Deep Learning for Person Reidentification Using Support Vector Machines

Table 6

Comparison of some other state-of-the-art results reported with VIPeR database. The cumulative matching scores (%) at ranks 1, 5, 10, and 20 are listed.

Method	VIPeR
	Top 1	Top 5	Top 10	Top 20
L2-norm	10.89	22.37	32.34	45.19
L1-norm	12.15	26.01	32.09	34.72
aPRDC	16.14	37.72	50.98	65.95
RankSVM	14.00	37.00	51.00	67.00
SSCDL	25.60	54.15	68.10	83.60
eSCD	26.31	46.61	58.86	72.77
PCCA	19.62	51.55	68.23	82.92
rPCCA	21.96	54.78	70.95	85.29
SVMML	30.07	63.17	77.44	88.08
MFA	32.24	65.99	79.66	90.64
KLFDA	32.33	65.78	79.72	90.95
Ours	34.15	67.86	80.95	90.63