Chg2Cap: A Novel Attentive Network for Remote Sensing Change Captioning

The proposed Chg2Cap method is constructed by a CNN-based feature extractor that uses the pre-trained ResNet-101 as the backbone, an attentive encoder that consists of a hierarchical self-attention block and a ResBlock, and a caption decoder.

Data and Resources

Cite this as

Shizhen Chang, Pedram Ghamisi (2024). Dataset: Chg2Cap: A Novel Attentive Network for Remote Sensing Change Captioning. https://doi.org/10.57702/yw3afjml

DOI retrieved: December 3, 2024

Additional Info

Field Value
Created December 3, 2024
Last update December 3, 2024
Author Shizhen Chang
More Authors
Pedram Ghamisi
Homepage https://github.com/ShizhenChang/Chg2Cap