通过提前预测运动轨迹，提升多目标跟踪的准确性。
Motion-Aware Transformer for Multi-Object Tracking
- 在Transformer解码器中引入运动感知机制，预先更新轨迹查询。
- DanceTrack上HOTA提升超9点，达71.3的新纪录。
- 无需外部数据，适合追求高精度的视频追踪应用。
视频中的多目标跟踪仍面临复杂运动与密集场景的挑战。现有基于DETR的端到端框架通常将检测与跟踪查询共同处理于单一Transformer解码层，导致冲突并降低关联精度。本文提出运动感知变换器（MATR），通过显式预测物体跨帧运动，提前更新轨迹查询。该设计减少查询冲突，实现更稳定的训练，并同时提升检测与关联性能。在DanceTrack、SportsMOT和BDD100k上的大量实验表明，MATR在标准指标上取得显著提升：在DanceTrack上，相比MOTR不依赖额外数据时HOTA提升超过9点，使用补充数据达到71.3的新峰值；在SportsMOT上获得72.2 HOTA，BDD100k上达54.7 mTETA、41.6 mHOTA，且未依赖外部数据集。结果证明，在端到端Transformer中显式建模运动是一种简单而高效的方法，可显著推进多目标跟踪性能。
原文摘要 · Abstract (English)
Multi-object tracking (MOT) in videos remains challenging due to complex object motions and crowded scenes. Recent DETR-based frameworks offer end-to-end solutions but typically process detection and tracking queries jointly within a single Transformer Decoder layer, leading to conflicts and degraded association accuracy. We introduce the Motion-Aware Transformer (MATR), which explicitly predicts object movements across frames to update track queries in advance. By reducing query collisions, MATR enables more consistent training and improves both detection and association. Extensive experiments on DanceTrack, SportsMOT, and BDD100k show that MATR delivers significant gains across standard metrics. On DanceTrack, MATR improves HOTA by more than 9 points over MOTR without additional data and reaches a new state-of-the-art score of 71.3 with supplementary data. MATR also achieves state-of-the-art results on SportsMOT (72.2 HOTA) and BDD100k (54.7 mTETA, 41.6 mHOTA) without relying on external datasets. These results demonstrate that explicitly modeling motion within end-to-end Transformers offers a simple yet highly effective approach to advancing multi-object tracking.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。