# Action Recognition on UAV-OVO (OOD)

Source: [Action Recognition on UAV-OVO (OOD)](<https://www.sota2.com/research/sota/action-recognition-on-uav-ovo-ood>)

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

Data updated: 2026-05-26T11:43:46.801Z

Evaluation of Action Recognition performance on the Out-of-Distribution (OOD) split of the UAV-OVO dataset.

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) | UAV-OVO (OOD) |
| Metric | Accuracy (OOD) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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 (OOD)](<https://www.sota2.com/research/sota/action-recognition-on-uav-ovo-ood.md?metric=Accuracy%20(OOD)>): Higher is better; unit: PERCENT.

- [PD (OOD)](<https://www.sota2.com/research/sota/action-recognition-on-uav-ovo-ood.md?metric=PD%20(OOD)>): Lower is better; unit: PERCENT.

- [H Score (OOD)](<https://www.sota2.com/research/sota/action-recognition-on-uav-ovo-ood.md?metric=H%20Score%20(OOD)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (OOD) | Result date | Report paper |
| --- | --- | --- | --- |
| LATER | 35.55 | Not recorded | 6a152947dbd7150506f7e17b |
| NEO | 34.58 | Not recorded | 6a152947dbd7150506f7e17b |
| MViTv2-B | 33.94 | Not recorded | 6a152947dbd7150506f7e17b |
| DejaVid | 30.97 | Not recorded | 6a152947dbd7150506f7e17b |
| ViViM | 28.56 | Not recorded | 6a152947dbd7150506f7e17b |
| X3D-M | 25.45 | Not recorded | 6a152947dbd7150506f7e17b |
| ViT-S | 15.58 | Not recorded | 6a152947dbd7150506f7e17b |
| FAR | 13.42 | Not recorded | 6a152947dbd7150506f7e17b |

### LATER

Accuracy (OOD): 35.55. Result ID: 6a15876efbc373592c0e06f6.

[Reporting paper](<https://www.sota2.com/research/paper/6a152947dbd7150506f7e17b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a152947dbd7150506f7e17b.md>)

Recorded evaluation configuration: {"Backbone":"MViTv2","Pretrain":"K400"}. This record does not assert independent reproduction.

### NEO

Accuracy (OOD): 34.58. Result ID: 6a15876efbc373592c0e06f5.

[Reporting paper](<https://www.sota2.com/research/paper/6a152947dbd7150506f7e17b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bf01e209131cea8b70d.md>)

Recorded evaluation configuration: {"Backbone":"MViTv2","Pretrain":"K400"}. This record does not assert independent reproduction.

### MViTv2-B

Accuracy (OOD): 33.94. Result ID: 6a15876efbc373592c0e06f3.

[Reporting paper](<https://www.sota2.com/research/paper/6a152947dbd7150506f7e17b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c2f1e209131cea32a41.md>)

[Implementation](<https://github.com/facebookresearch/mvit>)

Recorded evaluation configuration: {"Backbone":"MViTv2","Pretrain":"K400"}. This record does not assert independent reproduction.

### DejaVid

Accuracy (OOD): 30.97. Result ID: 6a15876efbc373592c0e06f4.

[Reporting paper](<https://www.sota2.com/research/paper/6a152947dbd7150506f7e17b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79681e209131cea7d724.md>)

[Implementation](<https://github.com/darrylho/DejaVid>)

Recorded evaluation configuration: {"Backbone":"MViTv2","Pretrain":"K400"}. This record does not assert independent reproduction.

### ViViM

Accuracy (OOD): 28.56. Result ID: 6a15876efbc373592c0e06f2.

[Reporting paper](<https://www.sota2.com/research/paper/6a152947dbd7150506f7e17b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa727e1e209131cea56bd9.md>)

[Implementation](<https://github.com/OpenGVLab/video-mamba-suite>)

Recorded evaluation configuration: {"Backbone":"ViViM","Pretrain":"K400"}. This record does not assert independent reproduction.

### X3D-M

Accuracy (OOD): 25.45. Result ID: 6a15876efbc373592c0e06f0.

[Reporting paper](<https://www.sota2.com/research/paper/6a152947dbd7150506f7e17b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67531e209131cea15826.md>)

Recorded evaluation configuration: {"Backbone":"X3D","Pretrain":"K400"}. This record does not assert independent reproduction.

### ViT-S

Accuracy (OOD): 15.58. Result ID: 6a15876efbc373592c0e06ef.

[Reporting paper](<https://www.sota2.com/research/paper/6a152947dbd7150506f7e17b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a0b1e209131cea25b04.md>)

[Implementation](<https://github.com/google-research/vision_transformer>)

Recorded evaluation configuration: {"Backbone":"ViT","Pretrain":"K400"}. This record does not assert independent reproduction.

### FAR

Accuracy (OOD): 13.42. Result ID: 6a15876efbc373592c0e06f1.

[Reporting paper](<https://www.sota2.com/research/paper/6a152947dbd7150506f7e17b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cfc1e209131cea371fb.md>)

[Implementation](<https://gamma.umd.edu/far>)

Recorded evaluation configuration: {"Backbone":"X3D","Pretrain":"K400"}. This record does not assert independent reproduction.

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