PointerNet: Spatiotemporal Modeling for Crowd Counting in Videos.

Changsheng Liu Yuan Huang Yadong Mu Xiaoming Yu

Published in: ICDLT (2021)

Keyphrases

crowd sourced
spatiotemporal features
video frames
information retrieval
space time
neural network
social networks
decision trees
video sequences
moving objects
active learning
low level
video data
spatial and temporal
modeling framework