Enhancing Facial Expression Recognition through Dual-Direction Attention Mixed Feature Networks and CLIP: Application to 8th ABAW Challenge
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_ | 1866915199913558016 |
|---|---|
| author | Cabacas-Maso, Josep Ortega-Beltrán, Elena Benito-Altamirano, Ismael Ventura, Carles |
| author_facet | Cabacas-Maso, Josep Ortega-Beltrán, Elena Benito-Altamirano, Ismael Ventura, Carles |
| contents | We present our contribution to the 8th ABAW challenge at CVPR 2025, where we tackle valence-arousal estimation, emotion recognition, and facial action unit detection as three independent challenges. Our approach leverages the well-known Dual-Direction Attention Mixed Feature Network (DDAMFN) for all three tasks, achieving results that surpass the proposed baselines. Additionally, we explore the use of CLIP for the emotion recognition challenge as an additional experiment. We provide insights into the architectural choices that contribute to the strong performance of our methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_12260 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhancing Facial Expression Recognition through Dual-Direction Attention Mixed Feature Networks and CLIP: Application to 8th ABAW Challenge Cabacas-Maso, Josep Ortega-Beltrán, Elena Benito-Altamirano, Ismael Ventura, Carles Computer Vision and Pattern Recognition I.4 We present our contribution to the 8th ABAW challenge at CVPR 2025, where we tackle valence-arousal estimation, emotion recognition, and facial action unit detection as three independent challenges. Our approach leverages the well-known Dual-Direction Attention Mixed Feature Network (DDAMFN) for all three tasks, achieving results that surpass the proposed baselines. Additionally, we explore the use of CLIP for the emotion recognition challenge as an additional experiment. We provide insights into the architectural choices that contribute to the strong performance of our methods. |
| title | Enhancing Facial Expression Recognition through Dual-Direction Attention Mixed Feature Networks and CLIP: Application to 8th ABAW Challenge |
| topic | Computer Vision and Pattern Recognition I.4 |
| url | https://arxiv.org/abs/2503.12260 |