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...

Полное описание

Библиографические подробности

Главные авторы:	Yan Zhang, Quan Zou, Yi Zhang, Guoqing Li, Wenyang Yu
Формат:	Artigo
Язык:	Inglês
Опубликовано:	IEEE 2026-01-01
Серии:	IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Предметы:	Cross-modal alignment knowledge-augmented generation remote sensing image captioning retrieval-augmented generation (RAG)
Online-ссылка:	https://ieeexplore.ieee.org/document/11481785/
Метки:	Добавить метку Нет меток, Требуется 1-ая метка записи!