EURASIP Journal on Wireless Communications and Networking

Table 1 Comparison with state-of-the-art results on the Market-1501 dataset [19]

From: Learning local embedding deep features for person re-identification in camera networks

Method	Rank-1	mAP
DADM [44]	39.4	19.6
BoW+KISSME [19]	44.42	20.76
Multiregion CNN [45]	45.58	26.11
Fisher Network [46]	48.15	29.94
CAN [47]	48.24	24.43
LS [48]	51.90	26.35
DNS [49]	55.43	29.87
Gate Reid [9]	65.88	39.55
Verif-identif [10]	79.51	59.87
LEDF	80.77	61.34

The rank-1 accuracy and mAP are listed. The italicized part shows the best results

Back to article page