ARGen: Affect-Reinforced Generative Augmentation towards Vision-based Dynamic Emotion Perception
For researchers in affective computing, ARGen provides a generative augmentation method to improve dynamic emotion recognition in data-scarce scenarios.
ARGen tackles data scarcity and long-tail distributions in dynamic facial expression recognition by generating synthetic video sequences. It improves recognition performance, e.g., achieving state-of-the-art results on benchmark datasets like DFEW and FERV39k.
Dynamic facial expression recognition in the wild remains challenging due to data scarcity and long-tail distributions, which hinder models from effectively learning the temporal dynamics of scarce emotions. To address these limitations, we propose ARGen, an Affect-Reinforced Generative Augmentation Framework that enables data-adaptive dynamic expression generation for robust emotion perception. ARGen operates in two stages: Affective Semantic Injection (ASI) and Adaptive Reinforcement Diffusion (ARD). The ASI stage establishes affective knowledge alignment through facial Action Units and employs a retrieval-augmented prompt generation strategy to synthesize consistent and fine-grained affective descriptions via large-scale visual-language models, thereby injecting interpretable emotional priors into the generation process. The ARD stage integrates text-conditioned image-to-video diffusion with reinforcement learning, introducing inter-frame conditional guidance and a multi-objective reward function to jointly optimize expression naturalness, facial integrity, and generative efficiency. Extensive experiments on both generation and recognition tasks verify that ARGen substantially enhances synthesis fidelity and improves recognition performance, establishing an interpretable and generalizable generative augmentation paradigm for vision-based affective computing.