journal-title":"Neural Comput Applic"},{"key":"pone.0359554.ref047","doi-asserted-by":"crossref","first-page":"131377","DOI":"10.1016\/j.eswa.2026.131377","article-title":"CNN-DET: A hybrid deep learning architecture for emotion recognition","volume":"312","author":"B Abdelkader","year":"2026","journal-title":"Expert Systems Appl"},{"key":"pone.0359554.ref048","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1016\/j.aej.2025.01.078","article-title":"Attention-enhanced optimized deep ensemble network for effective facial emotion recognition","volume":"119","author":"T Khan","year":"2025","journal-title":"Alexandria Eng J"},{"issue":"1","key":"pone.0359554.ref049","doi-asserted-by":"crossref","first-page":"13826","DOI":"10.1038\/s41598-026-44396-6","article-title":"FERMam: a lightweight dual-source and multi-scale fusion framework for facial expression recognition","volume":"16","author":"C Gao","year":"2026","journal-title":"Sci Rep"},{"issue":"1","key":"pone.0359554.ref050","doi-asserted-by":"crossref","first-page":"7323","DOI":"10.1038\/s41598-026-38734-x","article-title":"Facial expression recognition via variational inference","volume":"16","author":"G Lv","year":"2026","journal-title":"Sci Rep"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0359554","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T17:45:58Z","timestamp":1790876758000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0359554"}},"subtitle":[],"editor":[{"given":"Shih-Lin","family":"Lin","sequence":"first","affiliation":[{"name":"National Changhua University of Education","place":["TAIWAN"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,10,1]]},"references-count":50,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,10,1]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0359554","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,1]]}}}