Login / Signup
Cross-modal Prompts: Adapting Large Pre-trained Models for Audio-Visual Downstream Tasks.
Haoyi Duan
Yan Xia
Mingze Zhou
Li Tang
Jieming Zhu
Zhou Zhao
Published in:
NeurIPS (2023)
Keyphrases
</>
audio visual
cross modal
multi modal
visual data
pre trained
visual information
face recognition
spatio temporal
probabilistic model