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

Most existing crowd counting systems rely on the availability of the object location
annotation which can be expensive to obtain. To reduce the annotation cost, one attractive …

In crowd counting datasets, the location labels are costly, yet, they are not taken into the
evaluation metrics. Besides, existing multi-task approaches employ high-level tasks to …

Recent crowd counting approaches have achieved excellent performance. However, they
are essentially based on fully supervised paradigm and require large number of annotated …

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 …

Most existing crowd counting methods require object location-level annotation which is labor-
intensive and time-consuming to obtain. In contrast, weaker annotations that only label the …

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 …

Crowd counting is a challenging task due to factors such as large variations in crowdedness
and severe occlusions. Although recent deep learning based counting algorithms have …

State-of-the-art approaches for crowd counting resort to deepneural networks to predict
density maps. However, counting people in congested scenes remains a challenging task …

We present an unsupervised learning method for dense crowd count estimation. Marred by
large variability in appearance of people and extreme overlap in crowds, enumerating …