DDAMFN

Paper: A Dual-Direction Attention Mixed Feature Network for Facial Expression Recognition https://www.mdpi.com/2079-9292/12/17/3595

Data processing: https://qq742971636.blog.csdn.net/article/details/136841591(Thank the author of this blog for his interpretation and contribution to the paper. For further learning needs, you can subscribe to his column.)

Our new version DDAMFN++ is available in the folder https://github.com/simon20010923/DDAMFN/tree/main/DDAMFN%2B%2B, which includes new alignment code refer to https://github.com/biubug6/Pytorch_Retinaface and optimized by SAM (Sharpness aware minimization for efficiently improving generalization). The trained RAF-DB and AffectNet model is available in DDAMFN++/checkpoints_ver2.0, which is not our best.