DSNet uses cascaded dense dilated convolution blocks with a multi-scale density level consistency loss to report state-of-the-art results on four standard crowd counting datasets.
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
UNVERDICTED 1representative citing papers
citing papers explorer
-
Dense Scale Network for Crowd Counting
DSNet uses cascaded dense dilated convolution blocks with a multi-scale density level consistency loss to report state-of-the-art results on four standard crowd counting datasets.