# Referring Video Object Segmentation on Ref-YouTube-VOS 1.0 (val)

Source: [Referring Video Object Segmentation on Ref-YouTube-VOS 1.0 (val)](<https://www.sota2.com/research/sota/referring-video-object-segmentation-on-ref-youtube-vos-1-0-val>)

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

Data updated: 2026-02-26T05:47:33.370Z

Evaluation of Referring Video Object Segmentation performance on the validation split of the Ref-YouTube-VOS 1.0 dataset, measured using J&F, J, F, and FPS.

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 1.0 (val) |
| Metric | J&F |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 19 of 19 |
| 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](<https://www.sota2.com/research/sota/referring-video-object-segmentation-on-ref-youtube-vos-1-0-val.md?metric=J%26F>): Higher is better; unit: PERCENT.

- [J](<https://www.sota2.com/research/sota/referring-video-object-segmentation-on-ref-youtube-vos-1-0-val.md?metric=J>): Higher is better; unit: PERCENT.

- [F](<https://www.sota2.com/research/sota/referring-video-object-segmentation-on-ref-youtube-vos-1-0-val.md?metric=F>): Higher is better; unit: PERCENT.

- [FPS](<https://www.sota2.com/research/sota/referring-video-object-segmentation-on-ref-youtube-vos-1-0-val.md?metric=FPS>): Higher is better; unit: TIME.

## Recorded results

| Method | J&F | Result date | Report paper |
| --- | --- | --- | --- |
| VD-IT | 66.5 | Not recorded | 68fa73fd1e209131cea5f114 |
| SgMg | 65.7 | Not recorded | 68fa73fd1e209131cea5f114 |
| VD-IT | 64.8 | Not recorded | 68fa73fd1e209131cea5f114 |
| ReferFormer | 62.9 | Not recorded | 68fa73fd1e209131cea5f114 |
| OnlineRefer | 62.9 | Not recorded | 68fa73fd1e209131cea5f114 |
| SgMg | 62 | Not recorded | 68fa73fd1e209131cea5f114 |
| SgMg | 61.6 | Not recorded | 68fa73fd1e209131cea5f114 |
| ReferFormer | 59.4 | Not recorded | 68fa73fd1e209131cea5f114 |
| SgMg | 58.9 | Not recorded | 68fa73fd1e209131cea5f114 |
| ReferFormer | 56 | Not recorded | 68fa73fd1e209131cea5f114 |
| MANet | 55.6 | Not recorded | 68fa73fd1e209131cea5f114 |
| MTTR | 55.3 | Not recorded | 68fa73fd1e209131cea5f114 |
| PMINet | 53 | Not recorded | 68fa73fd1e209131cea5f114 |
| MLRL | 49.7 | Not recorded | 68fa73fd1e209131cea5f114 |
| LBDT | 49.4 | Not recorded | 68fa73fd1e209131cea5f114 |
| YOFO | 48.6 | Not recorded | 68fa73fd1e209131cea5f114 |
| CMPC-V | 47.5 | Not recorded | 68fa73fd1e209131cea5f114 |
| URVOS | 47.2 | Not recorded | 68fa73fd1e209131cea5f114 |
| CMSA | 36.4 | Not recorded | 68fa73fd1e209131cea5f114 |

### VD-IT

J&F: 66.5. Result ID: 699313663a6c314849138585.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73fd1e209131cea5f114.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73fd1e209131cea5f114.md>)

[Implementation](<https://github.com/buxiangzhiren/VD-IT>)

Recorded evaluation configuration: {"Backbone":"Video Diffusion","Pre-training":"RefCOCO/+/g"}. This record does not assert independent reproduction.

### SgMg

J&F: 65.7. Result ID: 699313663a6c314849138584.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73fd1e209131cea5f114.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70261e209131cea496a0.md>)

[Implementation](<https://github.com/bo-miao/SgMg>)

Recorded evaluation configuration: {"Backbone":"Video-Swin-B","Pre-training":"RefCOCO/+/g"}. This record does not assert independent reproduction.

### VD-IT

J&F: 64.8. Result ID: 699313663a6c31484913857f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73fd1e209131cea5f114.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73fd1e209131cea5f114.md>)

[Implementation](<https://github.com/buxiangzhiren/VD-IT>)

Recorded evaluation configuration: {"Backbone":"Video Diffusion"}. This record does not assert independent reproduction.

