Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Global Tracking Transformers

About

We present a novel transformer-based architecture for global multi-object tracking. Our network takes a short sequence of frames as input and produces global trajectories for all objects. The core component is a global tracking transformer that operates on objects from all frames in the sequence. The transformer encodes object features from all frames, and uses trajectory queries to group them into trajectories. The trajectory queries are object features from a single frame and naturally produce unique trajectories. Our global tracking transformer does not require intermediate pairwise grouping or combinatorial association, and can be jointly trained with an object detector. It achieves competitive performance on the popular MOT17 benchmark, with 75.3 MOTA and 59.1 HOTA. More importantly, our framework seamlessly integrates into state-of-the-art large-vocabulary detectors to track any objects. Experiments on the challenging TAO dataset show that our framework consistently improves upon baselines that are based on pairwise association, outperforming published works by a significant 7.7 tracking mAP. Code is available at https://github.com/xingyizhou/GTR.

Xingyi Zhou, Tianwei Yin, Vladlen Koltun, Philipp Kr\"ahenb\"uhl• 2022

Related benchmarks

TaskDatasetResultRank
Multiple Object TrackingMOT17 (test)
MOTA75.3
921
Multiple Object TrackingMOT20 (test)
MOTA63.6
358
Multi-Object TrackingDanceTrack (test)
HOTA0.48
355
Multi-Object TrackingSportsMOT (test)
HOTA54.5
199
Multi-Object TrackingTAO (val)
AssocA57.5
40
Multi-Object TrackingSportsMOT
HOTA54.5
25
Multi-Object TrackingDanceTrack 58 (test)
HOTA48
20
Multi-Object TrackingTAO (test)
mAP5020.1
13
Multi-Object TrackingSportsMOT 11 (test)
HOTA54.5
13
Closed-set MOT Track mAP comparisonTAO 1.0 (val)
Track mAP500.225
8
Showing 10 of 12 rows

Other info

Code

Follow for update