Visual Hallucinations of Multi-modal Large Language Models.
Wen HuangHongbin LiuMinxin GuoNeil Zhenqiang GongPublished in: CoRR (2024)
Keyphrases
- multi modal
- language model
- cross modal
- language modeling
- n gram
- probabilistic model
- document retrieval
- speech recognition
- video search
- single modality
- query expansion
- multi modality
- language modelling
- retrieval model
- statistical language models
- smoothing methods
- audio visual
- information retrieval
- visual features
- test collection
- language models for information retrieval
- high dimensional
- pseudo relevance feedback
- relevance model
- visual information
- document ranking
- auto annotation
- uni modal
- high level
- search engine
- machine learning
- low level
- image registration
- visual cues
- spoken term detection