Transform, contrast and tell: Coherent entity-aware multi-image captioning.
Jingqiang ChenPublished in: Comput. Vis. Image Underst. (2024)
Keyphrases
- image content
- image data
- image features
- input image
- single image
- image analysis
- contrast enhancement
- image segmentation
- multiscale
- test images
- lossless data compression
- template matching
- similarity measure
- high resolution
- segmentation method
- keypoints
- hough transform
- image classification
- vector field
- image pixels
- image representation
- lighting conditions
- knowledge base
- histogram equalization
- image collections
- image matching
- image enhancement
- low level
- image transformations
- transform coefficients
- discrete fourier transform
- enhanced image
- color channels
- feature points