├── DeepChangeAccessAgreement.pdf
├── README.md
└── figures
    ├── deepchange.gif
    ├── hair-style.png
    ├── identities.png
    ├── p0318.png
    └── snow-and-rain.png


/DeepChangeAccessAgreement.pdf:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/PengBoXiangShang/deepchange/eaa100ae9024379335e8c7a85c4b4bfaca8c80c8/DeepChangeAccessAgreement.pdf


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | # <center>DeepChange:</center>  A Long-Term Person Re-Identification Benchmark with Clothes Change ICCV 2023
 2 | 
 3 | ![](https://img.shields.io/badge/language-Python-{green}.svg)
 4 | 
 5 | <div align=center><img src="https://github.com/PengBoXiangShang/deepchange/blob/main/figures/deepchange.gif" width = 80% height = 80% /></div>
 6 | 
 7 | This is the official project page of the paper ["DeepChange: A Long-Term Person Re-Identification Benchmark with Clothes Change"](https://arxiv.org/abs/2105.14685) ICCV 2023.
 8 | <br/>
 9 | <br/>
10 | <br/>
11 | <br/>
12 | Authors: [XU Peng](http://www.pengxu.net/) and [ZHU Xiatian](https://xiatian-zhu.github.io/)
13 | <br/>
14 | <br/>
15 | <br/>
16 | <br/>
17 | We contribute a large, realistic long-term person re-identification benchmark. It consists of **178K** bounding boxes from **1.1K** person identities, collected and constructed over a course of **12 months**. Unique characteristics of this dataset include: (1) Natural/native personal appearance (e.g., clothes and hair style) variations: The clothes-change and dressing styles are highly diverse, with the reappearing gap in time ranging from minutes, hours, and days to weeks, months, seasons, and years. (2) Diverse walks of life: Persons across a wide range of ages and professions appear in different weather conditions (e.g., sunny, cloudy, windy, rainy, snowy, extremely cold) and events (e.g., working, leisure, daily activities). (3) Rich camera setups: The raw videos were recorded by 17 outdoor security cameras with various resolutions operating in a real-world surveillance system for a wide and dense block. (4) Largest scale: It covers the largest number of (**17**) cameras, (**1121**) identities, and (**178407**) bounding boxes, as compared to alternative datasets. 
18 | <br/>
19 | <br/>
20 | <br/>
21 | <br/>
22 | 
23 | 
24 | <div align=center><img src="https://github.com/PengBoXiangShang/deepchange/blob/main/figures/p0318.png"/></div>
25 | Figure A. Images of a random person identity from DeepChange with clothes change, as well as variation in behavior, pose, hair, illumination, weather, background, etc.
26 | <br/>
27 | <br/>
28 | <br/>
29 | <br/>
30 | 
31 | <div align=center><img src="https://github.com/PengBoXiangShang/deepchange/blob/main/figures/identities.png"/></div>
32 | Figure B. Image samples of random identities in DeepChange. Identities from top left to bottom right: an aunt (bbox#1-#19), an office lady (bbox#20-#27), a pupil (bbox#28-#36), a newspaper delivery (bbox#37-#41), an older aunt (bbox#42-#49), a worker (bbox#50-#51), a nun (bbox#52-#53), a Muslim man (bbox#54-#56), a chef (bbox#57-#58), a disabled person (bbox#59-#60), a dustman (bbox#61-#70). 
33 | <br/>
34 | <br/>
35 | <br/>
36 | <br/>
37 | 
38 | <div align=center><img src="https://github.com/PengBoXiangShang/deepchange/blob/main/figures/snow-and-rain.png"/></div>
39 | Figure C. Images collected in snow (top two lines, bbox#1-#20) and rain (bottom line, bbox#21-#30) weather from DeepChange. 
40 | <br/>
41 | <br/>
42 | <br/>
43 | <br/>
44 | 
45 | <div align=center><img src="https://github.com/PengBoXiangShang/deepchange/blob/main/figures/hair-style.png"/></div>
46 | Figure D. Image pairs of the specific persons with simultaneous clothes and hair style changes in the DeepChange. For each identity, only two cases are selected randomly. 
