Login / Signup

MSSTNet: Multi-scale facial videos pulse extraction network based on separable spatiotemporal convolution and dimension separable attention.

Changchen ZhaoHongsheng WangYuanjing Feng
Published in: Virtual Real. Intell. Hardw. (2023)
Keyphrases
  • multiscale
  • spatial and temporal
  • spatiotemporal features
  • face recognition
  • video sequences
  • edge detection
  • space time
  • multimedia
  • face images
  • scale space
  • human faces
  • video frames