SwinTransTrack: Multi-Object Tracking Using Shifted Window Transformers

Abstract—With the great popularity of Transformers, there has
been many works using Transformers to explore the temporal
association properties of objects between different video frames.
However, due to the large-scale variation of visual entities and
the high resolution of pixels in images, the original Transformers
take so long time for both training and inference. Based on
Swin Transformer, we propose SwinTransTrack, a novel shiftwindow encoder and decoder model. Different from the original
model, we fuse low-rank adaptation to achieve feature dimension
enhancement and propose a new shifted-window decoder network
to obtain accurate displacement to associate trajectories. Finally,
We conducted extensive quantitative experiments on different
MOT datasets, MOT17 and MOT20. The experimental results
show that SwinTransTrack achieves 75.5 MOTA on MOT17 and
67.5 MOTA on MOT20, leading both MOT competitions.
Index Terms—Multi-object tracking, Swin Transformer, Adaptation, Attention