Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering.
Weizhe LinJinghong ChenJingbiao MeiAlexandru CocaBill ByrnePublished in: CoRR (2023)
Keyphrases
- multi modal
- fine grained
- question answering
- cross modal
- information retrieval
- video search
- passage retrieval
- coarse grained
- audio visual
- information extraction
- document retrieval
- answer extraction
- image retrieval
- question answering systems
- text retrieval
- retrieval systems
- high level
- access control
- image annotation
- high dimensional
- information retrieval systems
- natural language processing
- artificial intelligence
- visual information
- visual features
- cross language
- machine learning
- relevance feedback
- low level