This dataset and model weights are for the publicly released code located at
https://github.com/byu-rvl/Ensemble_AU_release.
Please put all the contents of this huggingface repo into the data directory in the above github repository.
If you use this dataset in a publication, please cite:
@article{sumsion2025meta,
title={A Meta-Learner Based on the Combination of Stacking Ensembles and a Mixture of Experts for Balancing Action Unit Recognition},
author={Sumsion, Andrew and Lee, Dah-Jye}… See the full description on the dataset page:
https://huggingface.co/datasets/dwsum/Syn_AU.