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: | , , , , |
|---|---|
| 格式: | Artigo |
| 語言: | Inglês |
| 出版: |
MDPI AG
2024-01-01
|
| 叢編: | Remote Sensing |
| 主題: | |
| 在線閱讀: | https://www.mdpi.com/2072-4292/16/1/196 |
| 標簽: |
沒有標簽, 成為第一個標記此記錄!
|