Adventurer's Treasure Hunt: A Transparent System for Visually Grounded Compositional Visual Question Answering based on Scene Graphs.
Daniel ReichFelix PutzeTanja SchultzPublished in: CoRR (2021)
Keyphrases
- question answering
- visual data
- information retrieval
- natural language processing
- question classification
- cross language
- information extraction
- video sequences
- passage retrieval
- named entities
- visual information
- question answering systems
- open domain question answering
- qa clef
- visual features
- semantic roles
- natural language
- natural language questions
- low level
- structured data
- syntactic information
- sentence retrieval
- multi modal
- video data
- qa systems
- answer validation