47 | <br/>
48 | <br/>
49 | <br/>
50 | <br/>
51 | 
52 | ## Terms and conditions to apply
53 | - This dataset can be **ONLY** used for **non-commercial research purposes**.
54 | - Users are **NOT allowed** to reproduce, duplicate, copy, sell, trade, resell or exploit any portion of the images and any portion of derived data for any commercial purposes.
55 | - Users are **NOT allowed** to further publish or distribute any portion of this dataset.
56 | - Users **MUST** block the faces of any persons from this dataset when using images for any dissemination purposes, e.g., academic papers / slides / posters, presentations, personal websites, personal blogs.
57 | - **ALL** the rights to terminate the access are reserved.
58 | <br/>
59 | <br/>
60 | <br/>
61 | <br/>
62 | 
63 | ## Download
64 | Users need to download and sign our [**DeepChange Dataset Access Agreement**](https://github.com/PengBoXiangShang/deepchange/blob/main/DeepChangeAccessAgreement.pdf), and send it to XU Peng (peng.xu [AT] aliyun dOt com) with a title "DeepChange Dataset Access Agreement". We will verify the requests and contact users with the downloading **links** and other associate **documents**. Users should use your **institutional email address** to contact us. We will reply within 24 hours, and the download link is also valid for 24 hours, so after sending this request, please watch your email.
65 | <br/>
66 | 请大家用学校的邮箱发送申请表格。请勿使用163或qq等邮箱发送申请。请字迹工整地且完整地填写申请表格，可直接填写中文，Email 2里请填写一个可以永久联系的私人邮箱。我们通常会在24小时内回复，授权后下载链接有效期是24小时，所以发送申请后，请关注您的邮箱并及时下载。
67 | <br/>
68 | <br/>
69 | <br/>
70 | 
71 | ## Software tools
72 | We will release some codes and tools for this dataset very soon.
73 | <br/>
74 | <br/>
75 | <br/>
76 | <br/>
77 | 
78 | ## Citations
79 | If you would like to use this dataset, please cite the following papers:
80 | ```
81 | @inproceedings{xu2023deepchange,
82 |   title={DeepChange: A Long-Term Person Re-Identification Benchmark with Clothes Change},
83 |   author={Xu, Peng and Zhu, Xiatian},
84 |   booktitle={Proceedings of the IEEE international conference on computer vision (ICCV)},
85 |   year={2023}
86 | }
87 | ```
88 | <br/>
89 | <br/>
90 | <br/>
91 | <br/>
92 | 
93 | ## Contact
94 | Please email [XU Peng](http://www.pengxu.net/) for any questions.  
95 | Email: **peng.xu [AT] aliyun dOt com**
96 | 


--------------------------------------------------------------------------------
/figures/deepchange.gif:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/PengBoXiangShang/deepchange/eaa100ae9024379335e8c7a85c4b4bfaca8c80c8/figures/deepchange.gif


--------------------------------------------------------------------------------
/figures/hair-style.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/PengBoXiangShang/deepchange/eaa100ae9024379335e8c7a85c4b4bfaca8c80c8/figures/hair-style.png


--------------------------------------------------------------------------------
/figures/identities.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/PengBoXiangShang/deepchange/eaa100ae9024379335e8c7a85c4b4bfaca8c80c8/figures/identities.png


--------------------------------------------------------------------------------
/figures/p0318.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/PengBoXiangShang/deepchange/eaa100ae9024379335e8c7a85c4b4bfaca8c80c8/figures/p0318.png


--------------------------------------------------------------------------------
/figures/snow-and-rain.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/PengBoXiangShang/deepchange/eaa100ae9024379335e8c7a85c4b4bfaca8c80c8/figures/snow-and-rain.png


--------------------------------------------------------------------------------