Login / Signup

Induction Network: Audio-Visual Modality Gap-Bridging for Self-Supervised Sound Source Localization.

Tianyu LiuPeng ZhangWei HuangYufei ZhaTao YouYanning Zhang
Published in: CoRR (2023)
Keyphrases
  • audio visual
  • sound source
  • source localization
  • multi modal
  • visual information
  • wireless sensor networks
  • visual data
  • multi stream
  • domain knowledge
  • multimedia
  • audio features
  • machine learning
  • spatio temporal