Metraipolis › archive › dc_2a2cd8fa1281
ReWorld-Track: A Recursive Event World Model for Language-Guided Multi-Camera Tracking — arXiv:2609.36677
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.36677
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T18:38:21.281Z
- SHA-256 of the archived text
80e5ecca6494b2f122891575ce424d5526dfbc445b9d271d0383e2fb7ab9d81b- Stable URL of this page
https://metraipolis.com/documento/dc_2a2cd8fa1281
How to cite
ReWorld-Track: A Recursive Event World Model for Language-Guided Multi-Camera Tracking — arXiv:2609.36677 — arXiv (en), https://arxiv.org/abs/2609.36677 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2a2cd8fa1281 (Metraipolis archive dc_2a2cd8fa1281, sha256 80e5ecca6494b2f122891575ce424d5526dfbc445b9d271d0383e2fb7ab9d81b)
BibTeX
@misc{dc2a2cd8fa1281,
title = {ReWorld-Track: A Recursive Event World Model for Language-Guided Multi-Camera Tracking — arXiv:2609.36677},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.36677},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2a2cd8fa1281; sha256 80e5ecca6494b2f122891575ce424d5526dfbc445b9d271d0383e2fb7ab9d81b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36677. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Language-guided multi-camera tracking must preserve a target identity across unobserved gaps, where similar candidates and uncertain returns can make early associations unreliable. A wrong match can corrupt the history used to predict later observations and propagate identity errors across subsequent camera handoffs. We propose ReWorld-Track, a recursive event world model that carries association uncertainty into future predictions. Candidate matches and continued waiting define alternative target states, whose posterior probabilities are used to update a persistent recurrent belief. This representation preserves uncertainty about alternative trajectories through successive observations. This belief predicts the next camera, arrival time, and entry region, while appearance and language evidence guide association. By training across successive handoffs, the model learns to retain uncertainty that remains useful for later predictions and identity decisions. ReWorld-Track achieves HOTA scores of 65.19 on CityFlowV2 and 45.36 on MTMMC, with improved identity continuity across repeated handoffs. On MTMMC, its structured posterior update gains 0.50 HOTA points over a similarly sized generic updater and 0.94 points over fixed-moment soft association, raising next-camera accuracy from 86.03% to 87.41% and reducing median arrival-time error from 0.78 s to 0.71 s for subsequent target returns. 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/2609.36677 — 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 2026-10-07T18:04:24.729Z 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).