Abstract
General multi-object tracking (GMOT) tracks all instances of a user-specified category from a single first-frame exemplar. Prior work relies on bounding boxes and surrogate training, and struggles with non-rigid objects, crowded scenes, and distractors. We introduce UGO, a unified GMOT tracker that pairs a pretrained exemplar-conditioned detection head with an instance-propagation head in a common architecture. A novel training-free, energy-minimization consolidation method converts overlapping proposals into exclusive pixel-wise masks and detections, resolving over-segmentation, duplicates, and conflicts. A hierarchical memory spanning global and instance levels improves recall and per-instance segmentation accuracy using a new memory management protocol. UGO sets a new state-of-the-art on GMOT benchmarks and video object counting, and is competitive with specialist MOT methods, establishing a strong paradigm for unified, open-category multi-object tracking.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Pelhan, J., Lukezic, A., & Kristan, M. (2026). UGO: Unified Architecture for General Multi-Object Tracking by Segmentation. https://omanscience.com/en/articles/ugo-unified-architecture-for-general-multi-object-tracking-by-segmentation
MLA 9
Pelhan, Jer, et al. "UGO: Unified Architecture for General Multi-Object Tracking by Segmentation." https://omanscience.com/en/articles/ugo-unified-architecture-for-general-multi-object-tracking-by-segmentation.
Chicago (author–date)
Pelhan, Jer, Alan Lukezic, and Matej Kristan. 2026. "UGO: Unified Architecture for General Multi-Object Tracking by Segmentation." https://omanscience.com/en/articles/ugo-unified-architecture-for-general-multi-object-tracking-by-segmentation.
Harvard
Pelhan, J., Lukezic, A. and Kristan, M. (2026) 'UGO: Unified Architecture for General Multi-Object Tracking by Segmentation', Available at: https://omanscience.com/en/articles/ugo-unified-architecture-for-general-multi-object-tracking-by-segmentation.
Vancouver
Pelhan J, Lukezic A, Kristan M. UGO: Unified Architecture for General Multi-Object Tracking by Segmentation. https://omanscience.com/en/articles/ugo-unified-architecture-for-general-multi-object-tracking-by-segmentation
IEEE
J. Pelhan, A. Lukezic, and M. Kristan, "UGO: Unified Architecture for General Multi-Object Tracking by Segmentation," https://omanscience.com/en/articles/ugo-unified-architecture-for-general-multi-object-tracking-by-segmentation.