Table 2.

Recognition accuracies of methods on RGB datasets. The superscript D indicates a deep learning-based method.

Methods	Year	Hollywood2	HMDB51	Olympic Sports	UCF50	UCF101	Kinetic
[82]D	2018					86.4%
[46]D	2018						81.5%
[61]D	2018	68.1%		94%
[96]D	2017		78.7%			97.1%
[89]D	2017		63.5%			93.2%
[86]D	2017		75%			95.3%
[102]D	2017						79%
[90]D	2017		74.8%			95.8%
[88]D	2017		80.2%			97.9%
[95]D	2016		55.2%			85.4%
[85]D	2016		69.4%			94.2%
[63]	2016	66.8%	60.1%	90.4%	91.7%	86%
[29]D	2016			94.8%		78.86%
[84]D	2016		65.4%			92.5%
[45]D	2015		63.2%			91.5%
[109]	2016		61.7%			88.3%
[110]	2015	68%	65.1%	91.4%	94.4%	89.1%
[20]D	2015		49.9%			85.2%	79.5%
[40]	2015	70%	61.8%
[57]	2014		37.3%	86.04%	70.1%
[50]	2014		57.2%			85.9%
[19]	2014		59.4%			88%	81.3%
[62]	2014	54.4%	41.3%	85.5%
[100]	2013		27.02%		68.20%
[111]	2013	49.3%