面向多目标跟踪的超图-状态协同推理
Hypergraph-State Collaborative Reasoning for Multi-Object Tracking
将超图与状态空间模型结合，通过对象间协同推理增强运动估计，为遮挡和噪声下的多目标跟踪提供可复用的时空建模框架。
原文依据 we design HyperSSM, an architecture that integrates Hypergraph computation and a State Space Model (SSM) for unified spatial-temporal reasoning.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论运动推理是多目标跟踪（MOT）的基石，因为它能够实现目标跨帧的一致关联。然而，现有的运动估计方法面临两大局限：（1）由噪声或概率预测引起的不稳定性；（2）在遮挡下的脆弱性，一旦视觉线索消失，轨迹往往发生断裂。为克服这些问题，我们提出一种协同推理框架，通过多个相关对象之间的联合推理来增强运动估计。通过允许具有相似运动状态的对象相互约束和细化，我们的框架能够稳定噪声轨迹，并在目标被遮挡时推断出合理的运动连续性。为实现这一概念，我们设计了 HyperSSM，一种集成了超图计算和状态空间模型（SSM）的架构，用于统一的时空推理。超图模块通过动态超边捕获空间运动相关性，而 SSM 通过结构化状态转移强制时序平滑性。这种协同设计能够同时优化空间一致性和时序连贯性，从而实现鲁棒且稳定的运动估计。在涵盖多种运动模式和场景复杂度的四个主流且多样化的基准（MOT17、MOT20、DanceTrack 和 SportsMOT）上进行的大量实验表明，我们的方法在广泛的跟踪场景中达到了最优性能。
英文原文摘要 1501 字符
Motion reasoning serves as the cornerstone of multi-object tracking (MOT), as it enables consistent association of targets across frames. However, existing motion estimation approaches face two major limitations: (1) instability caused by noisy or probabilistic predictions, and (2) vulnerability under occlusion, where trajectories often fragment once visual cues disappear.To overcome these issues, we propose a collaborative reasoning framework that enhances motion estimation through joint inference among multiple correlated objects. By allowing objects with similar motion states to mutually constrain and refine each other, our framework stabilizes noisy trajectories and infers plausible motion continuity even when target is occluded.To realize this concept, we design HyperSSM, an architecture that integrates Hypergraph computation and a State Space Model (SSM) for unified spatial-temporal reasoning. The Hypergraph module captures spatial motion correlations through dynamic hyperedges, while the SSM enforces temporal smoothness via structured state transitions. This synergistic design enables simultaneous optimization of spatial consensus and temporal coherence, resulting in robust and stable motion estimation.Extensive experiments on four mainstream and diverse benchmarks(MOT17, MOT20, DanceTrack, and SportsMOT) covering various motion patterns and scene complexities, demonstrate that our approach achieves state-of-the-art performance across a wide range of tracking scenarios.