MTCNet improves crowd counting accuracy by adding an auxiliary count-group classification task to a shared VGG-16 and dilated-convolution density estimator.
ShanghaiTech dataset The ShanghaiTech dataset [9] comprises 1198 annotat ed images with to tal 330,165 people in them
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MTCNET: Multi-task Learning Paradigm for Crowd Count Estimation
MTCNet improves crowd counting accuracy by adding an auxiliary count-group classification task to a shared VGG-16 and dilated-convolution density estimator.