# Video Prediction on V-MNIST

Source: [Video Prediction on V-MNIST](<https://www.sota2.com/research/sota/video-prediction-on-v-mnist>)

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

Data updated: 2026-02-26T05:50:37.849Z

Evaluation of video prediction performance using the V-MNIST dataset, measured by metrics including MSE, SSIM, PSNR, and GDL.

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 Prediction |
| Dataset (including any stated split) | V-MNIST |
| Metric | MSE |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 10 of 10 |
| 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

- [MSE](<https://www.sota2.com/research/sota/video-prediction-on-v-mnist.md?metric=MSE>): Lower is better; unit: SCALAR.

- [SSIM](<https://www.sota2.com/research/sota/video-prediction-on-v-mnist.md?metric=SSIM>): Higher is better; unit: PERCENT.

- [PSNR](<https://www.sota2.com/research/sota/video-prediction-on-v-mnist.md?metric=PSNR>): Higher is better; unit: SCALAR.

- [GDL](<https://www.sota2.com/research/sota/video-prediction-on-v-mnist.md?metric=GDL>): Lower is better; unit: SCALAR.

## Recorded results

| Method | MSE | Result date | Report paper |
| --- | --- | --- | --- |
| PredRNN + MotionRNN | 25.1 | Not recorded | 68fa6a5a1e209131cea27a59 |
| MIM + MotionRNN | 28.9 | Not recorded | 68fa6a5a1e209131cea27a59 |
| MIM | 34.6 | Not recorded | 68fa6a5a1e209131cea27a59 |
| PredRNN | 35.6 | Not recorded | 68fa6a5a1e209131cea27a59 |
| ConvLSTM + MotionRNN | 44.4 | Not recorded | 68fa6a5a1e209131cea27a59 |
| ConvLSTM | 47 | Not recorded | 68fa6a5a1e209131cea27a59 |
| E3D-LSTM + MotionRNN | 52.8 | Not recorded | 68fa6a5a1e209131cea27a59 |
| E3D-LSTM | 57.6 | Not recorded | 68fa6a5a1e209131cea27a59 |
| Conv-TT-LSTM | 71.1 | Not recorded | 68fa6a5a1e209131cea27a59 |
| TrajGRU | 109 | Not recorded | 68fa6a5a1e209131cea27a59 |

### PredRNN + MotionRNN

MSE: 25.1. Result ID: 698e2dfeffc3901de09b7273.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a5a1e209131cea27a59.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a5a1e209131cea27a59.md>)

Recorded evaluation configuration: {"backbone":"PredRNN","framework":"MotionRNN"}. This record does not assert independent reproduction.

### MIM + MotionRNN

MSE: 28.9. Result ID: 698e2dfeffc3901de09b7271.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a5a1e209131cea27a59.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a5a1e209131cea27a59.md>)

Recorded evaluation configuration: {"backbone":"MIM","framework":"MotionRNN"}. This record does not assert independent reproduction.

### MIM

MSE: 34.6. Result ID: 698e2dfeffc3901de09b7270.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a5a1e209131cea27a59.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65ab1e209131cea0bd12.md>)

[Implementation](<https://github.com/Yunbo426/MIM>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### PredRNN

MSE: 35.6. Result ID: 698e2dfeffc3901de09b7272.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a5a1e209131cea27a59.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### ConvLSTM + MotionRNN

MSE: 44.4. Result ID: 698e2dfeffc3901de09b726f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a5a1e209131cea27a59.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a5a1e209131cea27a59.md>)

Recorded evaluation configuration: {"backbone":"ConvLSTM","framework":"MotionRNN"}. This record does not assert independent reproduction.

### ConvLSTM

MSE: 47. Result ID: 698e2dfeffc3901de09b726e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a5a1e209131cea27a59.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62181e209131ce9f78df.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### E3D-LSTM + MotionRNN

MSE: 52.8. Result ID: 698e2dfeffc3901de09b726d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a5a1e209131cea27a59.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a5a1e209131cea27a59.md>)

Recorded evaluation configuration: {"backbone":"E3D-LSTM","framework":"MotionRNN"}. This record does not assert independent reproduction.

### E3D-LSTM

MSE: 57.6. Result ID: 698e2dfeffc3901de09b726c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a5a1e209131cea27a59.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Conv-TT-LSTM

MSE: 71.1. Result ID: 698e2dfeffc3901de09b726b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a5a1e209131cea27a59.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa686f1e209131cea1c322.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### TrajGRU

MSE: 109. Result ID: 698e2dfeffc3901de09b726a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a5a1e209131cea27a59.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63ba1e209131cea006df.md>)

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.