A survey on Graph Deep Representation Learning for Facial Expression Recognition

TL;DR

This survey reviews how graph deep representation learning techniques are applied to facial expression recognition, covering methodologies, datasets, and future research directions in the field.

Contribution

It provides a comprehensive overview of graph-based methods for FER, highlighting recent advances and identifying open challenges.

Findings

Graph diffusion and spatio-temporal graphs are promising for FER.

Multiple graph architectures enhance recognition accuracy.

The survey outlines key datasets and future research directions.

Abstract

This comprehensive review delves deeply into the various methodologies applied to facial expression recognition (FER) through the lens of graph representation learning (GRL). Initially, we introduce the task of FER and the concepts of graph representation and GRL. Afterward, we discuss some of the most prevalent and valuable databases for this task. We explore promising approaches for graph representation in FER, including graph diffusion, spatio-temporal graphs, and multi-stream architectures. Finally, we identify future research opportunities and provide concluding remarks.