AI Paper Atlas

Research map / 3D vision / Human pose estimation

Learning Trajectory Dependencies for Human Motion Prediction

Wei Mao, Miaomiao Liu, Mathieu Salzmann, Hongdong Li

ICCV 2019 · 3D vision › Human pose estimation · approach: Human motion prediction · 570 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 DCT trajectory encoding instead of raw joint angles (ablation)DCT-GCN motion predictor · H3.6M 4-action avg @400msEuler angle error: 0.74 -> 0.71Improved
use DCT trajectory encoding instead of raw 3D coordinates (ablation)DCT-GCN motion predictor · H3.6M 4-action avg @400msMPJPE (mm): 43.1 -> 38.4Improved
add input padding with last observed frame (ablation)DCT-GCN motion predictor · H3.6M 4-action avg @400msEuler angle error: 0.86 -> 0.71Improved
add input padding with last observed frame (ablation)DCT-GCN motion predictor · H3.6M 4-action avg @400msMPJPE (mm): 50.4 -> 38.4Improved
add residual connections (ablation)DCT-GCN motion predictor · H3.6M 4-action avg @400msEuler angle error: 0.83 -> 0.71Improved
add residual connections (ablation)DCT-GCN motion predictor · H3.6M 4-action avg @400msMPJPE (mm): 50.2 -> 38.4Improved
learn graph connectivity instead of pre-defined kinematic tree adjacency (ablation)DCT-GCN motion predictor · H3.6M 4-action avg @400msEuler angle error: 0.88 -> 0.71Improved
learn graph connectivity instead of pre-defined kinematic tree adjacency (ablation)DCT-GCN motion predictor · H3.6M 4-action avg @400msMPJPE (mm): 71.0 -> 38.4Improved
use GCN with learned connectivity instead of fully-connected network (ablation)DCT-GCN motion predictor · H3.6M 4-action avg @400msEuler angle error: 0.76 -> 0.71Improved
use GCN with learned connectivity instead of fully-connected network (ablation)DCT-GCN motion predictor · H3.6M 4-action avg @400msMPJPE (mm): 42.8 -> 38.4Improved
train directly on 3D coordinates instead of angles then converting to 3DDCT-GCN motion predictor · H3.6M 15-action avg @400msMPJPE (mm): 65.0 -> 61.3Improved
compare against AGED w/adv at 1000ms in angle spaceDCT-GCN motion predictor · H3.6M long-term angle error @1000msEuler angle error: 1.09 -> 1.27Hurt

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