# Action Classification on EPIC-Kitchens Target (test)

Source: [Action Classification on EPIC-Kitchens Target (test)](<https://www.sota2.com/research/sota/action-classification-on-epic-kitchens-target-test>)

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

Data updated: 2026-03-17T09:50:42.674Z

Evaluation of Action Classification performance on the test split of the EPIC-Kitchens Target dataset, reporting accuracy across Video-only, Audio-only, and combined Video-Audio modalities.

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 Classification |
| Dataset (including any stated split) | EPIC-Kitchens Target (test) |
| Metric | Accuracy (Video) |
| 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 (Video)](<https://www.sota2.com/research/sota/action-classification-on-epic-kitchens-target-test.md?metric=Accuracy%20(Video)>): Higher is better; unit: PERCENT.

- [Accuracy (Audio)](<https://www.sota2.com/research/sota/action-classification-on-epic-kitchens-target-test.md?metric=Accuracy%20(Audio)>): Higher is better; unit: PERCENT.

- [Accuracy (Video-Audio)](<https://www.sota2.com/research/sota/action-classification-on-epic-kitchens-target-test.md?metric=Accuracy%20(Video-Audio)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (Video) | Result date | Report paper |
| --- | --- | --- | --- |
| Uni-video | 54.98 | Not recorded | 69b8e0390636e5bf4afbed0a |
| GMP | 52.33 | Not recorded | 69b8e0390636e5bf4afbed0a |
| Grad-Blending | 50.03 | Not recorded | 69b8e0390636e5bf4afbed0a |
| OGM-GE | 49.75 | Not recorded | 69b8e0390636e5bf4afbed0a |
| Base | 48.86 | Not recorded | 69b8e0390636e5bf4afbed0a |

### Uni-video

Accuracy (Video): 54.98. Result ID: 69b922e547f34ce924a236fc.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0390636e5bf4afbed0a.md>)

Recorded evaluation configuration: {"Modality":"Single-modality"}. This record does not assert independent reproduction.

### GMP

Accuracy (Video): 52.33. Result ID: 69b922e547f34ce924a23701.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0390636e5bf4afbed0a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0390636e5bf4afbed0a.md>)

Recorded evaluation configuration: {"Modality":"Multimodal"}. This record does not assert independent reproduction.

### Grad-Blending

Accuracy (Video): 50.03. Result ID: 69b922e547f34ce924a23700.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0390636e5bf4afbed0a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c161e209131cea32100.md>)

Recorded evaluation configuration: {"Modality":"Multimodal"}. This record does not assert independent reproduction.

### OGM-GE

Accuracy (Video): 49.75. Result ID: 69b922e547f34ce924a236ff.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0390636e5bf4afbed0a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67561e209131cea15a42.md>)

Recorded evaluation configuration: {"Modality":"Multimodal"}. This record does not assert independent reproduction.

### Base

Accuracy (Video): 48.86. Result ID: 69b922e547f34ce924a236fe.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0390636e5bf4afbed0a.md>)

Recorded evaluation configuration: {"Modality":"Multimodal"}. This record does not assert independent reproduction.

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