Skip to content

This repository is an implementation of "Exploiting deep residual networks for human action recognition from skeletal data" by Huy-Hieu Pham, Louahdi Khoudour, Alain Crouzil, Pablo Zegers, and Sergio A. Velastin. You can train deep Residual Networks on skeletal data for action recognition tasks from scratch.

Notifications You must be signed in to change notification settings

huyhieupham/Improved-ResNet-Action-Recognition-Skeletal-Data

Repository files navigation

Improved ResNet Action Recognition Skeletal Data

Introduction

This repository is an implementation of "Exploiting deep residual networks for human action recognition from skeletal data" by Huy-Hieu Pham, Louahdi Khoudour, Alain Crouzil, Pablo Zegers, and Sergio A. Velastin. You can train deep Residual Networks on skeletal data for action recognition tasks from scratch.

Training from scratch

Before running the experiments, you need to download and compile VLFeat, and MatConvNet. Then, start to train ResNets on GPU by the following commande:

experiments([20 32 44 56 110], 'resnet', 'gpus', [1]);

Experimental results

image-1

Learning curves on KARD dataset. Dashed lines denote training errors (%), bold lines denote test errors (%).

Learning curves on MSR Action3D dataset. Dashed lines denote training errors (%), bold lines denote test errors (%).

Learning curves on NTU-RGB+D dataset. Dashed lines denote training errors (%), bold lines denote test errors (%).

About

This repository is an implementation of "Exploiting deep residual networks for human action recognition from skeletal data" by Huy-Hieu Pham, Louahdi Khoudour, Alain Crouzil, Pablo Zegers, and Sergio A. Velastin. You can train deep Residual Networks on skeletal data for action recognition tasks from scratch.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages