. 2019 Apr;53:123–131. doi: 10.1016/j.media.2019.01.011

Table 1.

Quantitative analysis results obtained by our approach when trained with different target domains on case study CS₁ and CS₂.

		$T_{s y n}^{H R}$	$T_{o r i g}^{H R}$	$T_{r e s}^{H R}$	$T_{n a t}^{H R}$
CS₁	$S S I M_{\hat{H R}}$	0.90  ±  0.03	0.91  ±  0.03	0.87  ±  0.04	0.86  ±  0.03
	$▵ GC F_{\hat{HR}}$	0.01  ±  0.29	0.38  ±  0.27	−0.13  ±  0.40	0.66  ±  0.31
	$Δ G C F_{I^{L R}}$	−0.28  ±  0.19	0.09  ±  0.19	−0.42  ±  0.31	0.38  ±  0.26
	Tot_cs	0.52	0.63	0.44	0.64
CS₂	$S S I M_{\hat{H R}}$	0.91  ±  0.03	0.91  ±  0.03	0.87  ±  0.03	0.86  ±  0.04
	$▵ GC F_{\hat{HR}}$	−0.10  ±  0.36	0.24  ±  0.35	−0.26  ±  0.40	0.51  ±  0.40
	$Δ G C F_{I^{L R}}$	−0.33  ±  0.21	0.01  ±  0.18	−0.49  ±  0.28	0.28  ±  0.25
	Tot_cs	0.49	0.59	0.41	0.61