Anomaly detection, aka outlier detection or novelty detection, has been a lasting yet active
research area in various research communities for several decades. There are still some …

Machine learning has become an increasingly ubiquitous technology, as big data continues
to inform and influence everyday life and decision-making. Currently, in medicine and …

State-of-the-art methods for counting people in crowded scenes rely on deep networks to
estimate crowd density. They typically use the same filters over the whole image or over …

In crowd counting datasets, each person is annotated by a point, which is usually the center
of the head. And the task is to estimate the total count in a crowd scene. Most of the state-of …

Recently, counting the number of people for crowd scenes is a hot topic because of its
widespread applications (eg video surveillance, public security). It is a difficult task in the …

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 …

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

Crowd counting has recently attracted increasing interest in computer vision but remains a
challenging problem. In this paper, we propose a trellis encoder-decoder network (TEDnet) …

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 …