版权说明 操作指南
首页 > 成果 > 详情

Crowd counting in domain generalization based on multi-scale attention and hierarchy level enhancement

认领
导出
Link by DOI
反馈
分享
QQ微信 微博
成果类型:
期刊论文
作者:
Zhou, Jiarui;Zhang, Jianming;Gui, Yan
通讯作者:
Zhou, JR
作者机构:
[Gui, Yan; Zhang, Jianming; Zhou, Jiarui] Changsha Univ Sci & Technol, Sch Comp & Commun Engn, Changsha 410114, Peoples R China.
通讯机构:
[Zhou, JR ] C
Changsha Univ Sci & Technol, Sch Comp & Commun Engn, Changsha 410114, Peoples R China.
语种:
英文
关键词:
Channel attention;Crowd counting;Domain generalization;Multi-scale features;Spatial attention
期刊:
Scientific Reports
ISSN:
2045-2322
年:
2025
卷:
15
期:
1
页码:
155
基金类别:
2024 National College Students' Innovation and Entrepreneurship Training Program [S202410536035]; National College Students' Innovation and Entrepreneurship Training Program [2023JJ30050, 2024JJ5042]; Hunan Provincial Natural Science Foundation of China
机构署名:
本校为第一且通讯机构
院系归属:
计算机与通信工程学院
摘要:
In order to solve the problem of weak single domain generalization ability in existing crowd counting methods, this study proposes a new crowd counting framework called Multi-scale Attention and Hierarchy level Enhancement (MAHE). Firstly, the model can focus on both the detailed features and the macro information of structural position changes through the fusion of channel attention and spatial attention. Secondly, the addition of multi-head attention feature module facilitates the model's capacity to effectively capture complex dependency relationships between sequence elements. In addition,...

反馈

验证码:
看不清楚,换一个
确定
取消

成果认领

标题:
用户 作者 通讯作者
请选择
请选择
确定
取消

提示

该栏目需要登录且有访问权限才可以访问

如果您有访问权限,请直接 登录访问

如果您没有访问权限,请联系管理员申请开通

管理员联系邮箱:yun@hnwdkj.com