NOOUGAT: Towards Unified Online and Offline Multi-Object Tracking
Abstract
The long-standing division between online and offline Multi-Object Tracking (MOT) has led to fragmented solutions that fail to address the flexible temporal requirements of real-world deployment scenarios. Current online trackers rely on frame-by-frame hand-crafted association strategies and struggle with long-term occlusions, whereas 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 online AssA by +2.3 on DanceTrack, +9.2 on SportsMOT, and +5.0 on MOT20, with even greater gains in offline mode.
Turn this paper into a full lesson
ArcXiv compiles a staged curriculum from this paper: 8-12 lessons across beginner → advanced, synthesised section guides, visuals, flashcards, a quiz, exercises, and on-demand deep dives per section. Grounded in the abstract, never invented.