VETIM: Expanding the Vocabulary of Text-to-Image Models only with Text.
Martin Nicolas EveraertMarco BocchioSami ArpaSabine SüsstrunkRadhakrishna AchantaPublished in: BMVC (2023)
Keyphrases
- input image
- information retrieval
- image segmentation
- multiscale
- keywords
- text information
- image content
- image data
- text retrieval
- statistical model
- image features
- scanned documents
- web images
- region of interest
- edge detection
- image retrieval
- image classification
- image representation
- image regions
- low level
- high resolution
- template matching
- image analysis
- random fields
- parametric models
- textual information
- text regions
- textual descriptions
- semantic information
- bounding box
- image pixels
- probabilistic model
- search engine