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: https://github.com/ucas-vg/TinyBenchmark.
@article{arxiv.2009.07506,
title = {The 1st Tiny Object Detection Challenge:Methods and Results},
author = {Xuehui Yu and Zhenjun Han and Yuqi Gong and Nan Jiang and Jian Zhao and Qixiang Ye and Jie Chen and Yuan Feng and Bin Zhang and Xiaodi Wang and Ying Xin and Jingwei Liu and Mingyuan Mao and Sheng Xu and Baochang Zhang and Shumin Han and Cheng Gao and Wei Tang and Lizuo Jin and Mingbo Hong and Yuchao Yang and Shuiwang Li and Huan Luo and Qijun Zhao and Humphrey Shi},
journal= {arXiv preprint arXiv:2009.07506},
year = {2020}
}
Comments
ECCV2020 Workshop on Real-world Computer Vision from Inputs with Limited Quality (RLQ) and Tiny Object Detection Challenge