AI Paper Atlas

Research map / 3D vision / Human pose estimation

Weakly-supervised Learning of Human Dynamics

Petrissa Zell, Bodo Rosenhahn, Bastian Wandt

ECCV 2020 · 3D vision › Human pose estimation · approach: Human motion prediction · 20 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add cyclic forward-dynamics training on the full motion-set to the supervised baseline (Dynamics Network)Baseline net · Gait data set with 10% of ground-reaction and torque setsjoint torque RMSE and simulated-state RMSEImproved
add the inverse layer and contact loss (cFI-net) to forward-only training (F-net) for domain transfer gait to run (ablation)F-net · Domain transfer gait to runGRF RMSE (N/kg): 3.942 -> 1.445Improved
add the inverse layer and contact loss (cFI-net) to forward-only training (F-net) for domain transfer run to gait (ablation)F-net · Domain transfer run to gaitGRF RMSE (N/kg): 3.579 -> 0.685Improved
use cFI-net instead of F-net on the full gait set (ablation)Dynamics Network · Gait data setGRF RMSE (N/kg): 0.626 -> 0.733Hurt
use F-net instead of the supervised baseline net on the full gait setBaseline net · Gait data setjoint torque RMSE (Nm/kg): 0.055 -> 0.053Improved
use F-net instead of the supervised baseline net on the full gait setBaseline net · Gait data setGRF RMSE (N/kg): 0.591 -> 0.626Hurt
increase angle noise from 0.3 to 2.3 deg (ablation)F-net · Gait data set with angle noiseGRF RMSE (N/kg): 0.626 -> 1.096Hurt
increase angle noise from 0.3 to 2.3 deg (ablation)cFI-net · Gait data set with angle noiseGRF RMSE (N/kg): 0.674 -> 1.143Hurt
train F-net additionally on CMU samples with the forward lossF-net · CMU walking sequences (qualitative)vertical GRF symmetryImproved
add contact loss to inverse-loss training (ablation)cFI-net · Domain transferGRF plausibilityImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy