Human36m Pose Forecasting Eval

---
name: human36m-pose-forecasting-eval
description: Evaluates the ability of models to forecast future 3D human poses over a 1-second horizon given a short 40ms observation window. It probes long-term temporal prediction and personalization to individual-specific motion patterns. Use when the user wants to benchmark on Human3.6M, or asks about evaluating this task. Reports MPJE.
metadata:
  skill_kind: dataset_eval
  source_arxiv: 2312.03528
  bibtex_key: priisalu2023personalizedposeforecasting
  confidence: high
---

# human36m-pose-forecasting-eval

> Personalized Pose Forecasting — Priisalu et al. (2023) (arXiv:2312.03528, 2023)

## What this evaluates

Evaluates the ability of models to forecast future 3D human poses over a 1-second horizon given a short 40ms observation window. It probes long-term temporal prediction and personalization to individual-specific motion patterns.

## Datasets

- **Human3.6M** — total 3600000; splits: train (-1), val (-1), test (-1)

## Metrics

- `MPJE` **(primary)** — range: other (mm or degrees)
  - Mean Per Joint Position Error (or MAE) computed as the average absolute difference between predicted and ground-truth joint coordinates or Euler angles across all dimensions and prediction steps.

## Input / output format

**Input**: 40ms observation window of 3D human pose sequences (represented as 48 Euler angles or 66 joint position dimensions).

**Output**: Predicted 3D human pose sequence over a 1-second future horizon (25 steps at 40ms resolution).

## Scoring recipe

```python
def compute_mpje(predictions, ground_truth):
    # predictions, ground_truth: (T, J) arrays
    # T = 25 steps (1s horizon), J = 48 or 66 dimensions
    errors = np.abs(predictions - ground_truth)
    return np.mean(errors)
```

## Common pitfalls

- The input window is only 40ms, but the prediction horizon is 1s (25 steps); confusing observation vs prediction length leads to incorrect evaluation setup.
- MPJE and MAE are used interchangeably depending on whether Euler angles (48D) or joint positions (66D) are evaluated; units differ (degrees vs mm), so direct numerical comparison across representations is invalid.
- Splits are subject-based (1,6,7,9 train; 11 val; 5 test), not frame-based, meaning models are evaluated on unseen individuals rather than temporal generalization on the same person.

## Evidence (verbatim from paper)

> We report forecasting error, that is MPJE or MAE.

## Citation

```bibtex
@misc{priisalu2023personalizedposeforecasting,
  title={Personalized Pose Forecasting},
  author={Priisalu et al. (2023)},
  year={2023},
  note={arXiv:2312.03528}
}
```

- arXiv: 2312.03528