Facial Expression Recognition: Impact of Gender on Fairness and Expressions∗
C Manresa-Yee, S Ramis Guarinos… - Proceedings of the XXII …, 2022 - dl.acm.org
C Manresa-Yee, S Ramis Guarinos, JM Buades Rubio
Proceedings of the XXII International Conference on Human Computer Interaction, 2022•dl.acm.orgMultiple and varied domains can benefit from automated Facial Expression Recognition
(FER) like human computer interfaces or health applications. New approaches using
Machine learning (ML) are achieving successful results, but its use raises concerns related
with biases, fairness or explainability, which can undermine the trust of the users. This work
aims to study how gender biased training datasets alter fairness in FER. The main outcomes
show which facial expressions recognition are more impacted by gender bias.
(FER) like human computer interfaces or health applications. New approaches using
Machine learning (ML) are achieving successful results, but its use raises concerns related
with biases, fairness or explainability, which can undermine the trust of the users. This work
aims to study how gender biased training datasets alter fairness in FER. The main outcomes
show which facial expressions recognition are more impacted by gender bias.
Multiple and varied domains can benefit from automated Facial Expression Recognition (FER) like human computer interfaces or health applications. New approaches using Machine learning (ML) are achieving successful results, but its use raises concerns related with biases, fairness or explainability, which can undermine the trust of the users. This work aims to study how gender biased training datasets alter fairness in FER. The main outcomes show which facial expressions recognition are more impacted by gender bias.
ACM Digital Library以上显示的是最相近的搜索结果。 查看全部搜索结果