Turkish Image Captioning with Vision Transformer Based Encoders and Text Decoders.
Serdar YildizAbbas MemisSongül VarliPublished in: SIU (2024)
Keyphrases
- input image
- image data
- image content
- image segmentation
- hough transform
- image classification
- image retrieval
- image features
- single image
- visual perception
- template matching
- image matching
- image analysis
- high resolution
- multiscale
- image regions
- segmentation algorithm
- test images
- similarity measure
- information retrieval
- computer vision
- image processing
- real time
- image pixels
- edge detection
- low level image processing
- low level
- vision system
- text graphics
- video compression
- textual information
- web images
- text information
- text retrieval
- region of interest
- spatial information
- image representation
- markov random field
- text mining
- feature vectors
- object recognition
- neural network