└── README.md


/README.md:
--------------------------------------------------------------------------------
 1 | ## Learning Modal-Invariant and Temporal-Memory for Video-based Visible-Infrared Person Re-Identification
 2 | 
 3 | ### This is the page for HITSZ-VCM dataset. 
 4 | ### HITSZ-VCM is a large scale video-based cross-modal dataset for person re-identification.
 5 | 
 6 | #### Usage
 7 | 
 8 | - Download the [Train data](https://drive.google.com/file/d/16codXQuXcgOLtr2ADLzCRMu2FI5zKmSG/view?usp=sharing), [Test data](https://drive.google.com/file/d/1UGot89JorJif3MY5o2o9gnM50KudIeTX/view?usp=sharing) and [info](https://drive.google.com/file/d/1BApfA5k995wcjW9Ok6Xl6QOY03IOWG05/view?usp=sharing) from Google Drive or from [Baidu Netdisk](https://pan.baidu.com/s/1oFYQIJoxCCD1Wk9WTbhbxA) (password: kxzs).
 9 | 
10 | 
11 | - Unzip the data and put the data in the same directory. The path to the data is placed in ```data_manager.py```.
12 | 
13 | - Data structure.
14 |             
15 | 	    
16 | 		|____ data/
17 | 		     |____ 0001/
18 | 		          |____ ir/
19 | 		          |____ rgb/
20 | 		     |____ 0002/
21 | 		     …
22 | 		     |____ 0927/
23 | 		     |____test_name.txt
24 | 		     |____track_test_info.txt
25 | 		     |____query_IDX.txt
26 | 		     |____train_name.txt
27 | 		     |____track_train_info.txt
28 | 		 
29 | 
30 | #### License 
31 | - Data is available for academic only. This means that it cannot be used to train models for commercial use.
32 | - You may NOT redistribute the dataset. This includes posting it on a website or sending it to others.
33 | - Models trained using our data may only be distributed (posted on the internet or given to others) under the condition that the model can only be used for non-commercial uses.
34 | - Any publications utilizing this dataset should reference our paper.
35 | 
36 | ##### By downloading or using any of these files, you agree to be bound by and comply with the license agreement.
37 | 
38 | ```
39 | @inproceedings{lin2022learning,
40 |   title={Learning Modal-Invariant and Temporal-Memory for Video-Based Visible-Infrared Person Re-Identification},
41 |   author={Lin, Xinyu and Li, Jinxing and Ma, Zeyu and Li, Huafeng and Li, Shuang and Xu, Kaixiong and Lu, Guangming and Zhang, David},
42 |   booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
43 |   pages={20973--20982},
44 |   year={2022}
45 | }
46 | ```
47 | 


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