AI Paper Atlas

Research map / 3D vision / Human pose estimation

Propagating LSTM: 3D Pose Estimation based on Joint Interdependency

Kyoungoh Lee, Inwoong Lee, Sanghoon Lee

ECCV 2018 · 3D vision › Human pose estimation · approach: Monocular 2D-to-3D pose lifting · 248 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
replace the single LSTM with connected propagating LSTMs (ablation)3D pose lifting network (S=1, T=1) · Human3.6M Protocol 1MPJPE (mm): 108.5 -> 58.4Improved
add multi-stage refinement (1 to 3 stages) (ablation)p-LSTMs · Human3.6M Protocol 1MPJPE (mm): 58.4 -> 55.8Improved
add multi-stage refinement (1 to 3 stages) (ablation)single LSTM baseline · Human3.6M Protocol 1MPJPE (mm): 108.5 -> 104.3Improved
use 3 input frames instead of 1 (ablation)p-LSTMs (S=3) · Human3.6M Protocol 1MPJPE (mm): 55.8 -> 52.8Improved
use 3 input frames instead of 1 (ablation)single LSTM baseline (S=3) · Human3.6M Protocol 1MPJPE (mm): 104.3 -> 97.6Improved
use 10 input frames instead of 3 (ablation)p-LSTMs (S=3) · Human3.6M Protocol 1MPJPE (mm): 52.8 -> 68.8Hurt
use 5 input frames instead of 3 (ablation)p-LSTMs (S=3) · Human3.6M Protocol 1MPJPE (mm): 52.8 -> 60.2Mixed
add auxiliary 2D pose in the pose depth cue (replacement instead of elimination and addition) (ablation)p-LSTMs (S=3, T=1) · Human3.6M Protocol 1MPJPE (mm): 87.6 -> 55.8Improved
use replacement cue instead of concatenation cue (ablation)p-LSTMs (S=3, T=1) · Human3.6M Protocol 1MPJPE (mm): 79.8 -> 55.8Improved
propagate outward from the body center instead of inward (ablation)p-LSTMs (S=3, T=1) · Human3.6M Protocol 1MPJPE (mm): 83.6 -> 55.8Improved
p-LSTMs versus prior best single-frame methodp-LSTMs vs Sun ICCV'17 · Human3.6M Protocol 1MPJPE (mm): 59.1 -> 55.8Improved
p-LSTMs versus Martinez with GT 2D inputp-LSTMs vs Martinez ICCV'17 · Human3.6M Protocol 1 (GT 2D)MPJPE (mm): 45.5 -> 40.9Improved

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