Dynamic Multi-modal Prompting for Efficient Visual Grounding.

Wansen Wu Ting Liu Youkai Wang Kai Xu Quanjun Yin Yue Hu

Published in: PRCV (7) (2023)

Keyphrases

multi modal
cross modal
video search
multi modality
audio visual
semantic concepts
visual information
multiple modalities
single modality
machine learning
metadata
high dimensional
low level
image annotation