Knowledge Network Node
Journal of Beijing University of Aeronautics and Astronautics. Core
Version after Accepted▼
(Accepted Version) Online First Publishing Date: 2022-02-07 14:57:51Online First Certificate Download

Text-to-image synthesis based on modified deep convolutional generative adversarial networkChinese Full TextEnglish Full Text (MT)

LI Yunhong;ZHU Mianyun;REN Jie;SU Xueping;ZHOU Xiaoji;YU Huikang;

Abstract: When high-dimensional texts are adopted as input， images generated by the previously proposed deep convolutional generative adversarial network （DCGAN） model usually suffer from distortions and structure degradation due to the sparsity of texts， which seriously poses a negative impact on the generative performance. To address this issue， an improved modified deep convolutional generative adversarial network （CA-DCGAN） model is proposed. Technically， a deep convolutional network and a recurrent t... More
Keywords：

deep convolutional generative adversarial network; text-to-image synthesis; text embedding representation; conditional augmentation; KL regularization term;

  • DOI：

    10.13700/j.bh.1001-5965.2021.0588

  • Series：

    (I) Electronic Technology ＆ Information Science

  • Subject：

    Computer Software and Application of Computer; Automation Technology

  • Classification Code：

    TP391.41;TP183

CNKI exclusive online-first articles is prohibited to reprint and excerpt without permission.

Corrigendum statement
Tips: Please download CAJViewer to view CAJ format full text.

Download: 629 Pagecount: 10 Size: 805K

Related Literature
  • Similar Article
  • Reader Recommendation
  • Associated Author