ljn114514/m3d

Multi-scale 3d convolution network for video based person re-identification

M3D-AAAI2019

This is the code of AAAI2019 paper, "Multi-scale 3D Convolution Network for Video Based Person Re-Identification" If you are using the code/model provided here in a publication, please consider citing our paper:

Citations

@inproceedings{li2019multi,
  title={Multi-scale 3d convolution network for video based person re-identification},
  author={Li, Jianing and Zhang, Shiliang and Huang, Tiejun},
  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
  volume={33},
  pages={8618--8625},
  year={2019}
}

Prerequisites

• Python 2.7
• GPU
• Numpy
• Pytorch 0.3
• Torchvision

Some extracted feature and model for MARS dataset: Link：https://pan.baidu.com/s/1hWkNcxwtZDuD7uk-_LkROg Password：9lra

m3d's Issues

How to evaluate？

thanks for your excellent work, could you please upload evaluate code？