In recent years, urgent needs for counting crowds and vehicles have greatly promoted
research of crowd counting and density estimation. Benefiting from the rapid development of …

In crowd counting, each training image contains multiple people, where each person is
annotated by a dot. Existing crowd counting methods need to use a Gaussian to smooth …

Previous work shows that a better density map representation can improve the performance
of crowd counting. In this paper, we investigate learning the density map representation …

In the last decade, crowd counting and localization attract much attention of researchers due
to its wide-spread applications, including crowd monitoring, public safety, space design, etc …

The mainstream crowd counting methods usually utilize the convolution neural network
(CNN) to regress a density map, requiring point-level annotations. However, annotating …

Crowd localization, predicting head positions, is a more practical and high-level task than
simply counting. Existing methods employ pseudo-bounding boxes or pre-designed …

Abstract Convolutional Neural Network (CNN) based methods generally take crowd
counting as a regression task by outputting crowd densities. They learn the map** …

Scale variation is a deep-rooted problem in object counting, which has not been effectively
addressed by existing scale-aware algorithms. An important factor is that they typically …

In this paper, we address the large scale variation problem in crowd counting by taking full
advantage of the multi-scale feature representations in a multi-level network. We implement …

We introduce a new large scale unconstrained crowd counting dataset (JHU-CROWD++)
that contains “4,372” images with “1.51 million” annotations. In comparison to existing …