Semantic-meshed and content-guided transformer for image captioning.
Xuan LiWenkai ZhangXian SunXin GaoPublished in: IET Comput. Vis. (2022)
Keyphrases
- input image
- image classification
- image content
- image data
- image features
- single image
- multiscale
- low level
- semantic meaning
- image representation
- image pixels
- image retrieval
- image collections
- semantically meaningful
- image analysis
- template matching
- image matching
- image segmentation
- high resolution
- fuzzy logic
- neural network
- low level visual features
- semantic content
- image database
- visual concepts
- semantic gap
- web images
- semantic concepts
- low level image features
- textual descriptions
- image regions
- digital content
- web content
- edge detection
- region of interest
- test images
- visual features
- semantic information