ReFormer: The Relational Transformer for Image Captioning.
Xuewen YangYingru LiuXin WangPublished in: ACM Multimedia (2022)
Keyphrases
- image content
- image analysis
- image features
- image data
- image classification
- input image
- test images
- single image
- image retrieval
- image representation
- multiscale
- low level
- high resolution
- similarity measure
- relational databases
- image regions
- hough transform
- image segmentation
- image pixels
- image noise
- template matching
- relational data
- image collections
- spatial information
- fuzzy logic
- computer vision
- image matching
- vector field
- region of interest
- lighting conditions
- data model
- face recognition
- image structure
- aerial images
- neural network