# Video Recognition on Temporal Understanding Benchmark Temporal-50 Static-50

Source: [Video Recognition on Temporal Understanding Benchmark Temporal-50 Static-50](<https://www.sota2.com/research/sota/video-recognition-on-temporal-understanding-benchmark-temporal-50-static-50>)

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

Data updated: 2026-02-26T06:06:54.169Z

Evaluation of Video Recognition performance on the Temporal Understanding Benchmark, focusing on the Temporal-50 and Static-50 subsets using Top-1, Top-5, and Temporal Score metrics.

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 Recognition |
| Dataset (including any stated split) | Temporal Understanding Benchmark Temporal-50 Static-50 |
| Metric | Top-1 Acc (Temporal-50) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [Top-1 Acc (Temporal-50)](<https://www.sota2.com/research/sota/video-recognition-on-temporal-understanding-benchmark-temporal-50-static-50.md?metric=Top-1%20Acc%20(Temporal-50)>): Higher is better; unit: PERCENT.

- [Top-5 Acc (Temporal-50)](<https://www.sota2.com/research/sota/video-recognition-on-temporal-understanding-benchmark-temporal-50-static-50.md?metric=Top-5%20Acc%20(Temporal-50)>): Higher is better; unit: PERCENT.

- [Top-1 Acc (Static-50)](<https://www.sota2.com/research/sota/video-recognition-on-temporal-understanding-benchmark-temporal-50-static-50.md?metric=Top-1%20Acc%20(Static-50)>): Higher is better; unit: PERCENT.

- [Temporal Score (TS)](<https://www.sota2.com/research/sota/video-recognition-on-temporal-understanding-benchmark-temporal-50-static-50.md?metric=Temporal%20Score%20(TS)>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Top-1 Acc (Temporal-50) | Result date | Report paper |
| --- | --- | --- | --- |
| ILA | 0.819 | Not recorded | 68fa705a1e209131cea4a883 |
| X-CLIP | 0.759 | Not recorded | 68fa705a1e209131cea4a883 |
| EVL | 0.707 | Not recorded | 68fa705a1e209131cea4a883 |

### ILA

Top-1 Acc (Temporal-50): 0.819. Result ID: 69912bc13a6c3148490637a9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa705a1e209131cea4a883.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa705a1e209131cea4a883.md>)

[Implementation](<https://github.com/Francis-Rings/ILA>)

Recorded evaluation configuration: {"Pre-training":"CLIP-400M","Backbone":"ViT-B/16","Frames":"8f"}. This record does not assert independent reproduction.

### X-CLIP

Top-1 Acc (Temporal-50): 0.759. Result ID: 69912bc13a6c3148490637a7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa705a1e209131cea4a883.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d331e209131cea385df.md>)

[Implementation](<https://www.sota2.com/aka.ms/X-CLIP>)

Recorded evaluation configuration: {"Pre-training":"CLIP-400M","Backbone":"ViT-B/16","Frames":"8f"}. This record does not assert independent reproduction.

### EVL

Top-1 Acc (Temporal-50): 0.707. Result ID: 69912bc13a6c3148490637a8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa705a1e209131cea4a883.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d2d1e209131cea38153.md>)

[Implementation](<https://github.com/OpenGVLab/efficient-video-recognition>)

Recorded evaluation configuration: {"Pre-training":"CLIP-400M","Backbone":"ViT-B/16","Frames":"8f"}. This record does not assert independent reproduction.

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