Papers › Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition

Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition

24 Jul 2016arXiv:1607.07043archive 2025-07-28

Jun Liu, Amir Shahroudy, Dong Xu, Gang Wang

3D action recognition - analysis of human actions based on 3D skeleton data - becomes popular recently due to its succinctness, robustness, and view-invariant representation. Recent attempts on this problem suggested to develop RNN-based learning methods to model the contextual dependency in the temporal domain. In this paper, we extend this idea to spatio-temporal domains to analyze the hidden sources of action-related information within the input data over both domains concurrently. Inspired by the graphical structure of the human skeleton, we further propose a more powerful tree-structure based traversal method. To handle the noise and occlusion in 3D skeleton data, we introduce new gating mechanism within LSTM to learn the reliability of the sequential input data and accordingly adjust its effect on updating the long-term context information stored in the memory cell. Our method achieves state-of-the-art performance on 4 challenging benchmark datasets for 3D human action analysis.

PaperPDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Action RecognitionAction AnalysisAction RecognitionSkeleton Based Action RecognitionTemporal Action Localization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Skeleton Based Action Recognition NTU RGB+D Spatio-Temporal LSTM Accuracy (CS) 69.2 #127 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D Spatio-Temporal LSTM Accuracy (CV) 77.7 #127 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D ST-LSTM Accuracy (CS) 61.70 #129 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D ST-LSTM Accuracy (CV) 75.50 #129 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 Spatio-Temporal LSTM Accuracy (Cross-Setup) 57.9% #80 of 83 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 Spatio-Temporal LSTM Accuracy (Cross-Subject) 55.7% #80 of 83 Archive leaderboard report
Skeleton Based Action Recognition SBU / SBU-Refine ST-LSTM + Trust Gate Accuracy 93.3% #9 of 9 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

LSTMSigmoid ActivationTanh Activation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections