Optimal transport-based identity matching for identity-invariant facial expression recognition
Identity-invariant facial expression recognition (FER) has been one of the challenging
computer vision tasks. Since conventional FER schemes do not explicitly address the inter …
computer vision tasks. Since conventional FER schemes do not explicitly address the inter …
Metrics for Dataset Demographic Bias: A Case Study on Facial Expression Recognition
I Dominguez-Catena, D Paternain… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Demographic biases in source datasets have been shown as one of the causes of
unfairness and discrimination in the predictions of Machine Learning models. One of the …
unfairness and discrimination in the predictions of Machine Learning models. One of the …
Less can be more: representational vs. stereotypical gender bias in facial expression recognition
Abstract Machine learning models can inherit biases from their training data, leading to
discriminatory or inaccurate predictions. This is particularly concerning with the increasing …
discriminatory or inaccurate predictions. This is particularly concerning with the increasing …
[PDF][PDF] Multimodal Emotion Recognition using facial expression and other physiological condition
EH Unsvåg - 2022 - duo.uio.no
The task of emotion recognition has been attempted solved predominantly by unimodal
approaches, where facial emotion recognition is the most frequently used modality …
approaches, where facial emotion recognition is the most frequently used modality …
[PDF][PDF] Multimodal Emotion Recognition using facial expression and other physiological condition
A Mathisen - 2022 - simula.no
The task of emotion recognition has been attempted solved predominantly by unimodal
approaches, where facial emotion recognition is the most frequently used modality …
approaches, where facial emotion recognition is the most frequently used modality …