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

MULTI-SCALE TRANSFORMER NETWORK FOR SALIENCY PREDICTION ON 360-DEGREE IMAGES

Lin, Xu; Qing, Chunmei*; Tan, Junpeng; Xu, Xiangmin
30th IEEE International Conference on Image Processing (ICIP)2023DOI: 10.1109/ICIP49359.2023.10222683
3阅读
引用收藏
分享

摘要

The latest methods for saliency prediction on 360 degrees images show that better results can be obtained using equirectangular (ERP) images as input. Due to the limitation of the receptive field, existing convolution-based networks cannot capture long-range information in complex 360 degrees images. Although the transformer has the innate ability to capture long-range correlations with self-attention, large dataset requirement limit its application in saliency prediction of 360 degrees images. In this paper, we present a novel Multi-scale Transformer framework for Saliency prediction on 360 degrees images (MTSal360). The Multi-scale Transformer Module (MTM) is designed in the network to aggregate the contextual long-range information, which includes a Convolutional Positional Encoder (CPE) to enable the model could train and test on cubic and ERP format separately to address the insufficient data. Experiments on two public datasets illustrate that MTSal360 achieves better results over the state-of-the-art methods.

学科与关键词

关键词
360 degrees imagessaliency predictiontransformervirtual reality (VR)
相关
加载中…
  • SalBiNet360: Saliency Prediction on 360° Images with Local-Global Bifurcated Deep Network
    Chen, Dongwen; Qing, Chunmei*; Xu, Xiangmin; Zhu, Huansheng27th IEEE Conference on Virtual Reality and 3D User Interfaces (IEEE VR), Atlanta, GA, 2020-03-22 To 2020-03-26.被引 7
  • Attentive and context-aware deep network for saliency prediction on omni-directional images
    Qing, Chunmei; Zhu, Huansheng; Xing, Xiaofen*; Chen, Dongwen; Jin, JianxiuDigital Signal Processing: A Review Journal , 2022, 120: 103289.被引 4
  • Intra- and Inter-Reasoning Graph Convolutional Network for Saliency Prediction on 360° Images
    Chen, Dongwen; Qing, Chunmei*; Lin, Xu; Ye, Mengtao; Xu, Xiangmin; Dickinson, PatrickIEEE Transactions on Circuits and Systems for Video Technology, 2022, 32(12): 8730-8743.
查看全部 →

会议信息

会议名称
30th IEEE International Conference on Image Processing (ICIP)
会议日期
2023-10-08 至 2023-10-11
论文集名
2023 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP
发表日期
2023
起止页码
1700-1704
DOI
10.1109/ICIP49359.2023.10222683
资助标注
National Natural Science Foundation of China [61972163, U1801262]; Natural Science Foundation of Guangdong Province [2022A1515011555, 2023A1515012568]; Guangdong Provincial Key Laboratory of Human Digital Twin [2022B1212010004, 510330]
收录
ISTP

作者

  • L

    Lin, Xu (第一作者)

  • Q

    Qing, Chunmei (通讯)

查看全部 4 位作者收起作者
  • T

    Tan, Junpeng

  • X

    Xu, Xiangmin

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