Global Context Enhanced Multi-modal Fusion for Referring Image Segmentation.

Jianhua Yang Yan Huang Linjiang Huang Yunbo Wang Zhanyu Ma Liang Wang

Published in: PRCV (1) (2020)

Keyphrases

global context
multi modal fusion
image segmentation
global information
named entities
multiscale
sift descriptors
keywords
image processing
computer vision
image analysis
data mining
expectation maximization
facial features
feature representation
domain specific
co occurrence