# Video Object Segmentation on MOSE v2 (test)

Source: [Video Object Segmentation on MOSE v2 (test)](<https://www.sota2.com/research/sota/video-object-segmentation-on-mose-v2-test>)

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

Data updated: 2026-04-02T08:56:32.539Z

Evaluation of Video Object Segmentation performance on the test split of the MOSE v2 dataset.

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 Object Segmentation |
| Dataset (including any stated split) | MOSE v2 (test) |
| Metric | J&F Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [J&F Score](<https://www.sota2.com/research/sota/video-object-segmentation-on-mose-v2-test.md?metric=J%26F%20Score>): Higher is better; unit: PERCENT.

- [J Score](<https://www.sota2.com/research/sota/video-object-segmentation-on-mose-v2-test.md?metric=J%20Score>): Higher is better; unit: PERCENT.

- [F Score](<https://www.sota2.com/research/sota/video-object-segmentation-on-mose-v2-test.md?metric=F%20Score>): Higher is better; unit: PERCENT.

- [J&F Score (Disappear)](<https://www.sota2.com/research/sota/video-object-segmentation-on-mose-v2-test.md?metric=J%26F%20Score%20(Disappear)>): Higher is better; unit: PERCENT.

- [J&F Score (Reappear)](<https://www.sota2.com/research/sota/video-object-segmentation-on-mose-v2-test.md?metric=J%26F%20Score%20(Reappear)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | J&F Score | Result date | Report paper |
| --- | --- | --- | --- |
| TEP | 56.91 | Not recorded | 69cdf7ff0636e5bf4afcca5e |
| TEP | 55.57 | Not recorded | 69cdf7ff0636e5bf4afcca5e |
| SAM3 | 46.63 | Not recorded | 69cdf7ff0636e5bf4afcca5e |

### TEP

J&F Score: 56.91. Result ID: 69ce2f2347f34ce924b77707.

[Reporting paper](<https://www.sota2.com/research/paper/69cdf7ff0636e5bf4afcca5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69cdf7ff0636e5bf4afcca5e.md>)

Recorded evaluation configuration: {"Configuration":"Tracking Model & MLLM"}. This record does not assert independent reproduction.

### TEP

J&F Score: 55.57. Result ID: 69ce2f2347f34ce924b77706.

[Reporting paper](<https://www.sota2.com/research/paper/69cdf7ff0636e5bf4afcca5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69cdf7ff0636e5bf4afcca5e.md>)

Recorded evaluation configuration: {"Configuration":"MLLM"}. This record does not assert independent reproduction.

### SAM3

J&F Score: 46.63. Result ID: 69ce2f2347f34ce924b77705.

[Reporting paper](<https://www.sota2.com/research/paper/69cdf7ff0636e5bf4afcca5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6923e69bd6b0dd334292f0ad.md>)

[Implementation](<https://github.com/facebookresearch/sam3>)

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.
