# Per-facet Video Classification on MUFI Per-facet Video Evaluation Set 1.0 (test)

Source: [Per-facet Video Classification on MUFI Per-facet Video Evaluation Set 1.0 (test)](<https://www.sota2.com/research/sota/per-facet-video-classification-on-mufi-per-facet-video-evaluation-set-1-0-test>)

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

Data updated: 2026-02-26T05:34:06.046Z

Evaluation of Per-facet Video Classification performance on the test split of the MUFI Per-facet Video Evaluation Set 1.0.

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 | Per-facet Video Classification |
| Dataset (including any stated split) | MUFI Per-facet Video Evaluation Set 1.0 (test) |
| Metric | Accuracy (Action) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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 (Action)](<https://www.sota2.com/research/sota/per-facet-video-classification-on-mufi-per-facet-video-evaluation-set-1-0-test.md?metric=Accuracy%20(Action)>): Higher is better; unit: PERCENT.

- [Accuracy (Event)](<https://www.sota2.com/research/sota/per-facet-video-classification-on-mufi-per-facet-video-evaluation-set-1-0-test.md?metric=Accuracy%20(Event)>): Higher is better; unit: PERCENT.

- [Accuracy (Interaction)](<https://www.sota2.com/research/sota/per-facet-video-classification-on-mufi-per-facet-video-evaluation-set-1-0-test.md?metric=Accuracy%20(Interaction)>): Higher is better; unit: PERCENT.

- [Accuracy (Sport)](<https://www.sota2.com/research/sota/per-facet-video-classification-on-mufi-per-facet-video-evaluation-set-1-0-test.md?metric=Accuracy%20(Sport)>): Higher is better; unit: PERCENT.

- [Accuracy (Object)](<https://www.sota2.com/research/sota/per-facet-video-classification-on-mufi-per-facet-video-evaluation-set-1-0-test.md?metric=Accuracy%20(Object)>): Higher is better; unit: PERCENT.

- [Accuracy (Scene)](<https://www.sota2.com/research/sota/per-facet-video-classification-on-mufi-per-facet-video-evaluation-set-1-0-test.md?metric=Accuracy%20(Scene)>): Higher is better; unit: PERCENT.

- [Average Accuracy](<https://www.sota2.com/research/sota/per-facet-video-classification-on-mufi-per-facet-video-evaluation-set-1-0-test.md?metric=Average%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (Action) | Result date | Report paper |
| --- | --- | --- | --- |
| MUFI | 57.8 | Not recorded | 68fa6b9c1e209131cea2f4bd |
| R(2+1)D-34-IG65M+K400 | 54.1 | Not recorded | 68fa6b9c1e209131cea2f4bd |
| R(2+1)D-34-IG65M | 53.1 | Not recorded | 68fa6b9c1e209131cea2f4bd |
| P3D ResNet-152 | 35.8 | Not recorded | 68fa6b9c1e209131cea2f4bd |
| SeCo | 34.3 | Not recorded | 68fa6b9c1e209131cea2f4bd |
| ResNet-50 | 33.1 | Not recorded | 68fa6b9c1e209131cea2f4bd |
| MoCo v2 | 32 | Not recorded | 68fa6b9c1e209131cea2f4bd |
| SimCLR | 31.4 | Not recorded | 68fa6b9c1e209131cea2f4bd |
| C3D | 24.6 | Not recorded | 68fa6b9c1e209131cea2f4bd |

### MUFI

Accuracy (Action): 57.8. Result ID: 698e99d7ffc3901de09f069c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b9c1e209131cea2f4bd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b9c1e209131cea2f4bd.md>)

Recorded evaluation configuration: {"Representation Type":"Video-based"}. This record does not assert independent reproduction.

### R(2+1)D-34-IG65M+K400

Accuracy (Action): 54.1. Result ID: 698e99d7ffc3901de09f069a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b9c1e209131cea2f4bd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65c11e209131cea0c3d0.md>)

[Implementation](<https://github.com/dutran/R2Plus1D>)

Recorded evaluation configuration: {"Representation Type":"Video-based","Supervision":"weakly-supervised","Fine-tuned":"Kinetics-400"}. This record does not assert independent reproduction.

### R(2+1)D-34-IG65M

Accuracy (Action): 53.1. Result ID: 698e99d7ffc3901de09f0699.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b9c1e209131cea2f4bd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65c11e209131cea0c3d0.md>)

[Implementation](<https://github.com/dutran/R2Plus1D>)

Recorded evaluation configuration: {"Representation Type":"Video-based","Supervision":"weakly-supervised"}. This record does not assert independent reproduction.

### P3D ResNet-152

Accuracy (Action): 35.8. Result ID: 698e99d7ffc3901de09f0698.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b9c1e209131cea2f4bd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63d91e209131cea01461.md>)

[Implementation](<https://github.com/ZhaofanQiu/pseudo-3d-residual-networks>)

Recorded evaluation configuration: {"Representation Type":"Video-based","Supervision":"Supervised"}. This record does not assert independent reproduction.

### SeCo

Accuracy (Action): 34.3. Result ID: 698e99d7ffc3901de09f069b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b9c1e209131cea2f4bd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69321e209131cea20bed.md>)

Recorded evaluation configuration: {"Representation Type":"Video-based","Supervision":"self-supervised"}. This record does not assert independent reproduction.

### ResNet-50

Accuracy (Action): 33.1. Result ID: 698e99d7ffc3901de09f0694.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b9c1e209131cea2f4bd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62321e209131ce9f8328.md>)

Recorded evaluation configuration: {"Representation Type":"Image-based","Supervision":"Supervised"}. This record does not assert independent reproduction.

### MoCo v2

Accuracy (Action): 32. Result ID: 698e99d7ffc3901de09f0696.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b9c1e209131cea2f4bd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa673f1e209131cea15344.md>)

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

Recorded evaluation configuration: {"Representation Type":"Image-based","Supervision":"self-supervised"}. This record does not assert independent reproduction.

### SimCLR

Accuracy (Action): 31.4. Result ID: 698e99d7ffc3901de09f0695.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b9c1e209131cea2f4bd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67d71e209131cea18de5.md>)

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

Recorded evaluation configuration: {"Representation Type":"Image-based","Supervision":"self-supervised"}. This record does not assert independent reproduction.

### C3D

Accuracy (Action): 24.6. Result ID: 698e99d7ffc3901de09f0697.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b9c1e209131cea2f4bd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62171e209131ce9f77be.md>)

[Implementation](<http://vlg.cs.dartmouth.edu/c3d>)

Recorded evaluation configuration: {"Representation Type":"Video-based","Supervision":"Supervised"}. This record does not assert independent reproduction.

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