Context-Fused Guidance for Image Captioning Using Sequence-Level Training.
Junlong FengJianping ZhaoPublished in: Comput. Intell. Neurosci. (2022)
Keyphrases
- image features
- image retrieval
- input image
- image analysis
- template matching
- image data
- image content
- pixel level
- single image
- image segmentation
- image classification
- low level
- multiscale
- fusion method
- image set
- image representation
- region of interest
- segmentation method
- image regions
- pixel values
- contextual information
- data fusion
- higher level
- hough transform
- spatial information
- segmentation algorithm
- image processing
- context aware
- input data
- image pixels
- medical images
- supervised learning
- labeled images