Abstract
Facial affect analysis (FAA) using visual signals is a key step in human-computer interactions. Previous methods mainly focus on extracting appearance and geometry features associated with human affects. However, they do not consider the latent semantic information among each individual facial change, leading to limited performance and generalization. Recent trends attempt to establish a graph-based representation to model these semantic relationships and develop learning framework to leverage it for different FAA tasks. In this paper, we provide a comprehensive review of graph-based FAA, including the evolution of algorithms and their applications. First, we introduce the background knowledge of affect analysis, especially on the role of graph. We then discuss approaches that are widely used for graph-based affective representation in literatures and show a trend towards graph construction. For the relational reasoning in graph-based FAA, we classify existing studies according to their usage of traditional methods or deep models, with a special emphasis on latest graph neural networks. Experimental comparisons of the state-of-the-art on standard FAA problems are also summarized. Finally, we extend the review to the current challenges and potential directions. As far as we know, this is the first survey of graph-based FAA methods, and our findings can serve as a reference point for future research in this field.
Abstract (translated)
URL
https://arxiv.org/abs/2103.15599
