InDecGAN: Learning to Generate Complex Images From Captions via Independent Object-Level Decomposition and Enhancement

Author:

Cheng Jun1ORCID,Wu Fuxiang1ORCID,Liu Liu2ORCID,Zhang Qieshi1ORCID,Rutkowski Leszek3ORCID,Tao Dacheng2ORCID

Affiliation:

1. CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Beijing, China

2. School of Computer Science, Faculty of Engineering, The University of Sydney, Darlington, NSW, Australia

3. Systems Research Institute of the Polish Academy of Sciences, Warsaw, Poland

Funder

National Natural Science Foundation of China

Australian Research Council Project

National Natural Science Foundation of Guangdong Province

Shenzhen Technology Project

3D Digital Media Technology Engineering Laboratory

CAS Key Technology Talent Program

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Electrical and Electronic Engineering,Computer Science Applications,Media Technology,Signal Processing

Reference57 articles.

1. Generative adversarial text to image synthesis;Reed,2016

2. Image Generation from Scene Graphs

3. Chatpainter: Improving text to image generation using dialogue;Sharma,2018

4. Text2Scene: Generating Compositional Scenes From Textual Descriptions

5. StoryGAN: A Sequential Conditional GAN for Story Visualization

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3