# Action Recognition on Florence 3D (leave-one-subject-out cross val)

Source: [Action Recognition on Florence 3D (leave-one-subject-out cross val)](<https://www.sota2.com/research/sota/action-recognition-on-florence-3d-leave-one-subject-out-cross-val>)

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

Data updated: 2026-02-26T05:27:26.879Z

Evaluation of video action recognition performance on the Florence 3D dataset using the leave-one-subject-out cross-validation protocol.

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) | Florence 3D (leave-one-subject-out cross val) |
| 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/action-recognition-on-florence-3d-leave-one-subject-out-cross-val.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Deep STGCK | 99.07 | Not recorded | 68fa65a41e209131cea0b89b |
| ARRN-LSTM | 98.52 | Not recorded | 68fa65a41e209131cea0b89b |
| STGCK | 97.67 | Not recorded | 68fa65a41e209131cea0b89b |
| P-LSTM | 95.35 | Not recorded | 68fa65a41e209131cea0b89b |
| Graph-Based | 91.63 | Not recorded | 68fa65a41e209131cea0b89b |
| Lie Group | 90.88 | Not recorded | 68fa65a41e209131cea0b89b |

### Deep STGCK

Accuracy: 99.07. Result ID: 698cbe2d8b517eb4331c6e70.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65a41e209131cea0b89b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64161e209131cea02acc.md>)

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

### ARRN-LSTM

Accuracy: 98.52. Result ID: 698cbe2d8b517eb4331c6e71.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65a41e209131cea0b89b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65a41e209131cea0b89b.md>)

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

### STGCK

Accuracy: 97.67. Result ID: 698cbe2d8b517eb4331c6e6f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65a41e209131cea0b89b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64161e209131cea02acc.md>)

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

### P-LSTM

Accuracy: 95.35. Result ID: 698cbe2d8b517eb4331c6e6e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65a41e209131cea0b89b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62681e209131ce9f9306.md>)

[Implementation](<http://rose1.ntu.edu.sg/datasets/actionrecognition.asp>)

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

### Graph-Based

Accuracy: 91.63. Result ID: 698cbe2d8b517eb4331c6e6d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65a41e209131cea0b89b.md>)

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

### Lie Group

Accuracy: 90.88. Result ID: 698cbe2d8b517eb4331c6e6c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65a41e209131cea0b89b.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.