Multi-modal Learning with Prior Visual Relation Reasoning.

Zhuoqian Yang Jing Yu Chenghao Yang Zengchang Qin Yue Hu

Published in: CoRR (2018)

Keyphrases

multi modal
cross modal
auto annotation
prior knowledge
video search
high dimensional
multi modality
audio visual
semantic concepts
image processing
low level
x ray
image annotation
automatic image annotation
fusing multiple