To understand the real world using various types of data, Artificial Intelligence (AI) is the
most used technique nowadays. While finding the pattern within the analyzed data …

Despite the impressive achievements of Deep Neural Networks (DNNs) in computer vision,
their vulnerability to adversarial attacks remains a critical concern. Extensive research has …

Localizing individuals in crowds is more in accordance with the practical demands of
subsequent high-level crowd analysis tasks than simply counting. However, existing …

Supervised crowd counting relies heavily on costly manual labeling, which is difficult and
expensive, especially in dense scenes. To alleviate the problem, we propose a novel …

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 …

Previous work generally believes that improving the spatial invariance of convolutional
networks is the key to object counting. However, after verifying several mainstream counting …

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

We show that crowd counting can be viewed as a decomposable point querying process.
This formulation enables arbitrary points as input and jointly reasons whether the points are …

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 …

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 …