A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf
.
Crowd Counting Network with Self-attention Distillation
2020
Journal of Robotics, Networking and Artificial Life (JRNAL)
A B S T R A C T Context information is essential for crowd counting network to estimate crowd numbers, especially in the congested scene accurately. However, shallow layers of common crowd counting networks (i.e., congested scene recognition network) do not own large receptive filed so that they can't efficiently utilize context information from the crowd scene. To solve this problem, in this paper, we propose a crowd counting network with self-attention distillation. Each input image is first
doi:10.2991/jrnal.k.200528.009
fatcat:gh6hsa5snrbq7azl7wnj5usdbm