MIDAS: Mixing Ambiguous Data with Soft Labels for Dynamic Facial Expression Recognition
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929736189476864 |
|---|---|
| author | Kawamura, Ryosuke Hayashi, Hideaki Takemura, Noriko Nagahara, Hajime |
| author_facet | Kawamura, Ryosuke Hayashi, Hideaki Takemura, Noriko Nagahara, Hajime |
| contents | Dynamic facial expression recognition (DFER) is an important task in the field of computer vision. To apply automatic DFER in practice, it is necessary to accurately recognize ambiguous facial expressions, which often appear in data in the wild. In this paper, we propose MIDAS, a data augmentation method for DFER, which augments ambiguous facial expression data with soft labels consisting of probabilities for multiple emotion classes. In MIDAS, the training data are augmented by convexly combining pairs of video frames and their corresponding emotion class labels, which can also be regarded as an extension of mixup to soft-labeled video data. This simple extension is remarkably effective in DFER with ambiguous facial expression data. To evaluate MIDAS, we conducted experiments on the DFEW dataset. The results demonstrate that the model trained on the data augmented by MIDAS outperforms the existing state-of-the-art method trained on the original dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_00202 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MIDAS: Mixing Ambiguous Data with Soft Labels for Dynamic Facial Expression Recognition Kawamura, Ryosuke Hayashi, Hideaki Takemura, Noriko Nagahara, Hajime Computer Vision and Pattern Recognition Dynamic facial expression recognition (DFER) is an important task in the field of computer vision. To apply automatic DFER in practice, it is necessary to accurately recognize ambiguous facial expressions, which often appear in data in the wild. In this paper, we propose MIDAS, a data augmentation method for DFER, which augments ambiguous facial expression data with soft labels consisting of probabilities for multiple emotion classes. In MIDAS, the training data are augmented by convexly combining pairs of video frames and their corresponding emotion class labels, which can also be regarded as an extension of mixup to soft-labeled video data. This simple extension is remarkably effective in DFER with ambiguous facial expression data. To evaluate MIDAS, we conducted experiments on the DFEW dataset. The results demonstrate that the model trained on the data augmented by MIDAS outperforms the existing state-of-the-art method trained on the original dataset. |
| title | MIDAS: Mixing Ambiguous Data with Soft Labels for Dynamic Facial Expression Recognition |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.00202 |