Exploring Models and Data for Remote Sensing Image Caption Generation

XLXiaoqiang LuBWBinqiang WangXZXiangtao ZhengXLXuelong Li

Xi'an Institute of Optics and Precision Mechanics · University of Chinese Academy of Sciences

Indexed inarxivcrossref

Abstract

Inspired by recent development of artificial satellite, remote sensing images have attracted extensive attention. Recently, notable progress has been made in scene classification and target detection. However, it is still not clear how to describe the remote sensing image content with accurate and concise sentences. In this paper, we investigate to describe the remote sensing images with accurate and flexible sentences. First, some annotated instructions are presented to better describe the remote sensing images considering the special characteristics of remote sensing images. Second, in order to exhaustively exploit the contents of remote sensing images, a large-scale aerial image data set is constructed for…

Citation impact

569
total citations
FWCI
10.26
Percentile
100%
References
57
Citations per year

Authors

4
  • XL
    Xiaoqiang LuCorresponding

    Xi'an Institute of Optics and Precision Mechanics, University of Chinese Academy of Sciences

  • BW
    Binqiang Wang

    Xi'an Institute of Optics and Precision Mechanics, University of Chinese Academy of Sciences

  • XZ
    Xiangtao Zheng

    Xi'an Institute of Optics and Precision Mechanics, University of Chinese Academy of Sciences

  • XL
    Xuelong Li

    Xi'an Institute of Optics and Precision Mechanics, University of Chinese Academy of Sciences

Topics & keywords

Keywords
  • Remote sensing application
  • Set (abstract data type)
  • Image (mathematics)
  • Data set
  • Contextual image classification
  • Task (project management)
  • Exploit
No related works found for this paper.

Funding