信号处理2025，Vol.41Issue(2)：267-278,12.DOI:10.12466/xhcl.2025.02.006
基于视觉Transformer的运动特征选择融合微表情识别算法
Micro-Expression Recognition Algorithm Based on a Visual Transformer with Motion Feature Selection and Fusion
摘要
Abstract
Micro-expression recognition(MER)aims to reveal the hidden,true emotions of targets and is therefore of great significance in fields such as human-computer interaction,psychology,and security.However,micro-expressions occurred with weak intensity,transience of duration,and long-range dependence between facial motion units,making it difficult for traditional convolutional neural networks to effectively represent the inherent dynamic features of micro-expressions.In response to these issues,this paper proposes a micro-expression recognition algorithm based on a visual transformer and motion feature selection.The proposed algorithm first computes horizontal and vertical optical flow mo-tion maps to describe facial motion using the TV-L1 and then encodes the relationships between motion units using a vi-sual transformer.Next,this study introduced a feature selection and fusion module(FSFM)to effectively capture the key local information of micro-expressions and integrated a spatial consistency attention module(SCAM)to ensure spa-tial distribution consistency among different motion patterns.Finally,a cross attention fusion module(CAFM)was in-troduced to enhance micro-expression semantic information.Extensive experiments were conducted on three benchmark datasets,namely,MMEW,CASMEII,and SAMM.The proposed method achieved recognition accuracy values of 67.8%,73.3%,and 68.7%,respectively.Compared with existing methods,the proposed algorithm demonstrates a sig-nificant improvement in accuracy in micro-expression recognition tasks,thereby further validating the effectiveness and superiority of the method.关键词
微表情识别/特征选择与融合/交叉注意力机制/视觉TransformerKey words
micro-expression recognition/feature selection and fusion/cross-attention mechanism/vision transformer分类
信息技术与安全科学引用本文复制引用
杜含月,张鹏,林强,李晓桐,徐森,贲晛烨..基于视觉Transformer的运动特征选择融合微表情识别算法[J].信号处理,2025,41(2):267-278,12.基金项目
国家自然科学基金(62322111,62271289,62076215) （62322111,62271289,62076215）
山东省优秀青年基金项目(ZR2022YQ60) （ZR2022YQ60）
山东省泰山学者人才工程项目(tsqn202306064) （tsqn202306064）
济南市2023年人才发展专项资金"新高校20条"扶持项目(202333035) （202333035）
山东省杰出青年基金项目(ZR2024JQ007)The National Natural Science Foundation of China(62322111,62271289,62076215) （ZR2024JQ007）
The Natural Science Fund for Outstanding Young Scholars of Shandong Province(ZR2022YQ60) （ZR2022YQ60）
The Research Fund for the Taishan Scholar Project of Shandong Province(tsgn202306064) （tsgn202306064）
Jinan"20 Terms of New Universities"Funding Project(202333035) （202333035）
The Natural Science Fund for Distinguished Young Scientists of Shandong Province(ZR2024JQ007) （ZR2024JQ007）
