EveLoad: Cognitive Workload Recognition from Event-Based Eye Movements

2026-06-23

AI Summary

This study addresses the limitations of conventional frame-based eye-tracking methods, which suffer from low temporal resolution, poor robustness to rapid eye movements, and confounding of fixation distributions with genuine oculomotor dynamics, thereby hindering accurate cognitive load assessment. To overcome these challenges, the authors introduce event cameras for the first time in this domain and present EveLoad—the first event-based eye movement dataset—capturing six levels of cognitive load from 20 participants under spatial constraints and N-back task paradigms, effectively minimizing interference from fixation locations. They propose a learning framework tailored to spatiotemporal event representations, leveraging the microsecond-level temporal resolution and high dynamic range of event cameras to model oculomotor dynamics. Under mixed random-split evaluation, the approach achieves subject-specific accuracies of 96.36% and 96.13%, demonstrating the efficacy and superiority of event-based eye movement signals for cognitive load sensing.

Abstract

Cognitive workload monitoring is important for adaptive rehabilitation and assistive interfaces, where task difficulty, pacing, and feedback should be adjusted according to the user's cognitive state to avoid overload and under-challenge. Emerging extended reality and robot-assisted rehabilitation environments provide controllable training tasks, but they require unobtrusive sensing methods that can capture rapid ocular dynamics during interaction. Existing eye-movement-based cognitive workload recognition methods mainly rely on frame-based eye trackers, which often suffer from limited temporal resolution and degraded robustness under rapid eye movements. In contrast, event cameras provide microsecond-level temporal resolution, high dynamic range and low latency, making them suitable for capturing fine-grained ocular dynamics. Many previous studies rely on free-viewing or similar paradigms, where gaze locations can vary across tasks. As a result, models may learn associations between gaze-location distributions and cognitive workload, rather than workload-related eye movement characteristics themselves. In this work, we introduce EveLoad, which, to the best of our knowledge, is the first event-based eye-movement dataset with graded cognitive workload annotations, collected from 20 healthy participants under spatially constrained and task-driven conditions using a controlled N-back-guided fixation paradigm. Based on this dataset, we establish a benchmark for cognitive workload recognition with six workload levels and propose a learning framework that encodes spatiotemporal event representations. Experimental results show that our approach achieves an average subject-specific accuracy of 96.36% and 96.13% under mixed random split evaluation. These results suggest that event-based eye movements may provide a useful sensing pathway for future workload-aware rehabilitation.

Problem

• cognitive workload
• eye movements
• event cameras
• workload recognition
• oculomotor dynamics

Innovation

• event-based vision
• cognitive workload recognition
• eye movements
• spatiotemporal representation
• N-back paradigm