Att-Sinkhorn: Multimodal Alignment with Sinkhorn-based Deep Attention Architecture.

Qianxia Ma Ming Zhang Yan Tang Zhen Huang

Published in: ICAC (2023)

Keyphrases

management system
real time
data sets
multi modal
artificial intelligence
knowledge base
multimodal interaction
data mining
multimedia
bayesian networks
software architecture
visual attention
multi layer
data flow