Modeling Intra- and Inter-Modal Alignment with Optimal Transport for Visual Dialog.

Renjie Zheng Qin Chen Jie Zhou Junfeng Tian Liang He

Published in: ICTAI (2023)

Keyphrases

visual information
optimal strategy
optimal solution
natural language
worst case
visual features
image alignment
optimal control
modal logic
machine learning
data sets
low level
pairwise
high level
visual data
visual cues
modeling language
knowledge base
visual perception