Release Agreement for "NTU RGB+D" and "NTU RGB+D 120" Action Recognition Datasets

"NTU RGB+D" and "NTU RGB+D 120" action recognition datasets consist of RGB videos, depth map sequences, 3D skeletal data, and infrared videos. These two datasets are captured by 3 Microsoft Kinect v.2 cameras concurrently. The resolution of RGB videos are 1920×1080, depth maps and IR videos are all in 512×424, and 3D skeletal data contains the three dimensional locations of 25 major body joints, at each frame.

Both "NTU RGB+D" and "NTU RGB+D 120" action recognition datasets are the property of the Rapid-Rich Object Search (ROSE) Lab at the Nanyang Technological University, Singapore.

Usage for Academic Reseach

Both "NTU RGB+D" and "NTU RGB+D 120" are released for academic research only, and are free to researchers from educational or research institutes for non-commercial purposes.

Terms and Conditions:

The use of these two datasets is governed by the following terms and conditions:

Related Publications

All publications using "NTU RGB+D" or "NTU RGB+D 120" Action Recognition Database should include the following acknowledgement: “(Portions of) the research in this paper used the NTU RGB+D (or NTU RGB+D 120) Action Recognition Dataset made available by the ROSE Lab at the Nanyang Technological University, Singapore.”

Furthermore, these publications should cite the following references:
Amir Shahroudy, Jun Liu, Tian-Tsong Ng, Gang Wang, "NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis", IEEE Conference on Computer Vision and Pattern Recognition, 2016 [PDF] [bibtex].
Jun Liu, Amir Shahroudy, Mauricio Perez, Gang Wang, Ling-Yu Duan, Alex C. Kot, "NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding", IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019. [PDF] [bibtex].

Requestor may also wish to cite the following related work:

By completing this online form, you have accepted the above terms & conditions and agree to include the above acknowledgements in your publications.

We need to validate all requests. Therefore we require you to provide full name of organisation and affiliated email address.

Project Title
Requester's Details
First Name Last Name
Designation example: post-graduate student, research associate, research fellow, faculty, system analyst, data scientist
Email Address
Supervisor's Details (Leave all fields below blank if Supervisor is same as Requester)
First Name Last Name
Email Address
Designation example: research fellow, faculty, lead data scientist, chief data officer