### ReferFormer

J&F: 62.9. Result ID: 699313663a6c314849138582.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73fd1e209131cea5f114.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bff1e209131cea31875.md>)

[Implementation](<https://github.com/wjn922/ReferFormer>)

Recorded evaluation configuration: {"Backbone":"Video-Swin-B","Pre-training":"RefCOCO/+/g"}. This record does not assert independent reproduction.

### OnlineRefer

J&F: 62.9. Result ID: 699313663a6c314849138583.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73fd1e209131cea5f114.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa701e1e209131cea4927a.md>)

[Implementation](<https://github.com/wudongming97/OnlineRefer>)

Recorded evaluation configuration: {"Backbone":"Video-Swin-B","Pre-training":"RefCOCO/+/g"}. This record does not assert independent reproduction.

### SgMg

J&F: 62. Result ID: 699313663a6c314849138581.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73fd1e209131cea5f114.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70261e209131cea496a0.md>)

[Implementation](<https://github.com/bo-miao/SgMg>)

Recorded evaluation configuration: {"Backbone":"Video-Swin-T","Pre-training":"RefCOCO/+/g"}. This record does not assert independent reproduction.

### SgMg

J&F: 61.6. Result ID: 699313663a6c31484913857e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73fd1e209131cea5f114.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70261e209131cea496a0.md>)

[Implementation](<https://github.com/bo-miao/SgMg>)

Recorded evaluation configuration: {"Backbone":"Video-Swin-B","Note":"Evaluated using official code"}. This record does not assert independent reproduction.

### ReferFormer

J&F: 59.4. Result ID: 699313663a6c314849138580.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73fd1e209131cea5f114.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bff1e209131cea31875.md>)

[Implementation](<https://github.com/wjn922/ReferFormer>)

Recorded evaluation configuration: {"Backbone":"Video-Swin-T","Pre-training":"RefCOCO/+/g"}. This record does not assert independent reproduction.

### SgMg

J&F: 58.9. Result ID: 699313663a6c31484913857d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73fd1e209131cea5f114.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70261e209131cea496a0.md>)

[Implementation](<https://github.com/bo-miao/SgMg>)

Recorded evaluation configuration: {"Backbone":"Video-Swin-T"}. This record does not assert independent reproduction.

### ReferFormer

J&F: 56. Result ID: 699313663a6c31484913857c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73fd1e209131cea5f114.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bff1e209131cea31875.md>)

[Implementation](<https://github.com/wjn922/ReferFormer>)

Recorded evaluation configuration: {"Backbone":"Video-Swin-T"}. This record does not assert independent reproduction.

### MANet

J&F: 55.6. Result ID: 699313663a6c31484913857b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73fd1e209131cea5f114.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d1e1e209131cea37e48.md>)

[Implementation](<https://github.com/DexiangHong/MANet>)

Recorded evaluation configuration: {"Backbone":"Video-Swin-T"}. This record does not assert independent reproduction.

### MTTR

J&F: 55.3. Result ID: 699313663a6c31484913857a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73fd1e209131cea5f114.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c341e209131cea32c7c.md>)

[Implementation](<https://github.com/mttr2021/MTTR>)

Recorded evaluation configuration: {"Backbone":"Video-Swin-T"}. This record does not assert independent reproduction.

### PMINet

J&F: 53. Result ID: 699313663a6c314849138576.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73fd1e209131cea5f114.md>)

Recorded evaluation configuration: {"Backbone":"ResNeSt-101"}. This record does not assert independent reproduction.

### MLRL

J&F: 49.7. Result ID: 699313663a6c314849138579.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73fd1e209131cea5f114.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction.

### LBDT

J&F: 49.4. Result ID: 699313663a6c314849138578.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73fd1e209131cea5f114.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cb51e209131cea356fe.md>)

[Implementation](<https://github.com/dzh19990407/LBDT>)

Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction.

### YOFO

J&F: 48.6. Result ID: 699313663a6c314849138577.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73fd1e209131cea5f114.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction.

### CMPC-V

J&F: 47.5. Result ID: 699313663a6c314849138575.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73fd1e209131cea5f114.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69f41e209131cea253e9.md>)

[Implementation](<https://github.com/spyflying/CMPC-Refseg>)

Recorded evaluation configuration: {"Backbone":"I3D"}. This record does not assert independent reproduction.

### URVOS

J&F: 47.2. Result ID: 699313663a6c314849138574.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73fd1e209131cea5f114.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction.

### CMSA

J&F: 36.4. Result ID: 699313663a6c314849138573.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73fd1e209131cea5f114.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65a31e209131cea0b7c3.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction.

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