Adaptive Temporal Motion Guided Graph Convolution Network for Micro-expression Recognition

TL;DR

This paper introduces ATM-GCN, a novel graph convolutional network that effectively captures temporal dependencies and motion features for improved micro-expression recognition across multiple datasets.

Contribution

The proposed ATM-GCN framework uniquely integrates adaptive temporal motion layers to enhance clip-level micro-expression recognition by capturing global and local motion features.

Findings

Outperforms existing state-of-the-art methods on Composite dataset

Achieves superior results on CAS(ME)$^3$ dataset

Effectively captures temporal dependencies and motion features

Abstract

Micro-expressions serve as essential cues for understanding individuals' genuine emotional states. Recognizing micro-expressions attracts increasing research attention due to its various applications in fields such as business negotiation and psychotherapy. However, the intricate and transient nature of micro-expressions poses a significant challenge to their accurate recognition. Most existing works either neglect temporal dependencies or suffer from redundancy issues in clip-level recognition. In this work, we propose a novel framework for micro-expression recognition, named the Adaptive Temporal Motion Guided Graph Convolution Network (ATM-GCN). Our framework excels at capturing temporal dependencies between frames across the entire clip, thereby enhancing micro-expression recognition at the clip level. Specifically, the integration of Adaptive Temporal Motion layers empowers our method to aggregate global and local motion features inherent in micro-expressions. Experimental results demonstrate that ATM-GCN not only surpasses existing state-of-the-art methods, particularly on the Composite dataset, but also achieves superior performance on the latest micro-expression dataset CAS(ME)$^3$.