FaceSleuth-R: Adaptive Orientation-Aware Attention for Robust Micro-Expression Recognition
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917068418318336 |
|---|---|
| author | Wu, Linquan Jiang, Tianxiang Yang, Haoyu Duan, Wenhao Lin, Shaochao Wang, Zixuan Fang, Yini Keung, Jacky |
| author_facet | Wu, Linquan Jiang, Tianxiang Yang, Haoyu Duan, Wenhao Lin, Shaochao Wang, Zixuan Fang, Yini Keung, Jacky |
| contents | Micro-expression recognition (MER) has achieved impressive accuracy in controlled laboratory settings. However, its real-world applicability faces a significant generalization cliff, severely hindering practical deployment due to poor performance on unseen data and susceptibility to domain shifts. Existing attention mechanisms often overfit to dataset-specific appearance cues or rely on fixed spatial priors, making them fragile in diverse environments. We posit that robust MER requires focusing on quasi-invariant motion orientations inherent to micro-expressions, rather than superficial pixel-level features. To this end, we introduce \textbf{FaceSleuth-R}, a framework centered on our novel \textbf{Single-Orientation Attention (SOA)} module. SOA is a lightweight, differentiable operator that enables the network to learn layer-specific optimal orientations, effectively guiding attention towards these robust motion cues. Through extensive experiments, we demonstrate that SOA consistently discovers a universal near-vertical motion prior across diverse datasets. More critically, FaceSleuth-R showcases superior generalization in rigorous Leave-One-Dataset-Out (LODO) protocols, significantly outperforming baselines and state-of-the-art methods when confronted with domain shifts. Furthermore, our approach establishes \textbf{state-of-the-art results} across several benchmarks. This work highlights adaptive orientation-aware attention as a key paradigm for developing truly generalized and high-performing MER systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_02695 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FaceSleuth-R: Adaptive Orientation-Aware Attention for Robust Micro-Expression Recognition Wu, Linquan Jiang, Tianxiang Yang, Haoyu Duan, Wenhao Lin, Shaochao Wang, Zixuan Fang, Yini Keung, Jacky Computer Vision and Pattern Recognition Micro-expression recognition (MER) has achieved impressive accuracy in controlled laboratory settings. However, its real-world applicability faces a significant generalization cliff, severely hindering practical deployment due to poor performance on unseen data and susceptibility to domain shifts. Existing attention mechanisms often overfit to dataset-specific appearance cues or rely on fixed spatial priors, making them fragile in diverse environments. We posit that robust MER requires focusing on quasi-invariant motion orientations inherent to micro-expressions, rather than superficial pixel-level features. To this end, we introduce \textbf{FaceSleuth-R}, a framework centered on our novel \textbf{Single-Orientation Attention (SOA)} module. SOA is a lightweight, differentiable operator that enables the network to learn layer-specific optimal orientations, effectively guiding attention towards these robust motion cues. Through extensive experiments, we demonstrate that SOA consistently discovers a universal near-vertical motion prior across diverse datasets. More critically, FaceSleuth-R showcases superior generalization in rigorous Leave-One-Dataset-Out (LODO) protocols, significantly outperforming baselines and state-of-the-art methods when confronted with domain shifts. Furthermore, our approach establishes \textbf{state-of-the-art results} across several benchmarks. This work highlights adaptive orientation-aware attention as a key paradigm for developing truly generalized and high-performing MER systems. |
| title | FaceSleuth-R: Adaptive Orientation-Aware Attention for Robust Micro-Expression Recognition |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.02695 |