II-MMR: Identifying and Improving Multi-modal Multi-hop Reasoning in Visual Question Answering.
Jihyung KilFarideh TavazoeeDongyeop KangJoo-Kyung KimPublished in: CoRR (2024)
Keyphrases
- multi modal
- question answering
- multi hop
- cross modal
- wireless networks
- wireless sensor networks
- video search
- mobile ad hoc networks
- answering questions
- ad hoc networks
- qa clef
- data transmission
- information retrieval
- information extraction
- energy efficient
- single modality
- natural language processing
- passage retrieval
- visual information
- natural language
- base station
- natural language questions
- end to end
- audio visual
- routing protocol
- knowledge base
- visual features
- image annotation
- wifi
- high level
- energy consumption
- knowledge representation
- low level
- answer extraction
- multimedia
- metadata