# Surgical Video Recognition on HyperK

Source: [Surgical Video Recognition on HyperK](<https://www.sota2.com/research/sota/surgical-video-recognition-on-hyperk>)

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

Data updated: 2026-04-01T09:00:36.848Z

Evaluation of surgical video recognition performance using the HyperK dataset, reporting 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 | Surgical Video Recognition |
| Dataset (including any stated split) | HyperK |
| Metric | Top-1 Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 14 of 14 |
| 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/surgical-video-recognition-on-hyperk.md?metric=Top-1%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Top-1 Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| SurgRec-MAE | 55.28 | Not recorded | 69cca6ab0636e5bf4afcbcde |
| SurgRec-MAE | 55.28 | Not recorded | 69cca6ab0636e5bf4afcbcde |
| DINOv3 | 43.03 | Not recorded | 69cca6ab0636e5bf4afcbcde |
| SurgRec-JEPA | 42.27 | Not recorded | 69cca6ab0636e5bf4afcbcde |
| DINOv3 | 41.81 | Not recorded | 69cca6ab0636e5bf4afcbcde |
| JEPA | 41.65 | Not recorded | 69cca6ab0636e5bf4afcbcde |
| SurgRec-MAE | 36.91 | Not recorded | 69cca6ab0636e5bf4afcbcde |
| VideoMAE | 25.11 | Not recorded | 69cca6ab0636e5bf4afcbcde |
| LLaVA-NeXT-7B | 24.46 | Not recorded | 69cca6ab0636e5bf4afcbcde |
| LLaVA-NeXT-7B | 23.39 | Not recorded | 69cca6ab0636e5bf4afcbcde |
| Qwen3-VL-8B | 18.04 | Not recorded | 69cca6ab0636e5bf4afcbcde |
| Qwen3-VL-8B | 16.06 | Not recorded | 69cca6ab0636e5bf4afcbcde |
| Qwen2.5-VL-7B | 10.86 | Not recorded | 69cca6ab0636e5bf4afcbcde |
| Qwen2.5-VL-7B | 8.87 | Not recorded | 69cca6ab0636e5bf4afcbcde |

### SurgRec-MAE

Top-1 Accuracy: 55.28. Result ID: 69ccdea147f34ce924b6b68e.

[Reporting paper](<https://www.sota2.com/research/paper/69cca6ab0636e5bf4afcbcde.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69cca6ab0636e5bf4afcbcde.md>)

Recorded evaluation configuration: {"Balanced Sampling":"true"}. This record does not assert independent reproduction.

### SurgRec-MAE

Top-1 Accuracy: 55.28. Result ID: 69ccdea147f34ce924b6b6f9.

[Reporting paper](<https://www.sota2.com/research/paper/69cca6ab0636e5bf4afcbcde.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69cca6ab0636e5bf4afcbcde.md>)

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

### DINOv3

Top-1 Accuracy: 43.03. Result ID: 69ccdea147f34ce924b6b689.

[Reporting paper](<https://www.sota2.com/research/paper/69cca6ab0636e5bf4afcbcde.md>)

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

Recorded evaluation configuration: {"Pre-training Domain":"Generic"}. This record does not assert independent reproduction.

### SurgRec-JEPA

Top-1 Accuracy: 42.27. Result ID: 69ccdea147f34ce924b6b68f.

[Reporting paper](<https://www.sota2.com/research/paper/69cca6ab0636e5bf4afcbcde.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69cca6ab0636e5bf4afcbcde.md>)

Recorded evaluation configuration: {"Balanced Sampling":"true"}. This record does not assert independent reproduction.

### DINOv3

Top-1 Accuracy: 41.81. Result ID: 69ccdea147f34ce924b6b68a.

[Reporting paper](<https://www.sota2.com/research/paper/69cca6ab0636e5bf4afcbcde.md>)

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

Recorded evaluation configuration: {"Pre-training Domain":"Surgical"}. This record does not assert independent reproduction.

### JEPA

Top-1 Accuracy: 41.65. Result ID: 69ccdea147f34ce924b6b68d.

[Reporting paper](<https://www.sota2.com/research/paper/69cca6ab0636e5bf4afcbcde.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79651e209131cea7d6a4.md>)

[Implementation](<https://github.com/facebookresearch/vjepa2>)

Recorded evaluation configuration: {"Pre-training Domain":"Generic"}. This record does not assert independent reproduction.

### SurgRec-MAE

Top-1 Accuracy: 36.91. Result ID: 69ccdea147f34ce924b6b68c.

[Reporting paper](<https://www.sota2.com/research/paper/69cca6ab0636e5bf4afcbcde.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69cca6ab0636e5bf4afcbcde.md>)

Recorded evaluation configuration: {"Balanced Sampling":"false"}. This record does not assert independent reproduction.

### VideoMAE

Top-1 Accuracy: 25.11. Result ID: 69ccdea147f34ce924b6b68b.

[Reporting paper](<https://www.sota2.com/research/paper/69cca6ab0636e5bf4afcbcde.md>)

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

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

Recorded evaluation configuration: {"Pre-training Domain":"Generic"}. This record does not assert independent reproduction.

### LLaVA-NeXT-7B

Top-1 Accuracy: 24.46. Result ID: 69ccdea147f34ce924b6b6fd.

[Reporting paper](<https://www.sota2.com/research/paper/69cca6ab0636e5bf4afcbcde.md>)

Recorded evaluation configuration: {"Prompt strategy":"P2"}. This record does not assert independent reproduction.

### LLaVA-NeXT-7B

Top-1 Accuracy: 23.39. Result ID: 69ccdea147f34ce924b6b6fc.

[Reporting paper](<https://www.sota2.com/research/paper/69cca6ab0636e5bf4afcbcde.md>)

Recorded evaluation configuration: {"Prompt strategy":"P1"}. This record does not assert independent reproduction.

### Qwen3-VL-8B

Top-1 Accuracy: 18.04. Result ID: 69ccdea147f34ce924b6b6fb.

[Reporting paper](<https://www.sota2.com/research/paper/69cca6ab0636e5bf4afcbcde.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6927db54d6b0dd3342930f66.md>)

Recorded evaluation configuration: {"Prompt strategy":"P2"}. This record does not assert independent reproduction.

### Qwen3-VL-8B

Top-1 Accuracy: 16.06. Result ID: 69ccdea147f34ce924b6b6fa.

[Reporting paper](<https://www.sota2.com/research/paper/69cca6ab0636e5bf4afcbcde.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6927db54d6b0dd3342930f66.md>)

Recorded evaluation configuration: {"Prompt strategy":"P1"}. This record does not assert independent reproduction.

### Qwen2.5-VL-7B

Top-1 Accuracy: 10.86. Result ID: 69ccdea147f34ce924b6b6ff.

[Reporting paper](<https://www.sota2.com/research/paper/69cca6ab0636e5bf4afcbcde.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71d3c.md>)

Recorded evaluation configuration: {"Prompt strategy":"P2"}. This record does not assert independent reproduction.

### Qwen2.5-VL-7B

Top-1 Accuracy: 8.87. Result ID: 69ccdea147f34ce924b6b6fe.

[Reporting paper](<https://www.sota2.com/research/paper/69cca6ab0636e5bf4afcbcde.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71d3c.md>)

Recorded evaluation configuration: {"Prompt strategy":"P1"}. This record does not assert independent reproduction.

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