Li Kun ; Guo Dan ; Chen Guoliang ; Peng Xinge ; Wang Meng

Abstract

In this paper, we briefly introduce the solution of our team HFUT-VUT for theMicros-gesture Classification in the MiGA challenge at IJCAI 2023. Themicro-gesture classification task aims at recognizing the action category of agiven video based on the skeleton data. For this task, we propose a3D-CNNs-based micro-gesture recognition network, which incorporates a skeletaland semantic embedding loss to improve action classification performance.Finally, we rank 1st in the Micro-gesture Classification Challenge, surpassingthe second-place team in terms of Top-1 accuracy by 1.10%.