Beyond Universality: The GCC-FER Dataset and Culture-Aware Adaptation for Dynamic Facial Expression Recognition
For researchers in affective computing and cross-cultural AI, this work addresses the lack of culturally diverse benchmarks and proposes a method to reduce cultural bias in facial expression recognition.
The paper introduces GCC-FER, a large-scale cross-cultural dynamic facial expression recognition dataset with 23,934 videos across four cultural groups, and proposes a Culture-Aware FER system that adaptively recalibrates facial representations to mitigate cultural bias, achieving consistent performance improvements on GCC-FER and DFEW benchmarks.
Dynamic Facial Expression Recognition (DFER) is a key enabling technology in affective computing, human-computer interaction, and intelligent multimedia systems. Despite the significant influence of cultural nuances on FER performance, most existing FER systems assume that emotional expressions are universally consistent across populations. This variation can be attributed to systematic differences in facial muscle activation patterns across cultures. A major challenge in advancing cross-cultural FER lies in the scarcity of culturally diverse benchmark datasets. To address this, a new hybrid multicultural video dataset termed Global Cross-Cultural Facial Expression Recognition (GCC-FER) is introduced. GCC-FER comprises 23,934 video samples spanning four cultural groups (African, Caucasian, East Asian, and South Asian) across seven basic expressions, combining psychologically supervised in-house data collection for underrepresented populations with rigorous ethnicity filtering of existing sources. To the best of our knowledge, GCC-FER is the first large-scale global cross-cultural DFER dataset designed to address these demographic gaps. Leveraging this dataset, behaviorally grounded cultural priors are derived for each cultural group and a global prior for practical deployment. A Culture-Aware FER (CA-FER) system is proposed to mitigate cultural bias by adaptively recalibrating latent facial representations. Extensive experiments on GCC-FER and DFEW demonstrate that the proposed system consistently improves FER performance across multicultural settings.