# Video Action Recognition on CharadesEgo

Source: [Video Action Recognition on CharadesEgo](<https://www.sota2.com/research/sota/video-action-recognition-on-charadesego>)

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

Data updated: 2026-02-26T06:07:08.117Z

Evaluation of Video Action Recognition performance on the CharadesEgo dataset, measured using Top-1 Accuracy.

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 | Video Action Recognition |
| Dataset (including any stated split) | CharadesEgo |
| Metric | Top-1 Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 16 of 16 |
| 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

- [Top-1 Accuracy](<https://www.sota2.com/research/sota/video-action-recognition-on-charadesego.md?metric=Top-1%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Top-1 Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| DINOv3 | 14 | Not recorded | 698abc32c97a0b3e3b5de4a5 |
| DINOv3 | 13.2 | Not recorded | 698abc32c97a0b3e3b5de4a5 |
| OV-Encoder (Codec) | 12.9 | Not recorded | 698abc32c97a0b3e3b5de4a5 |
| OV-Encoder (Frame) | 12.6 | Not recorded | 698abc32c97a0b3e3b5de4a5 |
| AIMv2 | 12.4 | Not recorded | 698abc32c97a0b3e3b5de4a5 |
| OV-Encoder (Codec) | 12.3 | Not recorded | 698abc32c97a0b3e3b5de4a5 |
| OV-Encoder (Frame) | 12.1 | Not recorded | 698abc32c97a0b3e3b5de4a5 |
| AIMv2 | 12 | Not recorded | 698abc32c97a0b3e3b5de4a5 |
| SigLIP2 | 11.9 | Not recorded | 698abc32c97a0b3e3b5de4a5 |
| SigLIP | 11.7 | Not recorded | 698abc32c97a0b3e3b5de4a5 |
| SigLIP2 | 11.6 | Not recorded | 698abc32c97a0b3e3b5de4a5 |
| MetaCLIP2 | 11.2 | Not recorded | 698abc32c97a0b3e3b5de4a5 |
| MetaCLIP2 | 11 | Not recorded | 698abc32c97a0b3e3b5de4a5 |
| SigLIP | 10.9 | Not recorded | 698abc32c97a0b3e3b5de4a5 |
| CLIP | 10.8 | Not recorded | 698abc32c97a0b3e3b5de4a5 |
| MetaCLIP | 10.4 | Not recorded | 698abc32c97a0b3e3b5de4a5 |

### DINOv3

Top-1 Accuracy: 14. Result ID: 6997250d5698665ec4736fec.

[Reporting paper](<https://www.sota2.com/research/paper/698abc32c97a0b3e3b5de4a5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a931e209131cea83fc5.md>)

Recorded evaluation configuration: {"Backbone":"ViT-L/14","Resolution":"224","Input Configuration (Frames/Patches)":"16 Frames / 4096 Patches","Evaluation Protocol (Attentive probe with frozen backbones)":"Attentive probe with frozen backbones"}. This record does not assert independent reproduction.

### DINOv3

Top-1 Accuracy: 13.2. Result ID: 6997250d5698665ec4736fe5.

[Reporting paper](<https://www.sota2.com/research/paper/698abc32c97a0b3e3b5de4a5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a931e209131cea83fc5.md>)

Recorded evaluation configuration: {"Backbone":"ViT-L/14","Resolution":"224","Input Configuration (Frames/Patches)":"8 Frames / 2048 Patches","Evaluation Protocol (Attentive probe with frozen backbones)":"Attentive probe with frozen backbones"}. This record does not assert independent reproduction.

### OV-Encoder (Codec)

Top-1 Accuracy: 12.9. Result ID: 6997250d5698665ec4736fee.

[Reporting paper](<https://www.sota2.com/research/paper/698abc32c97a0b3e3b5de4a5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698abc32c97a0b3e3b5de4a5.md>)

[Implementation](<https://github.com/EvolvingLMMs-Lab/OneVision-Encoder>)

Recorded evaluation configuration: {"Backbone":"ViT-L/14","Resolution":"224","Input Configuration (Frames/Patches)":"16 Frames / 4096 Patches","Evaluation Protocol (Attentive probe with frozen backbones)":"Attentive probe with frozen backbones"}. This record does not assert independent reproduction.

