MambaGaze: Bidirectional Mamba with Explicit Missing Data Modeling for Cognitive Load Assessment from Eye-Gaze Tracking Data

TL;DR

MambaGaze is a novel framework for real-time cognitive load assessment from eye-gaze data that explicitly models missing data and captures long-range dependencies efficiently, outperforming existing methods.

Contribution

The paper introduces XMD encoding and bidirectional Mamba-2, enabling effective handling of missing data and temporal dependencies in eye-gaze based cognitive load assessment.

Findings

Achieves 76.8% and 73.1% accuracy on two datasets, outperforming baselines by 4-12 percentage points.

Enables real-time inference at 43-68 FPS on NVIDIA Jetson with low power consumption.

Demonstrates feasibility for wearable cognitive load monitoring in safety-critical applications.

Abstract

Real-time cognitive load assessment from eye-tracking signals could potentially enable adaptive human-centered-AI such as safety-critical applications such as driver vigilance monitoring or automated flight deck assistance, yet two challenges persist: handling frequent data missingness from blinks and tracking failures, and efficiently modeling long-range temporal dependencies. We propose MambaGaze, a framework that addresses these challenges through 1) XMD encoding, which augments raw features with observation masks and time-deltas to explicitly model data uncertainty, and 2) bidirectional Mamba-2, which captures temporal dependencies with linear computational complexity. Experiments on CLARE and CL-Drive datasets under leave-one-subject-out evaluation show that MambaGaze achieves 76.8% and 73.1% accuracy, respectively, outperforming CNN, Transformer, ResNet, and VGG baselines by 4-12 percentage points. Edge deployment benchmarks on NVIDIA Jetson platforms demonstrate real-time inference at 43-68 FPS with power consumption below 7.5W, confirming feasibility for wearable cognitive load monitoring.