Visual Question Answering based on Local-Scene-Aware Referring Expression Generation.
Jungjun KimDong-Gyu LeeJialin WuHonggyu JungSeong-Whan LeePublished in: CoRR (2021)
Keyphrases
- question answering
- information retrieval
- natural language
- visual data
- question classification
- video sequences
- qa clef
- information extraction
- visual information
- natural language processing
- named entities
- cross language
- open domain question answering
- passage retrieval
- question answering systems
- semantic roles
- syntactic information
- sentence retrieval
- visual features
- low level
- qa systems
- candidate answers
- natural language questions
- textual entailment recognition
- artificial intelligence