版权说明 操作指南
首页 > 成果 > 详情

TSGFormer: temporal-aware network and spatial encoding GCN for three-dimensional human pose estimation

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:
Xiao, Xinwang;Zhao, Huihuang;Li, Yuhang;Tang, Peng;Deng, Yue
通讯作者:
Zhao, HH
作者机构:
[Tang, Peng; Li, Yuhang; Zhao, Huihuang; Xiao, Xinwang; Deng, Yue; Zhao, HH] Hengyang Normal Univ, Coll Comp Sci & technol, Hengyang 421008, Peoples R China.
[Zhao, Huihuang; Zhao, HH] Hengyang Normal Univ, Hunan Prov Key Lab Intelligent Informat Proc & App, Hengyang 421008, Peoples R China.
通讯机构:
[Zhao, HH ] H
Hengyang Normal Univ, Coll Comp Sci & technol, Hengyang 421008, Peoples R China.
Hengyang Normal Univ, Hunan Prov Key Lab Intelligent Informat Proc & App, Hengyang 421008, Peoples R China.
语种:
英文
关键词:
Three-dimensional human pose estimation;Transformer;GCN;Prior knowledge
期刊:
Multimedia Systems
ISSN:
0942-4962
年:
2025
卷:
31
期:
3
页码:
1-19
基金类别:
This work was supported by the National Natural Science Foundation of China (61772179,12442056), Hunan Provincial Natural Science Foundation of China (2024JJ5059,2023JJ50095), The Science and Technology Innovation Program of Hunan Province(2016TP1020), The Science and Technology Innovation Project of Hengyang(202250045231), The Industry University Research Innovation Foundation of Ministry of Education Science and Technology Development Center (2020QT09), The "14th Five-Year Plan" Key Disciplines and Application-oriented Special Disciplines of Hunan Province (Xiangjiaotong [2022] 351), and Open Research Fund of The State Key Laboratory of Multimodal Artificial Intelligence Systems(MAIS-2023-09).
机构署名:
本校为第一且通讯机构
院系归属:
计算机科学与技术学院
物理与电子工程学院
摘要:
Transformer-based approaches have significantly driven recent progress in three-dimensional human pose estimation. However, existing transformer-based approaches are still deficient in capturing localized features, and they lack task-specific a priori information by obtaining queries, keys, and values through simple linear mappings. Existing methods lack effective human constraints for model training. We introduce the Spatial Encoding Graph Convolutional Network Transformer (SEGCNFormer), designed to enhance model capacity in capturing local features. In addition, we propose a Temporal-Aware N...

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