# Referring Video Object Segmentation on Ref-YouTube-VOS 45 (test)

Source: [Referring Video Object Segmentation on Ref-YouTube-VOS 45 (test)](<https://www.sota2.com/research/sota/referring-video-object-segmentation-on-ref-youtube-vos-45-test>)

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

Data updated: 2026-06-24T08:29:12.741Z

Evaluation of Referring Video Object Segmentation performance on the test split of the Ref-YouTube-VOS 45 dataset, measured using J&F, J, and F 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 | Referring Video Object Segmentation |
| Dataset (including any stated split) | Ref-YouTube-VOS 45 (test) |
| Metric | J&F Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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/referring-video-object-segmentation-on-ref-youtube-vos-45-test.md?metric=J%26F%20Score>): Higher is better; unit: SCALAR.

- [J Score (IoU)](<https://www.sota2.com/research/sota/referring-video-object-segmentation-on-ref-youtube-vos-45-test.md?metric=J%20Score%20(IoU)>): Higher is better; unit: SCALAR.

- [F Score (F1)](<https://www.sota2.com/research/sota/referring-video-object-segmentation-on-ref-youtube-vos-45-test.md?metric=F%20Score%20(F1)>): Higher is better; unit: SCALAR.

## Recorded results

| Method | J&F Score | Result date | Report paper |
| --- | --- | --- | --- |
| GeoLaV | 47 | Not recorded | 6a3b64d5206542251d7c98fd |
| ReMamber | 35.1 | Not recorded | 6a3b64d5206542251d7c98fd |
| SAMWISE | 31.9 | Not recorded | 6a3b64d5206542251d7c98fd |
| LAVT | 28.6 | Not recorded | 6a3b64d5206542251d7c98fd |
| DETRIS | 17.6 | Not recorded | 6a3b64d5206542251d7c98fd |
| DMMI | 9.6 | Not recorded | 6a3b64d5206542251d7c98fd |
| LMPM | 7.1 | Not recorded | 6a3b64d5206542251d7c98fd |
| DsHmp | 7.1 | Not recorded | 6a3b64d5206542251d7c98fd |

### GeoLaV

J&F Score: 47. Result ID: 6a3b954efbc373592c449804.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64d5206542251d7c98fd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3b64d5206542251d7c98fd.md>)

Recorded evaluation configuration: {"Zero-shot":"true","Model Type":"Video-based Model (Trained on Images Only)","Training Data":"RefCOCO/+/g"}. This record does not assert independent reproduction.

### ReMamber

J&F Score: 35.1. Result ID: 6a3b954efbc373592c4497fe.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64d5206542251d7c98fd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa744b1e209131cea60dbe.md>)

Recorded evaluation configuration: {"Zero-shot":"true","Model Type":"Image-based Model","Training Data":"RefCOCO/+/g"}. This record does not assert independent reproduction.

### SAMWISE

J&F Score: 31.9. Result ID: 6a3b954efbc373592c449803.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64d5206542251d7c98fd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77931e209131cea740d7.md>)

[Implementation](<https://github.com/ClaudiaCuttano/SAMWISE>)

Recorded evaluation configuration: {"Zero-shot":"true","Model Type":"Video-based Model (Trained on Images Only)","Training Data":"RefCOCO/+/g"}. This record does not assert independent reproduction.

### LAVT

J&F Score: 28.6. Result ID: 6a3b954efbc373592c449802.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64d5206542251d7c98fd.md>)

Recorded evaluation configuration: {"Zero-shot":"true","Model Type":"Video-based Model (Trained on Images Only)","Training Data":"RefCOCO/+/g"}. This record does not assert independent reproduction.

### DETRIS

J&F Score: 17.6. Result ID: 6a3b954efbc373592c4497ff.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64d5206542251d7c98fd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa769a1e209131cea6e10f.md>)

[Implementation](<https://github.com/jiaqihuang01/DETRIS>)

Recorded evaluation configuration: {"Zero-shot":"true","Model Type":"Image-based Model","Training Data":"RefCOCO/+/g"}. This record does not assert independent reproduction.

### DMMI

J&F Score: 9.6. Result ID: 6a3b954efbc373592c4497fd.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64d5206542251d7c98fd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70761e209131cea4b349.md>)

Recorded evaluation configuration: {"Zero-shot":"true","Model Type":"Image-based Model","Training Data":"RefCOCO/+/g"}. This record does not assert independent reproduction.

### LMPM

J&F Score: 7.1. Result ID: 6a3b954efbc373592c449800.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64d5206542251d7c98fd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70531e209131cea4a40f.md>)

[Implementation](<https://henghuiding.github.io/MeViS>)

Recorded evaluation configuration: {"Zero-shot":"true","Model Type":"Video-based Model (Trained on Images Only)","Training Data":"RefCOCO/+/g"}. This record does not assert independent reproduction.

### DsHmp

J&F Score: 7.1. Result ID: 6a3b954efbc373592c449801.

[Reporting paper](<https://www.sota2.com/research/paper/6a3b64d5206542251d7c98fd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72d31e209131cea58bb7.md>)

[Implementation](<https://github.com/heshuting555/DsHmp>)

Recorded evaluation configuration: {"Zero-shot":"true","Model Type":"Video-based Model (Trained on Images Only)","Training Data":"RefCOCO/+/g"}. This record does not assert independent reproduction.

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