【专知荟萃26】行人重识别 Person Re-identification知识资料全集（入门/进阶/论文/综述/代码，附查看）

行人重识别 Person Re-identification / Person Retrieval 专知荟萃

• 行人重识别 Person Re-identification / Person Retrieval 专知荟萃
• 入门学习
• 进阶论文及代码
  • Person Re-identification / Person Retrieval
  • Person Search
  • Re-ID with GAN
  • Vehicle Re-ID
  • Deep Metric Learning
  • Re-ID with Attributes Prediction
  • Video-based Person Re-Identification
  • Re-ranking
• 实战项目
• 教程
• 综述
• 数据集
  • 图像数据集
  • Attribute相关数据集
  • 视频相关数据集
  • NLP相关数据集
• 领域专家

入门学习

1. 行人重识别综述
   • [http://www.jianshu.com/p/98cc04cca0ae?utm_campaign=maleskine&utm_content=note&utm_medium=seo_notes&utm_source=recommendation\]
2. 基于深度学习的Person Re-ID（综述）
   • [http://blog.csdn.net/linolzhang/article/details/71075756]
3. 郑哲东 -Deep-ReID：行人重识别的深度学习方法
   • PPT：[https://www.slideshare.net/ZhedongZheng1/deep-reid]
   • 视频：[http://www.bilibili.com/video/av13796843/]
4. 【行人识别】Deep Transfer Learning for Person Re-identification
   • [http://blog.csdn.net/shenxiaolu1984/article/details/53607268]
5. 知乎专栏：行人重识别 [https://zhuanlan.zhihu.com/personReid]
   • 行人重识别综述：从哈利波特地图说起
   • 行人再识别中的迁移学习：图像风格转换（Learning via Translation）
   • 行人对齐+重识别网络
   • SVDNet for Pedestrian Retrieval：CNN到底认为哪个投影方向是重要的？
   • 用GAN生成的图像做训练？Yes！
   • 2017 ICCV 行人检索／重识别 接受论文汇总
   • 从人脸识别 到 行人重识别，下一个风口
6. GAN（生成式对抗网络）的研究现状，以及在行人重识别领域的应用前景？
   • [https://www.zhihu.com/question/53001881/answer/170077548]
7. Re-id Resources
   • [https://wangzwhu.github.io/home/re_id_resources.html\]
8. 行人再识别（行人重识别）【包含与行人检测的对比】
   • [http://blog.csdn.net/liuqinglong110/article/details/41699861]
9. 行人重识别综述（Person Re-identification: Past, Present and Future）
   • [http://blog.csdn.net/auto1993/article/details/74091803]

