A parallel-fusion RNN-LSTM architecture for image caption generation.

Minsi Wang Li Song Xiaokang Yang Chuanfei Luo

Published in: ICIP (2016)

Keyphrases

recurrent neural networks
image data
fusion method
image analysis
input image
image segmentation
single image
image classification
high resolution
fusion methods
low level
image features
image content
test images
image collections
visual features
image representation
image regions
region of interest
parallel processing
component labeling
long short term memory
similarity measure
image retrieval
object recognition
multiscale
data fusion
video retrieval
image pixels
keypoints