Cross-Modal Retrieval and Semantic Refinement for Remote Sensing Image Captioning

Two-stage remote sensing image captioning (RSIC) methods have achieved promising results by incorporating additional pre-trained remote sensing tasks to extract supplementary information and improve caption quality. However, these methods face limitations in semantic comprehension, as pre-trained de...

Celý popis

Podrobná bibliografie

Hlavní autoři:	Zhengxin Li, Wenzhe Zhao, Xuanyi Du, Guangyao Zhou, Songlin Zhang
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	MDPI AG 2024-01-01
Edice:	Remote Sensing
Témata:	semantic retrieving attention mechanism image captioning remote sensing
On-line přístup:	https://www.mdpi.com/2072-4292/16/1/196
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!