Unified Transformer with Cross-Modal Mixture Experts for Remote-Sensing Visual Question Answering
Remote-sensing visual question answering (RSVQA) aims to provide accurate answers to remote sensing images and their associated questions by leveraging both visual and textual information during the inference process. However, most existing methods ignore the significance of the interaction between...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/19/4682 |