进阶论文及代码

Person Re-identification / Person Retrieval

1. DeepReID: Deep Filter Pairing Neural Network for Person Re-Identification
   • intro: CVPR 2014
   • paper: [http://www.cv-foundation.org/openaccess/content_cvpr_2014/papers/Li_DeepReID_Deep_Filter_2014_CVPR_paper.pdf]
2. An Improved Deep Learning Architecture for Person Re-Identification
   • intro: CVPR 2015
   • paper: [http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Ahmed_An_Improved_Deep_2015_CVPR_paper.pdf]
   • github: [https://github.com/Ning-Ding/Implementation-CVPR2015-CNN-for-ReID]
3. Deep Ranking for Person Re-identification via Joint Representation Learning
   • intro: IEEE Transactions on Image Processing [TIP], 2016
   • arxiv: [https://arxiv.org/abs/1505.06821]
4. PersonNet: Person Re-identification with Deep Convolutional Neural Networks
   • arxiv: [http://arxiv.org/abs/1601.07255]
5. Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identification
   • intro: CVPR 2016
   • arxiv: [https://arxiv.org/abs/1604.07528]
   • github: [https://github.com/Cysu/dgd_person_reid]
6. Person Re-Identification by Multi-Channel Parts-Based CNN with Improved Triplet Loss Function
   • intro: CVPR 2016
   • paper: [http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Cheng_Person_Re-Identification_by_CVPR_2016_paper.pdf]
7. End-to-End Comparative Attention Networks for Person Re-identification
   • [https://arxiv.org/abs/1606.04404]
8. A Multi-task Deep Network for Person Re-identification
   • arxiv: [http://arxiv.org/abs/1607.05369]
9. Gated Siamese Convolutional Neural Network Architecture for Human Re-Identification
   • arxiv: [http://arxiv.org/abs/1607.08378]
10. A Siamese Long Short-Term Memory Architecture for Human Re-Identification
    • arxiv: [http://arxiv.org/abs/1607.08381]
11. Gated Siamese Convolutional Neural Network Architecture for Human Re-Identification
    • arxiv: [https://arxiv.org/abs/1607.08378]
12. Person Re-identification: Past, Present and Future
    • [https://arxiv.org/abs/1610.02984]
13. Deep Learning Prototype Domains for Person Re-Identification
    • arxiv: [https://arxiv.org/abs/1610.05047]
14. Deep Transfer Learning for Person Re-identification
    • arxiv: [https://arxiv.org/abs/1611.05244]
15. A Discriminatively Learned CNN Embedding for Person Re-identification
    • arxiv: [https://arxiv.org/abs/1611.05666]
    • github[MatConvnet]: [https://github.com/layumi/2016_person_re-ID]
16. Structured Deep Hashing with Convolutional Neural Networks for Fast Person Re-identification
    • arxiv: [https://arxiv.org/abs/1702.04179]
17. In Defense of the Triplet Loss for Person Re-Identification
    • arxiv: [https://arxiv.org/abs/1703.07737]
    • github[Theano]: [https://github.com/VisualComputingInstitute/triplet-reid]
18. Beyond triplet loss: a deep quadruplet network for person re-identification
    • intro: CVPR 2017
    • arxiv: [https://arxiv.org/abs/1704.01719]
19. Part-based Deep Hashing for Large-scale Person Re-identification
    • intro: IEEE Transactions on Image Processing, 2017
    • arxiv: [https://arxiv.org/abs/1705.02145]
20. Deep Person Re-Identification with Improved Embedding
    • [https://arxiv.org/abs/1705.03332]
21. Towards a Principled Integration of Multi-Camera Re-Identification and Tracking through Optimal Bayes Filters
    • arxiv: [https://arxiv.org/abs/1705.04608]
    • github: [https://github.com/VisualComputingInstitute/towards-reid-tracking]
22. Person Re-Identification by Deep Joint Learning of Multi-Loss Classification
    • intro: IJCAI 2017
    • arxiv: [https://arxiv.org/abs/1705.04724]
23. Attention-based Natural Language Person Retrieval
    • intro: CVPR 2017 Workshop [vision meets cognition]
    • keywords: Bidirectional Long Short- Term Memory [BLSTM]
    • arxiv: [https://arxiv.org/abs/1705.08923]
24. Unsupervised Person Re-identification: Clustering and Fine-tuning
    • arxiv: [https://arxiv.org/abs/1705.10444]
    • github: [https://github.com/hehefan/Unsupervised-Person-Re-identification-Clustering-and-Fine-tuning]
25. Deep Representation Learning with Part Loss for Person Re-Identification
    • [https://arxiv.org/abs/1707.00798]
26. Pedestrian Alignment Network for Large-scale Person Re-identification
    • [https://raw.githubusercontent.com/layumi/Pedestrian_Alignment/master/fig2.jpg]
    • arxiv: [https://arxiv.org/abs/1707.00408]
    • github: [https://github.com/layumi/Pedestrian_Alignment]
27. Deep Reinforcement Learning Attention Selection for Person Re-Identification
    • [https://arxiv.org/abs/1707.02785]
28. Learning Efficient Image Representation for Person Re-Identification
    • [https://arxiv.org/abs/1707.02319]
29. Person Re-identification Using Visual Attention
    • intro: ICIP 2017
    • arxiv: [https://arxiv.org/abs/1707.07336]
30. Deeply-Learned Part-Aligned Representations for Person Re-Identification
    • intro: ICCV 2017
    • arxiv: [https://arxiv.org/abs/1707.07256]
31. What-and-Where to Match: Deep Spatially Multiplicative Integration Networks for Person Re-identification
    • [https://arxiv.org/abs/1707.07074]
32. Deep Feature Learning via Structured Graph Laplacian Embedding for Person Re-Identification
    • [https://arxiv.org/abs/1707.07791]
33. Divide and Fuse: A Re-ranking Approach for Person Re-identification
    • intro: BMVC 2017
    • arxiv: [https://arxiv.org/abs/1708.04169]
34. Large Margin Learning in Set to Set Similarity Comparison for Person Re-identification
    • intro: IEEE Transactions on Multimedia
    • arxiv: [https://arxiv.org/abs/1708.05512]
35. Multi-scale Deep Learning Architectures for Person Re-identification
    • intro: ICCV 2017
    • arxiv: [https://arxiv.org/abs/1709.05165]
36. Pose-driven Deep Convolutional Model for Person Re-identification
    • [https://arxiv.org/abs/1709.08325]
37. HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis
    • intro: ICCV 2017. CUHK & SenseTime,
    • arxiv: [https://arxiv.org/abs/1709.09930]
    • github: [https://github.com/xh-liu/HydraPlus-Net]
38. Person Re-Identification with Vision and Language
    • [https://arxiv.org/abs/1710.01202]
39. Margin Sample Mining Loss: A Deep Learning Based Method for Person Re-identification
    • [https://arxiv.org/abs/1710.00478]
40. Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification
    • intro: CVPR 2017. CASIA
    • keywords: Multi-Scale Context-Aware Network [MSCAN]
    • arxiv: [https://arxiv.org/abs/1710.06555]
41. Pseudo-positive regularization for deep person re-identification
    • [https://arxiv.org/abs/1711.06500]
42. Let Features Decide for Themselves: Feature Mask Network for Person Re-identification
    • keywords: Feature Mask Network [FMN]
    • arxiv: [https://arxiv.org/abs/1711.07155]
43. Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification
    • [https://arxiv.org/abs/1711.07027]
44. AlignedReID: Surpassing Human-Level Performance in Person Re-Identification
    • intro: Megvii, Inc & Zhejiang University
    • arxiv: [https://arxiv.org/abs/1711.08184]
    • evaluation website: [Market1501]: [http://reid-challenge.megvii.com/]
    • evaluation website: [CUHK03]: [http://reid-challenge.megvii.com/cuhk03]
45. Region-based Quality Estimation Network for Large-scale Person Re-identification
    • intro: AAAI 2018
    • arxiv: [https://arxiv.org/abs/1711.08766]
46. Deep-Person: Learning Discriminative Deep Features for Person Re-Identification
    • [https://arxiv.org/abs/1711.10658]
47. A Pose-Sensitive Embedding for Person Re-Identification with Expanded Cross Neighborhood Re-Ranking
    • arxiv: [https://arxiv.org/abs/1711.10378]
    • github: [https://github.com/pse-ecn/pose-sensitive-embedding]

