# Fingerspelling Word Search (Video to Text) on ChicagoFSWild (test)

Source: [Fingerspelling Word Search (Video to Text) on ChicagoFSWild (test)](<https://www.sota2.com/research/sota/fingerspelling-word-search-video-to-text-on-chicagofswild-test>)

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

Data updated: 2026-02-26T06:09:26.351Z

Evaluation of the model's performance on Fingerspelling Word Search, converting video input to text output, using the test split of the ChicagoFSWild dataset.

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 | Fingerspelling Word Search (Video to Text) |
| Dataset (including any stated split) | ChicagoFSWild (test) |
| Metric | mAP |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [mAP](<https://www.sota2.com/research/sota/fingerspelling-word-search-video-to-text-on-chicagofswild-test.md?metric=mAP>): Higher is better; unit: PERCENT.

- [mF1](<https://www.sota2.com/research/sota/fingerspelling-word-search-video-to-text-on-chicagofswild-test.md?metric=mF1>): Higher is better; unit: PERCENT.

## Recorded results

| Method | mAP | Result date | Report paper |
| --- | --- | --- | --- |
| FSS-Net | 43.4 | Not recorded | 68fa6c1c1e209131cea324d5 |
| Ext-Det | 38.3 | Not recorded | 68fa6c1c1e209131cea324d5 |
| Recognizer | 31.8 | Not recorded | 68fa6c1c1e209131cea324d5 |
| Attn-KWS | 20.4 | Not recorded | 68fa6c1c1e209131cea324d5 |
| Whole-clip | 17.5 | Not recorded | 68fa6c1c1e209131cea324d5 |

### FSS-Net

mAP: 43.4. Result ID: 698edce3ffc3901de0a2688c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c1c1e209131cea324d5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c1c1e209131cea324d5.md>)

Recorded evaluation configuration: {"uses fingerspelling boundaries in training":true}. This record does not assert independent reproduction.

### Ext-Det

mAP: 38.3. Result ID: 698edce3ffc3901de0a2688b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c1c1e209131cea324d5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69b41e209131cea239aa.md>)

Recorded evaluation configuration: {"uses fingerspelling boundaries in training":true}. This record does not assert independent reproduction.

### Recognizer

mAP: 31.8. Result ID: 698edce3ffc3901de0a2688a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c1c1e209131cea324d5.md>)

Recorded evaluation configuration: {"uses fingerspelling boundaries in training":true}. This record does not assert independent reproduction.

### Attn-KWS

mAP: 20.4. Result ID: 698edce3ffc3901de0a26889.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c1c1e209131cea324d5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69b41e209131cea239aa.md>)

Recorded evaluation configuration: {"uses fingerspelling boundaries in training":true}. This record does not assert independent reproduction.

### Whole-clip

mAP: 17.5. Result ID: 698edce3ffc3901de0a26888.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c1c1e209131cea324d5.md>)

Recorded evaluation configuration: {"uses fingerspelling boundaries in training":false}. This record does not assert independent reproduction.

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