Robust Human Pose Estimation for Rotation via Self-Supervised Learning
The detection of abnormal postures, such as that of a reclining person, is a crucial part of visual surveillance. Further, even regular poses can appear rotated because of incongruity between the image and the angle of a pre-installed camera. However, most existing human pose estimation methods focu...
Main Authors: | Kimin Yun, Jongyoul Park, Jungchan Cho |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8995541/ |
Similar Items
-
Deep Learning Methods for 3D Human Pose Estimation under Different Supervision Paradigms: A Survey
by: Dejun Zhang, et al.
Published: (2021-09-01) -
Exploring Rare Pose in Human Pose Estimation
by: Jihye Hwang, et al.
Published: (2020-01-01) -
Improved Human-Object Interaction Detection Through On-the-Fly Stacked Generalization
by: Geonu Lee, et al.
Published: (2021-01-01) -
Improving robustness for pose estimation via stable heatmap regression
by: Chen, L., et al.
Published: (2022) -
Modelling Sign Language with Encoder-Only Transformers and Human Pose Estimation Keypoint Data
by: Rana, Z.A, et al.
Published: (2023)