Rethinking Global Context in Crowd Counting

doi:10.1007/s11633-023-1475-z

CASIA OpenIR > 学术期刊 > Machine Intelligence Research

	Rethinking Global Context in Crowd Counting
	Guolei Sun 1; Yun Liu 2; Thomas Probst 3; Danda Pani Paudel 1; Nikola Popovic 1; Luc Van Gool 1
发表期刊	Machine Intelligence Research
ISSN	2731-538X
	2024
卷号	21 期号:4 页码:640-651
摘要	This paper investigates the role of global context for crowd counting. Specifically, a pure transformer is used to extract features with global information from overlapping image patches. Inspired by classification, we add a context token to the input sequence, to facilitate information exchange with tokens corresponding to image patches throughout transformer layers. Due to the fact that trans formers do not explicitly model the tried-and-true channel-wise interactions, we propose a token-attention module (TAM) to recalibrate encoded features through channel-wise attention informed by the context token. Beyond that, it is adopted to predict the total person count of the image through regression-token module (RTM). Extensive experiments on various datasets, including ShanghaiTech, UCFQNRF, JHU-CROWD++ and NWPU, demonstrate that the proposed context extraction techniques can significantly improve the performance over the baselines.
关键词	Crowd counting vision transformer global context attention density map
DOI	10.1007/s11633-023-1475-z
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/58564
专题	学术期刊_Machine Intelligence Research
作者单位	1.Computer Vision Lab, ETH Zürich, Zürich 8092, Switzerland 2.Institute for Infocomm Research, A*STAR, Singapore 138632, Singapore 3.Magic Leap, Zürich 8050, Switzerland
推荐引用方式 GB/T 7714	Guolei Sun, Yun Liu, Thomas Probst,et al. Rethinking Global Context in Crowd Counting[J]. Machine Intelligence Research,2024,21(4):640-651.
APA	Guolei Sun, Yun Liu, Thomas Probst, Danda Pani Paudel,Nikola Popovic,& Luc Van Gool.(2024).Rethinking Global Context in Crowd Counting.Machine Intelligence Research,21(4),640-651.
MLA	Guolei Sun,et al."Rethinking Global Context in Crowd Counting".Machine Intelligence Research 21.4(2024):640-651.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
MIR-2023-04-056.pdf（2388KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载