FocusCap: Object-Focused Image Captioning with CLIP-Guided Language Model.
Zihan KongWei LiHaiwei ZhangXiaojie YuanPublished in: WISA (2023)
Keyphrases
- language model
- language modeling
- image classification
- image features
- image representation
- image retrieval
- probabilistic model
- image regions
- n gram
- information retrieval
- query expansion
- image content
- document retrieval
- mixture model
- language modelling
- statistical language models
- image segmentation
- language model for information retrieval
- speech recognition
- generative model
- key frames
- bayesian framework
- retrieval model
- test collection