Geometrically-Aware Dual Transformer Encoding Visual and Textual Features for Image Captioning.

Yu-Ling Chang Hao-Shang Ma Shiou-Chi Li Jen-Wei Huang

Published in: PAKDD (5) (2024)

Keyphrases

image analysis
single image
image data
image segmentation
multiscale
image content
image features
image retrieval
image classification
image matching
input image
image representation
edge detection
test images
keypoints
low level
segmentation method
multi modal
high resolution
image collections
fuzzy logic