English

Generating Image Sequence from Description with LSTM Conditional GAN

Computer Vision and Pattern Recognition 2018-06-11 v1

Abstract

Generating images from word descriptions is a challenging task. Generative adversarial networks(GANs) are shown to be able to generate realistic images of real-life objects. In this paper, we propose a new neural network architecture of LSTM Conditional Generative Adversarial Networks to generate images of real-life objects. Our proposed model is trained on the Oxford-102 Flowers and Caltech-UCSD Birds-200-2011 datasets. We demonstrate that our proposed model produces the better results surpassing other state-of-art approaches.

Keywords

Cite

@article{arxiv.1806.03027,
  title  = {Generating Image Sequence from Description with LSTM Conditional GAN},
  author = {Xu Ouyang and Xi Zhang and Di Ma and Gady Agam},
  journal= {arXiv preprint arXiv:1806.03027},
  year   = {2018}
}

Comments

Accepted by ICPR 2018

R2 v1 2026-06-23T02:23:20.331Z