clare-dataset-f650cb73·1 events·first seen Aliases: CLARE dataset
MambaGaze is a framework for real-time cognitive load assessment from eye-tracking data, combining XMD encoding (observation masks and time-deltas for missing data) with bidirectional Mamba-2 for efficient long-range temporal modeling. Evaluated on CLARE and CL-Drive datasets under leave-one-subject-out protocol, it achieves 76.8% and 73.1% accuracy, outperforming CNN, Transformer, ResNet, and VGG baselines by 4-12 percentage points. Edge deployment on NVIDIA Jetson platforms achieves 43-68 FPS at under 7.5W, demonstrating feasibility for wearable and safety-critical applications such as driver vigilance monitoring.