Facial expression recognition is the task of classifying the expressions on face images into various categories such as anger, fear, surprise, sadness, happiness and so on.
( Image credit: DeXpression )
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
Dense 3D facial motion capture from only monocular in-the-wild pairs of RGB images is a highly challenging problem with numerous applications, ranging from facial expression recognition to facial reenactment.
Annotating a qualitative large-scale facial expression dataset is extremely difficult due to the uncertainties caused by ambiguous facial expressions, low-quality facial images, and the subjectiveness of annotators.
Experiments on large-scale datasets suggest that ESRs reduce the remaining residual generalization error on the AffectNet and FER+ datasets, reach human-level performance, and outperform state-of-the-art methods on facial expression recognition in the wild using emotion and affect concepts.
SOTA for Facial Expression Recognition on FER+ (using extra training data)
This multi-task learning with dynamic weights also boosts of the performance on the different tasks comparing to the state-of-art methods with single-task learning.
SOTA for Face Verification on CK+
The feature embedding module is a deep Convolutional Neural Network (CNN) which embeds face images into feature vectors.
SOTA for Facial Expression Recognition on CK+
Extensive experiments show that our RAN and region biased loss largely improve the performance of FER with occlusion and variant pose.
The greater the distance, the more sensitive the feature map is to the facial feature unit.
This paper proposes two 3D-CNN methods: MicroExpSTCNN and MicroExpFuseNet, for spontaneous facial micro-expression recognition by exploiting the spatiotemporal information in CNN framework.
Deep learning based facial expression recognition (FER) has received a lot of attention in the past few years.
We present a new end-to-end network architecture for facial expression recognition with an attention model.