A Mask-Guided Transformer Network with Topic Token for Remote Sensing Image Captioning

A Mask-Guided Transformer Network with Topic Token for Remote Sensing Image Captioning

Remote sensing image captioning aims to describe the content of images using natural language. In contrast with natural images, the scale, distribution, and number of objects generally vary in remote sensing images, making it hard to capture global semantic information and the relationships between...

Full description

Bibliographic Details
Main Authors: Zihao Ren, Shuiping Gou, Zhang Guo, Shasha Mao, Ruimin Li
Format: Article
Language:English
Published: MDPI AG 2022-06-01
Series:Remote Sensing
Subjects:
image captioning
remote sensing
transformer network
global semantic information
topic token
Online Access:https://www.mdpi.com/2072-4292/14/12/2939

Internet

https://www.mdpi.com/2072-4292/14/12/2939

Similar Items