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

GPS-Net: Graph Property Sensing Network for Scene Graph Generation

Lin, Xin; Ding, Changxing; Zeng, Jinquan; Tao, Dacheng
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)2020DOI: 10.1109/CVPR42600.2020.00380
98被引3阅读
引用收藏
分享

摘要

Scene graph generation (SGG) aims to detect objects in an image along with their pairwise relationships. There are three key properties of scene graph that have been underexplored in recent works: namely, the edge direction information, the difference in priority between nodes, and the long-tailed distribution of relationships. Accordingly, in this paper, we propose a Graph Property Sensing Network (GPS-Net) that fully explores these three properties for SGG. First, we propose a novel message passing module that augments the node feature with node-specific contextual information and encodes the edge direction information via a tri-linear model. Second we introduce a node priority sensitive loss to reflect the difference in priority between nodes during training. This is achieved by designing a mapping firnction that adjusts the focusing parameter in the focal loss. Third, since the frequency of relationships is affected by the long-tailed distribution prob- lem, we mitigate this issue by first softening the distribution and then enabling it to be adjusted for each subjectobject pair according to their visual appearance. Systematic experiments demonstrate the effectiveness of the proposed techniques. Moreover, GPS-Net achieves state-ofthe-art performance on three popular databases: VG, OI, and VRD by significant gains under various settings and metrics. The code and models are available at https: //github.com/taksau/GPS-Net.

相关
加载中…
  • Scene Graph Generation using Depth-based Multimodal Network
    Chen, Lianggangxu*; Lu, Jiale; Wang, Changbo; He, GaoqiIEEE International Conference on Multimedia and Expo (ICME), Brisbane, AUSTRALIA, 2023-07-10 To 2023-07-14.
  • RU-Net: Regularized Unrolling Network for Scene Graph Generation
    Lin, Xin; Ding, Changxing*; Zhang, Jing; Zhan, Yibing; Tao, DachengIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, 2022-06-18 To 2022-06-24.
  • HL-Net: Heterophily Learning Network for Scene Graph Generation
    Lin, Xin; Ding, Changxing*; Zhan, Yibing; Li, Zijian; Tao, DachengIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, 2022-06-18 To 2022-06-24.被引 5
查看全部 →

会议信息

会议名称
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
会议日期
2020-06-14 至 2020-06-19
论文集名
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
发表日期
2020
起止页码
3743-3752
DOI
10.1109/CVPR42600.2020.00380
资助标注
NSF of China [61702193]; Science and Technology Program of Guangzhou [201804010272]; Program for Guangdong Introducing Innovative and Entrepreneurial Teams [2017ZT07X183]; ARC [FL-170100117, DP-180103424]
收录
ISTP

作者

  • L

    Lin, Xin (第一作者)

  • D

    Ding, Changxing

查看全部 4 位作者收起作者
  • Z

    Zeng, Jinquan

  • T

    Tao, Dacheng

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