Dual Global Enhanced Transformer for image captioning.
Tiantao XianZhixin LiCanlong ZhangHuifang MaPublished in: Neural Networks (2022)
Keyphrases
- input image
- image data
- image features
- single image
- template matching
- image analysis
- multiscale
- image content
- image segmentation
- image representation
- spatial information
- segmentation method
- image classification
- image retrieval
- high resolution
- natural images
- image noise
- image pixels
- test images
- edge detection
- computer vision
- image matching
- low level
- region of interest
- image collections
- pixel values
- feature points
- global features
- global structure