FaceSleuth-R: Adaptive Orientation-Aware Attention for Robust Micro-Expression Recognition

TL;DR

FaceSleuth-R introduces an adaptive orientation-aware attention mechanism focusing on invariant motion cues, significantly improving micro-expression recognition robustness and generalization across diverse datasets.

Contribution

The paper proposes the Single-Orientation Attention (SOA) module that learns optimal motion orientations, enhancing MER models' robustness to domain shifts and dataset variations.

Findings

SOA discovers a near-vertical motion prior across datasets

FaceSleuth-R outperforms state-of-the-art methods in LODO protocols

Achieves state-of-the-art results on multiple MER benchmarks

Abstract

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.