Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates

TLDR

Skeleton‑based action recognition has attracted significant research interest, with recent studies employing recurrent neural networks to capture temporal dependencies among 3D joint positions. This work extends such modeling to both spatial and temporal domains simultaneously to uncover hidden action‑related information in skeleton sequences. The authors propose a tree‑structured traversal of Kinect skeleton data, a trust‑gate LSTM that learns data reliability to modulate updates, and a multi‑modal feature fusion strategy within the LSTM unit. Experiments on seven challenging benchmark datasets confirm the method’s effectiveness for human action recognition.

Abstract

Skeleton-based human action recognition has attracted a lot of research attention during the past few years. Recent works attempted to utilize recurrent neural networks to model the temporal dependencies between the 3D positional configurations of human body joints for better analysis of human activities in the skeletal data. The proposed work extends this idea to spatial domain as well as temporal domain to better analyze the hidden sources of action-related information within the human skeleton sequences in both of these domains simultaneously. Based on the pictorial structure of Kinect's skeletal data, an effective tree-structure based traversal framework is also proposed. In order to deal with the noise in the skeletal data, a new gating mechanism within LSTM module is introduced, with which the network can learn the reliability of the sequential data and accordingly adjust the effect of the input data on the updating procedure of the long-term context representation stored in the unit's memory cell. Moreover, we introduce a novel multi-modal feature fusion strategy within the LSTM unit in this paper. The comprehensive experimental results on seven challenging benchmark datasets for human action recognition demonstrate the effectiveness of the proposed method.