Skeleton-based Human Action Recognition via Large-kernel Attention Graph Convolutional Network

• Published in: IEEE transactions on visualization and computer graphics Vol. 29; no. 5; pp. 2575 - 2585
• Main Authors: Liu, Yanan, Zhang, Hao, Li, Yanqiu, He, Kangjian, Xu, Dan
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.05.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: action recognition; Adaptation models; Artificial neural networks; Background noise; Computer architecture; Convolution; graph convolution; Graphical representations; Human activity recognition; human skeleton; Joints; Kernel; Kernels; large kernels; Modelling; Skeleton; Task analysis; Topology; Virtual reality

The skeleton-based human action recognition has broad application prospects in the field of virtual reality, as skeleton data is more resistant to data noise such as background interference and camera angle changes. Notably, recent works treat the human skeleton as a non-grid representation, e.g., s...