Product
Help
Pricing
About
Jobs
Log in
Get started
Work
Add to collection
P-STMO: Pre-trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimation
HTML
PDF
Details
Locations
Year:
2022
Type:
conference-paper
Source:
Lecture notes in computer science
Parent work:
Computer Vision – ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part V
DOI:
10.1007/978-3-031-20065-6_27
Authors:
Wenkang Shan,
Zhenhua Liu,
Xinfeng Zhang,
Shanshe Wang,
Siwei Ma,
Wen Gao
show all 6
Institutions:
Peking University,
Huawei Technologies (China),
University of Chinese Academy of Sciences,
Peng Cheng Laboratory
Language:
English
Topic:
Human Pose and Action Recognition
Subfield:
Computer Vision and Pattern Recognition
Field:
Computer Science
Domain:
Physical Sciences
Keywords:
3D human pose estimation,
2D-3D pose estimation,
pre-training,
fine-tuning,
self-supervised pre-training,
denoising autoencoder,
spatiotemporal dependencies
show all 7
Open Access status:
green
OpenAlex ID:
W4312797994
FWCI:
13.08
Cites:
52
Cited by:
287
Related to:
10