What's new

Multimodal Adversarial Networks


"To the best of our knowledge, the proposed MAN could be one of the first works to specifically design for the multimodal representation learning (more than two modalities) with adversarial learning."

CODE by primary author: https://github.com/penghu-cs

1-s2.0-S0950705119302230-gr1.jpg
http://www.scopus.com/scopus/inward...65829043&md5=4c23e260d35923da9610555cea5d458d
Citing Articles (23)

 
Last edited:

Daniel

Administrator
Staff member
Mar 21, 2021
142
0

"Our CAN is a supervised method, which needs all the training data to be labeled. However, it is time- and cost-prohibitive to obtain well-labeled data, which will be more serious for multiple modalities. Therefore, as future work, we plan to investigate how to apply our CAN in a semi-supervised setting under which only a few samples are labeled."
 
Last edited:
Top