Research map / 3D vision / Human pose estimation
Towards Motion Turing Test: Evaluating Human-Likeness in Humanoid Robots
Mingzhe Li, Mengyin Liu, Zekai Wu, Xincheng Lin, Junsheng Zhang, Ming Yan, Zengye Xie, Changwang Zhang, Chenglu Wen, Lan Xu, Siqi Shen, Cheng Wang
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 |
|---|---|---|---|
| add temporal encoder (BiLSTM) to PTR-Net (ablation) | PTR-Net · HHMotion | Spearman rho: 0.3610 -> 0.6841 | Improved |
| add attention pooling to PTR-Net (ablation) | PTR-Net · HHMotion | Spearman rho: 0.6255 -> 0.6841 | Improved |
| add smoothness regularizer Lreg (ablation) | PTR-Net · HHMotion | Spearman rho: 0.6215 -> 0.6841 | Improved |
| add attention pooling (ablation) | PTR-Net · HHMotion | MAE: 0.6185 -> 0.5813 | Improved |
| use trained PTR-Net instead of zero-shot Gemini 2.5 Pro | human-likeness assessment · HHMotion | MAE: 1.2682 -> 0.5813 | Improved |
| add prototype examples (PDE) to Gemini prompting vs direct evaluation (ablation) | Gemini 2.5 Pro · HHMotion | Spearman rho: 0.1609 -> 0.2188 | Improved |
| generic chain-of-thought prompting (DE-CoT) vs direct evaluation (ablation) | Gemini 2.5 Pro · HHMotion | MAE: 1.3105 -> 1.6040 | Hurt |
| posture-aware CoT instead of generic CoT (ablation) | Gemini 2.5 Pro · HHMotion | Spearman rho: 0.1353 -> 0.2303 | Improved |
| PTR-Net vs fine-tuned MotionBERT | human-likeness regression · HHMotion | Spearman rho: 0.6142 -> 0.6841 | Improved |
| fine-tune MotionBERT backbone instead of frozen (ablation) | MotionBERT · HHMotion | Spearman rho: 0.5315 -> 0.6142 | Improved |
Closest papers by meaning
- Universal Humanoid Motion Representations for Physics-Based Control (ICLR 2024 · similarity 0.89)
- PDF-HR: Pose Distance Fields for Humanoid Robots (NeurIPS 2026 · similarity 0.88)
- SUGAR: A Scalable Human-Video-Driven Generalizable Humanoid Loco-Manipulation Learning Framework (NeurIPS 2026 · similarity 0.87)
- H-GAP: Humanoid Control with a Generalist Planner (ICLR 2024 · similarity 0.87)
- MotionPRO: Exploring the Role of Pressure in Human MoCap and Beyond (CVPR 2025 · similarity 0.87)
- Humanoid Locomotion as Next Token Prediction (NeurIPS 2024 · 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.
