LexLIP: Lexicon-Bottlenecked Language-Image Pre-Training for Large-Scale Image-Text Sparse Retrieval.
Ziyang LuoPu ZhaoCan XuXiubo GengTao ShenChongyang TaoJing MaQingwei LinDaxin JiangPublished in: ICCV (2023)
Keyphrases
- image data
- image content
- input image
- image retrieval
- multiscale
- single image
- image analysis
- image classification
- image features
- image segmentation
- information retrieval
- image description
- similarity measure
- image representation
- low level
- image regions
- high resolution
- scanned documents
- web images
- text retrieval
- test images
- image matching
- segmentation method
- feature points
- edge detection
- image set
- image collections
- textual descriptions
- information retrieval systems