Scene-Aware Prompt for Multi-modal Dialogue Understanding and Generation.

Bin Li Yixuan Weng Ziyu Ma Bin Sun Shutao Li

Published in: NLPCC (2) (2022)

Keyphrases

multi modal
multi modality
audio visual
video sequences
high dimensional
semantic concepts
video search
fusing multiple
input image
computer vision
three dimensional
image sequences
image annotation
visual data
dialogue system
uni modal