A crowd counting network that trains a global count regressor with multi-scale density map supervision via gradient fusion, and detaches the auxiliary branches at inference.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Deep Density-aware Count Regressor
A crowd counting network that trains a global count regressor with multi-scale density map supervision via gradient fusion, and detaches the auxiliary branches at inference.