ClipCrop: Conditioned Cropping Driven by Vision-Language Model.
Zhihang ZhongMingxi ChengZhirong WuYuhui YuanYinqiang ZhengJi LiHan HuStephen LinYoichi SatoImari SatoPublished in: ICCV (Workshops) (2023)
Keyphrases
- language model
- language modeling
- probabilistic model
- n gram
- document retrieval
- information retrieval
- speech recognition
- context sensitive
- query terms
- retrieval model
- mixture model
- test collection
- query expansion
- language modelling
- vector space model
- statistical language models
- ad hoc information retrieval
- document length
- image content
- query specific
- pseudo relevance feedback
- translation model
- document ranking
- language model for information retrieval