Rethinking Visual Prompting for Multimodal Large Language Models with External Knowledge.
Yuanze LinYunsheng LiDongdong ChenWeijian XuRonald ClarkPhilip TorrLu YuanPublished in: CoRR (2024)
Keyphrases
- language model
- external knowledge
- language modeling
- domain knowledge
- n gram
- probabilistic model
- retrieval model
- document retrieval
- wordnet
- query expansion
- text categorization
- visual information
- information retrieval
- textual information
- test collection
- effective retrieval
- visual features
- smoothing methods
- vector space model
- document clustering
- bag of words
- knn
- knowledge representation
- low level
- image retrieval
- high level
- multimedia