Modeling coverage with semantic embedding for image caption generation.
Teng JiangZehan ZhangYupu YangPublished in: Vis. Comput. (2019)
Keyphrases
- image data
- input image
- single image
- image features
- image segmentation
- image content
- high resolution
- semantic information
- image representation
- image retrieval
- image analysis
- multiscale
- image regions
- image classification
- bounding box
- image collections
- edge detection
- low level
- caption text
- information redundancy
- semantic web
- segmentation method
- visual features
- high level