Micro Expression Recognition via Dual-Stream Spatiotemporal Attention Network

Table 1

Comparison of single-stream with dual-stream network (F1 : F1-score).

Method	SMIC		CASME		CASME II
	Accuracy	F1	Accuracy	F1	Accuracy	F1
STAN-A	0.683	0.672	0.669	0.627	0.602	0.559
STMN-A	0.652	0.649	0.651	0.612	0.638	0.607
DSTAN	0.774	0.778	0.779	0.752	0.752	0.728