megvii-research/MOTRv2
End-to-end multi-object tracking system that combines transformer architecture with pretrained object detectors for video-based tracking.
Not currently ranked — collecting fresh signals.
star history
MOTRv2 is a computer vision system for multi-object tracking in video. It bootstraps an end-to-end tracker using a pretrained object detector (YOLOX) to generate detection proposals as anchors, improving upon prior end-to-end approaches. The system uses transformer-based architecture and achieves state-of-the-art performance on large-scale benchmarks like DanceTrack (73.4% HOTA) and BDD100K.
Frequently asked
- What is megvii-research/MOTRv2?
- End-to-end multi-object tracking system that combines transformer architecture with pretrained object detectors for video-based tracking.
- Is MOTRv2 open source?
- Yes — megvii-research/MOTRv2 is an open-source project tracked on heatdrop.
- What language is MOTRv2 written in?
- megvii-research/MOTRv2 is primarily written in Python.
- How popular is MOTRv2?
- megvii-research/MOTRv2 has 484 stars on GitHub.
- Where can I find MOTRv2?
- megvii-research/MOTRv2 is on GitHub at https://github.com/megvii-research/MOTRv2.