This paper addresses the long-tail distribution issue in multi-object tracking (MOT) datasets, where the number of frames for different pedestrians varies significantly. The authors propose two data augmentation strategies, Stationary Camera View Data Augmentation (SVA) and Dynamic Camera View Data Augmentation (DVA), to simulate the motion trajectories of pedestrians in tail classes and change the background style, respectively. Additionally, they introduce the Group Softmax (GS) module to improve the appearance recognition performance for tail classes by grouping similar quantities of pedestrian categories and performing softmax operations individually. The proposed methods are evaluated on four public MOT benchmarks (MOT15, MOT16, MOT17, and MOT20) using two state-of-the-art multi-object tracking algorithms (FairMOT and CStrack). The results demonstrate that the proposed methods effectively mitigate the impact of long-tail distribution on MOT performance, achieving significant improvements in metrics such as MOTA, IDF1, and HOTA. The code for the proposed methods is available at <https://github.com/chen-si-jia/Trajectory-Long-tail-Distribution-for-MOT>.This paper addresses the long-tail distribution issue in multi-object tracking (MOT) datasets, where the number of frames for different pedestrians varies significantly. The authors propose two data augmentation strategies, Stationary Camera View Data Augmentation (SVA) and Dynamic Camera View Data Augmentation (DVA), to simulate the motion trajectories of pedestrians in tail classes and change the background style, respectively. Additionally, they introduce the Group Softmax (GS) module to improve the appearance recognition performance for tail classes by grouping similar quantities of pedestrian categories and performing softmax operations individually. The proposed methods are evaluated on four public MOT benchmarks (MOT15, MOT16, MOT17, and MOT20) using two state-of-the-art multi-object tracking algorithms (FairMOT and CStrack). The results demonstrate that the proposed methods effectively mitigate the impact of long-tail distribution on MOT performance, achieving significant improvements in metrics such as MOTA, IDF1, and HOTA. The code for the proposed methods is available at <https://github.com/chen-si-jia/Trajectory-Long-tail-Distribution-for-MOT>.