# Action Recognition on K400 open-vocabulary

Source: [Action Recognition on K400 open-vocabulary](<https://www.sota2.com/research/sota/action-recognition-on-k400-open-vocabulary>)

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

Data updated: 2026-02-26T05:37:38.145Z

Evaluation of Action Recognition performance on the Kinetics-400 dataset under an open-vocabulary setting, utilizing Base, Novel, and Harmonic Mean metrics.

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) | K400 open-vocabulary |
| Metric | Base Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [Base Accuracy](<https://www.sota2.com/research/sota/action-recognition-on-k400-open-vocabulary.md?metric=Base%20Accuracy>): Higher is better; unit: PERCENT.

- [Novel Accuracy](<https://www.sota2.com/research/sota/action-recognition-on-k400-open-vocabulary.md?metric=Novel%20Accuracy>): Higher is better; unit: PERCENT.

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

## Recorded results

| Method | Base Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| FROSTER | 78.8 | Not recorded | 692d2153d6b0dd33429319bc |
| FROSTER | 78.3 | Not recorded | 692d2153d6b0dd33429319bc |
| FROSTER | 77.8 | Not recorded | 692d2153d6b0dd33429319bc |
| Open-VCLIP | 76.5 | Not recorded | 692d2153d6b0dd33429319bc |
| ViFi-CLIP | 76.4 | Not recorded | 692d2153d6b0dd33429319bc |

### FROSTER

Base Accuracy: 78.8. Result ID: 6995e14c3badfaffe6e8b76b.

[Reporting paper](<https://www.sota2.com/research/paper/692d2153d6b0dd33429319bc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/692d2153d6b0dd33429319bc.md>)

Recorded evaluation configuration: {"Prompt Tuning":"MMRL+VaMP"}. This record does not assert independent reproduction.

### FROSTER

Base Accuracy: 78.3. Result ID: 6995e14c3badfaffe6e8b76a.

[Reporting paper](<https://www.sota2.com/research/paper/692d2153d6b0dd33429319bc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/692d2153d6b0dd33429319bc.md>)

Recorded evaluation configuration: {"Prompt Tuning":"MMRL"}. This record does not assert independent reproduction.

### FROSTER

Base Accuracy: 77.8. Result ID: 6995e14c3badfaffe6e8b769.

[Reporting paper](<https://www.sota2.com/research/paper/692d2153d6b0dd33429319bc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/692d2153d6b0dd33429319bc.md>)

Recorded evaluation configuration: {"Prompt Tuning":"None"}. This record does not assert independent reproduction.

### Open-VCLIP

Base Accuracy: 76.5. Result ID: 6995e14c3badfaffe6e8b768.

[Reporting paper](<https://www.sota2.com/research/paper/692d2153d6b0dd33429319bc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f961e209131cea46799.md>)

Recorded evaluation configuration: {"Prompt Tuning":"None"}. This record does not assert independent reproduction.

### ViFi-CLIP

Base Accuracy: 76.4. Result ID: 6995e14c3badfaffe6e8b767.

[Reporting paper](<https://www.sota2.com/research/paper/692d2153d6b0dd33429319bc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ee81e209131cea42cef.md>)

[Implementation](<https://github.com/muzairkhattak/ViFi-CLIP>)

Recorded evaluation configuration: {"Prompt Tuning":"None"}. This record does not assert independent reproduction.

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