CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model.
Dingkang LiangJiahao XieZhikang ZouXiaoqing YeWei XuXiang BaiPublished in: CVPR (2023)
Keyphrases
- language model
- language modeling
- n gram
- speech recognition
- document retrieval
- probabilistic model
- retrieval model
- language modelling
- statistical language models
- test collection
- information retrieval
- unsupervised learning
- supervised learning
- ad hoc information retrieval
- query expansion
- context sensitive
- mixture model
- word error rate
- document ranking
- semi supervised
- language models for information retrieval
- pseudo relevance feedback
- word segmentation
- dependency structure
- smoothing methods
- machine learning
- dirichlet prior