EDite-HRNet: Enhanced Dynamic Lightweight High-Resolution Network for Human Pose Estimation

EDite-HRNet: Enhanced Dynamic Lightweight High-Resolution Network for Human Pose Estimation

Lightweight pose estimation models have been widely used in devices with different computing powers, providing convenience for numerous downstream tasks, such as gait estimation, behavior analysis, motion capture, etc. Although these lightweight methods can run on low-performance equipment, their es...

Full description

Bibliographic Details
Main Authors: Liyuheng Rui, Yanyan Gao, Haopan Ren
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Access
Subjects:
Human pose estimation
lightweight network
computational cost
cross-block feature fusion
long-range dependencies
Online Access:https://ieeexplore.ieee.org/document/10235325/

Internet

https://ieeexplore.ieee.org/document/10235325/

Similar Items