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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use APS instead of SAGGB | SAGGB · H3.6M average, 1000 ms | MPJPE (mm): 122.8 -> 92.4 | Improved |
| use APS instead of DPnet | DPnet · CMU Mocap average, 1000 ms | MPJPE (mm): 91.3 -> 74.2 | Improved |
| use APS instead of FDU | FDU · 3DPW average, 1000 ms | MPJPE (mm): 94.5 -> 89.3 | Improved |
| add data perceptual module (quotient space) to E+L (ablation) | APS · H3.6M ablation, average 160 ms | MPJPE (mm): 20.1 -> 17.7 | Improved |
| use quotient space instead of 3D poses (ablation) | APS · H3.6M ablation, average 1000 ms | MPJPE (mm): 110.5 -> 92.4 | Improved |
| use decoupled spatio-temporal attention instead of standard Transformer (ablation) | APS · H3.6M ablation, average 1000 ms | MPJPE (mm): 93.5 -> 92.4 | Improved |
| add APS to SAGGB | SAGGB · H3.6M model-agnostic, 1000 ms | MPJPE (mm): 57.3 -> 50.5 | Improved |
| add APS to FDU | FDU · H3.6M model-agnostic, 1000 ms | MPJPE (mm): 59.3 -> 56.1 | Improved |
| add APS to LTD | LTD · H3.6M model-agnostic, 1000 ms | MPJPE (mm): 74.1 -> 72.0 | Improved |
| add APS to BiGAN | BiGAN · H3.6M model-agnostic, 1000 ms | MPJPE (mm): 84.1 -> 83.5 | No 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.
- MSR-GCN — MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Prediction (ICCV 2021) · better on 2 of 2 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
- Learning Progressive Joint Propagation for Human Motion Prediction (ECCV 2020 · similarity 0.88)
- Investigating Pose Representations and Motion Contexts Modeling for 3D Motion Prediction (TPAMI 2022 · similarity 0.88)
- MotionBERT: A Unified Perspective on Learning Human Motion Representations (ICCV 2023 · similarity 0.88)
- Scene-aware Human Motion Forecasting via Mutual Distance Prediction (ECCV 2024 · similarity 0.88)
- Look-Ahead Before You Leap: End-to-End Active Recognition by Forecasting the Effect of Motion (ECCV 2016 · similarity 0.88)
- HVIS: A Human-like Vision and Inference System for Human Motion Prediction (AAAI 2025 · similarity 0.87)
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.
