Micro-expression Recognition Based on Dual-branch Feature Extraction and Fusion

TL;DR

This paper introduces a dual-branch neural network with attention for micro-expression recognition, improving accuracy by effectively extracting and fusing features to handle subtle and transient expressions.

Contribution

It presents a novel dual-branch network with residual and Inception modules, along with an adaptive fusion mechanism, enhancing micro-expression recognition performance.

Findings

Achieved 74.67% accuracy on CASME II dataset

Outperformed LBP-TOP by 11.26%

Outperformed MSMMT by 3.36%

Abstract

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.