# Action Recognition on EK100, SSV2, and K400

Source: [Action Recognition on EK100, SSV2, and K400](<https://www.sota2.com/research/sota/action-recognition-on-ek100-ssv2-and-k400>)

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

Data updated: 2026-02-26T05:54:30.068Z

Evaluation of Action Recognition performance aggregated across the EK100, SSV2, and K400 video datasets, typically reported using an Overall Harmonic Mean.

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) | EK100, SSV2, and K400 |
| Metric | Overall Harmonic Mean |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 23 of 23 |
| 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

- [Overall Harmonic Mean](<https://www.sota2.com/research/sota/action-recognition-on-ek100-ssv2-and-k400.md?metric=Overall%20Harmonic%20Mean>): Higher is better; unit: PERCENT.

- [Harmonic Mean (SSV2, K400)](<https://www.sota2.com/research/sota/action-recognition-on-ek100-ssv2-and-k400.md?metric=Harmonic%20Mean%20(SSV2%2C%20K400)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Overall Harmonic Mean | Result date | Report paper |
| --- | --- | --- | --- |
| CAST | 71.6 | Not recorded | 68fa74ad1e209131cea6327b |
| CAST | 71.6 | Not recorded | 68fa77ad1e209131cea74a67 |
| OMNIVORE | 70.8 | Not recorded | 68fa74ad1e209131cea6327b |
| OMNIVORE | 70.8 | Not recorded | 68fa77ad1e209131cea74a67 |
| MTV-HR | 69.8 | Not recorded | 68fa74ad1e209131cea6327b |
| MTV-HR | 69.8 | Not recorded | 68fa77ad1e209131cea74a67 |
| ST-Adapter | 67.3 | Not recorded | 68fa74ad1e209131cea6327b |
| MFormer | 67.3 | Not recorded | 68fa74ad1e209131cea6327b |
| ST-Adapter | 67.3 | Not recorded | 68fa77ad1e209131cea74a67 |
| MFormer-HR | 67.3 | Not recorded | 68fa77ad1e209131cea74a67 |
| AIM | 66.7 | Not recorded | 68fa74ad1e209131cea6327b |
| AIM | 66.7 | Not recorded | 68fa77ad1e209131cea74a67 |
| ViViT FE | 66.6 | Not recorded | 68fa74ad1e209131cea6327b |
| VideoMAE | 66.6 | Not recorded | 68fa74ad1e209131cea6327b |
| VIVIT FE | 66.6 | Not recorded | 68fa77ad1e209131cea74a67 |
| VideoMAE-B | 66.6 | Not recorded | 68fa77ad1e209131cea74a67 |
| CLIP | 56.5 | Not recorded | 68fa74ad1e209131cea6327b |
| CLIP | 56.5 | Not recorded | 68fa77ad1e209131cea74a67 |

### CAST

Overall Harmonic Mean: 71.6. Result ID: 699353ce3a6c314849153667.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74ad1e209131cea6327b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74ad1e209131cea6327b.md>)

[Implementation](<https://github.com/KHU-VLL/CAST>)

Recorded evaluation configuration: {"GFLOPs/View":"391"}. This record does not assert independent reproduction.

### CAST

Overall Harmonic Mean: 71.6. Result ID: 69955bd43badfaffe64d598d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77ad1e209131cea74a67.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77ad1e209131cea74a67.md>)

[Implementation](<https://github.com/MCG-NJU/VideoMAE>)

Recorded evaluation configuration: {"GFLOPs/View":"391"}. This record does not assert independent reproduction.

### OMNIVORE

Overall Harmonic Mean: 70.8. Result ID: 699353ce3a6c314849153665.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74ad1e209131cea6327b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c2d1e209131cea328ef.md>)

[Implementation](<https://facebookresearch.github.io/omnivore>)

Recorded evaluation configuration: {"GFLOPs/View":null}. This record does not assert independent reproduction.

### OMNIVORE

Overall Harmonic Mean: 70.8. Result ID: 69955bd43badfaffe64d598b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77ad1e209131cea74a67.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c2d1e209131cea328ef.md>)

[Implementation](<https://facebookresearch.github.io/omnivore>)

Recorded evaluation configuration: {"GFLOPs/View":null}. This record does not assert independent reproduction.

### MTV-HR

Overall Harmonic Mean: 69.8. Result ID: 699353ce3a6c314849153666.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74ad1e209131cea6327b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ca11e209131cea35110.md>)

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

Recorded evaluation configuration: {"GFLOPs/View":"930"}. This record does not assert independent reproduction.

