2026-10-11T19:59:37Z https://api.figshare.com/v2/oai

oai:figshare.com:article/34049489 2026-10-01T17:46:51Z category_734 category_931 category_106 portal_5 item_type_3 month_year_10_2026

<p>Ablation study of OQ-FERNet.</p> Lianfei Gao (25158062) Junfeng Tan (1486195) Jiahao Zhang (4859203) Biological Sciences not elsewhere classified Information Systems not elsewhere classified Science Policy quantitative emotion prediction low computational cost high computational cost grained emotion representation grained affective outputs facial expression recognition enhancing visible expression emotion intensity estimation design suppresses occluded div >< p computer interaction scenarios partial facial occlusion fernet obtains 93 different occlusion conditions paper proposes oq computer interaction time human still limited source code results show results indicate related cues regional reliability publicly available practical application obtain compact inference speed improved robustness important task feature map efficient solution discriminative representations contributions according adaptively adjust 356 fps 26g flops 18m parameters <div><p>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: <a href="https://github.com/jiahao001-j/OQ-FERNet" target="_blank">https://github.com/jiahao001-j/OQ-FERNet</a>.</p></div> 2026-10-01T17:46:40Z Dataset Dataset 10.1371/journal.pone.0359554.t005 https://figshare.com/articles/dataset/_p_Ablation_study_of_OQ-FERNet_p_/34049489 CC BY 4.0