Inference-Time Gaze Refinement for Micro-Expression Recognition: Enhancing Event-Based Eye Tracking with Motion-Aware Post-Processing

TL;DR

This paper presents a post-processing framework that refines event-based gaze estimates at inference time, improving temporal smoothness and accuracy without retraining models, thereby enhancing micro-expression recognition capabilities.

Contribution

The work introduces a model-agnostic, inference-time refinement method with novel modules and metrics to improve event-based gaze signals for cognitive state inference.

Findings

Significant improvement in gaze signal consistency across baseline models.

Enhanced micro-expression recognition performance with refined gaze data.

Introduction of a new Jitter Metric for temporal smoothness evaluation.

Abstract

Event-based eye tracking holds significant promise for fine-grained cognitive state inference, offering high temporal resolution and robustness to motion artifacts, critical features for decoding subtle mental states such as attention, confusion, or fatigue. In this work, we introduce a model-agnostic, inference-time refinement framework designed to enhance the output of existing event-based gaze estimation models without modifying their architecture or requiring retraining. Our method comprises two key post-processing modules: (i) Motion-Aware Median Filtering, which suppresses blink-induced spikes while preserving natural gaze dynamics, and (ii) Optical Flow-Based Local Refinement, which aligns gaze predictions with cumulative event motion to reduce spatial jitter and temporal discontinuities. To complement traditional spatial accuracy metrics, we propose a novel Jitter Metric that captures the temporal smoothness of predicted gaze trajectories based on velocity regularity and local signal complexity. Together, these contributions significantly improve the consistency of event-based gaze signals, making them better suited for downstream tasks such as micro-expression analysis and mind-state decoding. Our results demonstrate consistent improvements across multiple baseline models on controlled datasets, laying the groundwork for future integration with multimodal affect recognition systems in real-world environments. Our code implementations can be found at https://github.com/eye-tracking-for-physiological-sensing/EyeLoRiN.