Papers › NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis

NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis

11 Apr 2016CVPR 2016 6arXiv:1604.02808archive 2025-07-28

Amir Shahroudy, Jun Liu, Tian-Tsong Ng, Gang Wang

Recent approaches in depth-based human activity analysis achieved outstanding performance and proved the effectiveness of 3D representation for classification of action classes. Currently available depth-based and RGB+D-based action recognition benchmarks have a number of limitations, including the lack of training samples, distinct class labels, camera views and variety of subjects. In this paper we introduce a large-scale dataset for RGB+D human action recognition with more than 56 thousand video samples and 4 million frames, collected from 40 distinct subjects. Our dataset contains 60 different action classes including daily, mutual, and health-related actions. In addition, we propose a new recurrent neural network structure to model the long-term temporal correlation of the features for each body part, and utilize them for better action classification. Experimental results show the advantages of applying deep learning methods over state-of-the-art hand-crafted features on the suggested cross-subject and cross-view evaluation criteria for our dataset. The introduction of this large scale dataset will enable the community to apply, develop and adapt various data-hungry learning techniques for the task of depth-based and RGB+D-based human activity analysis.

PaperPDFConference PDFCode

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

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

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

Tasks

3D Action RecognitionAction ClassificationAction RecognitionGeneral ClassificationSkeleton Based Action Recognition

Datasets

Introduced by this paper, per the archive.

NTU RGB+DNTU RGB+D 2D

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Skeleton Based Action Recognition CAD-120 P-LSTM (5-shot) Accuracy 68.1% #8 of 8 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D Part-aware LSTM Accuracy (CS) 62.93 #128 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D Part-aware LSTM Accuracy (CV) 70.27 #128 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D Deep LSTM Accuracy (CS) 60.7 #130 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D Deep LSTM Accuracy (CV) 67.3 #130 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 Part-Aware LSTM Accuracy (Cross-Setup) 26.3% #83 of 83 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 Part-Aware LSTM Accuracy (Cross-Subject) 25.5% #83 of 83 Archive leaderboard report
Skeleton Based Action Recognition Varying-view RGB-D Action-Skeleton P-LSTM Accuracy (AV I) 33% #4 of 7 Archive leaderboard report
Skeleton Based Action Recognition Varying-view RGB-D Action-Skeleton P-LSTM Accuracy (AV II) 50% #4 of 7 Archive leaderboard report
Skeleton Based Action Recognition Varying-view RGB-D Action-Skeleton P-LSTM Accuracy (CS) 60% #4 of 7 Archive leaderboard report
Skeleton Based Action Recognition Varying-view RGB-D Action-Skeleton P-LSTM Accuracy (CV I) 13% #4 of 7 Archive leaderboard report
Skeleton Based Action Recognition Varying-view RGB-D Action-Skeleton P-LSTM Accuracy (CV II) 33% #4 of 7 Archive leaderboard report
Skeleton Based Action Recognition Varying-view RGB-D Action-Skeleton LSTM Accuracy (AV I) 31% #7 of 7 Archive leaderboard report
Skeleton Based Action Recognition Varying-view RGB-D Action-Skeleton LSTM Accuracy (AV II) 68% #7 of 7 Archive leaderboard report
Skeleton Based Action Recognition Varying-view RGB-D Action-Skeleton LSTM Accuracy (CS) 56% #7 of 7 Archive leaderboard report
Skeleton Based Action Recognition Varying-view RGB-D Action-Skeleton LSTM Accuracy (CV I) 16% #7 of 7 Archive leaderboard report
Skeleton Based Action Recognition Varying-view RGB-D Action-Skeleton LSTM Accuracy (CV II) 31% #7 of 7 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.

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