Person Search

1. Joint Detection and Identification Feature Learning for Person Search
   • intro: CVPR 2017
   • keywords: Online Instance Matching OIM loss function
   • homepage[dataset+code]:[http://www.ee.cuhk.edu.hk/~xgwang/PS/dataset.html]
   • arxiv: [https://arxiv.org/abs/1604.01850]
   • paper: [http://www.ee.cuhk.edu.hk/~xgwang/PS/paper.pdf]
   • github[official. Caffe]: [https://github.com/ShuangLI59/person_search]
2. Person Re-identification in the Wild
   • intro: CVPR 2017 spotlight
   • keywords: PRW dataset
   • project page: [http://www.liangzheng.com.cn/Project/project_prw.html]
   • arxiv: [https://arxiv.org/abs/1604.02531]
   • github: [https://github.com/liangzheng06/PRW-baseline]
3. IAN: The Individual Aggregation Network for Person Search
   • [https://arxiv.org/abs/1705.05552]
4. Neural Person Search Machines
   • intro: ICCV 2017
   • arxiv: [https://arxiv.org/abs/1707.06777]

Re-ID with GAN

1. Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro
   • intro: ICCV 2017
   • arxiv: [https://arxiv.org/abs/1701.07717]
   • github: [https://github.com/layumi/Person-reID_GAN]
2. Person Transfer GAN to Bridge Domain Gap for Person Re-Identification
   • [https://arxiv.org/abs/1711.08565]

Vehicle Re-ID

1. Learning Deep Neural Networks for Vehicle Re-ID with Visual-spatio-temporal Path Proposals
   • intro: ICCV 2017
   • arxiv: [https://arxiv.org/abs/1708.03918]

