Multi-Modal Fusion Transformer for Visual Question Answering in Remote Sensing.
Tim SiebertKai Norman ClasenMahdyar RavanbakhshBegüm DemirPublished in: CoRR (2022)
Keyphrases
- question answering
- remote sensing
- multi modal fusion
- multispectral
- change detection
- remote sensing images
- satellite images
- hyperspectral
- information extraction
- information retrieval
- high resolution
- image processing
- remote sensing data
- satellite data
- image analysis
- question classification
- natural language processing
- visual information
- land cover
- passage retrieval
- natural language
- question answering systems
- visual features
- qa clef
- syntactic information
- answer extraction
- candidate answers
- answering questions
- natural language questions
- earth observation
- artificial intelligence