Hi, first of all, thanks for your work on this project—it's a great contribution to the computer vision community!

I wanted to ask if there are any plans to support offline (batch/global) tracking algorithms in addition to the current online trackers. While real-time, online tracking is essential for many use cases (especially with YOLO and similar models), offline tracking can be extremely valuable for post-processing tasks where speed isn’t as critical, such as video analytics, privacy blurring, or high-accuracy benchmarking.

Thank you for all the hard work that went into this