Crowd Counting Network with Self-attention Distillation
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 u...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Atlantis Press
2020-06-01
|
| Series: | Journal of Robotics, Networking and Artificial Life (JRNAL) |
| Subjects: | |
| Online Access: | https://www.atlantis-press.com/article/125941065/view |