Generating Videos from Stories Using Conditional GAN

Takahiro Kozaki, Fumihiko Sakaue, Jun Sato

2024

Abstract

In this paper, we propose a method for generating videos that represent stories described in multiple sentences. While research on generating images and videos from single sentences has been advancing, the generation of videos from long stories written in multiple sentences has not been achieved. In this paper, we use adversarial learning to train pairs of multi-sentence stories and videos to generate videos that replicate the flow of the stories. We also introduce caption loss for generating more contextually aligned videos from stories.

Paper Citation

in Harvard Style

Kozaki T., Sakaue F. and Sato J. (2024). Generating Videos from Stories Using Conditional GAN. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP; ISBN 978-989-758-679-8, SciTePress, pages 671-677. DOI: 10.5220/0012405300003660

in Bibtex Style

@conference{visapp24,
author={Takahiro Kozaki and Fumihiko Sakaue and Jun Sato},
title={Generating Videos from Stories Using Conditional GAN},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2024},
pages={671-677},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012405300003660},
isbn={978-989-758-679-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP
TI - Generating Videos from Stories Using Conditional GAN
SN - 978-989-758-679-8
AU - Kozaki T.
AU - Sakaue F.
AU - Sato J.
PY - 2024
SP - 671
EP - 677
DO - 10.5220/0012405300003660
PB - SciTePress