Table 6 CMC Rank-1 accuracy for different feature combination strategies.
From: A CNN-RNN Siamese framework with multi-level aggregation for video-based person re-identification
Combination method | iLIDS-VID CMC Rank 1 | PRID-2011 CMC Rank 1 |
|---|---|---|
ident alone | 31% | 55% |
low alone | 10% | 34% |
high alone | 5% | 12% |
high + low | 10% | 31% |
ident + low | 49% | 54% |
ident + high | 51% | 68% |
ident + high + low | 57% | 76% |
