Stacked Pooling: Improving Crowd Counting by Boosting Scale Invariance

22 Aug 2018Siyu HuangXi LiZhi-Qi ChengZhongfei ZhangAlexander Hauptmann

In this work, we explore the cross-scale similarity in crowd counting scenario, in which the regions of different scales often exhibit high visual similarity. This feature is universal both within an image and across different images, indicating the importance of scale invariance of a crowd counting model... (read more)

PDF Abstract

Evaluation results from the paper


  Submit results from this paper to get state-of-the-art GitHub badges and help community compare results to other papers.