Triple-level relationship enhanced transformer for image captioning.
Anqi ZhengShiqi ZhengCong BaiDeng ChenPublished in: Multim. Syst. (2023)
Keyphrases
- image data
- single image
- input image
- image classification
- image retrieval
- image features
- pixel level
- multiscale
- template matching
- image analysis
- image representation
- feature points
- segmentation method
- test images
- image pixels
- energy function
- image content
- image segmentation
- region of interest
- low level
- high resolution
- grey level
- image matching
- image structure
- pixel values
- fuzzy logic
- motion estimation
- multiresolution
- spatial information
- fault diagnosis
- binary images
- segmentation algorithm
- medical images
- edge detection
- feature extraction
- image sequences