This paper investigates crowd counting in the frequency domain, which is a novel direction
compared to the traditional view in the spatial domain. By transforming the density map into …

This paper proposes to handle the practical problem of learning a universal model for crowd
counting across scenes and datasets. We dissect that the crux of this problem is the …

Most recent methods used for crowd counting are based on the convolutional neural
network (CNN), which has a strong ability to extract local features. But CNN inherently fails …

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

Crowd counting is the task of estimating people numbers in crowd images. Modern crowd
counting methods employ deep neural networks to estimate crowd counts via crowd density …

Significant progress on the crowd counting problem has been achieved by integrating larger
context into convolutional neural networks (CNNs). This indicates that global scene context …

Recent works on crowd counting mainly leverage Convolutional Neural Networks (CNNs) to
count by regressing density maps, and have achieved great progress. In the density map …

Dense crowd counting aims to predict thousands of human instances from an image, by
calculating integrals of a density map over image pixels. Existing approaches mainly suffer …

In this work, we tackle the problem of crowd counting in images. We present a Convolutional
Neural Network (CNN) based density estimation approach to solve this problem. Predicting …

To learn a reliable people counter from crowd images, head center annotations are normally
required. Annotating head centers is however a laborious and tedious process in dense …