A Tri-Attention fusion guided multi-modal segmentation network.

Tongxue Zhou Su Ruan Pierre Vera Stéphane Canu

Published in: Pattern Recognit. (2022)

Keyphrases

multi modal
multi modality
fusing multiple
image segmentation
video search
audio visual
single modality
medical images
level set
high dimensional
semantic concepts
segmentation algorithm
energy function
cross modal
segmentation method
region growing
fully automatic
multiscale
similarity measure
feature extraction