Exploring Spatial-Temporal Dynamics in Event-based Facial Micro-Expression Analysis

TL;DR

This paper introduces a new dataset of synchronized RGB and event camera recordings for micro-expression analysis, demonstrating that event-based data enhances micro-expression recognition and frame reconstruction.

Contribution

The work presents a novel multi-resolution, multi-modal micro-expression dataset with synchronized RGB and event recordings, and evaluates baseline tasks showing the potential of event data.

Findings

Event data achieves 51.23% AU classification accuracy versus 23.12% with RGB.

Frame reconstruction with event data yields SSIM of 0.8513 and PSNR of 26.89 dB.

Event-based micro-expression analysis outperforms traditional RGB methods.

Abstract

Micro-expression analysis has applications in domains such as Human-Robot Interaction and Driver Monitoring Systems. Accurately capturing subtle and fast facial movements remains difficult when relying solely on RGB cameras, due to limitations in temporal resolution and sensitivity to motion blur. Event cameras offer an alternative, with microsecond-level precision, high dynamic range, and low latency. However, public datasets featuring event-based recordings of Action Units are still scarce. In this work, we introduce a novel, preliminary multi-resolution and multi-modal micro-expression dataset recorded with synchronized RGB and event cameras under variable lighting conditions. Two baseline tasks are evaluated to explore the spatial-temporal dynamics of micro-expressions: Action Unit classification using Spiking Neural Networks (51.23\% accuracy with events vs. 23.12\% with RGB), and frame reconstruction using Conditional Variational Autoencoders, achieving SSIM = 0.8513 and PSNR = 26.89 dB with high-resolution event input. These promising results show that event-based data can be used for micro-expression recognition and frame reconstruction.