[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).
Thanks for the excellent work!
Here is a question about the data preparation. Now, i'm preparing the data for mots task, in https://github.com/Zhongdao/UniTrack/blob/main/docs/DATA.md, you said that for this task we should 1.Download MOT-16 dataset from the page https://motchallenge.net/data/MOTS/. However, the data link corresponds to MOTS not MOT-16.
So, could you tell me which dataset you used for mots task? MOTS or MOT-16?
Thank you~