Low-Rank and Sparse Based Deep-Fusion Convolutional Neural Network for Crowd Counting

Table 4

Performance comparison of crowd counting methods for the WorldExpo10 dataset.

Network	The WorldExpo10 dataset
	MAE	MSE	MRE
ACF [3]	41.79	52.36	79.56
LBP + RR	31.01	44.53	80.97
LBP + LSSVM	28.86	42.79	74.69
Gabor + LSSVM	33.61	46.69	84.53
Patch-CNN [11]	12.90	9.62	40.96
MCNN [12]	11.60	16.78	36.50
Patch-count CNN [25]	12.56	17.75	35.21
Patch-multitask CNN [26]	10.56	14.86	30.76
TSCCM [27]	13.18	18.76	36.38
Long-short CNN [13]	13.93	19.70	41.71
Hydra-CNN [14]	8.76	11.83	25.25
Deep-fusion network	10.48	15.04	28.99
Fusion + RR	30.43	41.17	152.28
Fusion + LSSVM	13.81	16.60	67.59
LFCNN	7.78	11.57	20.25