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...
Na minha lista:
| Principais autores: | , , , , |
|---|---|
| Formato: | Artigo |
| Idioma: | Inglês |
| Publicado em: |
MDPI AG
2024-01-01
|
| coleção: | Remote Sensing |
| Assuntos: | |
| Acesso em linha: | https://www.mdpi.com/2072-4292/16/1/196 |
| Tags: |
Sem tags, seja o primeiro a adicionar uma tag!
|