Login / Signup

V2A-Mapper: A Lightweight Solution for Vision-to-Audio Generation by Connecting Foundation Models.

Heng WangJianbo MaSantiago PascualRichard CartwrightWeidong Cai
Published in: AAAI (2024)
Keyphrases
  • lightweight
  • multimedia
  • probabilistic model
  • data driven
  • real time
  • optimal solution
  • vision system
  • dos attacks
  • computer vision
  • signal processing
  • model selection
  • rfid tags