Chiral Action Recognition Eval

---
name: chiral-action-recognition-eval
description: Evaluates a video representation's sensitivity to temporal direction by distinguishing between temporally opposite actions (e.g., opening vs. closing a door). Also tests general action recognition capability via linear probing on standard benchmarks. Use when the user wants to benchmark on Something-Something v2, EPIC-Kitchens, Charades, Kinetics-400, UCF-101, HMDB-51, or asks about evaluating this task. Reports Chiral Accuracy.
metadata:
  skill_kind: dataset_eval
  source_arxiv: 2509.08502
  bibtex_key: [REDACTED]
  confidence: high
---

# chiral-action-recognition-eval

> Chirality in Action: Time-Aware Video Representation Learning by Latent Straightening — Bagad et al. (2025) (arXiv:2509.08502, 2025)

## What this evaluates

Evaluates a video representation's sensitivity to temporal direction by distinguishing between temporally opposite actions (e.g., opening vs. closing a door). Also tests general action recognition capability via linear probing on standard benchmarks.

## Datasets

- **Something-Something v2** — total ?; splits: test (-1)
- **EPIC-Kitchens** — total ?; splits: test (-1)
- **Charades** — total ?; splits: test (-1)
- **Kinetics-400** — total ?; splits: test (-1)
- **UCF-101** — total ?; splits: test (-1)
- **HMDB-51** — total ?; splits: test (-1)

## Metrics

- `Chiral Accuracy` **(primary)** — range: percent
  - Percentage of correctly classified chiral action pairs by a linear classifier trained on video descriptors.

## Input / output format

**Input**: Video clips sampled at T=16 frames linearly. Per-frame features extracted from an image encoder and concatenated or processed into a single video descriptor.

**Output**: Predicted class label for the chiral action pair or standard action class.

## Scoring recipe

```python
def compute_accuracy(predictions, gold_labels):
    correct = sum(1 for p, g in zip(predictions, gold_labels) if p == g)
    return correct / len(gold_labels) * 100
```

## Common pitfalls

- Naively concatenating per-frame features yields bulky descriptors that may be impractical for large-scale indexing, despite competitive performance.
- Average pooling over space and time can lose temporal sensitivity compared to average pooling over space and concatenating over time.
- Transformer-based models with a CLS token should be handled carefully (use CLS or average pool tokens), as treating them differently affects descriptor dimensionality.

## Evidence (verbatim from paper)

> From the results shown in Table 2, we observe that the proposed LiFT features achieve the best performance on SSv2, EPIC and Charade, while being compact (d=768). ... Chiral Accuracy ↑

## Citation

```bibtex
@misc{bagad2025chirality,
  title={Chirality in Action: Time-Aware Video Representation Learning by Latent Straightening},
  author={Bagad et al. (2025)},
  year={2025},
  note={arXiv:2509.08502}
}
```

- arXiv: 2509.08502