A Low-Dimensional Radial Silhouette-Based Feature for Fast Human Action Recognition Fusing Multiple Views

Table 5

Comparison of recognition rates and speeds obtained on the MuHAVi-8 dataset with other state-of-the-art approaches.

Approach	LOSO	LOAO	FPS
Singh et al. [8]	97.8%	76.4%	N/A
Martínez-Contreras et al. [18]	98.4%	—	N/A
Eweiwi et al. [17]	98.5%	85.3%	N/A
Cheema et al. [15]	95.6%	83.1%	56
Chaaraoui et al. [5]	97.1%	88.2%	81
Chaaraoui et al. [6]	98.5%	95.6%	66
Our approach	100%	97.1%	94