Dual-Path Transformer for 3D Human Pose Estimation
文献类型：期刊论文
| 作者 | Zhou Lu4 ; Chen Yingying4; Wang Jinqiao1,2,3,4
|
| 刊名 | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
 |
| 出版日期 | 2024 |
| 卷号 | 34期号:5页码:3260-3270 |
| 英文摘要 | Video-based 3D human pose estimation has
achieved great progress, however, it is still difficult to learn
precise 2D-3D projection under some hard cases. Multi-level
human knowledge and motion information serve as two key
elements in the field to conquer the challenges caused by various
factors, where the former encodes various human structure
information spatially and the latter captures the motion change
temporally. Inspired by this, we propose a DualFormer (dual-path
transformer) network which encodes multiple human contexts
and motion detail to perform the spatial-temporal modeling.
Firstly, motion information which depicts the movement change
of human body is embedded to provide explicit motion prior
for the transformer module. Secondly, a dual-path transformer
framework is proposed to model long-range dependencies of both
joint sequence and limb sequence. Parallel context embedding
is performed initially and a cross transformer block is then
appended to promote the interaction of the dual paths which
improves the feature robustness greatly. Specifically, predic
tions of multiple levels can be acquired simultaneously. Lastly,
we employ the weighted distillation technique to accelerate the
convergence of the dual-path framework. We conduct extensive
experiments on three different benchmarks, i.e., Human 3.6M,
MPI-INF-3DHP and HumanEva-I. We mainly compute the
MPJPE, P-MPJPE, PCK and AUC to evaluate the effective
ness of proposed approach and our work achieves competitive
results compared with state-of-the-art approaches. Specifically,
the MPJPE is reduced to 42.8mm which is 1.5mm lower than
PoseFormer on Human3.6M, which proves the efficacy of the
proposed approach. |
| 源URL | [http://ir.ia.ac.cn/handle/173211/57148]  |
| 专题 | 紫东太初大模型研究中心 |
| 通讯作者 | Chen Yingying |
| 作者单位 | 1.Wuhan AI Research 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.Peng Cheng Laboratory 4.Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences |
| 推荐引用方式 GB/T 7714 | Zhou Lu,Chen Yingying,Wang Jinqiao. Dual-Path Transformer for 3D Human Pose Estimation[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2024,34(5):3260-3270. |
| APA | Zhou Lu,Chen Yingying,&Wang Jinqiao.(2024).Dual-Path Transformer for 3D Human Pose Estimation.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,34(5),3260-3270. |
| MLA | Zhou Lu,et al."Dual-Path Transformer for 3D Human Pose Estimation".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 34.5(2024):3260-3270. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。