This paper focuses on crowd counting. As large-scale variations often exist within crowd
images, neither fixed-size convolution kernel of CNN nor fixed-size attentions of recent …

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

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 …

Counting high‐density objects quickly and accurately is a popular area of research. Crowd
counting has significant social and economic value and is a major focus in artificial …

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 …

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 …

The accuracy of crowd counting in images has improved greatly in recent years due to the
development of deep neural networks for predicting crowd density maps. However, most …

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 …

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 …

Crowd counting is a fundamental and challenging task that requires rich information to
generate a pixel-level crowd density map. Additionally, the development of thermal sensing …