• Stars
    star
    140
  • Rank 261,473 (Top 6 %)
  • Language
    Jupyter Notebook
  • Created over 6 years ago
  • Updated about 5 years ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Code for ECCV2018 paper: Part-Aligned Bilinear Representations for Person Re-Identification

Part-Aligned Bilinear Representations for Person Re-identification

Yumin Suh, Jingdong Wang, Siyu Tang, Tao Mei, and Kyoung Mu Lee. “Part-Aligned Bilinear Representations for Person Re-Identification”, Proceedings of the European Conference on Computer Vision (ECCV), 2018. (paper)

@InProceedings{suh_eccv18,
author = {Yumin Suh and Jingdong Wang and Siyu Tang and Tao Mei and Kyoung Mu Lee},
title = {Part-Aligned Bilinear Representations for Person Re-Identification},
booktitle = {European Conference on Computer Vision (ECCV)},
year = {2018}
}

Our paper is firstly implemented in caffe and reimplemented in pytorch. Minor details have been changed

Contact: Yumin Suh ([email protected])

Prerequisite

  • Pytorch 0.4

Acknowledgement

Usage

  • Run train_market1501.sh to train a model on the Market-1501 dataset

  • Run eval_market1501.sh to evaluate

  • Run train_dukemtmc.sh to train a model on the DukeMTMC dataset

  • Run eval_dukemtmc.sh to evaluate

More Repositories