CoCoOpter: Pre-train, prompt, and fine-tune the vision-language model for few-shot image classification.
Jie YanYuxiang XieYanming GuoYingmei WeiXiaoping ZhangXidao LuanPublished in: Int. J. Multim. Inf. Retr. (2023)
Keyphrases
- language model
- fine tune
- image classification
- visual features
- language modeling
- n gram
- fine tuning
- probabilistic model
- document retrieval
- speech recognition
- test collection
- retrieval model
- bag of words
- information retrieval
- image representation
- query expansion
- image features
- language modelling
- context sensitive
- computer vision
- feature extraction
- smoothing methods
- real time
- query terms
- relevance model
- pseudo relevance feedback
- word clouds
- ad hoc information retrieval
- mixture model
- statistical machine translation
- pid controller
- image annotation
- language models for information retrieval
- data fusion