search

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).
MIT License
334 stars 34 forks source link

YOLOR + Unitrack #8

Open augmentedstartups opened 2 years ago

augmentedstartups commented 2 years ago

Hi, Ritesh here from Augmented Startups (89k) would you be releasing an application on YOLOR and Unitrack. I would cover it on my YouTube Channel.

Zhongdao commented 2 years ago

Hi, Thanks, Rithesh, I'd love to do this. I guess the final results would be almost the same as YOLOX + UniTrack, is that okay for you? By the way, I am currently working on some other experiments, so it might take me some time to do this. I'll let you know when I finished.

augmentedstartups commented 2 years ago

That will be great! I'm running a course on YOLOR currently I'm running it with DeepSORT but would like to show my students this with Unitrack. Maybe we can discuss further collaborations. My LinkedIn posts get over 10k views so we can really cover a lot of applications. My email is rkanjee@augmentedstartups.com