Login / Signup

FoleyGAN: Visually Guided Generative Adversarial Network-Based Synchronous Sound Generation in Silent Videos.

Sanchita GhoseJohn J. Prevost
Published in: IEEE Trans. Multim. (2023)
Keyphrases
  • visually guided
  • video sequences
  • video frames
  • video analysis
  • generative model
  • generation process
  • obstacle avoidance
  • data driven
  • human activities
  • video data
  • video content
  • dynamic scenes