Login / Signup

Extending Segment Anything Model into Auditory and Temporal Dimensions for Audio-Visual Segmentation.

Juhyeong SeonWoobin ImSebin LeeJumin LeeSung-Eui Yoon
Published in: CoRR (2024)
Keyphrases
  • audio visual
  • temporal context
  • multi modal
  • visual information
  • data analysis
  • input data
  • multiscale
  • low level
  • spatial context
  • temporal segmentation