Predicting a Song Title from Audio Embeddings on a Pretrained Image-captioning Network.
Avi BleiweissPublished in: ICAART (2) (2020)
Keyphrases
- single image
- image analysis
- image data
- input image
- image content
- image classification
- image features
- image collections
- image representation
- image segmentation
- image pixels
- image set
- hough transform
- high resolution
- multiscale
- region of interest
- feature points
- low level
- wireless sensor networks
- image retrieval
- visual information
- test images
- similarity measure
- template matching
- visual data
- medical images
- multimedia
- pixel values
- network structure
- segmentation method
- image restoration
- edge detection