# Surgical Gesture Segmentation on JIGSAWS Video suturing task

Source: [Surgical Gesture Segmentation on JIGSAWS Video suturing task](<https://www.sota2.com/research/sota/surgical-gesture-segmentation-on-jigsaws-video-suturing-task>)

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

Data updated: 2026-02-26T05:27:19.819Z

Evaluation of Surgical Gesture Segmentation performance on the JIGSAWS Video suturing task dataset, typically measured using Accuracy, Edit Distance, and F1 scores at various thresholds (F1@10, F1@25, F1@50).

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 | Surgical Gesture Segmentation |
| Dataset (including any stated split) | JIGSAWS Video suturing task |
| Metric | Accuracy |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/surgical-gesture-segmentation-on-jigsaws-video-suturing-task.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Edit Distance](<https://www.sota2.com/research/sota/surgical-gesture-segmentation-on-jigsaws-video-suturing-task.md?metric=Edit%20Distance>): Lower is better; unit: SCALAR.

- [F1 Score @ 10](<https://www.sota2.com/research/sota/surgical-gesture-segmentation-on-jigsaws-video-suturing-task.md?metric=F1%20Score%20%40%2010>): Higher is better; unit: PERCENT.

- [F1 Score @ 25](<https://www.sota2.com/research/sota/surgical-gesture-segmentation-on-jigsaws-video-suturing-task.md?metric=F1%20Score%20%40%2025>): Higher is better; unit: PERCENT.

- [F1 Score @ 50](<https://www.sota2.com/research/sota/surgical-gesture-segmentation-on-jigsaws-video-suturing-task.md?metric=F1%20Score%20%40%2050>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| TCN\* | 81.71 | Not recorded | 68fa647d1e209131cea04ce4 |
| RL (full) | 81.43 | Not recorded | 68fa647d1e209131cea04ce4 |
| TCN | 81.4 | Not recorded | 68fa647d1e209131cea04ce4 |
| RL (no trans) | 81.32 | Not recorded | 68fa647d1e209131cea04ce4 |
| RL (no future) | 80.84 | Not recorded | 68fa647d1e209131cea04ce4 |
| Seg-ST-CNN | 74.7 | Not recorded | 68fa647d1e209131cea04ce4 |
| RL (no tcn) | 32.35 | Not recorded | 68fa647d1e209131cea04ce4 |

### TCN\*

Accuracy: 81.71. Result ID: 698c47e637894ef7d9cd385f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa647d1e209131cea04ce4.md>)

Recorded evaluation configuration: {"re-implemented":"true"}. This record does not assert independent reproduction.

### RL (full)

Accuracy: 81.43. Result ID: 698c47e637894ef7d9cd3863.

[Reporting paper](<https://www.sota2.com/research/paper/68fa647d1e209131cea04ce4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa647d1e209131cea04ce4.md>)

Recorded evaluation configuration: {"state\_design":"full state"}. This record does not assert independent reproduction.

### TCN

Accuracy: 81.4. Result ID: 698c47e637894ef7d9cd385e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa647d1e209131cea04ce4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62b51e209131ce9faa66.md>)

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

### RL (no trans)

Accuracy: 81.32. Result ID: 698c47e637894ef7d9cd3862.

[Reporting paper](<https://www.sota2.com/research/paper/68fa647d1e209131cea04ce4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa647d1e209131cea04ce4.md>)

Recorded evaluation configuration: {"state\_design":"without transition probabilities"}. This record does not assert independent reproduction.

### RL (no future)

Accuracy: 80.84. Result ID: 698c47e637894ef7d9cd3861.

[Reporting paper](<https://www.sota2.com/research/paper/68fa647d1e209131cea04ce4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa647d1e209131cea04ce4.md>)

Recorded evaluation configuration: {"state\_design":"without TCN features at future frames"}. This record does not assert independent reproduction.

### Seg-ST-CNN

Accuracy: 74.7. Result ID: 698c47e637894ef7d9cd385d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa647d1e209131cea04ce4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62d01e209131ce9fb479.md>)

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

### RL (no tcn)

Accuracy: 32.35. Result ID: 698c47e637894ef7d9cd3860.

[Reporting paper](<https://www.sota2.com/research/paper/68fa647d1e209131cea04ce4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa647d1e209131cea04ce4.md>)

Recorded evaluation configuration: {"state\_design":"without TCN features"}. This record does not assert independent reproduction.

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