Cross-scale Vision Transformer for crowd localization
Crowd localization can provide the positions of individuals and the total number of people, which has great application value for security monitoring and public management, meanwhile it meets the challenges of lighting, occlusion and perspective effect. In recent times, Transformer has been applied...
Main Authors: | Shuang Liu, Yu Lian, Zhong Zhang, Baihua Xiao, Tariq S. Durrani |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2024-02-01
|
Series: | Journal of King Saud University: Computer and Information Sciences |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S1319157824000612 |
Similar Items
-
Congested Crowd Counting via Adaptive Multi-Scale Context Learning
by: Yani Zhang, et al.
Published: (2021-05-01) -
An Automatic Scale-Adaptive Approach With Attention Mechanism-Based Crowd Spatial Information for Crowd Counting
by: Weihang Kong, et al.
Published: (2019-01-01) -
Learning Multi-Level Features to Improve Crowd Counting
by: Zhanqiang Huo, et al.
Published: (2020-01-01) -
Residual Transformer YOLO for Detecting Multi-Scale Crowded Pedestrian
by: Hechao Ye, et al.
Published: (2023-11-01) -
An Enhanced Scale Robust Network for Crowd Counting
by: Caihua Liu, et al.
Published: (2020-01-01)