Supportive and Self Attentions for Image Caption.
Jen-Tzung ChienTing-An LinPublished in: APSIPA (2020)
Keyphrases
- input image
- multiscale
- image representation
- image data
- caption text
- image content
- image analysis
- high resolution
- single image
- image segmentation
- image features
- image regions
- image collections
- grey level
- image classification
- visual features
- spatial information
- template matching
- pixel values
- hough transform
- image retrieval
- region of interest
- lighting conditions
- edge map