Attention mechanics for improving online Multi-Object Tracking

In recent years, FairMOT is a known online one-shot model for tracking pedestrians with a focus on fairness between detection and re-identification (re-ID) tasks with remarkable performance. In this paper, we integrate some attention modules with more relating-object information to improve the performance of FairMOT. Firstly, we propose a spatial attention module which is the proper combination between deformable convolution and key-content factors to improve detection accuracy. Furthermore, we introduce a channel attention module in re-ID branch that can enhance efficient tracking capability. Our experimental evaluation shows that our extensions increase IDF1 and MOTA in tracking challenges MOT17, MOT20 with provided training data only.