无人机蜂群>> awesome_video_person_reid>> 返回
项目作者： AsuradaYuci

项目描述 ：
papers collection and understanding for video person re-identification
高级语言：
项目地址: git://github.com/AsuradaYuci/awesome_video_person_reid.git
创建时间： 2019-03-05T09:51:21Z
项目社区：https://github.com/AsuradaYuci/awesome_video_person_reid
开源协议：
下载


awesome_video_person_reid

only focus on video person re-identification.

TODO

This repository is a bit outdated. I will update this repository in May.

SOTA:

No. Dataset Rank1 mAP Link
1 PRID 97.4% Null paper
2 iLIDS-VID 92.0% Null paper[ICCV2021]
3 Mars 91.4% 86.7% paper[CVPR2021]
4 DukeMTMC 98.3% 97.4% paper[ICCV2021]
5 LS-VID 84.6% 75.1% paper[CVPR2021]

Leaderboard for 4 benchmarks

please refer to LEADERBOARD.md for the leaderboard on public benchmarks.

Citation

If you find this repo useful, please kindly cite the following paper:

  1. @inproceedings{yu2024tf,
  2.   title={TF-CLIP: Learning Text-Free CLIP for Video-Based Person Re-identification},
  3.   author={Yu, Chenyang and Liu, Xuehu and Wang, Yingquan and Zhang, Pingping and Lu, Huchuan},
  4.   booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
  5.   volume={38},
  6.   number={7},
  7.   pages={6764--6772},
  8.   year={2024}
  9. }
  10. @inproceedings{liu2021watching, 
  11.   title={Watching You: Global-guided Reciprocal Learning for Video-based Person Re-identification}, 
  12.   author={Liu, Xuehu and Zhang, Pingping and Yu, Chenyang and Lu, Huchuan and Yang, Xiaoyun}, 
  13.   booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, 
  14.   pages={13334--13343}, 
  15.   year={2021} 
  16. } 
  17. @article{liu2023deeply,
  18.   title={Deeply coupled convolution--transformer with spatial--temporal complementary learning for video-based person re-identification},
  19.   author={Liu, Xuehu and Yu, Chenyang and Zhang, Pingping and Lu, Huchuan},
  20.   journal={IEEE Transactions on Neural Networks and Learning Systems},
  21.   year={2023},
  22.   publisher={IEEE}
  23. }
  24. @article{liu2021video,
  25.   title={A Video Is Worth Three Views: Trigeminal Transformers for Video-based Person Re-identification},
  26.   author={Liu, Xuehu and Zhang, Pingping and Yu, Chenyang and Lu, Huchuan and Qian, Xuesheng and Yang, Xiaoyun},
  27.   journal={arXiv preprint arXiv:2104.01745},
  28.   year={2021}
  29. }
  30. @inproceedings{gao2024part,
  31.   title={Part Representation Learning with Teacher-Student Decoder for Occluded Person Re-Identification},
  32.   author={Gao, Shang and Yu, Chenyang and Zhang, Pingping and Lu, Huchuan},
  33.   booktitle={ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  34.   pages={2660--2664},
  35.   year={2024},
  36.   organization={IEEE}
  37. }
  38. @inproceedings{gao2023ped,
  39.   title={Ped-Mix: Mix Pedestrians for Occluded Person Re-identification},
  40.   author={Gao, Shang and Yu, Chenyang and Zhang, Pingping and Lu, Huchuan},
  41.   booktitle={Chinese Conference on Pattern Recognition and Computer Vision (PRCV)},
  42.   pages={265--277},
  43.   year={2023},
  44.   organization={Springer}
  45. }