This program (MTS-ConvNet) is designed to perform the real-time human activity recognition. The MTS-ConvNet includes a multi-temporal sampling module that allows the neural networks to consider multiple sampling intervals simultaneously.

This software is a PyTorch implementation of the proposed method. The original version of this program was written by Jaegyun Park. You can find detailed information in our manuscript.

Jaegyun Park, Won-Seon Lim, Dae-Won Kim, and Jaesung Lee, "Multitemporal Sampling Module for Real-Time Human Activity Recognition," IEEE Access, 2022

This program is available for download for non-commercial use, licensed under the GNU General Public License, which is allows its use for research purposes or other free software projects but does not allow its incorporation into any type of commerical software.

The repository contains following files.

• main.py, Python script file, containing the implementation for training and test phasees of the MTS-ConvNet,
• model.py, Python script file, containing the PyTorch implementation of the MTS-ConvNet,
• utils.py, Python script file, containing a collection of small Python functions,
• README.md.