A simple yet strong baseline for facial AU detection:

• Extract basic AU features from a pretrained face alignment model
• Instantiate TDN to model temporal dynamics on static AU features
• Use VAE module to regulate the initial prediction

• Python 3
• PyTorch

We use RetinaFace to do face detection:

• BP4D
• DISFA
• AffWild2

• train the VAE module on BP4D split 1, run:

python train_vae.py --data BP4D --subset 1 --weight 0.3 

• train the AU-Net, run:

python train_video_vae.py --data BP4D --vae 'pretrained vae model'

• Pretrained models Test

• Demo to predict 15 AUs Demo

This repo is built using components from JAANet and EmoNet

This project is licensed under the MIT License