Login / Signup

Multi-level feature fusion based Locality-Constrained Spatial Transformer network for video crowd counting.

Yanyan FangShenghua GaoJing LiWeixin LuoLinfang HeBo Hu
Published in: Neurocomputing (2020)
Keyphrases
  • feature fusion
  • video sequences
  • feature extraction
  • video data
  • space time
  • data sets
  • fuzzy logic
  • multiple features
  • video frames
  • computer vision
  • human actions