Text Prompt Region Decomposition for Effective Facial Expression Recognition

Facial expressions are conveyed through semantically distinct visual cues distributed across different facial regions, making region-aware feature modeling essential for accurate Facial Expression Recognition (FER). However, existing methods typically rely on implicit attention mechanisms or manually defined region cues without grounding in semantically aligned supervision, which often leads to suboptimal representation of regional expression cues, increased risk of overfitting, and limited interpretability. To address these limitations, we propose a Text Prompt Region Decomposition (TPRD) network that explicitly disentangles expression-relevant features across key facial regions via text prompt guidance. Specifically, TPRD comprises a visual-language pretrained encoder (e.g., CLIP), a Region Decomposition Module (RDM), and a Regional Integration Module (RIM). The visual encoder extracts global visual features from full-face images, while the text encoder embeds region-specific prompts (e.g., “mouth”, “eye”) into semantic vectors within a shared visual-language embedding space. The RDM employs a multi-branch architecture to project global visual features onto the semantic directions of region-specific text embeddings, enabling explicit extraction of local visual features. Subsequently, the RIM models the interaction between regional and global features, adaptively generating distinct regional contributions that modulate the global representation for different facial expression samples. Experimental results demonstrate that our proposed TPRD achieves leading performance in both within- and cross-dataset evaluations, as well as in scenarios involving occlusion and large head pose variations.