OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.
翻译 - OpenMMLab视频感知工具箱。它通过统一的框架支持单对象跟踪(SOT),多对象跟踪(MOT),视频对象检测(VID)。
[ECCV'22 Oral] Towards Grand Unification of Object Tracking