Deep Metric Learning

1. Deep Metric Learning for Person Re-Identification
   • intro: ICPR 2014
   • paper: [http://www.cbsr.ia.ac.cn/users/zlei/papers/ICPR2014/Yi-ICPR-14.pdf]
2. Deep Metric Learning for Practical Person Re-Identification
   • [https://arxiv.org/abs/1407.4979]
3. Constrained Deep Metric Learning for Person Re-identification
   • [https://arxiv.org/abs/1511.07545]
4. DarkRank: Accelerating Deep Metric Learning via Cross Sample Similarities Transfer
   • intro: TuSimple
   • keywords: pedestrian re-identification
   • arxiv: [https://arxiv.org/abs/1707.01220]

Re-ID with Attributes Prediction

1. Deep Attributes Driven Multi-Camera Person Re-identification
   • intro: ECCV 2016
   • arxiv: [https://arxiv.org/abs/1605.03259]
2. Improving Person Re-identification by Attribute and Identity Learning
   • [https://arxiv.org/abs/1703.07220]

Video-based Person Re-Identification

1. Recurrent Convolutional Network for Video-based Person Re-Identification
   • intro: CVPR 2016
   • paper: [http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/McLaughlin_Recurrent_Convolutional_Network_CVPR_2016_paper.pdf]
   • github: [https://github.com/niallmcl/Recurrent-Convolutional-Video-ReID]
2. Deep Recurrent Convolutional Networks for Video-based Person Re-identification: An End-to-End Approach
   • [https://arxiv.org/abs/1606.01609]
3. Jointly Attentive Spatial-Temporal Pooling Networks for Video-based Person Re-Identification
   • intro: ICCV 2017
   • arxiv: [https://arxiv.org/abs/1708.02286]
4. Three-Stream Convolutional Networks for Video-based Person Re-Identification
   • [https://arxiv.org/abs/1712.01652]

Re-ranking

1. Re-ranking Person Re-identification with k-reciprocal Encoding
   • intro: CVPR 2017
   • arxiv: [https://arxiv.org/abs/1701.08398]
   • github: [https://github.com/zhunzhong07/person-re-ranking]

实战项目

1. Open-ReID: Open source person re-identification library in python
   • intro: Open-ReID is a lightweight library of person re-identification for research purpose. It aims to provide a uniform interface for different datasets, a full set of models and evaluation metrics, as well as examples to reproduce [near] state-of-the-art results.
   • project page: [https://cysu.github.io/open-reid/]
   • github[PyTorch]: [https://github.com/Cysu/open-reid]
   • examples: [https://cysu.github.io/open-reid/examples/training_id.html]
   • benchmarks: [https://cysu.github.io/open-reid/examples/benchmarks.html]
2. caffe-PersonReID
   • intro: Person Re-Identification: Multi-Task Deep CNN with Triplet Loss
   • gtihub: [https://github.com/agjayant/caffe-Person-ReID]
3. DukeMTMC-reID_baseline Matlab
   • [https://github.com/layumi/DukeMTMC-reID_baseline]
4. Code for IDE baseline on Market-1501
   • [https://github.com/zhunzhong07/IDE-baseline-Market-1501]

教程

1. 1st Workshop on Target Re-Identification and Multi-Target Multi-Camera Tracking
   • [https://reid-mct.github.io/]
2. 郑哲东 -Deep-ReID：行人重识别的深度学习方法
   • PPT：[https://www.slideshare.net/ZhedongZheng1/deep-reid]
   • 视频：[http://www.bilibili.com/video/av13796843/]
3. Person Identification in Large Scale Camera Networks Wei-Shi Zheng (郑伟诗)
   • [http://isee.sysu.edu.cn/~zhwshi/Research/ADL-OPEN.pdf\]
4. Person Re-Identification: Theory and Best Practice
   • [http://www.micc.unifi.it/reid-tutorial/slides/]