### MTV-HR

Overall Harmonic Mean: 69.8. Result ID: 69955bd43badfaffe64d598c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77ad1e209131cea74a67.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ca11e209131cea35110.md>)

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

Recorded evaluation configuration: {"GFLOPs/View":"930"}. This record does not assert independent reproduction.

### ST-Adapter

Overall Harmonic Mean: 67.3. Result ID: 699353ce3a6c314849153660.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74ad1e209131cea6327b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d9f1e209131cea3aeec.md>)

[Implementation](<https://github.com/linziyi96/st-adapter>)

Recorded evaluation configuration: {"GFLOPs/View":"607"}. This record does not assert independent reproduction.

### MFormer

Overall Harmonic Mean: 67.3. Result ID: 699353ce3a6c314849153663.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74ad1e209131cea6327b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b191e209131cea2c2a8.md>)

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

Recorded evaluation configuration: {"GFLOPs/View":"1185"}. This record does not assert independent reproduction.

### ST-Adapter

Overall Harmonic Mean: 67.3. Result ID: 69955bd43badfaffe64d5982.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77ad1e209131cea74a67.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d9f1e209131cea3aeec.md>)

[Implementation](<https://github.com/linziyi96/st-adapter>)

Recorded evaluation configuration: {"GFLOPs/View":"607"}. This record does not assert independent reproduction.

### MFormer-HR

Overall Harmonic Mean: 67.3. Result ID: 69955bd43badfaffe64d5987.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77ad1e209131cea74a67.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b191e209131cea2c2a8.md>)

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

Recorded evaluation configuration: {"GFLOPs/View":"1185"}. This record does not assert independent reproduction.

### AIM

Overall Harmonic Mean: 66.7. Result ID: 699353ce3a6c314849153661.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74ad1e209131cea6327b.md>)

Recorded evaluation configuration: {"GFLOPs/View":"404"}. This record does not assert independent reproduction.

### AIM

Overall Harmonic Mean: 66.7. Result ID: 69955bd43badfaffe64d5983.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77ad1e209131cea74a67.md>)

Recorded evaluation configuration: {"GFLOPs/View":"404","Parameter-efficient tuning with adapters":true}. This record does not assert independent reproduction.

### ViViT FE

Overall Harmonic Mean: 66.6. Result ID: 699353ce3a6c314849153662.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74ad1e209131cea6327b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b2d1e209131cea2c9cc.md>)

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

Recorded evaluation configuration: {"GFLOPs/View":"990"}. This record does not assert independent reproduction.

### VideoMAE

Overall Harmonic Mean: 66.6. Result ID: 699353ce3a6c314849153664.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74ad1e209131cea6327b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6da81e209131cea3b2fd.md>)

[Implementation](<https://github.com/MCG-NJU/VideoMAE>)

Recorded evaluation configuration: {"GFLOPs/View":"180"}. This record does not assert independent reproduction.

### VIVIT FE

Overall Harmonic Mean: 66.6. Result ID: 69955bd43badfaffe64d5984.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77ad1e209131cea74a67.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b2d1e209131cea2c9cc.md>)

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

Recorded evaluation configuration: {"GFLOPs/View":"990"}. This record does not assert independent reproduction.

### VideoMAE-B

Overall Harmonic Mean: 66.6. Result ID: 69955bd43badfaffe64d598a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77ad1e209131cea74a67.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6da81e209131cea3b2fd.md>)

[Implementation](<https://github.com/MCG-NJU/VideoMAE>)

Recorded evaluation configuration: {"GFLOPs/View":"180","Parameter-efficient tuning with adapters":true}. This record does not assert independent reproduction.

### CLIP

Overall Harmonic Mean: 56.5. Result ID: 699353ce3a6c31484915365f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74ad1e209131cea6327b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69581e209131cea21ad0.md>)

[Implementation](<https://github.com/OpenAI/CLIP>)

Recorded evaluation configuration: {"GFLOPs/View":"140"}. This record does not assert independent reproduction.

### CLIP

Overall Harmonic Mean: 56.5. Result ID: 69955bd43badfaffe64d5980.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77ad1e209131cea74a67.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69581e209131cea21ad0.md>)

[Implementation](<https://github.com/OpenAI/CLIP>)

Recorded evaluation configuration: {"GFLOPs/View":"140","Parameter-efficient tuning with adapters":true}. This record does not assert independent reproduction.

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