基于过渡帧概念训练的微表情检测深度网络

付晓峰,牛力,胡卓群,李建军,吴卿

Deep micro-expression spotting network training based on concept of transition frame

Xiao-feng FU,Li NIU,Zhuo-qun HU,Jian-jun LI,Qing WU

表 5 SMIC-E-HS数据库上MesNet与已有方法的性能对比

Tab.5 Performance comparison among MesNet and existing methods on SMIC-E-HS

方法 Precision Recall F-Measure Accuracy AUC HOOF[30] − − − − 0.694 1 LBP[30] − − − − 0.833 2 Riesz Pyramid[31] − − − − 0.898 0 CFD[28] − − − − 0.970 6 MesNet 0.969 0 0.988 5 0.978 7 0.959 6 0.933 8