Metraipolis › archive › dc_dadb01eae28c
UGO: Unified Architecture for General Multi-Object Tracking by Segmentation — arXiv:2609.37339
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.37339
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T18:41:10.856Z
- SHA-256 of the archived text
90ae4c0d824870875f4b05c756b2972a150410ce68d98f5ae6ac6df8374f62c4- Stable URL of this page
https://metraipolis.com/documento/dc_dadb01eae28c
How to cite
UGO: Unified Architecture for General Multi-Object Tracking by Segmentation — arXiv:2609.37339 — arXiv (en), https://arxiv.org/abs/2609.37339 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dadb01eae28c (Metraipolis archive dc_dadb01eae28c, sha256 90ae4c0d824870875f4b05c756b2972a150410ce68d98f5ae6ac6df8374f62c4)
BibTeX
@misc{dcdadb01eae28c,
title = {UGO: Unified Architecture for General Multi-Object Tracking by Segmentation — arXiv:2609.37339},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.37339},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dadb01eae28c; sha256 90ae4c0d824870875f4b05c756b2972a150410ce68d98f5ae6ac6df8374f62c4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37339. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-30 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.37339 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T18:04:24.856Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).