The paper describes our proposed methodology for the seven basic expression classification track of Affective Behavior Analysis in-the-wild (ABAW) Competition 2021. In this task, facial expression recognition (FER) methods aim to classify the correct expression category from a diverse background, but there are several challenges. First, to adapt the model to in-the-wild scenarios, we use the knowledge from pre-trained large-scale face recognition data. Second, we propose an ensemble model with a convolution neural network (CNN), a CNN-recurrent neural network (CNN-RNN), and a CNN-Transformer (CNN-Transformer), to incorporate both spatial and temporal information. Our ensemble model achieved F1 as 0.4133, accuracy as 0.6216 and final metric as 0.4821 on the validation set.
@article{arxiv.2107.05160,
title = {Spatial and Temporal Networks for Facial Expression Recognition in the Wild Videos},
author = {Shuyi Mao and Xinqi Fan and Xiaojiang Peng},
journal= {arXiv preprint arXiv:2107.05160},
year = {2021}
}