Dual‐view 3D human pose estimation without camera parameters for action recognition
Abstract The purpose of 3D human pose estimation is to estimate the 3D coordinates of key points of the human body directly from images. Although multi‐view based methods have better performance and higher precision of coordinate estimation than a single‐view based, they need to know the camera para...
Saved in:
Main Authors: | Long Liu, Le Yang, Wanjun Chen, Xin Gao |
---|---|
Format: | article |
Language: | EN |
Published: |
Wiley
2021
|
Subjects: | |
Online Access: | https://doaj.org/article/b1a281c8a03a41f4b1a5c3d70f0f5386 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Class structure‐aware adversarial loss for cross‐domain human action recognition
by: Wanjun Chen, et al.
Published: (2021) -
Multi‐view intrinsic low‐rank representation for robust face recognition and clustering
by: Zhi‐yang Wang, et al.
Published: (2021) -
A deep learning method for video‐based action recognition
by: Guanwen Zhang, et al.
Published: (2021) -
Latent label mining for group activity recognition in basketball videos
by: Lifang Wu, et al.
Published: (2021) -
Human behaviour recognition with mid‐level representations for crowd understanding and analysis
by: Bangyong Sun, et al.
Published: (2021)