Motion Prediction on Motion-X
0.009FIDReal
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Real2024.05 | 0.009 | 2.316 | — | — | |
| Ground Truth2024.05 | 0.009 | 2.316 | — | — | |
| M³GPTStrategy=Instruction-tuned2024.05 | 0.682 | 1.838 | — | — | |
| M3GPTstage=finetune2024.05 | 0.682 | 1.838 | 6.898 | 8.091 | |
| M³GPT (Instruction-tuned)Training Strategy=Instruction-tuned, Hardware Platform=Ascend 910B NPU2024.05 | 0.684 | 1.841 | — | — | |
| MotionGPT2024.05 | 0.701 | 1.818 | — | — | |
| M³GPTStrategy=Pre-trained2024.05 | 0.707 | 1.874 | — | — | |
| M3GPTstage=pretrain2024.05 | 0.707 | 1.874 | 6.954 | 8.684 | |
| M³GPT (Pre-trained)Training Strategy=Pre-trained, Hardware Platform=Ascend 910B NPU2024.05 | 0.71 | 1.882 | — | — | |
| Trained single taskStrategy=Single Task Training2024.05 | 0.774 | 1.778 | — | — | |
| Trained single task2024.05 | 0.774 | 1.778 | 7.84 | 9.575 | |
| Trained single taskTraining Strategy=single task training, Hardware Platform=Ascend 910B NPU2024.05 | 0.776 | 1.818 | — | — | |
| T2M-GPT2024.05 | 0.814 | 1.755 | — | — | |
| MDM2024.05 | 1.028 | 1.746 | — | — | |
| MDM2024.05 | 1.028 | 1.746 | 8.057 | 11.266 |