首个支持任意时间跨度的多目标追踪框架，兼顾实时与离线场景。
NOOUGAT: Towards Unified Online and Offline Multi-Object Tracking
- 统一图神经网络处理分段视频，通过自回归长时追踪层融合信息。
- 在线追踪在DanceTrack、SportsMOT等数据集上提升2.3至9.2点，离线更优。
- 可灵活调节片段大小，适应从帧级到批量处理的各种部署需求。
长期以来，在线与离线多目标追踪（MOT）的分裂导致解决方案碎片化，难以满足真实场景中灵活的时间需求。现有在线追踪依赖逐帧手工关联策略，难以应对长期遮挡；而离线方法虽能覆盖更长时间跨度，仍依赖启发式拼接处理任意长序列。本文提出NOOUGAT，首个支持任意时间跨度的追踪框架。其采用统一图神经网络（GNN）处理非重叠子片段，并通过新型自回归长时追踪（ALT）层实现融合。子片段大小控制延迟与时间上下文间的权衡，支持从逐帧到批量处理的广泛部署场景。NOOUGAT在两类追踪模式下均达领先性能，在DanceTrack上在线模式提升AssA +2.3，SportsMOT +9.2，MOT20 +5.0，离线模式收益更大。
原文摘要 · Abstract (English)
The long-standing division between \textit{online} and \textit{offline} Multi-Object Tracking (MOT) has led to fragmented solutions that fail to address the flexible temporal requirements of real-world deployment scenarios. Current \textit{online} trackers rely on frame-by-frame hand-crafted association strategies and struggle with long-term occlusions, whereas \textit{offline} approaches can cover larger time gaps, but still rely on heuristic stitching for arbitrarily long sequences. In this paper, we introduce NOOUGAT, the first tracker designed to operate with arbitrary temporal horizons. NOOUGAT leverages a unified Graph Neural Network (GNN) framework that processes non-overlapping subclips, and fuses them through a novel Autoregressive Long-term Tracking (ALT) layer. The subclip size controls the trade-off between latency and temporal context, enabling a wide range of deployment scenarios, from frame-by-frame to batch processing. NOOUGAT achieves state-of-the-art performance across both tracking regimes, improving \textit{online} AssA by +2.3 on DanceTrack, +9.2 on SportsMOT, and +5.0 on MOT20, with even greater gains in \textit{offline} mode.
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。