ST-VQA: shrinkage transformer with accurate alignment for visual question answering.
Haiying XiaRicheng LanHaisheng LiShuxiang SongPublished in: Appl. Intell. (2023)
Keyphrases
- question answering
- qa clef
- information extraction
- natural language processing
- question classification
- information retrieval
- natural language
- passage retrieval
- natural language questions
- cross language
- visual features
- named entities
- denoising
- low level
- visual information
- answer validation
- semantic roles
- question answering systems
- syntactic information
- image database
- open domain question answering
- multimedia
- answering questions
- sentence retrieval
- textual entailment
- co occurrence
- textual entailment recognition
- machine learning