Using a hue-lightness skin tone measure reveals larger emotion recognition gaps for dark-skinned faces on AffectNet than the ITA measure, but the dark group has only 52 test images.
NIST special publication 1270. Towards a standard for identifying and managing bias in AI,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
TrustSkin: A Fairness Pipeline for Trustworthy Facial Affect Analysis Across Skin Tone
Using a hue-lightness skin tone measure reveals larger emotion recognition gaps for dark-skinned faces on AffectNet than the ITA measure, but the dark group has only 52 test images.