# Driver Action Recognition on 100-Driver D4

Source: [Driver Action Recognition on 100-Driver D4](<https://www.sota2.com/research/sota/driver-action-recognition-on-100-driver-d4>)

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

Data updated: 2026-04-01T07:37:42.563Z

Evaluation of Driver Action Recognition performance on the 100-Driver D4 dataset, typically measured by Top-1 and Top-5 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 | Driver Action Recognition |
| Dataset (including any stated split) | 100-Driver D4 |
| Metric | Top-1 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

- [Top-1 Accuracy](<https://www.sota2.com/research/sota/driver-action-recognition-on-100-driver-d4.md?metric=Top-1%20Accuracy>): Higher is better; unit: PERCENT.

- [Top-5 Accuracy](<https://www.sota2.com/research/sota/driver-action-recognition-on-100-driver-d4.md?metric=Top-5%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Top-1 Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| DBMNet | 11.29 | Not recorded | 68fa79941e209131cea7e621 |
| DGCCL | 10.78 | Not recorded | 68fa79941e209131cea7e621 |
| GhostNet | 8.85 | Not recorded | 68fa79941e209131cea7e621 |
| OLCMNet | 8.48 | Not recorded | 68fa79941e209131cea7e621 |
| Duan et al. | 7.25 | Not recorded | 68fa79941e209131cea7e621 |
| Hu et al. | 5.45 | Not recorded | 68fa79941e209131cea7e621 |

### DBMNet

Top-1 Accuracy: 11.29. Result ID: 69cccb3a47f34ce924b62c4b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79941e209131cea7e621.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79941e209131cea7e621.md>)

Recorded evaluation configuration: {"Training Cameras":"D{1,2,3}"}. This record does not assert independent reproduction.

### DGCCL

Top-1 Accuracy: 10.78. Result ID: 69cccb3a47f34ce924b62c46.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79941e209131cea7e621.md>)

Recorded evaluation configuration: {"Training Cameras":"D{1,2,3}"}. This record does not assert independent reproduction.

### GhostNet

Top-1 Accuracy: 8.85. Result ID: 69cccb3a47f34ce924b62c48.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79941e209131cea7e621.md>)

Recorded evaluation configuration: {"Training Cameras":"D{1,2,3}"}. This record does not assert independent reproduction.

### OLCMNet

Top-1 Accuracy: 8.48. Result ID: 69cccb3a47f34ce924b62c4a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79941e209131cea7e621.md>)

Recorded evaluation configuration: {"Training Cameras":"D{1,2,3}"}. This record does not assert independent reproduction.

### Duan et al.

Top-1 Accuracy: 7.25. Result ID: 69cccb3a47f34ce924b62c47.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79941e209131cea7e621.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa766f1e209131cea6cf9b.md>)

Recorded evaluation configuration: {"Training Cameras":"D{1,2,3}"}. This record does not assert independent reproduction.

### Hu et al.

Top-1 Accuracy: 5.45. Result ID: 69cccb3a47f34ce924b62c49.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79941e209131cea7e621.md>)

Recorded evaluation configuration: {"Training Cameras":"D{1,2,3}"}. This record does not assert independent reproduction.

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