KARG-RSIC: Knowledge-Augmented Retrieval Generation for Remote Sensing Image Captioning

The task of remote sensing image captioning faces dual challenges: complex scene semantics and scarce training data. This results in existing parameterized model-based descriptions often being impoverished in content and lacking diversity. To this end, this article proposes the knowledge-augmented r...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Yan Zhang, Quan Zou, Yi Zhang, Guoqing Li, Wenyang Yu
Formato:	Artigo
Idioma:	Inglês
Publicado em:	IEEE 2026-01-01
coleção:	IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Assuntos:	Cross-modal alignment knowledge-augmented generation remote sensing image captioning retrieval-augmented generation (RAG)
Acesso em linha:	https://ieeexplore.ieee.org/document/11481785/
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!