# Sign Recognition on BSL-1K 2K (test)

Source: [Sign Recognition on BSL-1K 2K (test)](<https://www.sota2.com/research/sota/sign-recognition-on-bsl-1k-2k-test>)

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

Data updated: 2026-02-26T06:07:15.719Z

Evaluation of Sign Recognition performance on the test split of the BSL-1K 2K dataset, measured using per-instance and per-class Top-1 and Top-5 accuracies.

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 | Sign Recognition |
| Dataset (including any stated split) | BSL-1K 2K (test) |
| Metric | Top-1 Accuracy (Instance) |
| 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 Accuracy (Instance)](<https://www.sota2.com/research/sota/sign-recognition-on-bsl-1k-2k-test.md?metric=Top-1%20Accuracy%20(Instance)>): Higher is better; unit: PERCENT.

- [Top-5 Accuracy (Instance)](<https://www.sota2.com/research/sota/sign-recognition-on-bsl-1k-2k-test.md?metric=Top-5%20Accuracy%20(Instance)>): Higher is better; unit: PERCENT.

- [Top-1 Accuracy (Class)](<https://www.sota2.com/research/sota/sign-recognition-on-bsl-1k-2k-test.md?metric=Top-1%20Accuracy%20(Class)>): Higher is better; unit: PERCENT.

- [Top-5 Accuracy (Class)](<https://www.sota2.com/research/sota/sign-recognition-on-bsl-1k-2k-test.md?metric=Top-5%20Accuracy%20(Class)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Top-1 Accuracy (Instance) | Result date | Report paper |
| --- | --- | --- | --- |
| M+D | 80.8 | Not recorded | 68fa699a1e209131cea22ff9 |
| M | 76.6 | Not recorded | 68fa699a1e209131cea22ff9 |
| D | 70.8 | Not recorded | 68fa699a1e209131cea22ff9 |

### M+D

Top-1 Accuracy (Instance): 80.8. Result ID: 698dc2128b517eb433238c9a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa699a1e209131cea22ff9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa699a1e209131cea22ff9.md>)

[Implementation](<https://www.robots.ox.ac.uk/~vgg/research/bslattend/>)

Recorded evaluation configuration: {"Training #ann.":"678K"}. This record does not assert independent reproduction.

### M

Top-1 Accuracy (Instance): 76.6. Result ID: 698dc2128b517eb433238c98.

[Reporting paper](<https://www.sota2.com/research/paper/68fa699a1e209131cea22ff9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b101e209131cea2be20.md>)

[Implementation](<https://www.robots.ox.ac.uk/~vgg/research/bsl1k/>)

Recorded evaluation configuration: {"Training #ann.":"169K"}. This record does not assert independent reproduction.

### D

Top-1 Accuracy (Instance): 70.8. Result ID: 698dc2128b517eb433238c99.

[Reporting paper](<https://www.sota2.com/research/paper/68fa699a1e209131cea22ff9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68811e209131cea1c86e.md>)

Recorded evaluation configuration: {"Training #ann.":"510K"}. This record does not assert independent reproduction.

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