Tag2Text: Guiding Vision-Language Model via Image Tagging.
Xinyu HuangYoucai ZhangJinyu MaWeiwei TianRui FengYuejie ZhangYaqian LiYandong GuoLei ZhangPublished in: ICLR (2024)
Keyphrases
- language model
- image tagging
- information retrieval
- language modeling
- image search
- n gram
- probabilistic model
- query expansion
- image annotation
- computer vision
- retrieval model
- test collection
- relevance model
- image database
- distance metric learning
- keywords
- text documents
- web images
- semantic information
- web documents
- text mining
- translation model
- textual content
- smoothing methods