# Video Tasks on Waymo

Source: [Video Tasks on Waymo](<https://www.sota2.com/research/sota/video-tasks-on-waymo>)

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

Data updated: 2026-02-26T06:10:47.179Z

Evaluation of various video-related tasks on the Waymo dataset, measured using Mean Intersection over Union (mIoU).

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 Tasks |
| Dataset (including any stated split) | Waymo |
| Metric | mIoU |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 11 of 11 |
| 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-tasks-on-waymo.md?metric=mIoU>): Higher is better; unit: PERCENT.

## Recorded results

| Method | mIoU | Result date | Report paper |
| --- | --- | --- | --- |
| 4DS-H | 76.1 | Not recorded | 6940e7e5456146936284fcf2 |
| 4DS-L | 75.9 | Not recorded | 6940e7e5456146936284fcf2 |
| VideoMAE-L | 74.9 | Not recorded | 6940e7e5456146936284fcf2 |
| V-JEPA-H | 74.9 | Not recorded | 6940e7e5456146936284fcf2 |
| VideoMAE-H | 74.6 | Not recorded | 6940e7e5456146936284fcf2 |
| RVM-H | 74.2 | Not recorded | 6940e7e5456146936284fcf2 |
| V-JEPA-L | 73.3 | Not recorded | 6940e7e5456146936284fcf2 |
| RVM-L | 73.2 | Not recorded | 6940e7e5456146936284fcf2 |
| VideoMAEv2-g | 72.6 | Not recorded | 6940e7e5456146936284fcf2 |
| DINOv2-L (distilled) | 51.7 | Not recorded | 6940e7e5456146936284fcf2 |
| DINOv2-g | 50.6 | Not recorded | 6940e7e5456146936284fcf2 |

### 4DS-H

mIoU: 76.1. Result ID: 699ab2125698665ec43fa2a3.

[Reporting paper](<https://www.sota2.com/research/paper/6940e7e5456146936284fcf2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79f41e209131cea803fa.md>)

Recorded evaluation configuration: {"Size(M)":"639"}. This record does not assert independent reproduction.

### 4DS-L

mIoU: 75.9. Result ID: 699ab2125698665ec43fa29f.

[Reporting paper](<https://www.sota2.com/research/paper/6940e7e5456146936284fcf2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79f41e209131cea803fa.md>)

Recorded evaluation configuration: {"Size(M)":"310"}. This record does not assert independent reproduction.

### VideoMAE-L

mIoU: 74.9. Result ID: 699ab2125698665ec43fa29d.

[Reporting paper](<https://www.sota2.com/research/paper/6940e7e5456146936284fcf2.md>)

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

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

Recorded evaluation configuration: {"Size(M)":"305"}. This record does not assert independent reproduction.

### V-JEPA-H

mIoU: 74.9. Result ID: 699ab2125698665ec43fa2a2.

[Reporting paper](<https://www.sota2.com/research/paper/6940e7e5456146936284fcf2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72e11e209131cea5926c.md>)

Recorded evaluation configuration: {"Size(M)":"635"}. This record does not assert independent reproduction.

### VideoMAE-H

mIoU: 74.6. Result ID: 699ab2125698665ec43fa2a1.

[Reporting paper](<https://www.sota2.com/research/paper/6940e7e5456146936284fcf2.md>)

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

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

Recorded evaluation configuration: {"Size(M)":"633"}. This record does not assert independent reproduction.

### RVM-H

mIoU: 74.2. Result ID: 699ab2125698665ec43fa2a4.

[Reporting paper](<https://www.sota2.com/research/paper/6940e7e5456146936284fcf2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6940e7e5456146936284fcf2.md>)

Recorded evaluation configuration: {"Size(M)":"743"}. This record does not assert independent reproduction.

### V-JEPA-L

mIoU: 73.3. Result ID: 699ab2125698665ec43fa29e.

[Reporting paper](<https://www.sota2.com/research/paper/6940e7e5456146936284fcf2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72e11e209131cea5926c.md>)

Recorded evaluation configuration: {"Size(M)":"307"}. This record does not assert independent reproduction.

### RVM-L

mIoU: 73.2. Result ID: 699ab2125698665ec43fa2a0.

[Reporting paper](<https://www.sota2.com/research/paper/6940e7e5456146936284fcf2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6940e7e5456146936284fcf2.md>)

Recorded evaluation configuration: {"Size(M)":"375"}. This record does not assert independent reproduction.

### VideoMAEv2-g

mIoU: 72.6. Result ID: 699ab2125698665ec43fa2a6.

[Reporting paper](<https://www.sota2.com/research/paper/6940e7e5456146936284fcf2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f171e209131cea43db1.md>)

Recorded evaluation configuration: {"Size(M)":"1013"}. This record does not assert independent reproduction.

### DINOv2-L (distilled)

mIoU: 51.7. Result ID: 699ab2125698665ec43fa29c.

[Reporting paper](<https://www.sota2.com/research/paper/6940e7e5456146936284fcf2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72181e209131cea546c3.md>)

[Implementation](<https://github.com/facebookresearch/dinov2>)

Recorded evaluation configuration: {"Size(M)":"303"}. This record does not assert independent reproduction.

### DINOv2-g

mIoU: 50.6. Result ID: 699ab2125698665ec43fa2a5.

[Reporting paper](<https://www.sota2.com/research/paper/6940e7e5456146936284fcf2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72181e209131cea546c3.md>)

[Implementation](<https://github.com/facebookresearch/dinov2>)

Recorded evaluation configuration: {"Size(M)":"1135"}. This record does not assert independent reproduction.

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