Attentive 3D-Ghost Module for Dynamic Hand Gesture Recognition with Positive Knowledge Transfer

Table 12

Accuracy comparison of different multimodal fusion-based hand gesture recognition methods on the NVGesture dataset.

Method	Fused modalities	Accuracy
HOG + HOG2 [28]	RGB + depth	36.9
I3D [6]	RGB + depth	83.82
MTUT [5]	RGB + depth	85.48
Ours	RGB + depth	86.72

In the experiment results, the best recognition accuracy is in bold.