VT-CLIP: Enhancing Vision-Language Models with Visual-guided Texts.
Renrui ZhangLongtian QiuWei ZhangZiyao ZengPublished in: CoRR (2021)
Keyphrases
- language model
- language modeling
- n gram
- document retrieval
- probabilistic model
- speech recognition
- query expansion
- language modelling
- retrieval model
- statistical language models
- smoothing methods
- information retrieval
- ad hoc information retrieval
- visual information
- query terms
- language models for information retrieval
- test collection
- visual features
- low level
- query specific
- document ranking
- translation model
- pseudo relevance feedback
- video clips
- okapi bm
- document length
- context sensitive
- text documents