FaSRnet: a feature and semantics refinement network for human pose estimation

Yuanhong ZHONG; Qianfeng XU; Daidi ZHONG; Xun YANG; Shanshan WANG

doi:10.1631/FITEE.2200639

Your Location：

Home >

Browse articles >

FaSRnet: a feature and semantics refinement network for human pose estimation

Regular Papers | Updated：2024-04-29

- FaSRnet: a feature and semantics refinement network for human pose estimation
  Enhanced Publication
- FaSRnet：用于人体姿态估计的特征和语义修正网络
- “2023年12月1日，来自重庆大学生物工程学院的ZHONG Daidi团队和微电子与通信工程学院的ZHONG Yuanhong团队在《Frontiers of Information Technology & Electronic Engineering》杂志上发表了一篇重要论文。该研究针对多帧人体姿态估计的挑战性问题，提出了一种创新的框架，通过特征和语义层面的精细化来提升姿态估计的准确性。论文指出，由于运动模糊、视频失焦和遮挡等因素，多帧人体姿态估计一直是研究的难点。大多数现有方法主要依赖对最终热图的优化来利用帧间的时间一致性，但这种做法忽视了特征层面的精细化。为此，ZHONG团队提出了一种新的方法，不仅对齐辅助特征与当前帧特征以减少特征分布差异带来的损失，还利用注意力机制融合这两种特征。在语义层面，团队引入相邻热图间的差异信息作为辅助特征来优化当前热图。该方法在PoseTrack2017和PoseTrack2018等大型基准数据集上进行了验证，并取得了显著成效。这一研究成果不仅为人体姿态估计领域提供了新的解决方案，也为未来相关研究开辟了新方向，并为相关体系建设奠定了坚实基础。”
  
  ”
- Frontiers of Information Technology & Electronic Engineering Vol. 25, Issue 4, Pages: 513-526(2024)
- Affiliations：
  
  1.School of Microelectronics and Communication Engineering, Chongqing University, Chongqing 400044, China
  2.Bioengineering College of Chongqing University, Chongqing University, Chongqing 400044, China
  3.School of Information Science and Technology, University of Science and Technology of China, Hefei 230039, China
  4.Institutes of Physical Science and Information Technology, Anhui University, Hefei 230039, China
- Author bio：
  
  ‡Corresponding author
  daidi.zhong@cqu.edu.cn
- Funds：
- DOI：10.1631/FITEE.2200639
  CLC： TP391
- Published： April 2024，
  
  Received：12 December 2022，
  
  Accepted：27 June 2023
Scan for full text
Yuanhong ZHONG, Qianfeng XU, Daidi ZHONG, et al. FaSRnet: a feature and semantics refinement network for human pose estimation. [J]. Frontiers of Information Technology & Electronic Engineering 25(4):513-526(2024)
DOI：

Yuanhong ZHONG, Qianfeng XU, Daidi ZHONG, et al. FaSRnet: a feature and semantics refinement network for human pose estimation. [J]. Frontiers of Information Technology & Electronic Engineering 25(4):513-526(2024) DOI： 10.1631/FITEE.2200639.

Views

Downloads

CSCD

Alert me when the article has been cited

Submit

Tools

Publicity Resources

RFPose-OT: RF-based 3D human pose estimation via optimal transport theory

Related Author

Cong YU

Dongheng ZHANG

Zhi WU

Zhi LU

Chunyang XIE

Yang HU

Yan CHEN

Cong Yu

Related Institution

School of Information and Communication Engineering, University of Electronic Science and Technology of China

School of Cyber Science and Technology, University of Science and Technology of China

School of Information Science and Technology, University of Science and Technology of China

University of Electronic Science and Technology of China

University of Science and Technology of China

Address：Zhejiang University Press, 148 Tianmushan Road, Hangzhou, China Postal code：310028
Tel：+86-571-88273162 Email：fitee@zju.edu.cn
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰

FaSRnet: a feature and semantics refinement network for human pose estimation

DOI：10.1631/FITEE.2200639