Two-Stream Auto-Encoder Network for Unsupervised Skeleton-Based Action Recognition  

作　　者：WANG Gang GUAN Yaonan LI Dewei 王刚;管耀南;李德伟

机构地区：[1]Department of Automation,Shanghai Jiao Tong University,Shanghai 200240,China

出　　处：《Journal of Shanghai Jiaotong university(Science)》2025年第2期330-336,共7页上海交通大学学报(英文版)

摘　　要：Representation learning from unlabeled skeleton data is a challenging task.Prior unsupervised learning algorithms mainly rely on the modeling ability of recurrent neural networks to extract the action representations.However,the structural information of the skeleton data,which also plays a critical role in action recognition,is rarely explored in existing unsupervised methods.To deal with this limitation,we propose a novel twostream autoencoder network to combine the topological information with temporal information of skeleton data.Specifically,we encode the graph structure by graph convolutional network(GCN)and integrate the extracted GCN-based representations into the gate recurrent unit stream.Then we design a transfer module to merge the representations of the two streams adaptively.According to the characteristics of the two-stream autoencoder,a unified loss function composed of multiple tasks is proposed to update the learnable parameters of our model.Comprehensive experiments on NW-UCLA,UWA3D,and NTU-RGBD 60 datasets demonstrate that our proposed method can achieve an excellent performance among the unsupervised skeleton-based methods and even perform a similar or superior performance over numerous supervised skeleton-based methods.

关 键 词：representation learning skeleton-based action recognition unsupervised deep learning 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]