Transformer model incorporating local graph semantic attention for image caption.

Kui Qian Yuchen Pan Hao Xu Lei Tian

Published in: Vis. Comput. (2024)

Keyphrases

multiscale
high level
graph representation
image data
image segmentation
statistical model
probabilistic model
graph model
bayesian framework
bipartite graph
image classification
pixel level
low level
image processing
bounding box
neural network
semantic description
image content
image representation
denoising
input image
image analysis
face recognition