Ensemble of Multi-Task Learning Networks for Facial Expression Recognition In-the-Wild with Learning from Synthetic Data
Abstract
Facial expression recognition in-the-wild is essential for various interactive computing applications. Especially, “Learning from Synthetic Data” is an important topic in the facial expression recognition task. In this paper, we propose a multi-task learning-based facial expression recognition approach where emotion and appearance perspectives of facial images are jointly learned. We also present our experimental results on validation and test set of the LSD challenge introduced in the 4th affective behavior analysis in-the-wild competition. Our method achieved the mean F1 score of 71.82 on the validation and 35.87 on the test set, ranking third place on the final leaderboard.
Cite
Text
Jeong et al. "Ensemble of Multi-Task Learning Networks for Facial Expression Recognition In-the-Wild with Learning from Synthetic Data." European Conference on Computer Vision Workshops, 2022. doi:10.1007/978-3-031-25075-0_5Markdown
[Jeong et al. "Ensemble of Multi-Task Learning Networks for Facial Expression Recognition In-the-Wild with Learning from Synthetic Data." European Conference on Computer Vision Workshops, 2022.](https://mlanthology.org/eccvw/2022/jeong2022eccvw-ensemble/) doi:10.1007/978-3-031-25075-0_5BibTeX
@inproceedings{jeong2022eccvw-ensemble,
title = {{Ensemble of Multi-Task Learning Networks for Facial Expression Recognition In-the-Wild with Learning from Synthetic Data}},
author = {Jeong, Jae-Yeop and Hong, Yeong-Gi and Hong, Sumin and Oh, Jiyeon and Jung, Yuchul and Kim, Sang-Ho and Jeong, Jin-Woo},
booktitle = {European Conference on Computer Vision Workshops},
year = {2022},
pages = {60-75},
doi = {10.1007/978-3-031-25075-0_5},
url = {https://mlanthology.org/eccvw/2022/jeong2022eccvw-ensemble/}
}