Dual Position Relationship Transformer for Image Captioning.

Yaohan Wang Wenhua Qian Rencan Nie Dan Xu Jinde Cao Pyoungwon Kim

Published in: Big Data (2022)

Keyphrases

image data
input image
image analysis
single image
image features
template matching
multiscale
image content
image representation
image segmentation
image classification
image collections
high resolution
test images
position and orientation
image retrieval
segmentation method
coordinate frame
image regions
segmentation algorithm
natural images
fuzzy logic
low level
object recognition
image matching
digital images
image structure
image pixels
relative position
image coordinates