Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.02111 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914490152386560 |
|---|---|
| author | Missaoui, Benjamin Cetintas, Orcun Brasó, Guillem Meinhardt, Tim Leal-Taixé, Laura |
| author_facet | Missaoui, Benjamin Cetintas, Orcun Brasó, Guillem Meinhardt, Tim Leal-Taixé, Laura |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_02111 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | NOOUGAT: Towards Unified Online and Offline Multi-Object Tracking Missaoui, Benjamin Cetintas, Orcun Brasó, Guillem Meinhardt, Tim Leal-Taixé, Laura Computer Vision and Pattern Recognition 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. |
| title | NOOUGAT: Towards Unified Online and Offline Multi-Object Tracking |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.02111 |