A multi-scale contextual attention network for remote sensing visual question answering

Remote sensing visual question answering (RSVQA) is a user-friendly method used for analyzing remote sensing images (RSIs) in various tasks. However, current methods often overlook geospatial objects, which possess a multi-scale representation and require contextual information. Furthermore, limited...

Full description

Bibliographic Details

Published in:	International Journal of Applied Earth Observations and Geoinformation
Main Authors:	Jiangfan Feng, Hui Wang
Format:	Article
Language:	English
Published:	Elsevier 2024-02-01
Subjects:	Remote sensing Visual question answering (VQA) Cross-modal Attention Multi-scales
Online Access:	http://www.sciencedirect.com/science/article/pii/S156984322300465X