AI Paper Atlas

Research map / 3D vision / Human pose estimation

Estimating 3D Motion and Forces of Human–Object Interactions from Internet Videos

Zongmian Li, Jiří Sedlář, Justin Carpentier, Ivan Laptev, Nicolas Mansard, Josef Šivic

IJCV 2022 · 3D vision › Human pose estimation · approach: Physics and sensor-based motion capture · 11 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 the 3D data term (ablation)generic model · ParkourMPJPE (mm): 117.55 -> 116.13Improved
add the 3D data term (ablation)generic model · Parkour (Muscle-up)MPJPE (mm): 124.12 -> 124.55Hurt
add force magnitude regularization on top of temporal smoothing (ablation)generic model · Parkour (L. sole moment)error (N.m): 23.78 -> 22.91Improved
add temporal and magnitude force regularization (ablation)generic model · Parkour (L. sole moment)error (N.m): 86.54 -> 22.91Improved
add temporal and magnitude force regularization (ablation)generic model · Parkour (L. sole linear force)error (N): 148.74 -> 142.11Improved
add force magnitude regularization (ablation)generic model · Parkour (L. hand linear force)error (N): 109.10 -> 105.07Improved
use action-specific hyperparameters instead of generic onesOurs · ParkourMPJPE (mm): 116.13 -> 115.45Improved
use action-specific hyperparameters instead of generic onesOurs · HandtoolMPJPE (mm): 97.51 -> 94.09Improved
model person-object contact dynamics vs HMR single-frame baselineOurs (generic model) · ParkourMPJPE (mm): 135.65 -> 116.13Improved
model person-object contact dynamics vs HMR single-frame baselineOurs (generic model) · HandtoolMPJPE (mm): 103.49 -> 97.51Improved
model person-object interaction vs Mask R-CNN endpointsOurs (generic model) · Handtool barbell% within 25 px: 33 -> 47Improved
model person-object interaction vs Mask R-CNN endpoints (scythe modelled as line segment)Ours (generic model) · Handtool scythe% within 25 px: 63 -> 51Hurt

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