ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
会议论文

Gated Cross Word-Visual Attention-Driven Generative Adversarial Networks for Text-to-Image Synthesis

Lai, Borun; Ma, Lihong; Tian, Jing*
16th Asian Conference on Computer Vision (ACCV)2023DOI: 10.1007/978-3-031-26293-7_6
11阅读
引用收藏
分享

摘要

The main objective of text-to-image (Txt2Img) synthesis is to generate realistic images from text descriptions. We propose to insert a gated cross word-visual attention unit (GCAU) into the conventional multiple-stage generative adversarial network Txt2Img framework. Our GCAU consists of two key components. First, a cross word-visual attention mechanism is proposed to draw fine-grained details at different subregions of the image by focusing on the relevant words (via the visual-to-word attention), and select important words by paying attention to the relevant synthesized subregions of the image (via the word-to-visual attention). Second, a gated refinement mechanism is proposed to dynamically select important word information for refining the generated image. Extensive experiments are conducted to demonstrate the superior image generation performance of the proposed approach on CUB and MS-COCO benchmark datasets.

相关
加载中…

文献加载失败,请重试

重试

会议信息

会议名称
16th Asian Conference on Computer Vision (ACCV)
会议日期
2022-12-04 至 2022-12-08
论文集名
COMPUTER VISION - ACCV 2022, PT VII
发表日期
2023
起止页码
88-100
DOI
10.1007/978-3-031-26293-7_6
资助标注
China GDSF [2019A1515011949]
收录
ISTP

作者

  • L

    Lai, Borun (第一作者)

  • M

    Ma, Lihong

查看全部 3 位作者收起作者
  • T

    Tian, Jing (通讯)

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417