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

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 …

Recently, developing automated video surveillance systems (VSSs) has become crucial to
ensure the security and safety of the population, especially during events involving large …

Recently, indiscernible scene understanding has attracted a lot of attention in the vision
community. We further advance the frontier of this field by systematically studying a new …

Crowd counting methods typically predict a density map as an intermediate representation
of counting, and achieve good performance. However, due to the perspective phenomenon …

Abstract Domain shift across crowd data severely hinders crowd counting models to
generalize to unseen scenarios. Although domain adaptive crowd counting approaches …

State-of-the-art methods for counting people in crowded scenes rely on deep networks to
estimate crowd density. While effective, these data-driven approaches rely on large amount …

Abstract Data-Free Meta-Learning (DFML) aims to extract knowledge from a collection of pre-
trained models without requiring the original data presenting practical benefits in contexts …

Perspective distortions and crowd variations make crowd counting a challenging task in
computer vision. To tackle it, many previous works have used multi-scale architecture in …

In recent decades, remote sensing object counting has attracted increasing attention from
academia and industry due to its potential benefits in urban traffic, public safety, and road …