RGB-D Human Action Recognition of Deep Feature Enhancement and Fusion Using Two-Stream ConvNet

Table 7

Comparison of SV-GCN with other state-of-the-art methods.

Network	CS (top 1)	CV (top 1)
DSSCA-SSLM [32]	74.9%
TCN [33]	74.3%	83.10%
GCA-LSTM [16]	76.1%	84.0%
Skelemotion [34]	76.5%	84.7%
Slowfastnet [12]	80.25%	93.74%
St-gcn [18]	81.5%	88.3%
LSTM-CNN [35]	82.9%	91.0%
Two-stream CNN [36]	83.2%	89.3%
DPRL+GCNN [19]	83.5%	89.8%
Cross-attention [21]	84.2%	89.3%
SV-GCN (ours)	85.51%	94.15%