版权说明 操作指南
首页 > 成果 > 详情

Multi-stream CNN: Learning representations based on human-related regions for action recognition

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:
Tu, Zhigang;Xie, Wei(谢伟);Qin, Qianqing*;Poppe, Ronald;Veltkamp, Remco C.;...
通讯作者:
Qin, Qianqing
作者机构:
[Tu, Zhigang] Nanyang Technol Univ, Sch Elect & Elect Engn, Singapore 639798, Singapore.
[Xie, Wei] Cent China Normal Univ, Sch Comp, LuoyuRd 152, Wuhan, Hubei, Peoples R China.
[Qin, Qianqing] Wuhan Univ, State Key Lab Informat Engn Surveying Mapping & R, LuoyuRd 129, Wuhan, Hubei, Peoples R China.
[Poppe, Ronald; Veltkamp, Remco C.] Univ Utrecht, Dept Informat & Comp Sci, Princetonpl 5, Utrecht, Netherlands.
[Li, Baoxin] Arizona State Univ, Sch Comp Informat, Decis Syst Engn, Tempe, AZ 85287 USA.
通讯机构:
[Qin, Qianqing] W
Wuhan Univ, State Key Lab Informat Engn Surveying Mapping & R, LuoyuRd 129, Wuhan, Hubei, Peoples R China.
语种:
英文
关键词:
Convolutional Neural Network;Action recognition;Multi-Stream;Motion salient region
期刊:
Pattern Recognition
ISSN:
0031-3203
年:
2018
卷:
79
期:
1
页码:
32-43
基金类别:
This work is supported by the Singapore Ministry of Education Academic Research Fund Tier 2 MOE2015-T2-2-114 , and by grants from Office of Naval Research, US. Any opinions expressed in this material are those of the authors and do not necessarily reflect the views of ONR. It was also supported by the Natural Science Foundation of China ( 61501198 ), Natural Science Foundation of Hubei Province ( 2014CFB461 ), Wuhan Youth Science and Technology Chenguang program (2014072704011248), the Dutch national program COMMIT and Dutch NWO TOP grant ARBITER.
机构署名:
本校为其他机构
院系归属:
计算机学院
摘要:
The most successful video-based human action recognition methods rely on feature representations extracted using Convolutional Neural Networks (CNNs). Inspired by the two-stream network (TS-Net), we propose a multi-stream Convolutional Neural Network (CNN) architecture to recognize human actions. We additionally consider human-related regions that contain the most informative features. First, by improving foreground detection, the region of interest corresponding to the appearance and the motion of an actor can be detected robustly under realis...

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