A Simple Baseline for Multi-Object Tracking

Title: A Simple Baseline for Multi-Object Tracking

Teams: Huazhong University of Science and Technology，Microsoft Research Asia

Writers: Yifu Zhang, Chunyu Wang, Xinggang Wang, Wenjun Zeng, Wenyu Liu

PubDate: Apr 2020

Project: A Simple Baseline for Multi-Object Tracking

Abstract

There has been remarkable progress on object detection and re-identification in recent years which are the core components for multi-object tracking. However, little attention has been focused on accomplishing the two tasks in a single network to improve the inference speed. The initial attempts along this path ended up with degraded results mainly because the re-identification branch is not appropriately learned. In this work, we study the essential reasons behind the failure, and accordingly present a simple baseline to addresses the problems. It remarkably outperforms the state-of-the-arts on the public datasets at [Math Processing Error] fps. We hope this baseline could inspire and help evaluate new ideas in this field.