CLERA: A Unified Model for Joint Cognitive Load and Eye Region Analysis in the Wild

Non-intrusive, real-time analysis of the dynamics eye region allows us to monitor humans' visual attention allocation and estimate their mental state during performance real-world tasks, which can potentially benefit a wide range human-computer interaction (HCI) applications. While commercial eye-tracking devices have been frequently employed, difficulty customizing these places unnecessary constraints on exploration more efficient, end-to-end models dynamics. In this work, we propose CLERA, unified model for Cognitive Load Eye Region Analysis, achieves precise keypoint detection spatiotemporal tracking in joint-learning framework. Our method demonstrates significant efficiency outperforms prior work tasks including cognitive load estimation, landmark detection, blink estimation. We also introduce large-scale dataset 30k human faces with joint pupil, eye-openness, annotation, aims support future HCI research factors eye-related analysis.