Fig. 7
From: A CNN-RNN Siamese framework with multi-level aggregation for video-based person re-identification
Impact of recurrent depth on person re-ID accuracy. Rank-1 accuracy across 1–4 layers for SimpleRNN, LSTM, and GRU on (a) PRID-2011 and (b) iLIDS-VID. The visualization illustrates that GRU achieves the best accuracy at shallow depths, while LSTM suffers from pronounced degradation as layers increase.
