# Robotic Grasp Recognition on Cornell grasping dataset extended (five-fold cross-validation)

Source: [Robotic Grasp Recognition on Cornell grasping dataset extended (five-fold cross-validation)](<https://www.sota2.com/research/sota/robotic-grasp-recognition-on-cornell-grasping-dataset-extended-five-fold-cross-validation>)

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

Data updated: 2026-02-26T05:27:11.052Z

Evaluation of Robotic Grasp Recognition performance on the extended Cornell Grasping Dataset using a five-fold cross-validation setup, measured by 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 | Robotic Grasp Recognition |
| Dataset (including any stated split) | Cornell grasping dataset extended (five-fold cross-validation) |
| Metric | Accuracy |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/robotic-grasp-recognition-on-cornell-grasping-dataset-extended-five-fold-cross-validation.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Sparse AE | 93.7 | Not recorded | 68fa617a1e209131ce9f44c4 |
| Sparse AE, group reg. | 93.7 | Not recorded | 68fa617a1e209131ce9f44c4 |
| Sparse AE | 92.8 | Not recorded | 68fa617a1e209131ce9f44c4 |
| Jiang et al. + FPFH | 89.6 | Not recorded | 68fa617a1e209131ce9f44c4 |
| Jiang et al. | 84.7 | Not recorded | 68fa617a1e209131ce9f44c4 |
| Chance | 50 | Not recorded | 68fa617a1e209131ce9f44c4 |

### Sparse AE

Accuracy: 93.7. Result ID: 698bcca67a967eddb7717214.

[Reporting paper](<https://www.sota2.com/research/paper/68fa617a1e209131ce9f44c4.md>)

Recorded evaluation configuration: {"Regularization":"L1"}. This record does not assert independent reproduction.

### Sparse AE, group reg.

Accuracy: 93.7. Result ID: 698bcca67a967eddb7717215.

[Reporting paper](<https://www.sota2.com/research/paper/68fa617a1e209131ce9f44c4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa617a1e209131ce9f44c4.md>)

[Implementation](<http://pr.cs.cornell.edu/deepgrasping>)

Recorded evaluation configuration: {"Regularization":"Group-regularized multimodal"}. This record does not assert independent reproduction.

### Sparse AE

Accuracy: 92.8. Result ID: 698bcca67a967eddb7717213.

[Reporting paper](<https://www.sota2.com/research/paper/68fa617a1e209131ce9f44c4.md>)

Recorded evaluation configuration: {"Features":"separate layer-1 feat."}. This record does not assert independent reproduction.

### Jiang et al. + FPFH

Accuracy: 89.6. Result ID: 698bcca67a967eddb7717212.

[Reporting paper](<https://www.sota2.com/research/paper/68fa617a1e209131ce9f44c4.md>)

Recorded evaluation configuration: {"Features":"Jiang features + FPFH"}. This record does not assert independent reproduction.

### Jiang et al.

Accuracy: 84.7. Result ID: 698bcca67a967eddb7717211.

[Reporting paper](<https://www.sota2.com/research/paper/68fa617a1e209131ce9f44c4.md>)

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

### Chance

Accuracy: 50. Result ID: 698bcca67a967eddb7717210.

[Reporting paper](<https://www.sota2.com/research/paper/68fa617a1e209131ce9f44c4.md>)

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

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