Dataset for paper: Jersey Number Recognition with Semi-Supervised Spatial Transformer Network

SJN-210k is a dataset that contains nearly 210,000 jersey number images for soccer games. It is used to train and evaluate vision models to recognize player jersey numbers. 

Pos with axis
pos without axis
neg

training set
8952
6004
130890

testing set
3794
2660
55795

Please cite the following paper if you use this dataset: 

Gen Li, Shikun Xu, Xiang Liu, Lei Li and Changhu Wang, "Jersey Number Recognition with Semi-Supervised Spatial Transformer Network," 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Salt Lake City, UT, USA, 2018, pp. 1864-18647, doi: 10.1109/CVPRW.2018.00231.

[Paper link]

@INPROCEEDINGS{li2018jersey,
author={Li, Gen and Xu, Shikun and Liu, Xiang and Li, Lei and Wang, Changhu},
booktitle={2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
title={Jersey Number Recognition with Semi-Supervised Spatial Transformer Network},
year={2018},
pages={1864-18647},
doi={10.1109/CVPRW.2018.00231}}