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

Two-stream Gabor-AGraph Convolutional Networks for Facial Expression Recognition

Jiang, Shaoping; Xu, Xiangmin*; Xing, Xiaofen; Wang, Lin; Liu, Fang广东金融学院
16th IEEE International Conference on Automatic Face and Gesture Recognition (FG)2021DOI: 10.1109/FG52635.2021.9666935
5阅读
引用收藏
分享

摘要

Facial expression recognition (FER) has recently attracted much attention in computer vision. However, existing methods mostly focus on the texture information of faces and overlook their inherent topological features. Hence more informative and significant contents are ignored for expression recognition. In this work, we propose a Two-stream Gabor-AGraph Convolutional Network (2s-GAGCN) to exploit the facial texture and topological features simultaneously. The Gabor Stream and the Attention-Graph (AGraph) Stream are respectively introduced to capture the salient visual properties and discriminative landmark features of faces. In particular, we adopt a flexible node attention mechanism in AGraph Stream through utilizing global and local information to enhance the potential relationships among landmarks. Furthermore, a novel landmark feature descriptor is proposed to alleviate the redundant topological features, which shows promising improvement for the recognition accuracy. We conduct extensive experiments on two wild datasets: RAF-DB and SFEW. The results show that the proposed 2s-GAGCN achieves superior performance against the state-of-the-art methods.

学科与关键词

关键词
ATTENTION
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 IEEE International Conference on Automatic Face and Gesture Recognition (FG)
会议日期
2021-12-15 至 2021-12-18
论文集名
2021 16TH IEEE INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION (FG 2021)
发表日期
2021
DOI
10.1109/FG52635.2021.9666935
资助标注
National Natural Science Foundation of China [U1801262, 62102102, 61802131]; Natural Science Foundation of Guangdong Province, China [2019A1515012146, 2020A1515010781]; Key-Area Research and Development Program of Guangdong [2019B010154003]; Guangzhou Key Laboratory of Body Data Science [201605030011]; Foundation for Characteristic Innovation in Higher Education of Guangdong Province, China [2019KTSCX112]
收录
ISTP

作者

  • J

    Jiang, Shaoping (第一作者)

  • X

    Xu, Xiangmin (通讯)

查看全部 5 位作者收起作者
  • X

    Xing, Xiaofen

    guangdong univ finance

  • W

    Wang, Lin

  • L

    Liu, Fang

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