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 6 CAS(ME)2数据库上MesNet与已有方法的性能对比

Tab.6 Performance comparison among MesNet and existing methods on CAS(ME)2

方法 Precision Recall F-Measure Accuracy AUC MDMD[32] 0.352 1 0.319 0 0.334 8 0.735 5 0.654 8 LBP[18] − − − − 0.663 9 MesNet 0.960 2 0.996 2 0.977 9 0.957 0 0.785 3