Learning to Caption Images with Two-Stream Attention and Sentence Auto-Encoder.

Arushi Goel Basura Fernando Thanh-Son Nguyen Hakan Bilen

Published in: CoRR (2019)

Keyphrases

image database
object recognition
learning process
learning algorithm
image classification
image analysis
image registration
image features
image data
image collections
machine learning
image matching
supervised learning
edge detection
image annotation
low complexity
rate distortion
visual features
three dimensional
wavelet transform
active learning
computational complexity
input image
visual attention
image retrieval
ground truth