# Beatv2 Eval

> Evaluates cross-dataset generalization of co-speech gesture generation on a standard English benchmark, measuring gesture quality, beat consistency, and diversity. Use when the user wants to benchmark on BEATv2, or asks about evaluating this task. Reports FGD.

- Skill: `qhjqhj00/beatv2-eval` (Agent Skill)
- Install (CLI): `npx skillmds add qhjqhj00/beatv2-eval`
- Raw SKILL.md: https://api.skillmd.com/api/skills/qhjqhj00/beatv2-eval/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: qhjqhj00 (https://skillmd.com/u/qhjqhj00)
- Updated: 2026-09-08
- Page: https://skillmd.com/skills/qhjqhj00/beatv2-eval

---


# beatv2-eval

> SentiAvatar: Towards Expressive and Interactive Digital Humans — Chuhao Jin et al. (2026) (arXiv:2604.02908, 2026)

## What this evaluates

Evaluates cross-dataset generalization of co-speech gesture generation on a standard English benchmark, measuring gesture quality, beat consistency, and diversity.

## Datasets

- **BEATv2** — total ?; splits: test (-1)

## Metrics

- `FGD` **(primary)** — range: other
  - Fréchet Gesture Distance measuring gesture quality distribution match. Lower is better.
- `BC` — range: [0, 1]
  - Beat Consistency measuring synchronization with audio beats. Higher is better.
- `Diversity` — range: other
  - Mean pairwise L2 distance among motion latent features. Higher is better.

## Input / output format

**Input**: Audio and text conditioning.

**Output**: Generated 3D co-speech gesture sequences.

## Scoring recipe

```python
FGD: Compute mean and covariance of real vs generated gesture latent features; FGD = ||μ_r - μ_g||^2 + Tr(Σ_r + Σ_g - 2(Σ_r Σ_g)^0.5).
BC: Measure consistency of generated gestures with audio beat events.
Diversity: Compute mean pairwise L2 distance among generated gesture latent features.
```

## Common pitfalls

- FGD and BC are standard BEATv2 metrics; lower FGD and higher BC indicate better performance.
- Diversity is computed on BEATv2's latent space, not raw coordinates.
- Model is retrained on BEATv2 before evaluation to verify cross-dataset generalization.

## Evidence (verbatim from paper)

> On BEATv2, we follow the standard protocol and report FGD ($\downarrow$, Fréchet Gesture Distance), BC ($\uparrow$, Beat Consistency), and Diversity.

## Citation

```bibtex
@misc{jin2026sentiavatar,
  title={SentiAvatar: Towards Expressive and Interactive Digital Humans},
  author={Chuhao Jin et al. (2026)},
  year={2026},
  note={arXiv:2604.02908}
}
```

- arXiv: 2604.02908