Skip to main content

Advertisement

Table 3 Comparison with the state-of-the-art methods on the CUHK03 dataset using the multi-shot setting

From: Learning deep features from body and parts for person re-identification in camera networks

Method Rank-1 Rank-5 Rank-10 mAP
S-LSTM [33] 57.3 80.1 88.3 46.3
Gate-SCNN [34] 68.1 88.1 94.6 58.8
Part-based features 20.6 42.8 55.5 19.8
Body-based features 81.0 90.3 95.0 76.2
DFBP 81.8 91.8 95.7 78.0
  1. The data in italics are the best result in each evaluation protocol