Covariance Pooling For Facial Expression Recognition

13 May 2018Dinesh AcharyaZhiwu HuangDanda PaudelLuc Van Gool

Classifying facial expressions into different categories requires capturing regional distortions of facial landmarks. We believe that second-order statistics such as covariance is better able to capture such distortions in regional facial fea- tures... (read more)

PDF Abstract
Task Dataset Model Metric name Metric value Global rank Compare
Facial Expression Recognition Real-World Affective Faces Covariance Pooling Accuracy 87.0% # 1
Facial Expression Recognition Static Facial Expressions in the Wild Covariance Pooling Accuracy 58.14% # 1