Direct Speech-to-image Translation.
Jiguo LiXinfeng ZhangChuanmin JiaJizheng XuLi ZhangYue WangSiwei MaWen GaoPublished in: CoRR (2020)
Keyphrases
- image data
- image features
- single image
- image analysis
- input image
- image representation
- multiscale
- image classification
- template matching
- high resolution
- test images
- image retrieval
- vector field
- image segmentation
- speech recognition
- segmentation method
- image collections
- energy function
- region of interest
- spatial information
- hough transform
- edge detection
- low level
- background noise
- image set
- grey level
- wavelet transform
- image matching
- image regions
- segmentation algorithm
- scale space