“…The methods proposed in this paper were compared with ML-KNN [13], ML-RBF [14], Kosti et al [11], Lee et al [21], Zhang et al [22], ML-GCN [27], ESRs [8], Ilyes et al [23], Q2L [15], LGLM [28], RCL-Net [9], ML-Decoder [16], SAML [26], FLNet [29], BHARAT [10], and LFPLM [17]. The comparison results of mAP and JC are shown in Table 5 and Figure 9.…”