版权说明 操作指南
首页 > 成果 > 详情

Channel and spatial attention based deep object co-segmentation

认领
导出
Link by 万方学术期刊
反馈
分享
QQ微信 微博
成果类型:
期刊论文
作者:
Chen, Jia;Chen, Yasong;Li, Weihao;Ning, Guoqin(宁国勤);Tong, Mingwen*;...
通讯作者:
Tong, Mingwen
作者机构:
[Ning, Guoqin; Chen, Yasong; Chen, Jia; Tong, Mingwen] Cent China Normal Univ, Sch Educ Informat Technol, Wuhan, Peoples R China.
[Li, Weihao] Heidelberg Univ, Visual Learning Lab, Heidelberg, Germany.
[Hilton, Adrian] Univ Surrey, Ctr Vis Speech & Signal Proc, Guildford, Surrey, England.
通讯机构:
[Tong, Mingwen] C
Cent China Normal Univ, Sch Educ Informat Technol, Wuhan, Peoples R China.
语种:
英文
关键词:
Object co-segmentation;Channel attention;Spatial attention;Deep learning
期刊:
Knowledge-Based Systems
ISSN:
0950-7051
年:
2021
卷:
211
页码:
106550
基金类别:
CRediT authorship contribution statement Jia Chen: Conceptualization, acquisition, Writing - original draft, Writing - review and editing. Yasong Chen: Data curation, Software, Writing - original draft. Weihao Li: Supervision. Guoqin Ning: Project administration, Resources, Supervision. Mingwen Tong: Investigation, Resources, Writing - review and editing. Adrian Hilton: Formal analysis, Resources, Writing - review and editing.
机构署名:
本校为第一且通讯机构
院系归属:
教育信息技术学院
摘要:
Object co-segmentation is a challenging task, which aims to segment common objects in multiple images at the same time. Generally, common information of the same object needs to be found to solve this problem. For various scenarios, common objects in different images only have the same semantic information. In this paper, we propose a deep object co-segmentation method based on channel and spatial attention, which combines the attention mechanism with a deep neural network to enhance the common semantic information. Siamese encoder and decoder structure are used for this task. Firstly, the enc...

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