MambaGaze: Bidirectional Mamba with Explicit Missing Data Modeling for Cognitive Load Assessment from Eye-Gaze Tracking Data
📰 ArXiv cs.AI
Learn how MambaGaze assesses cognitive load from eye-gaze tracking data using bidirectional modeling and explicit missing data handling, enabling adaptive human-centered AI applications.
Action Steps
- Implement MambaGaze framework using bidirectional Mamba to model eye-gaze tracking data
- Handle missing data from blinks and tracking failures using explicit modeling techniques
- Assess cognitive load in real-time using the proposed framework
- Evaluate the performance of MambaGaze on benchmark datasets
- Compare the results with existing state-of-the-art methods for cognitive load assessment
Who Needs to Know This
Data scientists and AI engineers working on human-centered AI applications, such as driver vigilance monitoring or automated flight deck assistance, can benefit from this research to improve their models' accuracy and robustness.
Key Insight
💡 MambaGaze addresses two key challenges in cognitive load assessment: handling missing data and modeling long-range temporal dependencies, enabling more accurate and robust predictions.
Share This
🚀 MambaGaze: A new framework for real-time cognitive load assessment from eye-gaze tracking data using bidirectional modeling and explicit missing data handling #AI #EyeTracking #CognitiveLoad
Full Article
Title: MambaGaze: Bidirectional Mamba with Explicit Missing Data Modeling for Cognitive Load Assessment from Eye-Gaze Tracking Data
Abstract:
arXiv:2605.22775v1 Announce Type: cross 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 thr
Abstract:
arXiv:2605.22775v1 Announce Type: cross 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 thr
DeepCamp AI