### OV-Encoder (Frame)

Top-1 Accuracy: 12.6. Result ID: 6997250d5698665ec4736fed.

[Reporting paper](<https://www.sota2.com/research/paper/698abc32c97a0b3e3b5de4a5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698abc32c97a0b3e3b5de4a5.md>)

[Implementation](<https://github.com/EvolvingLMMs-Lab/OneVision-Encoder>)

Recorded evaluation configuration: {"Backbone":"ViT-L/14","Resolution":"224","Input Configuration (Frames/Patches)":"16 Frames / 4096 Patches","Evaluation Protocol (Attentive probe with frozen backbones)":"Attentive probe with frozen backbones"}. This record does not assert independent reproduction.

### AIMv2

Top-1 Accuracy: 12.4. Result ID: 6997250d5698665ec4736fea.

[Reporting paper](<https://www.sota2.com/research/paper/698abc32c97a0b3e3b5de4a5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75db1e209131cea6a431.md>)

[Implementation](<https://github.com/apple/ml-aim>)

Recorded evaluation configuration: {"Backbone":"ViT-L/14","Resolution":"224","Input Configuration (Frames/Patches)":"16 Frames / 4096 Patches","Evaluation Protocol (Attentive probe with frozen backbones)":"Attentive probe with frozen backbones"}. This record does not assert independent reproduction.

### OV-Encoder (Codec)

Top-1 Accuracy: 12.3. Result ID: 6997250d5698665ec4736fe7.

[Reporting paper](<https://www.sota2.com/research/paper/698abc32c97a0b3e3b5de4a5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698abc32c97a0b3e3b5de4a5.md>)

[Implementation](<https://github.com/EvolvingLMMs-Lab/OneVision-Encoder>)

Recorded evaluation configuration: {"Backbone":"ViT-L/14","Resolution":"224","Input Configuration (Frames/Patches)":"8 Frames / 2048 Patches","Evaluation Protocol (Attentive probe with frozen backbones)":"Attentive probe with frozen backbones"}. This record does not assert independent reproduction.

### OV-Encoder (Frame)

Top-1 Accuracy: 12.1. Result ID: 6997250d5698665ec4736fe6.

[Reporting paper](<https://www.sota2.com/research/paper/698abc32c97a0b3e3b5de4a5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698abc32c97a0b3e3b5de4a5.md>)

[Implementation](<https://github.com/EvolvingLMMs-Lab/OneVision-Encoder>)

Recorded evaluation configuration: {"Backbone":"ViT-L/14","Resolution":"224","Input Configuration (Frames/Patches)":"8 Frames / 2048 Patches","Evaluation Protocol (Attentive probe with frozen backbones)":"Attentive probe with frozen backbones"}. This record does not assert independent reproduction.

### AIMv2

Top-1 Accuracy: 12. Result ID: 6997250d5698665ec4736fe3.

[Reporting paper](<https://www.sota2.com/research/paper/698abc32c97a0b3e3b5de4a5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75db1e209131cea6a431.md>)

[Implementation](<https://github.com/apple/ml-aim>)

Recorded evaluation configuration: {"Backbone":"ViT-L/14","Resolution":"224","Input Configuration (Frames/Patches)":"8 Frames / 2048 Patches","Evaluation Protocol (Attentive probe with frozen backbones)":"Attentive probe with frozen backbones"}. This record does not assert independent reproduction.

### SigLIP2

Top-1 Accuracy: 11.9. Result ID: 6997250d5698665ec4736feb.

[Reporting paper](<https://www.sota2.com/research/paper/698abc32c97a0b3e3b5de4a5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa770a1e209131cea70ad4.md>)

Recorded evaluation configuration: {"Backbone":"ViT-L/16","Resolution":"256","Input Configuration (Frames/Patches)":"16 Frames / 4096 Patches","Evaluation Protocol (Attentive probe with frozen backbones)":"Attentive probe with frozen backbones"}. This record does not assert independent reproduction.

