We present our contribution to the 8th ABAW challenge at CVPR 2025, where we tackle valence-arousal estimation, emotion recognition, and facial action unit detection as three independent challenges. Our approach leverages the well-known Dual-Direction Attention Mixed Feature Network (DDAMFN) for all three tasks, achieving results that surpass the proposed baselines. Additionally, we explore the use of CLIP for the emotion recognition challenge as an additional experiment. We provide insights into the architectural choices that contribute to the strong performance of our methods.
View on arXiv@article{cabacas-maso2025_2503.12260,
title={ Enhancing Facial Expression Recognition through Dual-Direction Attention Mixed Feature Networks and CLIP: Application to 8th ABAW Challenge },
author={ Josep Cabacas-Maso and Elena Ortega-Beltrán and Ismael Benito-Altamirano and Carles Ventura },
journal={arXiv preprint arXiv:2503.12260},
year={ 2025 }
}