Learning attention for object tracking with adversarial learning network

EURASIP Journal on Image and Video Processing

Table 2 Tracking performance and frame per second (FPS) of the state-of-the-art approaches on OTB-100 benchmark. “-“denotes invalid state; the bold fonts indicate the best results

Algorithms	Techinique	Code type	Precision	Success rate	FPS
Ours	Deep Learning	MATLAB & C++	0.919	0.719	14.8
MUSTer	Correlation Filter	MATLAB & C++	0.774	0.575	6.1
DSST	Correlation Filter	MATLAB & C++	0.693	0.52	35.5
SiamFC	Deep Learning	MATLAB & C++	0.771	0.691	31.2
CCOT	Correlation Filter	MATLAB & C++	0.691	0.682	2.6
MDNet	Deep Learning	MATLAB	0.788	0.678	1.4
SIT	Deep Learning	MATLAB	0.732	0.575	225.5
PCOM		MATLAB & C++	-	-	27.6
KCF	Correlation Filter	MATLAB	0.690	0.477	124.1
CN		MATLAB & C++			65.4
Struck	SVM	C++	-	-	9.6
TLD	Boosting	MATLAB & C++	-	-	2.7
MIL	Boosting	C++	-	-	31.8