Abstract
Multi-object tracking aims to maintain object identities over time by associating detections across video frames. Two dominant paradigms exist in literature: tracking-by-detection methods, which are computationally efficient but rely on handcrafted association heuristics, and end-to-end approaches, which learn association from data at the cost of higher computational complexity. We propose Track-Detection Link Prediction (TDLP), a tracking-by-detection method that performs per-frame association via link prediction between tracks and detections, i.e., by predicting the correct continuation of each track at every frame. TDLP is architecturally designed primarily for geometric features such as bounding boxes, while optionally incorporating additional cues, including pose and appearance. Unlike heuristic-based methods, TDLP learns association directly from data without handcrafted rules, while remaining modular and computationally efficient compared to end-to-end trackers. Extensive experiments on multiple benchmarks demonstrate that TDLP consistently surpasses state-of-the-art performance across both tracking-by-detection and end-to-end methods. Finally, we provide a detailed analysis comparing link prediction with metric learning-based association and show that link prediction is more effective, particularly when handling heterogeneous features such as detection bounding boxes. Our code is available at \href{this https URL}{this https URL}.
Abstract (translated)
多目标跟踪旨在通过在视频帧之间关联检测结果来维护对象的身份。文献中存在两种主要范式：基于检测的跟踪方法，这些方法计算效率高但依赖于手工设计的相关启发式规则；以及端到端的方法，它们从数据中学习相关性，代价是更高的计算复杂度。我们提出了一种名为“Track-Detection Link Prediction”（TDLP）的新方法，这是一种基于检测的跟踪技术，它通过在轨迹和检测之间的链接预测来进行帧内关联，即通过对每个轨道在未来每一帧中的正确延续进行预测来实现这一目标。TDLP主要针对几何特征如边界框进行架构设计，同时可选地整合其他线索，包括姿态和外观信息。与基于启发式的方法不同的是，TDLP直接从数据中学习关联性而不依赖于手工规则，并且在计算效率方面仍保持模块化特性，相较于端到端跟踪器而言更为高效。 通过多个基准测试的广泛实验表明，TDLP在基于检测的跟踪方法和端到端方法之间始终超越了最先进的性能。最后，我们进行了详细的分析比较链接预测与度量学习为基础的相关性，并证明了对于处理异构特征（例如检测边界框）时，链接预测更为有效。我们的代码可以在\href{this https URL}{此URL}获取。
URL
https://arxiv.org/abs/2512.22105
