gzqy1026/RemoteCLIP

该数据集包含图像的原始字节和用于描述图像内容的文本。图像可以通过图像处理库（如PIL）读取，文本则是描述图像内容的字符串。数据集的结构以CSV文件形式呈现，包含图像标题和文件名。

The RemoteCLIP dataset is primarily used for image-to-text and text-to-image tasks. It consists of images and texts, where the image part is raw bytes that can be read using image processing libraries like PIL; the text part is a string describing the content of the image. The dataset structure is presented in a CSV file format, with each row containing a title and filename, where the title is a description of the corresponding image. The dataset size ranges between 100K and 1M.

原始信息汇总

数据集描述

概述

• 图像: 图像的原始字节，可以使用图像处理库（如PIL）读取。
• 文本: 用于描述图像内容的字符串。

数据集结构

数据集以CSV文件格式存储，包含以下字段：

• title: 描述图像内容的文本。
• filename: 图像文件名。

示例数据： shell title filename Many planes are parked next to a long building in an airport. rsicd_airport_1.jpg Some planes are parked in an airport . rsicd_airport_10.jpg The airport here is full of airplanes and containers . rsicd_airport_10.jpg There is a small tennis court with some cars and a swimming pool beside . ucm_2080.png

引用信息

bibtex @article{liu2024remoteclip, title={Remoteclip: A vision language foundation model for remote sensing}, author={Liu, Fan and Chen, Delong and Guan, Zhangqingyun and Zhou, Xiaocong and Zhu, Jiale and Ye, Qiaolin and Fu, Liyong and Zhou, Jun}, journal={IEEE Transactions on Geoscience and Remote Sensing}, year={2024}, publisher={IEEE} }