# Video Semantic Segmentation on VIPSeg (val)

Source: [Video Semantic Segmentation on VIPSeg (val)](<https://www.sota2.com/research/sota/video-semantic-segmentation-on-vipseg-val>)

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

Data updated: 2026-02-26T06:10:20.995Z

Evaluation of Video Semantic Segmentation performance on the validation split of the VIPSeg dataset, reporting mIoU and mVC 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 | Video Semantic Segmentation |
| Dataset (including any stated split) | VIP-Seg (val) |
| Metric | mIoU |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [mIoU](<https://www.sota2.com/research/sota/video-semantic-segmentation-on-vipseg-val.md?metric=mIoU>): Higher is better; unit: PERCENT.

- [mVC (k=8)](<https://www.sota2.com/research/sota/video-semantic-segmentation-on-vipseg-val.md?metric=mVC%20(k%3D8)>): Higher is better; unit: PERCENT.

- [mVC (k=16)](<https://www.sota2.com/research/sota/video-semantic-segmentation-on-vipseg-val.md?metric=mVC%20(k%3D16)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | mIoU | Result date | Report paper |
| --- | --- | --- | --- |
| Tube-Link | 64.9 | Not recorded | 68fa70581e209131cea4a6d9 |
| Tube-Link | 62.3 | Not recorded | 68fa70581e209131cea4a6d9 |
| Video K-Net+ | 57.2 | Not recorded | 68fa70581e209131cea4a6d9 |
| Tube-Link | 43.4 | Not recorded | 68fa70581e209131cea4a6d9 |
| Video K-Net (PSPNet) | 39 | Not recorded | 68fa70581e209131cea4a6d9 |
| Mask2Former | 38.4 | Not recorded | 68fa70581e209131cea4a6d9 |
| Video K-Net (Deeplabv3+) | 38.3 | Not recorded | 68fa70581e209131cea4a6d9 |

### Tube-Link

mIoU: 64.9. Result ID: 69912a723a6c314849062bdf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70581e209131cea4a6d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70581e209131cea4a6d9.md>)

[Implementation](<https://github.com/lxtGH/Tube-Link>)

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

### Tube-Link

mIoU: 62.3. Result ID: 69912a723a6c314849062bde.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70581e209131cea4a6d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70581e209131cea4a6d9.md>)

[Implementation](<https://github.com/lxtGH/Tube-Link>)

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

### Video K-Net+

mIoU: 57.2. Result ID: 69912a723a6c314849062bdc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70581e209131cea4a6d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6da91e209131cea3b423.md>)

[Implementation](<https://github.com/lxtGH/Video-K-Net>)

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

### Tube-Link

mIoU: 43.4. Result ID: 69912a723a6c314849062bdd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70581e209131cea4a6d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70581e209131cea4a6d9.md>)

[Implementation](<https://github.com/lxtGH/Tube-Link>)

Recorded evaluation configuration: {"Backbone":"ResNet50"}. This record does not assert independent reproduction.

### Video K-Net (PSPNet)

mIoU: 39. Result ID: 69912a723a6c314849062bda.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70581e209131cea4a6d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6da91e209131cea3b423.md>)

[Implementation](<https://github.com/lxtGH/Video-K-Net>)

Recorded evaluation configuration: {"Backbone":"ResNet101"}. This record does not assert independent reproduction.

### Mask2Former

mIoU: 38.4. Result ID: 69912a723a6c314849062bdb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70581e209131cea4a6d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cbf1e209131cea35c19.md>)

[Implementation](<https://bowenc0221.github.io/mask2former>)

Recorded evaluation configuration: {"Backbone":"ResNet50"}. This record does not assert independent reproduction.

### Video K-Net (Deeplabv3+)

mIoU: 38.3. Result ID: 69912a723a6c314849062bd9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70581e209131cea4a6d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6da91e209131cea3b423.md>)

[Implementation](<https://github.com/lxtGH/Video-K-Net>)

Recorded evaluation configuration: {"Backbone":"ResNet101"}. This record does not assert independent reproduction.

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