The World in My Mind: Visual Dialog with Adversarial Multi-modal Feature Encoding.

Yiqun Yao Jiaming Xu Bo Xu

Published in: NAACL-HLT (1) (2019)

Keyphrases

multi modal
cross modal
video search
single modality
audio visual
multi modality
image features
visual information
auto annotation
high level
high dimensional
feature set
fusing multiple
feature selection
multiple modalities
uni modal