Zhongdao/UniTrack
[NeurIPS'21] Unified tracking framework with a single appearance model. It supports Single Object Tracking (SOT), Video Object Segmentation (VOS), Multi-Object Tracking (MOT), Multi-Object Tracking and Segmentation (MOTS), Pose Tracking, Video Instance Segmentation (VIS), and class-agnostic MOT (e.g. TAO dataset).
PythonMIT
Stargazers
- ali-robot
- amadeuzou
- chingswy
- cmputeUniversity of Michigan
- CYS-888
- felixfuu
- fly51flyPRIS
- HaoLiuHustHangzhou, Zhejiang, China
- hszhaoThe University of Hong Kong
- hyaihjq
- ifzhangBaidu | HUST
- JiamingSuenZJU-3DV
- Just5D
- laoxihongshilala
- LegendBCHuazhong Uni. of Sci. and Tec.
- michalwolsNew York
- nrupatungaLightmetrics
- ProfFanGeorgia Tech
- raypineZhejiang University
- rhythm92Japan
- senlinucBeijing
- SherryJYCUniversity of Zurich
- tang-hyTsinghua university
- thuyngchCyberCoreVN
- tianweiyMIT
- TsingularityGoogle DeepMind
- vealociaNew York University
- wangjingbo1219Shanghai AI LAB
- wangxiao5791509Anhui University (安徽大学)
- wangzheallenComputer Vision Researcher
- wuyujackNorthwestern University
- xingyizhouGoogle
- YaqiLYUHangzhou, China
- Yuxin-CVMicrosoft Research
- zhanght021
- ZhongdaoTsinghua University