Micro-expression Recognition Based on Dual-branch Feature Extraction and Fusion
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917299648200704 |
|---|---|
| author | Zhang, Mingjie Li, Bo Liu, Wanting Cui, Hongyan Li, Yue Li, Qingwen Li, Hong Gao, Ge |
| author_facet | Zhang, Mingjie Li, Bo Liu, Wanting Cui, Hongyan Li, Yue Li, Qingwen Li, Hong Gao, Ge |
| contents | Micro-expressions, characterized by transience and subtlety, pose challenges to existing optical flow-based recognition methods. To address this, this paper proposes a dual-branch micro-expression feature extraction network integrated with parallel attention. Key contributions include: 1) a residual network designed to alleviate gradient anishing and network degradation; 2) an Inception network constructed to enhance model representation and suppress interference from irrelevant regions; 3) an adaptive feature fusion module developed to integrate dual-branch features. Experiments on the CASME II dataset demonstrate that the proposed method achieves 74.67% accuracy, outperforming LBP-TOP (by 11.26%), MSMMT (by 3.36%), and other comparative methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_23950 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Micro-expression Recognition Based on Dual-branch Feature Extraction and Fusion Zhang, Mingjie Li, Bo Liu, Wanting Cui, Hongyan Li, Yue Li, Qingwen Li, Hong Gao, Ge Computer Vision and Pattern Recognition Artificial Intelligence Micro-expressions, characterized by transience and subtlety, pose challenges to existing optical flow-based recognition methods. To address this, this paper proposes a dual-branch micro-expression feature extraction network integrated with parallel attention. Key contributions include: 1) a residual network designed to alleviate gradient anishing and network degradation; 2) an Inception network constructed to enhance model representation and suppress interference from irrelevant regions; 3) an adaptive feature fusion module developed to integrate dual-branch features. Experiments on the CASME II dataset demonstrate that the proposed method achieves 74.67% accuracy, outperforming LBP-TOP (by 11.26%), MSMMT (by 3.36%), and other comparative methods. |
| title | Micro-expression Recognition Based on Dual-branch Feature Extraction and Fusion |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2602.23950 |