Login / Signup

Cross-modal Prompts: Adapting Large Pre-trained Models for Audio-Visual Downstream Tasks.

Haoyi DuanYan XiaMingze ZhouLi TangJieming ZhuZhou Zhao
Published in: CoRR (2023)
Keyphrases
  • audio visual
  • cross modal
  • multi modal
  • visual data
  • pre trained
  • probabilistic model
  • visual information