Dynamic Gesture Recognition Based on Two-Scale 3-D-ConvNeXt

As a straightforward method for human-machine interaction, gesture recognition is vital in many practical applications. However, effectively extracting spatiotemporal information from video is still a fundamental problem and designing an accurate and efficient network is a feasible solution. The ConvNeXt, renowned for its superior still image processing capabilities, is chosen as the basis of this work. Then, the network is extended to a 3-D pattern for dynamic data and a two-scale convolution kernel is introduced to focus on the hand region. Therefore, a novel two-scale 3-D-ConvNeXt network (TS3C-Net) is established. Furthermore, the Mixup, Cutmix data augmentation, and label smoothing regularization are also applied to enhance the performance further. The experiments show that the accuracy of the proposed TS3C-Net achieves 95.36%, 97.1%, and 87.55% on EgoGesture, Jester, and NVGesture datasets, respectively.