Modality-Aware Integration with Large Language Models for Knowledge-based Visual Question Answering.
Junnan DongQinggang ZhangHuachi ZhouDaochen ZhaPai ZhengXiao HuangPublished in: CoRR (2024)
Keyphrases
- question answering
- language model
- passage retrieval
- information retrieval
- language modeling
- document retrieval
- n gram
- question classification
- retrieval model
- probabilistic model
- sentence retrieval
- natural language processing
- query expansion
- question answering systems
- speech recognition
- test collection
- relevance model
- cross language
- visual information
- natural language
- information extraction
- vector space model
- multi modal
- tf idf
- pseudo relevance feedback
- query terms
- named entities
- image classification
- news video
- visual features