Login / Signup

Audio-Visual Class Association Based on Two-stage Self-supervised Contrastive Learning towards Robust Scene Analysis.

Kei SuzukiKatsutoshi ItoyamaKenji NishidaKazuhiro Nakadai
Published in: SII (2023)
Keyphrases
  • scene analysis
  • audio visual
  • multi modal
  • visual data
  • emotion recognition
  • feature selection
  • three dimensional
  • image sequences
  • face recognition