Gaze Matters: Eye Contact Detection in Unscripted Human-Robot Interaction Scenarios

Gaze Matters: Eye Contact Detection in Unscripted Human-Robot Interaction Scenarios

This paper presents a user study in a realistic collaborative HRI scenario with unscripted tasks to evaluate the performance of current eye contact detection models under realistic conditions. A new dataset of 5,888 manually annotated visual engagement instances was created to reflect the complexity of real-world interactions and to validate previous work on NITEC, a large-scale dataset for eye contact detection. The results indicate that models trained on the NITEC dataset perform best with an AUC of 0.74 compared to other models, highlighting the importance of training on diverse and unconstrained data for robust eye contact recognition in HRI.

Fulltext Access

https://doi.org/10.1109/SMC58881.2025.11343353

Citing

@inproceedings{hempel2025gaze,
  title={Gaze Matters: Eye Contact Detection in Unscripted Human-Robot Interaction Scenarios},
  author={Hempel, Thorsten and Jung, Magnus and Strazdas, Dominykas and Al-Hamadi, Ayoub},
  booktitle={2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)},
  pages={7312--7317},
  year={2025},
  organization={IEEE}
}