Quantifying and Enhancing Multi-modal Robustness with Modality Preference.

Zequn Yang Yake Wei Ce Liang Di Hu

Published in: CoRR (2024)

Keyphrases

multi modal
audio visual
cross modal
image annotation
high dimensional
multi modality
multiple modalities
video search
single modality
machine learning
computer vision
e learning
face recognition
humanoid robot
semantic concepts