CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios.
Qilang YeZitong YuRui ShaoXinyu XiePhilip H. S. TorrXiaochun CaoPublished in: CoRR (2024)
Keyphrases
- audio visual
- language model
- answer questions
- multi modal
- language modeling
- multi stream
- document retrieval
- n gram
- probabilistic model
- passage retrieval
- retrieval model
- context sensitive
- visual information
- speech recognition
- test collection
- visual data
- information retrieval
- multimedia
- query expansion
- multimodal fusion
- ad hoc information retrieval
- mixture model
- smoothing methods
- machine learning
- relevance model
- natural language processing