• 综合
  • 标题
  • 关键词
  • 摘要
  • 学者
  • 期刊-刊名
  • 期刊-ISSN
  • 会议名称
搜索

作者:

Chen, Shicun (Chen, Shicun.) | Zhang, Yong (Zhang, Yong.) (学者:张勇) | Yin, Baocai (Yin, Baocai.) (学者:尹宝才) | Wang, Boyue (Wang, Boyue.)

收录:

Scopus SCIE

摘要:

Nowadays, face detection and head pose estimation have a lot of application such as face recognition, aiding in gaze estimation and modeling attention. For these two tasks, it is usually to design two different models. However, the head pose estimation model often depends on the region of interest (ROI) detected in advance, which means that a serial face detector is needed. Even the lightest face detector will slow down the whole forward inference time and cannot achieve real-time performance when detecting the head pose of multiple people. We can see that both face detection and head pose estimation need face features, so a shared face feature map can be used between them. In this paper, a multi-task learning model is proposed that can solve both problems simultaneously. We directly detect the location of the center point of the bounding box of face; at this location, we calculate the size of the bounding box of face and the head attitude. We evaluate our model's performance on the AFLW. The proposed model has great competitiveness with the multi-stage face attribute analysis model, and our model can achieve real-time performance.

关键词:

Multi-task Head pose Face detection Anchor Free

作者机构:

  • [ 1 ] [Chen, Shicun]Beijing Univ Technol, Beijing, Peoples R China
  • [ 2 ] [Zhang, Yong]Beijing Univ Technol, Beijing, Peoples R China
  • [ 3 ] [Yin, Baocai]Beijing Univ Technol, Beijing, Peoples R China
  • [ 4 ] [Wang, Boyue]Beijing Univ Technol, Beijing, Peoples R China

通讯作者信息:

  • 张勇

    [Zhang, Yong]Beijing Univ Technol, Beijing, Peoples R China

电子邮件地址:

查看成果更多字段

相关关键词:

来源 :

PATTERN ANALYSIS AND APPLICATIONS

ISSN: 1433-7541

年份: 2021

期: 4

卷: 24

页码: 1745-1755

3 . 9 0 0

JCR@2022

ESI学科: ENGINEERING;

ESI高被引阀值:87

JCR分区:3

被引次数:

WoS核心集被引频次: 12

SCOPUS被引频次: 10

ESI高被引论文在榜: 0 展开所有

万方被引频次:

中文被引频次:

近30日浏览量: 0

归属院系:

在线人数/总访问数:465/4968794
地址:北京工业大学图书馆(北京市朝阳区平乐园100号 邮编:100124) 联系我们:010-67392185
版权所有:北京工业大学图书馆 站点建设与维护:北京爱琴海乐之技术有限公司