While the performance of crowd counting via deep learning has been improved dramatically in the recent years, it remains an ingrained problem due to cluttered backgrounds and …
VA Sindagi, R Yasarla… - Proceedings of the IEEE …, 2019 - openaccess.thecvf.com
In this work, we propose a novel crowd counting network that progressively generates crowd density maps via residual error estimation. The proposed method uses VGG16 as the …
Z Ma, X Hong, X Wei, Y Qiu… - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
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 …
B Chen, Z Yan, K Li, P Li, B Wang… - Proceedings of the …, 2021 - openaccess.thecvf.com
In crowd counting, due to the problem of laborious labelling, it is perceived intractability of collecting a new large-scale dataset which has plentiful images with large diversity in …
Crowd counting has attracted increasing attentions in recent years due to its challenges and wide societal applications. Despite persevering efforts made by the research community …
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 …
Y Xu, Z Zhong, D Lian, J Li, Z Li… - Proceedings of the …, 2021 - openaccess.thecvf.com
To fully leverage the data captured from different scenes with different view angles while reducing the annotation cost, this paper studies a novel crowd counting setting, ie only using …
Research in neural networks in the field of computer vision has achieved remarkable accuracy for point estimation. However, the uncertainty in the estimation is rarely addressed …
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 …