AffectNet
burak yılmaz
ImagesCustom (non-commercial)Introduced 2019-01-01
AffectNet is a large facial expression dataset with around 0.4 million images manually labeled for the presence of eight (neutral, happy, angry, sad, fear, surprise, disgust, contempt) facial expressions along with the intensity of valence and arousal.
Source: Landmark Guidance Independent Spatio-channel Attention and Complementary Context Information based Facial Expression Recognition Image Source: http://mohammadmahoor.com/affectnet/
Benchmarks
3D/Accuracy (8 emotion)3D/Accuracy (7 emotion)3D Face Modelling/Accuracy (8 emotion)3D Face Modelling/Accuracy (7 emotion)3D Face Reconstruction/Accuracy (8 emotion)3D Face Reconstruction/Accuracy (7 emotion)Continuous Affect Estimation/Concordance correlation coefficient (CCC)Face Reconstruction/Accuracy (8 emotion)Face Reconstruction/Accuracy (7 emotion)Facial Expression Recognition/Accuracy (7 emotion)Facial Expression Recognition (FER)/Accuracy (8 emotion)Facial Expression Recognition (FER)/Accuracy (7 emotion)Facial Recognition and Modelling/Accuracy (8 emotion)Facial Recognition and Modelling/Accuracy (7 emotion)