EVLM: An Efficient Vision-Language Model for Visual Understanding.
Kaibing ChenDong ShenHanwen ZhongHuasong ZhongKui XiaDi XuWei YuanYifei HuBin WenTianke ZhangChangyi LiuDewen FanHuihui XiaoJiahong WuFan YangSize LiDi ZhangPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- probabilistic model
- document retrieval
- n gram
- speech recognition
- language modelling
- query expansion
- test collection
- ad hoc information retrieval
- context sensitive
- retrieval model
- visual features
- information retrieval
- query terms
- visual representation
- mixture model
- statistical language models
- word error rate
- pseudo relevance feedback
- visual representations
- vector space model
- dependency structure
- smoothing methods
- translation model
- relevance model
- language model for information retrieval