Text-to-Text Pre-Training with Paraphrasing for Improving Transformer-Based Image Captioning.
Ryo MasumuraNaoki MakishimaMana IhoriAkihiko TakashimaTomohiro TanakaShota OrihashiPublished in: EUSIPCO (2023)
Keyphrases
- web images
- input image
- text retrieval
- single image
- multiscale
- image data
- image segmentation
- high resolution
- image classification
- image content
- image features
- image analysis
- text information
- information retrieval
- image pixels
- hough transform
- text graphics
- textual and visual information
- keywords
- text mining
- image retrieval
- image collections
- neural network
- similarity measure
- document analysis
- training set
- textual information
- context sensitive
- gray level
- image set
- low level
- text documents
- image matching
- edge detection
- segmentation method
- feature points