Olaf Hellwich

Different Paradigms from Computer Vision Align with Human Assessment of the Mouse Grimace Scale

This paper evaluates three computer vision paradigms for automated mouse well-being assessment using the Mouse Grimace Scale and finds they achieve low error rates and use relevant visual features.

Automatic pain face analysis in mice: Applied to a varied dataset with non-standardized conditions

This paper introduces a deep learning model for automated pain face analysis in mice using the Mouse Grimace Scale, achieving high correlation with human raters and outperforming them in error magnitude.

Towards Fully Automated Investigation of Social Learning in Mice

This paper develops an automated system for studying social learning in mice using behavioral tracking tools, finding that co-learning does not enhance place learning but reveals prosocial interactions.

Mechanical problem solving in mice

This study uses a lockbox task to show that mice primarily develop motor skills before adopting a cognitive strategy for solving a complex mechanical puzzle.

Objects Guide Human Gaze Behavior in Dynamic Real-World Scenes

This paper introduces a computational framework to simulate human gaze behavior in dynamic scenes, showing that object-based attention improves the accuracy of simulated eye movements compared to spatial-based models.