Grounding Language Models to Images for Multimodal Generation.
Jing Yu KohRuslan SalakhutdinovDaniel FriedPublished in: CoRR (2023)
Keyphrases
- language model
- language modeling
- image database
- image data
- image features
- n gram
- image classification
- retrieval model
- image retrieval
- speech recognition
- information retrieval
- document retrieval
- language modelling
- image regions
- image collections
- probabilistic model
- image content
- image annotation
- audio visual
- smoothing methods
- statistical language models
- language models for information retrieval