Image and audio caps: automated captioning of background sounds and images using deep learning.
M. PoongodiMounir HamdiHuihui WangPublished in: Multim. Syst. (2023)
Keyphrases
- input image
- image data
- test images
- image features
- deep learning
- image retrieval
- image classification
- image regions
- segmentation method
- bounding box
- region of interest
- lighting conditions
- segmentation algorithm
- image database
- single image
- color histogram
- keypoints
- multiple images
- image content
- machine learning
- multiple objects
- image representation
- spatial information
- object recognition
- image processing
- image segmentation
- target object
- similarity measure
- multiscale
- natural images
- partial occlusion
- high resolution
- higher order