Semi-Supervised 3D Human Pose Estimation by Jointly Considering Temporal and Multiview Information
Three-dimensional human pose estimation is usually conducted in a supervised manner. However, because collecting labeled 3D skeletons is expensive and time-consuming, semi-supervised methods that need much fewer amount of labeled 3D data are urgently demanded. Some semi-supervised learning methods p...
Main Authors: | Wei-Ta Chu, Zong-Wei Pan |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9298758/ |
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) -
Adaptive Anchor-Based Partial Multiview Clustering
by: Xia Ji, et al.
Published: (2020-01-01) -
Supervised language models for temporal resolution of text in absence of explicit temporal cues
by: Kumar, Abhimanu
Published: (2014) -
Semi-Supervised Learning for Ill-Posed Polarimetric SAR Classification
by: Stefan Uhlmann, et al.
Published: (2014-05-01) -
Human pose estimation and action recognition by multi-robot systems
by: Dogan, Emre
Published: (2017)