Enhancing Facial Expression Recognition through Dual-Direction Attention Mixed Feature Networks: Application to 7th ABAW Challenge

TL;DR

This paper introduces a Dual-Direction Attention Mixed Feature Network (DDAMFN) for multitask facial expression recognition, achieving superior results in the 7th ABAW challenge by effectively predicting multiple facial emotion-related tasks simultaneously.

Contribution

The paper presents a novel application of DDAMFN architecture for multitask facial expression recognition, demonstrating improved performance over baseline methods in the ABAW challenge.

Findings

Outperforms baseline in multitask facial expression recognition

Effectively predicts valence-arousal, emotion, and facial action units simultaneously

Provides insights into architecture design and task handling

Abstract

We present our contribution to the 7th ABAW challenge at ECCV 2024, by utilizing a Dual-Direction Attention Mixed Feature Network (DDAMFN) for multitask facial expression recognition, we achieve results far beyond the proposed baseline for the Multi-Task ABAW challenge. Our proposal uses the well-known DDAMFN architecture as base to effectively predict valence-arousal, emotion recognition, and facial action units. We demonstrate the architecture ability to handle these tasks simultaneously, providing insights into its architecture and the rationale behind its design. Additionally, we compare our results for a multitask solution with independent single-task performance.