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...
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Artigo |
| Langue: | Inglês |
| Publié: |
MDPI AG
2024-01-01
|
| Collection: | Remote Sensing |
| Sujets: | |
| Accès en ligne: | https://www.mdpi.com/2072-4292/16/1/196 |
| Tags: |
Pas de tags, Soyez le premier à ajouter un tag!
|