# Video Anomaly Understanding Evaluation on UCF-Crime

Source: [Video Anomaly Understanding Evaluation on UCF-Crime](<https://www.sota2.com/research/sota/video-anomaly-understanding-evaluation-on-ucf-crime>)

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

Data updated: 2026-02-27T11:10:17.013Z

Evaluation of video anomaly understanding performance on the UCF-Crime dataset, utilizing specific metrics such as CLS, KM, FLU, INF, FAC, and Total scores.

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 | Video Anomaly Understanding Evaluation |
| Dataset (including any stated split) | UCF-Crime |
| Metric | CLS |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [CLS](<https://www.sota2.com/research/sota/video-anomaly-understanding-evaluation-on-ucf-crime.md?metric=CLS>): Higher is better; unit: SCALAR.

- [KM](<https://www.sota2.com/research/sota/video-anomaly-understanding-evaluation-on-ucf-crime.md?metric=KM>): Higher is better; unit: SCALAR.

- [FLU](<https://www.sota2.com/research/sota/video-anomaly-understanding-evaluation-on-ucf-crime.md?metric=FLU>): Higher is better; unit: SCALAR.

- [INF](<https://www.sota2.com/research/sota/video-anomaly-understanding-evaluation-on-ucf-crime.md?metric=INF>): Higher is better; unit: SCALAR.

- [FAC](<https://www.sota2.com/research/sota/video-anomaly-understanding-evaluation-on-ucf-crime.md?metric=FAC>): Higher is better; unit: SCALAR.

- [Total Score](<https://www.sota2.com/research/sota/video-anomaly-understanding-evaluation-on-ucf-crime.md?metric=Total%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | CLS | Result date | Report paper |
| --- | --- | --- | --- |
| SRVAU-R1 | 7.22 | Not recorded | 6981812ea8b01e76cc8e231c |
| Qwen2.5-VL-7B | 4.8 | Not recorded | 6981812ea8b01e76cc8e231c |
| VAU-R1 | 4.42 | Not recorded | 6981812ea8b01e76cc8e231c |
| InternVL2.5-2B | 4.4 | Not recorded | 6981812ea8b01e76cc8e231c |
| Qwen2.5-VL-3B | 4.31 | Not recorded | 6981812ea8b01e76cc8e231c |
| InternVL2.5-8B-MPO | 3.79 | Not recorded | 6981812ea8b01e76cc8e231c |
| Qwen2-VL-2B | 3.47 | Not recorded | 6981812ea8b01e76cc8e231c |
| HolmesVAU | 3.05 | Not recorded | 6981812ea8b01e76cc8e231c |

### SRVAU-R1

CLS: 7.22. Result ID: 69a17b8f35dfcabb00e759d8.

[Reporting paper](<https://www.sota2.com/research/paper/6981812ea8b01e76cc8e231c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6981812ea8b01e76cc8e231c.md>)

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

### Qwen2.5-VL-7B

CLS: 4.8. Result ID: 69a17b8f35dfcabb00e759d2.

[Reporting paper](<https://www.sota2.com/research/paper/6981812ea8b01e76cc8e231c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71d3c.md>)

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

### VAU-R1

CLS: 4.42. Result ID: 69a17b8f35dfcabb00e759d7.

[Reporting paper](<https://www.sota2.com/research/paper/6981812ea8b01e76cc8e231c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78f01e209131cea7b517.md>)

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

### InternVL2.5-2B

CLS: 4.4. Result ID: 69a17b8f35dfcabb00e759d1.

[Reporting paper](<https://www.sota2.com/research/paper/6981812ea8b01e76cc8e231c.md>)

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

### Qwen2.5-VL-3B

CLS: 4.31. Result ID: 69a17b8f35dfcabb00e759d5.

[Reporting paper](<https://www.sota2.com/research/paper/6981812ea8b01e76cc8e231c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71d3c.md>)

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

### InternVL2.5-8B-MPO

CLS: 3.79. Result ID: 69a17b8f35dfcabb00e759d3.

[Reporting paper](<https://www.sota2.com/research/paper/6981812ea8b01e76cc8e231c.md>)

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

### Qwen2-VL-2B

CLS: 3.47. Result ID: 69a17b8f35dfcabb00e759d4.

[Reporting paper](<https://www.sota2.com/research/paper/6981812ea8b01e76cc8e231c.md>)

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

### HolmesVAU

CLS: 3.05. Result ID: 69a17b8f35dfcabb00e759d6.

[Reporting paper](<https://www.sota2.com/research/paper/6981812ea8b01e76cc8e231c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77741e209131cea73373.md>)

[Implementation](<https://github.com/pipixin321/HolmesVAU>)

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

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