版权说明 操作指南
首页 > 成果 > 详情

GMDL: Toward precise head pose estimation via Gaussian mixed distribution learning for students’ attention understanding

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:
Liu, Tingting;Yang, Bing;Liu, Hai;Ju, Jianping;Tang, Jianyin;...
通讯作者:
Liu, H;Ju, JP
作者机构:
[Yang, Bing; Liu, Tingting] Hubei Univ, Sch Educ, 368 Youyi Rd, Wuhan 430062, Hubei, Peoples R China.
[Subramanian, Sriram; Liu, Tingting; Zhang, Zhaoli; Liu, Hai] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Peoples R China.
[Ju, Jianping] Hubei Business Coll, Sch Artificial Intelligence, Wuhan 430079, Peoples R China.
[Tang, Jianyin] Changchun Univ Sci & Technol, Sch Electromech Engn, Changchun 130022, Peoples R China.
[Liu, Hai] UCL, UCL Interact Ctr, London, England.
通讯机构:
[Ju, JP ] H
[Liu, H ] C
Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Peoples R China.
Hubei Business Coll, Sch Artificial Intelligence, Wuhan 430070, Peoples R China.
语种:
英文
关键词:
Attention understanding;Gaussian mixed distribution;Infrared head pose estimation;Infrared imaging;Label learning;Learning behavior analysis;Regularization
期刊:
Infrared Physics & Technology
ISSN:
1350-4495
年:
2022
卷:
122
页码:
104099
基金类别:
Two public benchmark datasets are selected for our comparison experiments, such as Pointing’04, and AFW datasets. To simulate the infrared images, all the RGB images in the experimental datasets are converted to gray images. The experimental datasets are shown in Fig. 5. Pointing’04 [1], [20] consists of 2790 images and angle label pairs. Those head pose images are captured from 15 different individuals at two different times. The angel labels are distributed in 9 pitch angles and 13 yaw
机构署名:
本校为通讯机构
院系归属:
国家数字化学习工程技术研究中心
摘要:
Students’ head pose estimation is a very difficult task since the training data is insufficient for many head pose angles. In this study, we consider each head pose image as a Gaussian mixed distribution other than the traditional hard label, in which the adjacent head pose images can provide supplementary information for the target image. Specifically, the Gaussian mixed distribution covers the current head pose image and its adjacent 8 head pose images. Each label of head pose image describes the similar degree between the current image and ...

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