FER-YOLO-Mamba: An Efficient Facial Expression Detection and Classification Model Leveraging Selective State Space Techniques
The FER-YOLO-Mamba model integrates the principles of Mamba and YOLO technologies to enable efficient and accurate facial expression detection and classification. It employs a dual-branch module that combines the strengths of convolutional layers and state space models to capture both local and long-distance dependencies in facial expression images.