# Motion Generation on BABEL 2021 (test)

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

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

Data updated: 2026-02-26T05:44:23.599Z

Evaluation of models generating human motion sequences conditioned on inputs (implied by the task context, though not explicitly stated in the input task name) using the test split of the BABEL 2021 dataset. Metrics include R-precision, FID, Diversity, and MultiModal Distance.

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 Generation |
| Dataset (including any stated split) | BABEL 2021 (test) |
| Metric | FID |
| 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

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

- [R-precision (top-3)](<https://www.sota2.com/research/sota/motion-generation-on-babel-2021-test.md?metric=R-precision%20(top-3)>): Higher is better; unit: SCALAR.

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

- [MultiModal Distance](<https://www.sota2.com/research/sota/motion-generation-on-babel-2021-test.md?metric=MultiModal%20Distance>): Lower is better; unit: SCALAR.

## Recorded results

| Method | FID | Result date | Report paper |
| --- | --- | --- | --- |
| Ground Truth | 0.0004 | Not recorded | 68fa706f1e209131cea4af49 |
| Ground Truth | 0.0009 | Not recorded | 68fa706f1e209131cea4af49 |
| Double Take | 0.79 | Not recorded | 68fa706f1e209131cea4af49 |
| Double Take | 0.91 | Not recorded | 68fa706f1e209131cea4af49 |
| Double Take | 1.04 | Not recorded | 68fa706f1e209131cea4af49 |
| TEACH | 1.12 | Not recorded | 68fa706f1e209131cea4af49 |
| Double Take | 3.45 | Not recorded | 68fa706f1e209131cea4af49 |
| Double Take | 6.05 | Not recorded | 68fa706f1e209131cea4af49 |
| Double Take | 7.23 | Not recorded | 68fa706f1e209131cea4af49 |
| TEACH | 7.93 | Not recorded | 68fa706f1e209131cea4af49 |

### Ground Truth

FID: 0.0004. Result ID: 69912f533a6c314849064dc0.

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

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

### Ground Truth

FID: 0.0009. Result ID: 69912f533a6c314849064dca.

[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: 0.79. Result ID: 69912f533a6c314849064dc3.

[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.

### Double Take

FID: 0.91. Result ID: 69912f533a6c314849064dc4.

[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: 1.04. Result ID: 69912f533a6c314849064dc2.

[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.

### TEACH

FID: 1.12. Result ID: 69912f533a6c314849064dc1.

[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.

### Double Take

FID: 3.45. Result ID: 69912f533a6c314849064dcc.

[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: 6.05. Result ID: 69912f533a6c314849064dce.

[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: 7.23. Result ID: 69912f533a6c314849064dcd.

[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: 7.93. Result ID: 69912f533a6c314849064dcb.

[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.
