AI Paper Atlas

Research map / 3D vision / Human pose estimation

Investigating Pose Representations and Motion Contexts Modeling for 3D Motion Prediction

Zhenguang Liu, Shuang Wu, Shuyuan Jin, Shouling Ji, Qi Liu, Shijian Lu, Li Cheng

TPAMI 2022 · 3D vision › Human pose estimation · approach: Human motion prediction · 94 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
use Stiefel manifold instead of 3D coordinates representation (ablation)AHMR · H3.6mMAE at 400ms: 1.25 -> 0.91Improved
use Stiefel manifold instead of axis angles under L2 loss (ablation)AHMR · H3.6mMAE at 400ms: 1.04 -> 0.99Improved
use Stiefel manifold instead of quaternions under L2 loss (ablation)AHMR · H3.6mMAE at 400ms: 1.02 -> 0.99Improved
use geodesic loss instead of L2 loss with Stiefel manifold (ablation)AHMR · H3.6mMAE at 400ms: 0.99 -> 0.91Improved
use geodesic loss instead of L2 with axis angle representation (ablation)AHMR · H3.6mMAE at 400ms: 1.04 -> 1.09Hurt
use geodesic loss instead of L2 with quaternion representation (ablation)AHMR · H3.6mMAE at 400ms: 1.02 -> 1.10Hurt
train with forward kinematics loss instead of geodesic loss (ablation)AHMR · H3.6m MPEMPE at 400ms: 58.4 -> 23.1Improved
use forward kinematics loss with axis angle or quaternion representation (ablation)AHMR · H3.6m MPEMPE: Fails to ConvergeHurt
add left and right forget gates in the encoder (ablation)AHMR · H3.6mMAE at 400ms: 1.03 -> 0.91Improved
add the sequence level state g (ablation)AHMR · H3.6mMAE at 1000ms: 1.73 -> 1.58Improved
add spatial attention (ablation)AHMR · H3.6mMAE at 400ms: 0.95 -> 0.91Improved
add spatial and temporal attention (ablation)AHMR · H3.6mMAE at 400ms: 1.05 -> 0.91Improved

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