Meerkat: Audio-Visual Large Language Model for Grounding in Space and Time.
Sanjoy ChowdhurySayan NagSubhrajyoti DasguptaJun ChenMohamed ElhoseinyRuohan GaoDinesh ManochaPublished in: CoRR (2024)
Keyphrases
- language model
- audio visual
- language modeling
- multi modal
- passage retrieval
- probabilistic model
- document retrieval
- n gram
- query expansion
- information retrieval
- speech recognition
- multi stream
- test collection
- visual information
- retrieval model
- visual data
- smoothing methods
- ad hoc information retrieval
- space time
- multimedia
- mixture model
- translation model
- pattern recognition
- vector space
- text classification
- knn
- feature selection