ArCo: Attention-reinforced transformer with contrastive learning for image captioning.

Zhongan Wang Shuai Shi Zirong Zhai Yingna Wu Rui Yang

Published in: Image Vis. Comput. (2022)

Keyphrases

image classification
input image
learning systems
learning process
image pixels
image regions
image features
learning algorithm
image matching
low level
image data
image processing
single image
edge detection
image segmentation
online learning
unsupervised learning
image analysis
image collections
template matching
image representation
supervised learning
multiscale
reinforcement learning
hough transform
high resolution
expert systems
image retrieval
machine learning