AI Paper Atlas

Research map / 3D vision / Human pose estimation

Breaking the Passive Learning Trap: An Active Perception Strategy for Human Motion Prediction

Juncheng Hu, Zijian Zhang, Zeyu Wang, Guoyu Wang, Yingji Li, Kedi Lyu

AAAI 2026 · 3D vision › Human pose estimation · approach: Human motion prediction · 2 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 APS instead of SAGGBSAGGB · H3.6M average, 1000 msMPJPE (mm): 122.8 -> 92.4Improved
use APS instead of DPnetDPnet · CMU Mocap average, 1000 msMPJPE (mm): 91.3 -> 74.2Improved
use APS instead of FDUFDU · 3DPW average, 1000 msMPJPE (mm): 94.5 -> 89.3Improved
add data perceptual module (quotient space) to E+L (ablation)APS · H3.6M ablation, average 160 msMPJPE (mm): 20.1 -> 17.7Improved
use quotient space instead of 3D poses (ablation)APS · H3.6M ablation, average 1000 msMPJPE (mm): 110.5 -> 92.4Improved
use decoupled spatio-temporal attention instead of standard Transformer (ablation)APS · H3.6M ablation, average 1000 msMPJPE (mm): 93.5 -> 92.4Improved
add APS to SAGGBSAGGB · H3.6M model-agnostic, 1000 msMPJPE (mm): 57.3 -> 50.5Improved
add APS to FDUFDU · H3.6M model-agnostic, 1000 msMPJPE (mm): 59.3 -> 56.1Improved
add APS to LTDLTD · H3.6M model-agnostic, 1000 msMPJPE (mm): 74.1 -> 72.0Improved
add APS to BiGANBiGAN · H3.6M model-agnostic, 1000 msMPJPE (mm): 84.1 -> 83.5No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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