# Video Anomaly Detection on ShanghaiTech (SHT) (tIOU-based F1)

Source: [Video Anomaly Detection on ShanghaiTech (SHT) (tIOU-based F1)](<https://www.sota2.com/research/sota/video-anomaly-detection-on-shanghaitech-sht-tiou-based-f1>)

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

Data updated: 2026-04-13T09:30:12.498Z

Evaluation of Video Anomaly Detection performance on the ShanghaiTech (SHT) dataset, measured using Precision, Recall, and F1 scores across various temporal Intersection over Union (tIOU) thresholds.

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 Detection |
| Dataset (including any stated split) | SHT (ShanghaiTech) |
| Metric | Precision (tIOU=0.5) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [Precision (tIOU=0.5)](<https://www.sota2.com/research/sota/video-anomaly-detection-on-shanghaitech-sht-tiou-based-f1.md?metric=Precision%20(tIOU%3D0.5)>): Higher is better; unit: PERCENT.

- [Recall (tIOU=0.5)](<https://www.sota2.com/research/sota/video-anomaly-detection-on-shanghaitech-sht-tiou-based-f1.md?metric=Recall%20(tIOU%3D0.5)>): Higher is better; unit: PERCENT.

- [F1 (tIOU=0.5)](<https://www.sota2.com/research/sota/video-anomaly-detection-on-shanghaitech-sht-tiou-based-f1.md?metric=F1%20(tIOU%3D0.5)>): Higher is better; unit: PERCENT.

- [Precision (tIOU=0.4)](<https://www.sota2.com/research/sota/video-anomaly-detection-on-shanghaitech-sht-tiou-based-f1.md?metric=Precision%20(tIOU%3D0.4)>): Higher is better; unit: PERCENT.

- [Recall (tIOU=0.4)](<https://www.sota2.com/research/sota/video-anomaly-detection-on-shanghaitech-sht-tiou-based-f1.md?metric=Recall%20(tIOU%3D0.4)>): Higher is better; unit: PERCENT.

- [F1 (tIOU=0.4)](<https://www.sota2.com/research/sota/video-anomaly-detection-on-shanghaitech-sht-tiou-based-f1.md?metric=F1%20(tIOU%3D0.4)>): Higher is better; unit: PERCENT.

- [Precision (tIOU=0.3)](<https://www.sota2.com/research/sota/video-anomaly-detection-on-shanghaitech-sht-tiou-based-f1.md?metric=Precision%20(tIOU%3D0.3)>): Higher is better; unit: PERCENT.

- [Recall (tIOU=0.3)](<https://www.sota2.com/research/sota/video-anomaly-detection-on-shanghaitech-sht-tiou-based-f1.md?metric=Recall%20(tIOU%3D0.3)>): Higher is better; unit: PERCENT.

- [F1 (tIOU=0.3)](<https://www.sota2.com/research/sota/video-anomaly-detection-on-shanghaitech-sht-tiou-based-f1.md?metric=F1%20(tIOU%3D0.3)>): Higher is better; unit: PERCENT.

- [Precision (tIOU=0.2)](<https://www.sota2.com/research/sota/video-anomaly-detection-on-shanghaitech-sht-tiou-based-f1.md?metric=Precision%20(tIOU%3D0.2)>): Higher is better; unit: PERCENT.

- [Recall (tIOU=0.2)](<https://www.sota2.com/research/sota/video-anomaly-detection-on-shanghaitech-sht-tiou-based-f1.md?metric=Recall%20(tIOU%3D0.2)>): Higher is better; unit: PERCENT.

- [F1 (tIOU=0.2)](<https://www.sota2.com/research/sota/video-anomaly-detection-on-shanghaitech-sht-tiou-based-f1.md?metric=F1%20(tIOU%3D0.2)>): Higher is better; unit: PERCENT.

- [Average F1](<https://www.sota2.com/research/sota/video-anomaly-detection-on-shanghaitech-sht-tiou-based-f1.md?metric=Average%20F1>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Precision (tIOU=0.5) | Result date | Report paper |
| --- | --- | --- | --- |
| STG-NF w/ ES | 56.58 | Not recorded | 69dc78767d0172140ec78a4e |
| STG-NF | 51.79 | Not recorded | 69dc78767d0172140ec78a4e |
| SPARTA w/ ES | 47.8 | Not recorded | 69dc78767d0172140ec78a4e |
| SPARTA | 45.83 | Not recorded | 69dc78767d0172140ec78a4e |
| Dual | 44.44 | Not recorded | 69dc78767d0172140ec78a4e |
| TS-GAD w/ ES | 41.46 | Not recorded | 69dc78767d0172140ec78a4e |
| TS-GAD | 41.38 | Not recorded | 69dc78767d0172140ec78a4e |

### STG-NF w/ ES

Precision (tIOU=0.5): 56.58. Result ID: 69dcb77747f34ce924c3f9b1.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78767d0172140ec78a4e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69dc78767d0172140ec78a4e.md>)

Recorded evaluation configuration: {"Configuration":"Baselines + Proposed Post-Processing"}. This record does not assert independent reproduction.

### STG-NF

Precision (tIOU=0.5): 51.79. Result ID: 69dcb77747f34ce924c3f9ae.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78767d0172140ec78a4e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa705c1e209131cea4a976.md>)

[Implementation](<https://github.com/orhir/STG-NF>)

Recorded evaluation configuration: {"Configuration":"Baselines"}. This record does not assert independent reproduction.

### SPARTA w/ ES

Precision (tIOU=0.5): 47.8. Result ID: 69dcb77747f34ce924c3f9b3.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78767d0172140ec78a4e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69dc78767d0172140ec78a4e.md>)

Recorded evaluation configuration: {"Configuration":"Baselines + Proposed Post-Processing"}. This record does not assert independent reproduction.

### SPARTA

Precision (tIOU=0.5): 45.83. Result ID: 69dcb77747f34ce924c3f9b0.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78767d0172140ec78a4e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa777b1e209131cea737a2.md>)

Recorded evaluation configuration: {"Configuration":"Baselines"}. This record does not assert independent reproduction.

### Dual

Precision (tIOU=0.5): 44.44. Result ID: 69dcb77747f34ce924c3f9b4.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78767d0172140ec78a4e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69dc78767d0172140ec78a4e.md>)

Recorded evaluation configuration: {"Configuration":"Dual-Branch Event Detection"}. This record does not assert independent reproduction.

### TS-GAD w/ ES

Precision (tIOU=0.5): 41.46. Result ID: 69dcb77747f34ce924c3f9b2.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78767d0172140ec78a4e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69dc78767d0172140ec78a4e.md>)

Recorded evaluation configuration: {"Configuration":"Baselines + Proposed Post-Processing"}. This record does not assert independent reproduction.

### TS-GAD

Precision (tIOU=0.5): 41.38. Result ID: 69dcb77747f34ce924c3f9af.

[Reporting paper](<https://www.sota2.com/research/paper/69dc78767d0172140ec78a4e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73b71e209131cea5e17d.md>)

[Implementation](<https://github.com/TeCSAR-UNCC/TSGAD>)

Recorded evaluation configuration: {"Configuration":"Baselines"}. This record does not assert independent reproduction.

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