Inspired by the recent advances in generative models, we introduce a human action generation model in order to generate a consecutive sequence of human motions to formulate novel actions. We propose a framework of an autoencoder and a generative adversarial network (GAN) to produce multiple and consecutive human actions conditioned on the initial state and the given class label. The proposed model is trained in an end-to-end fashion, where the autoencoder is jointly trained with the GAN. The model is trained on the NTU RGB+D dataset and we show that the proposed model can generate different styles of actions. Moreover, the model can successfully generate a sequence of novel actions given different action labels as conditions. The conventional human action prediction and generation models lack those features, which are essential for practical applications.
@article{arxiv.1805.10416,
title = {Human Action Generation with Generative Adversarial Networks},
author = {Mohammad Ahangar Kiasari and Dennis Singh Moirangthem and Minho Lee},
journal= {arXiv preprint arXiv:1805.10416},
year = {2018}
}