Enhancing Multimodal Compositional Reasoning of Visual Language Models with Generative Negative Mining.
Ugur SahinHang LiQadeer KhanDaniel CremersVolker TrespPublished in: CoRR (2023)
Keyphrases
- language model
- language modeling
- probabilistic model
- n gram
- query expansion
- generative model
- document retrieval
- retrieval model
- information retrieval
- language modelling
- statistical language models
- text mining
- language modeling framework
- language models for information retrieval
- speech recognition
- visual information
- context sensitive
- test collection
- web mining
- smoothing methods
- ad hoc information retrieval
- language model for information retrieval
- relevance model
- data mining
- pseudo relevance feedback
- query terms
- multi modal
- query specific
- vector space model
- visual features
- low level
- machine learning
- visual data
- knowledge discovery
- spoken term detection