MDS: A Fine-Grained Dataset for Multi-Modal Dialogue Summarization.

Zhipeng Liu Xiaoming Zhang Litian Zhang Zelong Yu

Published in: LREC/COLING (2024)

Keyphrases

multi modal
fine grained
coarse grained
access control
video search
cross modal
high dimensional
uni modal
tightly coupled
audio visual
semantic concepts
multidimensional scaling
co occurrence
feature set
image annotation
fusing multiple