Remote sensing visual question answering with a self-attention multi-modal encoder.
João Daniel SilvaJoão MagalhãesDevis TuiaBruno MartinsPublished in: GeoAI@SIGSPATIAL (2022)
Keyphrases
- multi modal
- question answering
- remote sensing
- change detection
- multispectral
- information retrieval
- video search
- image analysis
- natural language
- single modality
- information extraction
- high resolution
- visual information
- natural language processing
- image processing
- qa clef
- medical imaging
- question answering systems
- visual features
- machine learning
- high dimensional
- answer extraction
- natural language questions
- low level