Social Motion Prediction with Cognitive Hierarchies (NeurIPS 2023)

This is the official PyTorch implementation of the paper "Social Motion Prediction with Cognitive Hierarchies" (NeurIPS 2023).

Dependencies

• python 3.9
• pytorch 1.13.1
• torch_dct

Dataset

Please refer to Wusi Basketball Training Dataset.

Train

python train.py \
--config configs/wusi_ch.yaml \
--train

Test

python train.py \
--config configs/wusi_ch.yaml \
--eval --ckpt checkpoint/wusi_ch/best.pth

You can download the pretrained model weight from here.

Citation

If you find our work useful for your project, please cite the paper:

@inproceedings{zhu2023social,
    title={Social Motion Prediction with Cognitive Hierarchies},
    author={Zhu, Wentao and Qin, Jason and Lou, Yuke and Ye, Hang and Ma, Xiaoxuan and Ci, Hai and Wang, Yizhou},
    booktitle={Thirty-seventh Conference on Neural Information Processing Systems},
    year={2023}
}

Acknowledgement

This repo is built on MRT. The motion capture algorithm is based on Faster-VoxelPose. Thank the authors for releasing their codes.