OQ-FERNet: An occlusion-aware quantitative facial expression recognition network for real-time human-computer interaction
- 1Shandong Huitong Financial Leasing Co., Ltd., Jinan, Shandong, China
Abstract
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: https://github.com/jiahao001-j/OQ-FERNet.
Related
- Antigen recognition licenses therapeutic CD8+ T cells to organize a multicellular myeloid interaction network in the tumor microenvironment
- Evidence-resolved benchmarks separate biological context recognition from direct-partner specificity in protein interaction models
- Processing abstract concepts through interaction: effects on social recognition
- Facial Expression Recognition in Food Studies
- Subtle positive facial expression recognition is enhanced by comedy viewing: individual differences in empathy and depressive tendencies
BibTeX
@article{gao2026oqfernet,
title = {{OQ-FERNet: An occlusion-aware quantitative facial expression recognition network for real-time human-computer interaction}},
author = {Lianfei Gao and Junfeng Tan and Jiahao Zhang},
journal = {PLOS One},
year = {2026},
month = oct,
doi = {10.1371/journal.pone.0359554},
url = {https://doi.org/10.1371/journal.pone.0359554},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - OQ-FERNet: An occlusion-aware quantitative facial expression recognition network for real-time human-computer interaction
AU - Lianfei Gao
AU - Junfeng Tan
AU - Jiahao Zhang
PY - 2026
DA - 2026/10/01
JO - PLOS One
DO - 10.1371/journal.pone.0359554
UR - https://doi.org/10.1371/journal.pone.0359554
AB - 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: https://github.com/jiahao001-j/OQ-FERNet.
SN - 1932-6203
ER -