
Facial expression recognition (FER) models can be made more interpretable by aligning their internal feature representations with spatial cues derived from facial action units, without requiring additional manual annotations.


coremsg

guided-interpretable-facial-expression-recognition-via-spatial-action-unit-cues


Guided Interpretable Facial Expression Recognition via Spatial Action Unit Cues


title_rewrite


Leveraging spatial action unit cues to train deep models that can perform accurate facial expression recognition while providing interpretable decisions.


leveraging-spatial-action-unit-cues-for-interpretable-deep-facial-expression-recognition


Leveraging Spatial Action Unit Cues for Interpretable Deep Facial Expression Recognition
