Motion Captioning On Humanml3D
Metrics
BERTScore
BLEU-4
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | BERTScore | BLEU-4 |
|---|---|---|
| motiongpt-human-motion-as-a-foreign-language | 32.4 | 12.47 |
| guided-attention-for-interpretable-motion | 40.3 | 25.0 |
| tm2t-stochastic-and-tokenized-modeling-for | 37.8 | 22.3 |
| motion2language-unsupervised-learning-of | 37.2 | 23.4 |