Audio Description from Image by Modal Translation Network.
Hailong NingXiangtao ZhengYuan YuanXiaoqiang LuPublished in: CoRR (2021)
Keyphrases
- image data
- input image
- image features
- single image
- multiscale
- image segmentation
- image representation
- template matching
- image analysis
- image classification
- low level
- image content
- image regions
- image pixels
- test images
- image description
- rotation and translation
- segmentation method
- high resolution
- image retrieval
- hough transform
- spatial information
- image matching
- pixel values
- high level
- multimedia
- energy function
- segmentation algorithm
- image compression
- visual information
- edge detection
- region of interest
- image collections
- image structure