A soft-assignment Bayesian loss that supervises expected counts at each annotated point improves crowd counting accuracy over pixel-wise density-map regression on four benchmarks.
Cumulative attribute space for age and crowd density estimation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Bayesian Loss for Crowd Count Estimation with Point Supervision
A soft-assignment Bayesian loss that supervises expected counts at each annotated point improves crowd counting accuracy over pixel-wise density-map regression on four benchmarks.