A Training Method For VideoPose3D With Ideology of Action Recognition
Not on the map. Why?
Abstract (arXiv)
Action recognition and pose estimation from videos are closely related to understand human motions, but more literature focuses on how to solve pose estimation tasks alone from action recognition. This research shows a faster and more flexible training method for VideoPose3D which is based on action recognition. This model is fed with the same type of action as the type that will be estimated, and different types of actions can be trained separately. Evidence has shown that, for common pose-estimation tasks, this model requires a relatively small amount of data to carry out similar results with the original research, and for action-oriented tasks, it outperforms the original research by 4.5% with a limited receptive field size and training epoch on Velocity Error of MPJPE. This model can handle both action-oriented and common pose-estimation problems.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 8 of its 19 references that are in the map. First posted on arXiv 13 Jun 2022.
Builds on
8 of 19 references.
References · 8
- 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
- 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 403
- 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 221
- 2016Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learningcited by 209
- 20182D/3D Pose Estimation and Action Recognition using Multitask Deep Learningcited by 103
- 2015Maximum-Margin Structured Learning with Deep Networks for 3D Human Pose Estimationcited by 37
- 2016Training a Feedback Loop for Hand Pose Estimationcited by 21
- 2016Pose for Action - Action for Posecited by 16
Built on by
Not cited yet.