Impact of Action Unit Occurrence Patterns on Detection

TL;DR

This paper investigates how patterns in the occurrence of facial action units affect their detection accuracy, reviewing literature and proposing a neural network training method to improve detection performance.

Contribution

It introduces a novel approach that explicitly incorporates action unit occurrence patterns into deep neural network training for enhanced detection accuracy.

Findings

Action unit patterns significantly influence evaluation metrics.

The proposed method improves detection accuracy by leveraging occurrence patterns.

Literature review confirms the impact of occurrence patterns on AU detection performance.

Abstract

Detecting action units is an important task in face analysis, especially in facial expression recognition. This is due, in part, to the idea that expressions can be decomposed into multiple action units. In this paper we investigate the impact of action unit occurrence patterns on detection of action units. To facilitate this investigation, we review state of the art literature, for AU detection, on 2 state-of-the-art face databases that are commonly used for this task, namely DISFA, and BP4D. Our findings, from this literature review, suggest that action unit occurrence patterns strongly impact evaluation metrics (e.g. F1-binary). Along with the literature review, we also conduct multi and single action unit detection, as well as propose a new approach to explicitly train deep neural networks using the occurrence patterns to boost the accuracy of action unit detection. These experiments validate that action unit patterns directly impact the evaluation metrics.