Detect2Interact: Localizing Object Key Field in Visual Question Answering (VQA) with LLMs.
Jialou WangManli ZhuYulei LiHonglei LiLongzhi YangWai Lok WooPublished in: CoRR (2024)
Keyphrases
- question answering
- passage retrieval
- information retrieval
- natural language processing
- question classification
- syntactic information
- natural language
- qa clef
- information extraction
- named entities
- cross language
- image database
- open domain question answering
- visual features
- sentence retrieval
- natural language questions
- relation extraction
- visual information
- qa systems
- video database
- question answering systems
- answer extraction
- low level
- answer validation
- relational databases