# Motion Transition Generation (70 frames) on BABEL 2021 (test)

Source: [Motion Transition Generation (70 frames) on BABEL 2021 (test)](<https://www.sota2.com/research/sota/motion-transition-generation-70-frames-on-babel-2021-test>)

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

Data updated: 2026-02-26T05:44:23.612Z

Evaluation of models generating motion transitions over 70 frames using the test split of the BABEL 2021 dataset, assessed using metrics like FID and Diversity.

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 | Motion Transition Generation (70 frames) |
| Dataset (including any stated split) | BABEL 2021 (test) |
| Metric | FID |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 5 of 5 |
| 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

- [FID](<https://www.sota2.com/research/sota/motion-transition-generation-70-frames-on-babel-2021-test.md?metric=FID>): Lower is better; unit: SCALAR.

- [Diversity](<https://www.sota2.com/research/sota/motion-transition-generation-70-frames-on-babel-2021-test.md?metric=Diversity>): Higher is better; unit: SCALAR.

## Recorded results

| Method | FID | Result date | Report paper |
| --- | --- | --- | --- |
| Ground Truth | 0.0008 | Not recorded | 68fa706f1e209131cea4af49 |
| Double Take | 1.88 | Not recorded | 68fa706f1e209131cea4af49 |
| Double Take | 2.39 | Not recorded | 68fa706f1e209131cea4af49 |
| Double Take | 3.43 | Not recorded | 68fa706f1e209131cea4af49 |
| TEACH | 3.86 | Not recorded | 68fa706f1e209131cea4af49 |

### Ground Truth

FID: 0.0008. Result ID: 69912f533a6c314849064dc5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa706f1e209131cea4af49.md>)

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

### Double Take

FID: 1.88. Result ID: 69912f533a6c314849064dc7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa706f1e209131cea4af49.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa706f1e209131cea4af49.md>)

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

Recorded evaluation configuration: {"Transition Embedding":false,"Geometric Losses":false}. This record does not assert independent reproduction.

### Double Take

FID: 2.39. Result ID: 69912f533a6c314849064dc9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa706f1e209131cea4af49.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa706f1e209131cea4af49.md>)

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

Recorded evaluation configuration: {"Transition Embedding":true,"Geometric Losses":true}. This record does not assert independent reproduction.

### Double Take

FID: 3.43. Result ID: 69912f533a6c314849064dc8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa706f1e209131cea4af49.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa706f1e209131cea4af49.md>)

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

Recorded evaluation configuration: {"Transition Embedding":true,"Geometric Losses":false}. This record does not assert independent reproduction.

### TEACH

FID: 3.86. Result ID: 69912f533a6c314849064dc6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa706f1e209131cea4af49.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d6d1e209131cea39c6f.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.
