• 综合
  • 标题
  • 关键词
  • 摘要
  • 学者
  • 期刊-刊名
  • 期刊-ISSN
  • 会议名称
搜索

作者:

Tan, Hongchen (Tan, Hongchen.) | Yin, Baocai (Yin, Baocai.) (学者:尹宝才) | Wei, Kun (Wei, Kun.) | Liu, Xiuping (Liu, Xiuping.) | Li, Xin (Li, Xin.)

收录:

EI Scopus SCIE

摘要:

We propose a novel Text-to-Image Generation Network, Adaptive Layout Refinement Generative Adversarial Network (ALR-GAN), to adaptively refine the layout of synthesized images without any auxiliary information. The ALR-GAN includes an Adaptive Layout Refinement (ALR) module and a Layout Visual Refinement (LVR) loss. The ALR module aligns the layout structure (which refers to locations of objects and background) of a synthesized image with that of its corresponding real image. In ALR module, we proposed an Adaptive Layout Refinement (ALR) loss to balance the matching of hard and easy features, for more efficient layout structure matching. Based on the refined layout structure, the LVR loss further refines the visual representation within the layout area. Experimental results on two widely-used datasets show that ALR-GAN performs competitively at the Text-to-Image generation task.

关键词:

text-to-image synthesis information consistency constraint Task analysis Adaptation models Training Visualization Semantics object layout refinement Layout Generators Generative adversarial network

作者机构:

  • [ 1 ] [Tan, Hongchen]Beijing Univ Technol, Beijing Inst Artificial Intelligence, Beijing 100124, Peoples R China
  • [ 2 ] [Yin, Baocai]Beijing Univ Technol, Beijing Inst Artificial Intelligence, Beijing 100124, Peoples R China
  • [ 3 ] [Wei, Kun]Xidian Univ, Sch Elect Engn, Xian 710071, Peoples R China
  • [ 4 ] [Liu, Xiuping]Dalian Univ Technol, Sch Math Sci, Dalian 116024, Peoples R China
  • [ 5 ] [Li, Xin]Texas A&M Univ, Sch Performance Visualizat & Fine Arts, Sect Visual Comp & Creat Media, College Stn, TX 77843 USA

通讯作者信息:

查看成果更多字段

相关关键词:

来源 :

IEEE TRANSACTIONS ON MULTIMEDIA

ISSN: 1520-9210

年份: 2023

卷: 25

页码: 8620-8631

7 . 3 0 0

JCR@2022

被引次数:

WoS核心集被引频次:

SCOPUS被引频次: 21

ESI高被引论文在榜: 0 展开所有

万方被引频次:

中文被引频次:

近30日浏览量: 1

归属院系:

在线人数/总访问数:481/4912424
地址:北京工业大学图书馆(北京市朝阳区平乐园100号 邮编:100124) 联系我们:010-67392185
版权所有:北京工业大学图书馆 站点建设与维护:北京爱琴海乐之技术有限公司