Normalized and Geometry-Aware Self-Attention Network for Image Captioning.

Longteng Guo Jing Liu Xinxin Zhu Peng Yao Shichen Lu Hanqing Lu

Published in: CVPR (2020)

Keyphrases

single image
input image
image analysis
image content
image data
multiscale
image features
similarity measure
template matching
image regions
image representation
image retrieval
low level
pixel values
image classification
edge detection
image pixels
neural network
segmentation method
relative position
multi view
image collections
geometric constraints
hough transform
keypoints
peer to peer
multiresolution
image segmentation