# Unsupervised Action Segmentation on Hollywood Extended

Source: [Unsupervised Action Segmentation on Hollywood Extended](<https://www.sota2.com/research/sota/unsupervised-action-segmentation-on-hollywood-extended>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-24T08:28:22.017Z

Evaluation of unsupervised action segmentation performance on the Hollywood Extended dataset, reporting metrics including MoF, IoU, and F1.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Unsupervised Action Segmentation |
| Dataset (including any stated split) | Hollywood Extended |
| Metric | MoF |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [MoF](<https://www.sota2.com/research/sota/unsupervised-action-segmentation-on-hollywood-extended.md?metric=MoF>): Higher is better; unit: PERCENT.

- [IoU](<https://www.sota2.com/research/sota/unsupervised-action-segmentation-on-hollywood-extended.md?metric=IoU>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/unsupervised-action-segmentation-on-hollywood-extended.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | MoF | Result date | Report paper |
| --- | --- | --- | --- |
| ABD | 60.7 | Not recorded | 69eaf93655a3c32af89f8ac5 |
| Deep kernel video approximation | 55.1 | Not recorded | 69eaf93655a3c32af89f8ac5 |
| TW-FINCH | 55 | Not recorded | 69eaf93655a3c32af89f8ac5 |
| Deep kernel video approximation | 54.1 | Not recorded | 69eaf93655a3c32af89f8ac5 |

### ABD

MoF: 60.7. Result ID: 69eb299347f34ce924d36487.

[Reporting paper](<https://www.sota2.com/research/paper/69eaf93655a3c32af89f8ac5.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Deep kernel video approximation

MoF: 55.1. Result ID: 69eb299347f34ce924d36489.

[Reporting paper](<https://www.sota2.com/research/paper/69eaf93655a3c32af89f8ac5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69eaf93655a3c32af89f8ac5.md>)

Recorded evaluation configuration: {"Initialization strategy":"default"}. This record does not assert independent reproduction.

### TW-FINCH

MoF: 55. Result ID: 69eb299347f34ce924d36486.

[Reporting paper](<https://www.sota2.com/research/paper/69eaf93655a3c32af89f8ac5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa699f1e209131cea232ac.md>)

[Implementation](<https://github.com/ssarfraz/FINCH-Clustering/tree/master/TW-FINCH>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Deep kernel video approximation

MoF: 54.1. Result ID: 69eb299347f34ce924d36488.

[Reporting paper](<https://www.sota2.com/research/paper/69eaf93655a3c32af89f8ac5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69eaf93655a3c32af89f8ac5.md>)

Recorded evaluation configuration: {"Initialization strategy":"uniform init"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.