.png){kind=icon}
.png){kind=icon}
Return
VMamba-Crowd: Bridging multi-scale features from Visual Mamba for weakly-supervised crowd counting
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patrec.2025.08.005.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• We introduce Visual Mamba into weakly-supervised crowd counting for the first time. • We propose an Adjacent-scale Progressive Bridging Module APBM. • Using coordinated attention to process bridging features. • Our method outperforms most existing weakly-supervised crowd counting networks.
Keywords:
Visual Mamba
weakly-supervised crowd counting
Adjacent-scale Progressive Bridging Module
coordinated attention
crowd counting networks
Journal
IF:
3.3
Papers:
7.9K
Citations:
1.6W