Facial Expression Recognition In-the-Wild with Deep Pre-Trained Models
Abstract
Facial expression recognition (FER) is challenging, when transiting from the laboratory to in-the-wild situations. In this paper, we present a general framework for the Learning from Synthetic Data Challenge in the 4th Affective Behavior Analysis In-The-Wild (ABAW4) competition, to learn as much knowledge as possible from synthetic faces with expressions. To cope with four problems in training robust deep FER models, including uncertain labels, class imbalance, mismatch between pretraining and downstream tasks, and incapability of a single model structure, our framework consists of four respective modules, which can be utilized for FER in-the-wild. Experimental results on the official validation set from the competition demonstrated that our proposed approach outperformed the baseline by a large margin.
Cite
Text
Li et al. "Facial Expression Recognition In-the-Wild with Deep Pre-Trained Models." European Conference on Computer Vision Workshops, 2022. doi:10.1007/978-3-031-25075-0_14Markdown
[Li et al. "Facial Expression Recognition In-the-Wild with Deep Pre-Trained Models." European Conference on Computer Vision Workshops, 2022.](https://mlanthology.org/eccvw/2022/li2022eccvw-facial/) doi:10.1007/978-3-031-25075-0_14BibTeX
@inproceedings{li2022eccvw-facial,
title = {{Facial Expression Recognition In-the-Wild with Deep Pre-Trained Models}},
author = {Li, Siyang and Xu, Yifan and Wu, Huanyu and Wu, Dongrui and Yin, Yingjie and Cao, Jiajiong and Ding, Jingting},
booktitle = {European Conference on Computer Vision Workshops},
year = {2022},
pages = {181-190},
doi = {10.1007/978-3-031-25075-0_14},
url = {https://mlanthology.org/eccvw/2022/li2022eccvw-facial/}
}