BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship Detection.
Hedi Ben-younesRémi CadèneNicolas ThomeMatthieu CordPublished in: CoRR (2019)
Keyphrases
- question answering
- visual information
- natural language processing
- visual features
- low level
- information extraction
- information retrieval
- cross language
- textual entailment recognition
- sentence retrieval
- passage retrieval
- relation extraction
- named entities
- natural language
- visual data
- semantic roles
- question answering systems
- qa clef
- multi modal
- answering questions