Modeling graph-structured contexts for image captioning.
Zhixin LiJiahui WeiFeicheng HuangHuifang MaPublished in: Image Vis. Comput. (2023)
Keyphrases
- image data
- multiscale
- input image
- single image
- image content
- image features
- image analysis
- image classification
- image segmentation
- region of interest
- image retrieval
- grey level
- image regions
- high resolution
- test images
- image matching
- image noise
- hough transform
- segmentation algorithm
- image representation
- low level
- keypoints
- energy function
- structured data
- connected components
- directed graph
- graph matching
- image structure
- pixel values
- graph theory
- graph structure
- computer vision