The 1st Tiny Object Detection Challenge: Methods and Results
Abstract
The 1st Tiny Object Detection (TOD) Challenge aims to encourage research in developing novel and accurate methods for tiny object detection in images which have wide views, with a current focus on tiny person detection. The TinyPerson dataset was used for the TOD Challenge and is publicly released. It has 1610 images and 72651 box-levelannotations. Around 36 participating teams from the globe competed inthe 1st TOD Challenge. In this paper, we provide a brief summary of the1st TOD Challenge including brief introductions to the top three methods.The submission leaderboard will be reopened for researchers that areinterested in the TOD challenge. The benchmark dataset and other information can be found at: this https URL.
Cite
Text
Yu et al. "The 1st Tiny Object Detection Challenge: Methods and Results." European Conference on Computer Vision Workshops, 2020. doi:10.1007/978-3-030-68238-5_23Markdown
[Yu et al. "The 1st Tiny Object Detection Challenge: Methods and Results." European Conference on Computer Vision Workshops, 2020.](https://mlanthology.org/eccvw/2020/yu2020eccvw-1st/) doi:10.1007/978-3-030-68238-5_23BibTeX
@inproceedings{yu2020eccvw-1st,
title = {{The 1st Tiny Object Detection Challenge: Methods and Results}},
author = {Yu, Xuehui and Han, Zhenjun and Gong, Yuqi and Jan, Nan and Zhao, Jian and Ye, Qixiang and Chen, Jie and Feng, Yuan and Zhang, Bin and Wang, Xiaodi and Xin, Ying and Liu, Jingwei and Mao, Mingyuan and Xu, Sheng and Zhang, Baochang and Han, Shumin and Gao, Cheng and Tang, Wei and Jin, Lizuo and Hong, Mingbo and Yang, Yuchao and Li, Shuiwang and Luo, Huan and Zhao, Qijun and Shi, Humphrey},
booktitle = {European Conference on Computer Vision Workshops},
year = {2020},
pages = {315-323},
doi = {10.1007/978-3-030-68238-5_23},
url = {https://mlanthology.org/eccvw/2020/yu2020eccvw-1st/}
}