# Action Recognition on SSv2-LT

Source: [Action Recognition on SSv2-LT](<https://www.sota2.com/research/sota/action-recognition-on-ssv2-lt>)

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

Data updated: 2026-02-26T05:34:15.961Z

Evaluation of Action Recognition performance on the SSv2-LT (Long-Tail) variant of the Something-Something V2 dataset, focusing on performance across different class frequency groups (Head, Tail, Few).

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) | SSv2-LT |
| Metric | Accuracy (Few) |
| 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 (Few)](<https://www.sota2.com/research/sota/action-recognition-on-ssv2-lt.md?metric=Accuracy%20(Few)>): Higher is better; unit: PERCENT.

- [Accuracy (Tail)](<https://www.sota2.com/research/sota/action-recognition-on-ssv2-lt.md?metric=Accuracy%20(Tail)>): Higher is better; unit: PERCENT.

- [Accuracy (Head)](<https://www.sota2.com/research/sota/action-recognition-on-ssv2-lt.md?metric=Accuracy%20(Head)>): Higher is better; unit: PERCENT.

- [Average Accuracy](<https://www.sota2.com/research/sota/action-recognition-on-ssv2-lt.md?metric=Average%20Accuracy>): Higher is better; unit: PERCENT.

- [Accuracy](<https://www.sota2.com/research/sota/action-recognition-on-ssv2-lt.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (Few) | Result date | Report paper |
| --- | --- | --- | --- |
| LMR | 17.9 | Not recorded | 68fa6ef41e209131cea43297 |
| Mixup | 17.4 | Not recorded | 68fa6ef41e209131cea43297 |
| Framestack | 15.5 | Not recorded | 68fa6ef41e209131cea43297 |
| CRT | 14.9 | Not recorded | 68fa6ef41e209131cea43297 |
| EQL | 3.1 | Not recorded | 68fa6ef41e209131cea43297 |
| CE | 2 | Not recorded | 68fa6ef41e209131cea43297 |

### LMR

Accuracy (Few): 17.9. Result ID: 6990752f3a6c31484900b1c5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ef41e209131cea43297.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ef41e209131cea43297.md>)

[Implementation](<https://www.sota2.com/tobyperrett.github.io/lmr>)

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

### Mixup

Accuracy (Few): 17.4. Result ID: 6990752f3a6c31484900b1c3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ef41e209131cea43297.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa644e1e209131cea03e44.md>)

[Implementation](<https://github.com/facebookresearch/mixup-cifar10>)

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

### Framestack

Accuracy (Few): 15.5. Result ID: 6990752f3a6c31484900b1c4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ef41e209131cea43297.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a8e1e209131cea28c4b.md>)

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

### CRT

Accuracy (Few): 14.9. Result ID: 6990752f3a6c31484900b1c2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ef41e209131cea43297.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa671b1e209131cea144a9.md>)

[Implementation](<https://github.com/facebookresearch/classifier-balancing>)

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

### EQL

Accuracy (Few): 3.1. Result ID: 6990752f3a6c31484900b1c1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ef41e209131cea43297.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa675c1e209131cea15df9.md>)

[Implementation](<https://github.com/tztztztztz/eql.detectron2>)

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

### CE

Accuracy (Few): 2. Result ID: 6990752f3a6c31484900b1c0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ef41e209131cea43297.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.
