Sign in

Resnet-Conformer Network using Multi-Scale Channel Attention for Sound Event Localization and Detection in Real Scenes.

Lihua XueHongqing LiuYi ZhouLu Gan
Published in: WCSP (2023)
Keyphrases
  • real scenes
  • multiscale
  • event detection
  • augmented reality
  • image processing
  • depth map
  • image sequences
  • viewpoint
  • computer vision
  • pairwise
  • image data
  • ground truth
  • post processing
  • stereo pair