### SigLIP

Top-1 Accuracy: 11.7. Result ID: 6997250d5698665ec4736fe8.

[Reporting paper](<https://www.sota2.com/research/paper/698abc32c97a0b3e3b5de4a5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70ae1e209131cea4c7a4.md>)

Recorded evaluation configuration: {"Backbone":"ViT-L/16","Resolution":"256","Input Configuration (Frames/Patches)":"16 Frames / 4096 Patches","Evaluation Protocol (Attentive probe with frozen backbones)":"Attentive probe with frozen backbones"}. This record does not assert independent reproduction.

### SigLIP2

Top-1 Accuracy: 11.6. Result ID: 6997250d5698665ec4736fe4.

[Reporting paper](<https://www.sota2.com/research/paper/698abc32c97a0b3e3b5de4a5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa770a1e209131cea70ad4.md>)

Recorded evaluation configuration: {"Backbone":"ViT-L/16","Resolution":"256","Input Configuration (Frames/Patches)":"8 Frames / 2048 Patches","Evaluation Protocol (Attentive probe with frozen backbones)":"Attentive probe with frozen backbones"}. This record does not assert independent reproduction.

### MetaCLIP2

Top-1 Accuracy: 11.2. Result ID: 6997250d5698665ec4736fe9.

[Reporting paper](<https://www.sota2.com/research/paper/698abc32c97a0b3e3b5de4a5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a571e209131cea829d6.md>)

Recorded evaluation configuration: {"Backbone":"ViT-L/14","Resolution":"224","Input Configuration (Frames/Patches)":"16 Frames / 4096 Patches","Evaluation Protocol (Attentive probe with frozen backbones)":"Attentive probe with frozen backbones"}. This record does not assert independent reproduction.

### MetaCLIP2

Top-1 Accuracy: 11. Result ID: 6997250d5698665ec4736fe2.

[Reporting paper](<https://www.sota2.com/research/paper/698abc32c97a0b3e3b5de4a5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a571e209131cea829d6.md>)

Recorded evaluation configuration: {"Backbone":"ViT-L/14","Resolution":"224","Input Configuration (Frames/Patches)":"8 Frames / 2048 Patches","Evaluation Protocol (Attentive probe with frozen backbones)":"Attentive probe with frozen backbones"}. This record does not assert independent reproduction.

### SigLIP

Top-1 Accuracy: 10.9. Result ID: 6997250d5698665ec4736fe0.

[Reporting paper](<https://www.sota2.com/research/paper/698abc32c97a0b3e3b5de4a5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70ae1e209131cea4c7a4.md>)

Recorded evaluation configuration: {"Backbone":"ViT-L/16","Resolution":"256","Input Configuration (Frames/Patches)":"8 Frames / 2048 Patches","Evaluation Protocol (Attentive probe with frozen backbones)":"Attentive probe with frozen backbones"}. This record does not assert independent reproduction.

### CLIP

Top-1 Accuracy: 10.8. Result ID: 6997250d5698665ec4736fdf.

[Reporting paper](<https://www.sota2.com/research/paper/698abc32c97a0b3e3b5de4a5.md>)

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

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

Recorded evaluation configuration: {"Backbone":"ViT-L/14","Resolution":"224","Input Configuration (Frames/Patches)":"8 Frames / 2048 Patches","Evaluation Protocol (Attentive probe with frozen backbones)":"Attentive probe with frozen backbones"}. This record does not assert independent reproduction.

### MetaCLIP

Top-1 Accuracy: 10.4. Result ID: 6997250d5698665ec4736fe1.

[Reporting paper](<https://www.sota2.com/research/paper/698abc32c97a0b3e3b5de4a5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76721e209131cea6d0be.md>)

Recorded evaluation configuration: {"Backbone":"ViT-L/14","Resolution":"224","Input Configuration (Frames/Patches)":"8 Frames / 2048 Patches","Evaluation Protocol (Attentive probe with frozen backbones)":"Attentive probe with frozen backbones"}. This record does not assert independent reproduction.

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