# Ntu Rgb D Eval

> Evaluates a model's ability to recognize human activities from RGB videos by leveraging skeleton-driven attention to focus on spatial-temporal regions of interest. It measures classification accuracy under standard cross-subject and cross-view protocols. Use when the user wants to benchmark on NTU-RGB+D, Northwestern-UCLA Multiview, or asks about evaluating this task. Reports accuracy.

- Skill: `qhjqhj00/ntu-rgb-d-eval` (Agent Skill)
- Install (CLI): `npx skillmds add qhjqhj00/ntu-rgb-d-eval`
- Raw SKILL.md: https://api.skillmd.com/api/skills/qhjqhj00/ntu-rgb-d-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/ntu-rgb-d-eval

---


# ntu-rgb-d-eval

> Skeleton Focused Human Activity Recognition in RGB Video — Yu et al. (2020) (arXiv:2004.13979, 2020)

## What this evaluates

Evaluates a model's ability to recognize human activities from RGB videos by leveraging skeleton-driven attention to focus on spatial-temporal regions of interest. It measures classification accuracy under standard cross-subject and cross-view protocols.

## Datasets

- **NTU-RGB+D** — total ?; splits: cross-subject (-1), cross-view (-1)
- **Northwestern-UCLA Multiview** — total ?; splits: cross-view (-1)

## Metrics

- `accuracy` **(primary)** — range: percent
  - Percentage of correctly classified video samples out of the total number of samples in the evaluation split.

## Input / output format

**Input**: RGB video frames and corresponding skeleton joint coordinates for each frame.

**Output**: Predicted activity class label.

## Scoring recipe

```python
correct = sum(1 for pred, gold in zip(predictions, gold_labels) if pred == gold)
accuracy = (correct / len(gold_labels)) * 100
return accuracy
```

## Common pitfalls

- Must strictly follow the official cross-subject and cross-view train/test splits for NTU-RGB+D.
- Ensemble methods require freezing the GCN skeleton encoder weights during RGB branch training and evaluation to match reported results.
- Accuracy is reported as a percentage, not a decimal fraction.

## Evidence (verbatim from paper)

> In Fig. 6, we illustrated the effectiveness of the weighted ST-ROI method that improves the recognition accuracy of every activity of Northwestern-UCLA Dataset.

## Citation

```bibtex
@misc{yu2020skeleton,
  title={Skeleton Focused Human Activity Recognition in RGB Video},
  author={Yu et al. (2020)},
  year={2020},
  note={arXiv:2004.13979}
}
```

- arXiv: 2004.13979