Adaptive Semantic-Enhanced Transformer for Image Captioning.

Jing Zhang Zhongjun Fang Han Sun Zhe Wang

Published in: IEEE Trans. Neural Networks Learn. Syst. (2024)

Keyphrases

image data
input image
single image
image representation
image features
image classification
image retrieval
multiscale
template matching
image analysis
image segmentation
low level
natural language
image matching
image regions
edge detection
image content
region of interest
fuzzy logic
segmentation method
image collections
image pixels
image processing
neural network
high voltage
semantic similarity
test images
high resolution
similarity measure
computer vision