Learning Multi-dimensional Edge Feature-based AU Relation Graph for Facial Action Unit Recognition

2 May 2022  ·  Cheng Luo, Siyang Song, Weicheng Xie, Linlin Shen, Hatice Gunes ·

The activations of Facial Action Units (AUs) mutually influence one another. While the relationship between a pair of AUs can be complex and unique, existing approaches fail to specifically and explicitly represent such cues for each pair of AUs in each facial display. This paper proposes an AU relationship modelling approach that deep learns a unique graph to explicitly describe the relationship between each pair of AUs of the target facial display. Our approach first encodes each AU's activation status and its association with other AUs into a node feature. Then, it learns a pair of multi-dimensional edge features to describe multiple task-specific relationship cues between each pair of AUs. During both node and edge feature learning, our approach also considers the influence of the unique facial display on AUs' relationship by taking the full face representation as an input. Experimental results on BP4D and DISFA datasets show that both node and edge feature learning modules provide large performance improvements for CNN and transformer-based backbones, with our best systems achieving the state-of-the-art AU recognition results. Our approach not only has a strong capability in modelling relationship cues for AU recognition but also can be easily incorporated into various backbones. Our PyTorch code is made available.

PDF Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Facial Action Unit Detection BP4D ResNet 50 Average F1 59.1 # 6
Facial Action Unit Detection BP4D Multi-dimensional Edge Feature-based AU Relation Graph (Swin-B) Average F1 65.5 # 1
Average AUC 83.1 # 1
Facial Action Unit Detection BP4D Swin-B Average F1 62.6 # 4
Facial Action Unit Detection BP4D Multi-dimensional Edge Feature-based AU Relation Graph (ResNet 50) Average F1 64.7 # 2
Average AUC 82.6 # 2
Facial Action Unit Detection DISFA Multi-dimensional Edge Feature-based AU Relation Graph (ResNet 50) Average F1 63.1 # 1
Average AUC 92.9 # 1
Facial Action Unit Detection DISFA Multi-dimensional Edge Feature-based AU Relation Graph (Swin-B) Average F1 62.4 # 2
Average AUC 92.1 # 2

Methods


No methods listed for this paper. Add relevant methods here