search

layumi / Person_reID_baseline_pytorch

:bouncing_ball_person: Pytorch ReID: A tiny, friendly, strong pytorch implement of person re-id / vehicle re-id baseline. Tutorial 👉https://github.com/layumi/Person_reID_baseline_pytorch/tree/master/tutorial
https://www.zdzheng.xyz
MIT License
4.13k stars 1.01k forks source link

关于引用的问题 #216

Closed finger-monkey closed 4 years ago

finger-monkey commented 4 years ago

您好，我在您提供的基准代码上（不加任何训练技巧）做了实验，想在自己的论文里引用您的这个代码，不知道要如何引用？您的下面代码不知是在哪一片论文里提出来的？ [ResNet-50] | 88.84% | 71.59% | python train.py --train_all

layumi commented 4 years ago

感谢。可以引用我这一篇， The following paper uses and reports the result of the baseline model. You may cite it in your paper.

@article{zheng2019joint,
  title={Joint discriminative and generative learning for person re-identification},
  author={Zheng, Zhedong and Yang, Xiaodong and Yu, Zhiding and Zheng, Liang and Yang, Yi and Kautz, Jan},
  journal={IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2019}
}
finger-monkey commented 4 years ago

抱歉刚才没有说清楚，我指的是下面的这一个： [ResNet-50] | 88.84% | 71.59% | python train.py --train_all 我们提出了一个新技巧，只在这个上面做了对比实验

layumi commented 4 years ago

image 接近我paper里面table 3 这个？

finger-monkey commented 4 years ago

和这个接近，不过精度会再低一点。就是您开源代码里面列表上的 https://github.com/layumi/Person_reID_baseline_pytorch Trained Model模块下的第一个。

layumi commented 4 years ago

我没有report过完全一样的，，或者你可以引用一个我早期的结果

@article{zheng2018discriminatively,
  title={A discriminatively learned CNN embedding for person reidentification},
  author={Zheng, Zhedong and Zheng, Liang and Yang, Yi},
  journal={ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)},
  volume={14},
  number={1},
  pages={13},
  year={2018},
  publisher={ACM}
}
finger-monkey commented 4 years ago

好的，十分感谢