MEFormer: Multi-Object Tracking with Multi-Scale Feature Enhanced Transformer

Track-by-attention model, such as TrackFormer, have been one of the most popular deep models for multi-object tracking (MOT). However, one of their core limitations is image recognition accuracy and local feature attention due to the long sequence attention mechanism. To remedy this problem, MEFormer, a multi-scale feature enhanced model is proposed, in which both the channel attention and spatial attention mechanisms are leveraged for feature enhanced. MEFormer can effectively capture discriminative representation for MOT with attention and aggregation. Experiments on the MOT17 dataset indicate that the proposed MEFormer is able to achieve competitive performance on the task of multi-object tracking with 56.0% MOTA and 2400 ID switches.