BRAVE: Broadening the visual encoding of vision-language models.
Oguzhan Fatih KarAlessio TonioniPetra PoklukarAchin KulshresthaAmir ZamirFederico TombariPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- probabilistic model
- n gram
- document retrieval
- language modelling
- retrieval model
- information retrieval
- computer vision
- query expansion
- statistical language models
- visual information
- smoothing methods
- speech recognition
- context sensitive
- test collection
- pseudo relevance feedback
- ad hoc information retrieval
- language models for information retrieval
- query terms
- visual features
- query specific
- translation model
- word error rate
- relevance model