From Images to Textual Prompts: Zero-shot Visual Question Answering with Frozen Large Language Models.
Jiaxian GuoJunnan LiDongxu LiAnthony Meng Huat TiongBoyang LiDacheng TaoSteven C. H. HoiPublished in: CVPR (2023)
Keyphrases
- question answering
- language model
- passage retrieval
- information retrieval
- document retrieval
- sentence retrieval
- natural language
- language modeling
- n gram
- question classification
- query expansion
- natural language processing
- retrieval model
- image retrieval
- image features
- cross language
- named entities
- probabilistic model
- visual data
- test collection
- speech recognition
- image classification
- quantitative evaluation
- question answering systems
- information extraction
- query terms
- image annotation
- image representation
- vector space model
- visual features
- multi modal
- low level
- translation model
- text mining