综述

1. Person Re-identification: Past, Present and Future Liang Zheng, Yi Yang, Alexander G. Hauptmann
   • [https://arxiv.org/abs/1610.02984]
2. Person Re-Identification Book
   • [https://link.springer.com/book/10.1007/978-1-4471-6296-4]
3. A Systematic Evaluation and Benchmark for Person Re-Identification: Features, Metrics, and Datasets
   • [http://lanl.arxiv.org/abs/1605.09653]
4. People reidentification in surveillance and forensics: A survey
   • [https://dl.acm.org/citation.cfm?doid=2543581.2543596]

数据集

1. Re-ID 数据集汇总
   • [https://robustsystems.coe.neu.edu/sites/robustsystems.coe.neu.edu/files/systems/projectpages/reiddataset.html]

图像数据集

1. Market-1501 Dataset 751个人，27种属性，一共约三万张图像（一人多图）
   • [http://www.liangzheng.org/Project/project_reid.html\]
   • Code for IDE baseline on Market-1501 :[https://github.com/zhunzhong07/IDE-baseline-Market-1501]
2. DukeMTMC-reID DukeMTMC数据集的行人重识别子集，原始数据集地址(http://vision.cs.duke.edu/DukeMTMC/) ，为行人跟踪数据集。原始数据集包含了85分钟的高分辨率视频，采集自8个不同的摄像头。并且提供了人工标注的bounding box。最终，DukeMTMC-reID 包含了 16,522张训练图片（来自702个人）， 2,228个查询图像（来自另外的702个人），以及 17,661 张图像的搜索库（gallery）。并提供切割后的图像供下载。
   • [https://github.com/layumi/DukeMTMC-reID_evaluation\]
3. CUHK01, 02, 03
   • [http://www.ee.cuhk.edu.hk/~rzhao/\]

Attribute相关数据集

1. RAP
   • [https://link.zhihu.com/?target=http%3A//rap.idealtest.org/]
2. Attribute for Market-1501and DukeMTMC_reID
   • [https://link.zhihu.com/?target=https%3A//vana77.github.io/]

视频相关数据集

1. Mars
   • [http://liangzheng.org/Project/project_mars.html]
2. PRID2011
   • [https://www.tugraz.at/institute/icg/research/team-bischof/lrs/downloads/]

NLP相关数据集：

1. 自然语言搜图像
   • [http://xiaotong.me/static/projects/person-search-language/dataset.html]
2. 自然语言搜索行人所在视频
   • [http://www.mi.t.u-tokyo.ac.jp/projects/person_search]

领域专家

1. Shaogang Gong -[http://www.eecs.qmul.ac.uk/~sgg/\]
2. Xiaogang Wang
   • [http://www.ee.cuhk.edu.hk/~xgwang/\]
3. Weishi Zheng
   • [https://sites.google.com/site/sunnyweishi/]
4. Liang Zheng
   • [http://www.liangzheng.com.cn/]
5. Chen Change Loy
   • [https://staff.ie.cuhk.edu.hk/~ccloy/\]
6. Qi Tian
   • [http://www.cs.utsa.edu/~qitian/tian-publication-year.html\]
7. Shengcai Liao
   • [http://www.cbsr.ia.ac.cn/users/scliao/]
8. Rui Zhao
   • [http://www.ee.cuhk.edu.hk/~rzhao/\]
9. Yang Yang
   • [http://www.cbsr.ia.ac.cn/users/yyang/main.htm]
10. Ling Shao
    • [http://lshao.staff.shef.ac.uk/]
11. Ziyan Wu
    • [http://wuziyan.com/]
12. DaPeng Chen
    • [http://gr.xjtu.edu.cn/web/dapengchen/home]
13. Horst Bischof
    • [https://www.tugraz.at/institute/icg/research/team-bischof/lrs/downloads/prid450s]
14. Niki Martinel
    • [http://users.dimi.uniud.it/~niki.martinel/\]
15. Liang Lin
    • [http://hcp.sysu.edu.cn/home/]
16. Le An
    • [http://auto.hust.edu.cn/index.php?a=shows&catid=28&id=134]
17. Xiang Bai
    • [http://mc.eistar.net/~xbai/index.html\]
18. Xiaoyuan Jing
    • [http://mla.whu.edu.cn/plus/list.php?tid=2]
19. Fei Xiong
    • [http://robustsystems.coe.neu.edu/?q=content/research]
20. DaPeng Chen
    • [http://gr.xjtu.edu.cn/web/dapengchen/home]