Skip to main content

Table 3 Results on Market-1501 [19] and CUHK03 [7] with different inputs in the identification network

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

Method

Market-1501

CUHK03

 

Rank-1

mAP

Rank-1

mAP

ResNet-50 (O)

73.69

51.48

71.5

75.8

ResNet-50 (W)

75.03

53.52

75.8

79.4

LEDF

80.77

61.34

84.6

86.9

  1. “O” and “W” indicate the original pedestrian images and the whole feature maps extracted from the original pedestrian images, respectively. The italicized part shows the best results