Micro Expression Recognition via Dual-Stream Spatiotemporal Attention Network

Table 3

Comparison results of two model integration methods.

Metrics	DSTAN-Average			DSTAN-SVM
	SMIC	CASME	CASME II	SMIC	CASME	CASME II
Accuracy	0.73	0.74	0.71	0.77	0.78	0.75
Precision	0.75	0.73	0.74	0.79	0.76	0.77
Recall	0.73	0.72	0.63	0.77	0.75	0.70
F1-score	0.74	0.73	0.68	0.78	0.75	0.73