Data-aware relation learning-based graph convolution neural network for facial action unit recognition

Xibin Jia

doi:10.1016/j.patrec.2022.02.010

Data-aware relation learning-based graph convolution neural network for facial action unit recognition

2022-03-01

4

PRE

AI

DOI：10.1016/j.patrec.2022.02.010

Original

Original request for help

Save

Abstract

En 中文

In the paper, we propose a novel Data-aware relation graph convolutional neural network (DAR-GCN) for AU recognition. With learning and updating the relation dynamically, it facilitates modeling the potential dynamic individual facial expressing manner and accordingly improves the AU recognition under the unconstrained environment. Taking the psychological research knowledge of AUs as a reference, we adopt the consensus widely-used AUs and six basic emotions as vertexes, and their co-occurrence or ex-occurrence relations between AUs and the emotion dependent relation as the edges to construct the graph. Moreover, the Data-aware relation Graph Generator (DAR-GG) module is proposed to learn the relations with data-driven metric learning. This proposed scheme is benefit for calculating and updating AU relations from data, which facilitates to extract specific relations causing by individual expressing characteristics as well as inherent relations due to facial anatomical structure. Comparative experiments are done on three public datasets: CK+, RAF-AU and DISFA. Experimental results demonstrate that our proposed method achieves a higher AU recognition accuracy rate than the baseline based on the graph with fixed AU relations defined from the psychological knowledge. Additionally, our proposed approach outperforms several existing state-of-the-art AU recognition method by utilizing GCN-based dynamic AU relations learning strategies. (C) 2022 Elsevier B.V. All rights reserved.

Keywords:

AU recognition

FACS

GCN

Relation representation

Metric learning

Data-aware relation learning-based graph convolution neural network for facial action unit recognition

Abstract

Journal

Organization

Cited Papers