arrow
返回

An Interactive Image Editing System Using an Uncertainty-Based Confirmation Strategy

delete2020-01-01
delete1
delete
OA
AI
S
Seitaro Shinagawa *
K
Koichiro Yoshino
S
Seyed Hossein Alavi
K
Kallirroi Georgila
D
David Traum
S
Sakriani Sakti
S
Satoshi Nakamura
DOI:10.1109/ACCESS.2020.2997012delete
delete原文链接
delete分享
delete收藏
查看原文
摘要

摘要

En 中文
We propose an interactive image editing system that has a confirmation dialogue strategy using an entropy-based uncertainty calculation on its generated images with Deep Convolutional Generative Adversarial Networks (DCGAN). DCGAN is an image generative model that learns an image manifold of a given dataset and enables continuous change of an image. Our proposed image editing system combines DCGAN with a natural language interface that accepts image editing requests in natural language. Although such a system is helpful for human users, it often faces uncertain requests to generate acceptable images. A promising approach to solve this problem is introducing a dialogue process that shows multiple candidates and confirms the user's intention. However, confirming every editing request creates redundant dialogues. To achieve more efficient dialogues, we propose an entropy-based dialogue strategy that decides when the system should confirm, and enables effective image editing through a dialogue that reduces redundant confirmations. We conducted image editing dialogue experiments using an avatar face illustration dataset for editing by natural language requests. Through quantitative and qualitative analysis, our results show that our entropy-based confirmation strategy achieved an effective dialogue by generating images desired by users.
Keyword:
Natural languages
Generators
Generative adversarial networks
Task analysis
Training
Hair
Image generation
Confirmation
generative adversarial networks
image editing
natural language interface
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

IEEE Access 封面图
IEEE Access
IF:
3.6
论文数:
9.8W
被引数:
29.4W

机构

U
university of southern california
学者数:
4.7W
论文数: 3.8W
被引数: 51
N
nara institute of science & technology
学者数:
4.1K
论文数: 3.1K
被引数: 7
引用论文

引用论文

err分享
err收藏
Influence of B content substituting for Al on the magnetic properties of Nd60Fe30Al10−xBx
err2002-04-01
err0
PREAI
errNguyen Chau; Nguyen Hoang Luong; Cao Xuan Huu; Nguyen Xuan Phuc; Nguyen Huy Dan
err分享
err收藏
Current management of Wilms’ tumor in children
err2009-02-01
err0
PREAI
errEdmund Y. Ko; Michael L. Ritchey
err分享
err收藏
学者 查看更多内容