EHPE: Skeleton Cues-based Gaussian Coordinate Encoding for Efficient Human Pose Estimation

首页 > 成果 > 详情

认领

导出

Link by DOI

反馈

作者信息关键词期刊信息基础信息归属信息摘要

成果类型：

期刊论文

作者：

Hai Liu;Tingting Liu;Yu Chen;Zhaoli Zhang;You-Fu Li

作者机构：

School of Education, Hubei University, No. 368 Youyi Road, Wuhan, Hubei, China

Department of Mechanical Engineering, City University of Hong Kong, Kowloon, Hong Kong

[Hai Liu; Yu Chen; Zhaoli Zhang] National Engineering Research Center for E-Learning, Central China Normal University, Wuhan, China

City University of Hong Kong Shenzhen Research Institute, Shenzhen, China

[Tingting Liu] School of Education, Hubei University, No. 368 Youyi Road, Wuhan, Hubei, China<&wdkj&>Department of Mechanical Engineering, City University of Hong Kong, Kowloon, Hong Kong

语种：

英文

关键词：

Biological system modeling;Deep learning;Encoding;Feature extraction;gaussian coordinate encoding;Heating systems;human pose estimation;Pose estimation;regularization;Skeleton;skeleton direction;Task analysis

期刊：

IEEE Transactions on Multimedia

ISSN：

1520-9210

年：

2022

页码：

1-12

DOI：

10.1109/TMM.2022.3197364

基金类别：

National Key R&D Program of China (Grant Number: 2021YFC3340802) 10.13039/501100001809-National Natural Science Foundation of China (Grant Number: 62177018, 62173286, 62011530436, 62077020, 62005092 and 61875068) 10.13039/501100012226-Fundamental Research Funds for the Central Universities (Grant Number: CCNU20ZT017 and CCNU2020ZN008)

机构署名：

本校为第一机构

院系归属：

国家数字化学习工程技术研究中心

摘要：

Human pose estimation (HPE) has many wide applications such as multimedia processing, behavior understanding and human-computer interaction. Most previous studies have encountered many constraints, such as restricted scenarios and RGB inputs. To mitigate constraints to estimating the human poses in general scenarios, we present an efficient human pose estimation model (i.e., EHPE) with joint direction cues and Gaussian coordinate encoding. Specifically, we propose an anisotropic Gaussian coordinate coding method to describe the skeleton direction cues among adjacent keypoints. To the best of o...

反馈

产权有误：本人成果被他人认领

数据有误：数据基本信息有误

归属有误：成果的院系归属、机构署名归属有误

其他原因：

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

EHPE: Skeleton Cues-based Gaussian Coordinate Encoding for Efficient Human Pose Estimation

反馈

成果认领

提示

该栏目需要登录且有访问权限才可以访问