Weakly-supervised Learning of Human Dynamics

07/17/2020
by   Petrissa Zell, et al.
0

This paper proposes a weakly-supervised learning framework for dynamics estimation from human motion. Although there are many solutions to capture pure human motion readily available, their data is not sufficient to analyze quality and efficiency of movements. Instead, the forces and moments driving human motion (the dynamics) need to be considered. Since recording dynamics is a laborious task that requires expensive sensors and complex, time-consuming optimization, dynamics data sets are small compared to human motion data sets and are rarely made public. The proposed approach takes advantage of easily obtainable motion data which enables weakly-supervised learning on small dynamics sets and weakly-supervised domain transfer. Our method includes novel neural network (NN) layers for forward and inverse dynamics during end-to-end training. On this basis, a cyclic loss between pure motion data can be minimized, i.e. no ground truth forces and moments are required during training. The proposed method achieves state-of-the-art results in terms of ground reaction force, ground reaction moment and joint torque regression and is able to maintain good performance on substantially reduced sets.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/22/2019

Reliable Weakly Supervised Learning: Maximize Gain and Maintain Safeness

Weakly supervised data are widespread and have attracted much attention....
research
08/13/2020

Weakly Supervised Generative Network for Multiple 3D Human Pose Hypotheses

3D human pose estimation from a single image is an inverse problem due t...
research
02/11/2022

Towards Weakly-Supervised Text Spotting using a Multi-Task Transformer

Text spotting end-to-end methods have recently gained attention in the l...
research
08/09/2022

UnderPressure: Deep Learning for Foot Contact Detection, Ground Reaction Force Estimation and Footskate Cleanup

Human motion synthesis and editing are essential to many applications li...
research
10/10/2020

Weakly Supervised Learning for Judging the Credibility of Movie Reviews

In this paper, we deal with the problem of judging the credibility of mo...
research
03/18/2019

Multidimensional ground reaction forces and moments from wearable sensor accelerations via deep learning

Objective: Monitoring athlete internal workload exposure, including prev...

Please sign up or login with your details

Forgot password? Click here to reset