Evaluation of Self-taught Learning-based Representations for Facial Emotion Recognition
This work addresses facial emotion recognition for applications like human-computer interaction, but it is incremental as it builds on existing unsupervised feature learning methods.
The paper tackled facial emotion recognition by generating diverse unsupervised representations through self-taught learning, and found that these methods outperformed state-of-the-art approaches on Jaffe and Cohn-Kanade datasets using a leave-one-subject-out protocol.
This work describes different strategies to generate unsupervised representations obtained through the concept of self-taught learning for facial emotion recognition (FER). The idea is to create complementary representations promoting diversity by varying the autoencoders' initialization, architecture, and training data. SVM, Bagging, Random Forest, and a dynamic ensemble selection method are evaluated as final classification methods. Experimental results on Jaffe and Cohn-Kanade datasets using a leave-one-subject-out protocol show that FER methods based on the proposed diverse representations compare favorably against state-of-the-art approaches that also explore unsupervised feature learning.