Multimodal Neural Networks in the Problem of Captioning Images in Newspapers.

Published in: FedCSIS (2023)

Keyphrases

neural network
input image
ground truth
image analysis
image collections
object recognition
image data
test images
three dimensional
image registration
image database
artificial neural networks
image features
pattern recognition
image classification
lighting conditions
region of interest
image regions
image retrieval
multiple images
image matching
original images
edge detection
image pixels
segmentation algorithm
natural images
multi modal
feature points
multiscale
genetic algorithm