AI Paper Atlas

Research map / 3D vision / Human pose estimation

Motion Prediction Using Trajectory Cues

Zhenguang Liu, Pengxiang Su, Shuang Wu, Xuanjing Shen, Haipeng Chen, Yanbin Hao, Meng Wang

ICCV 2021 · 3D vision › Human pose estimation · approach: Human motion prediction · 65 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 trajectory representation (velocities plus last position) instead of pose coordinates (ablation)MPT · H3.6MMPJPE at 80 ms (mm): 11.3 -> 8.3Improved
use trajectory representation instead of pose coordinates, long-term (ablation)MPT · H3.6MMPJPE at 1,000 ms (mm): 111.7 -> 96.4Improved
add learnt implicit connection matrix to fixed skeletal and prior connections (ablation)MPT · H3.6MMPJPEImproved
add fixed skeletal and prior-knowledge connections to the learnt matrix (ablation)MPT · H3.6MMPJPEImproved
model motion in trajectory space with semi-constrained GCN vs best prior methodMPT · H3.6Maverage accuracy: 17.5% accuracy improvementImproved
apply MPT to fish pose prediction vs HMRMPT · Fishaccuracy: 24.1% accuracy improvementImproved
apply MPT to mouse pose prediction vs HMRMPT · Mouseaccuracy: 13.8%Improved
longer prediction horizonMPT · H3.6Madvantage of trajectory representationHurt

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