Unified Transformer with Cross-Modal Mixture Experts for Remote-Sensing Visual Question Answering.
Gang LiuJinlong HePengfei LiShenjun ZhongHongyang LiGenrong HePublished in: Remote. Sens. (2023)
Keyphrases
- question answering
- remote sensing
- cross modal
- multi modal
- information retrieval
- image analysis
- high resolution
- information extraction
- natural language processing
- visual data
- image processing
- multimedia databases
- natural language
- visual similarity
- image retrieval
- object recognition
- low level
- similarity search
- machine learning
- visual information
- artificial intelligence
- image segmentation
- image data