# Action Recognition on JIGSAWS Needle-Passing (LOSO)

Source: [Action Recognition on JIGSAWS Needle-Passing (LOSO)](<https://www.sota2.com/research/sota/action-recognition-on-jigsaws-needle-passing-loso>)

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

Data updated: 2026-02-26T05:57:46.114Z

Evaluation of Action Recognition performance on the JIGSAWS Needle-Passing dataset using a Leave-One-Subject-Out (LOSO) cross-validation scheme, typically measured by Per-frame accuracy.

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 | Action Recognition |
| Dataset (including any stated split) | JIGSAWS Needle-Passing (LOSO) |
| Metric | Per-frame Acc |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [Per-frame Acc](<https://www.sota2.com/research/sota/action-recognition-on-jigsaws-needle-passing-loso.md?metric=Per-frame%20Acc>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Per-frame Acc | Result date | Report paper |
| --- | --- | --- | --- |
| SDL + SC-CRF | 75.19 | Not recorded | 68fa63f41e209131cea01c86 |
| SC-CRF-SL | 75.09 | Not recorded | 68fa63f41e209131cea01c86 |
| SDSDL | 74.88 | Not recorded | 68fa63f41e209131cea01c86 |
| KSVD-SHMM | 73.09 | Not recorded | 68fa63f41e209131cea01c86 |
| MsM-CRF | 72.44 | Not recorded | 68fa63f41e209131cea01c86 |
| GMM-HMM | 70.55 | Not recorded | 68fa63f41e209131cea01c86 |

### SDL + SC-CRF

Per-frame Acc: 75.19. Result ID: 698c087ff729bc7f68e7ec78.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63f41e209131cea01c86.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63f41e209131cea01c86.md>)

Recorded evaluation configuration: {"Input features":"Kinematic"}. This record does not assert independent reproduction.

### SC-CRF-SL

Per-frame Acc: 75.09. Result ID: 698c087ff729bc7f68e7ec76.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63f41e209131cea01c86.md>)

Recorded evaluation configuration: {"Input features":"Kinematic"}. This record does not assert independent reproduction.

### SDSDL

Per-frame Acc: 74.88. Result ID: 698c087ff729bc7f68e7ec77.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63f41e209131cea01c86.md>)

Recorded evaluation configuration: {"Input features":"Kinematic"}. This record does not assert independent reproduction.

### KSVD-SHMM

Per-frame Acc: 73.09. Result ID: 698c087ff729bc7f68e7ec74.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63f41e209131cea01c86.md>)

Recorded evaluation configuration: {"Input features":"Kinematic"}. This record does not assert independent reproduction.

### MsM-CRF

Per-frame Acc: 72.44. Result ID: 698c087ff729bc7f68e7ec75.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63f41e209131cea01c86.md>)

Recorded evaluation configuration: {"Input features":"Kinematic"}. This record does not assert independent reproduction.

### GMM-HMM

Per-frame Acc: 70.55. Result ID: 698c087ff729bc7f68e7ec73.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63f41e209131cea01c86.md>)

Recorded evaluation configuration: {"Input features":"Kinematic"}. This record does not assert independent reproduction.

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