Metraipolis › archive › dc_b8d030c0eb2d

RISE: Roadside Infrastructure Sequence Understanding across 3D Tracking and Structured Vision-Language Reasoning — arXiv:2608.16480

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.16480
License (as archived)
CC0-1.0
Archived
2026-10-18T18:07:18.108Z
SHA-256 of the archived text
1c94a5edbe6a41503112e44c98bb2b41ca5346b1bbbc2bceaf4e0525d2cb79b7
Stable URL of this page
https://metraipolis.com/documento/dc_b8d030c0eb2d

How to cite

RISE: Roadside Infrastructure Sequence Understanding across 3D Tracking and Structured Vision-Language Reasoning — arXiv:2608.16480 — arXiv (en), https://arxiv.org/abs/2608.16480 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b8d030c0eb2d (Metraipolis archive dc_b8d030c0eb2d, sha256 1c94a5edbe6a41503112e44c98bb2b41ca5346b1bbbc2bceaf4e0525d2cb79b7)
BibTeX
@misc{dcb8d030c0eb2d,
  title = {RISE: Roadside Infrastructure Sequence Understanding across 3D Tracking and Structured Vision-Language Reasoning — arXiv:2608.16480},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.16480},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b8d030c0eb2d; sha256 1c94a5edbe6a41503112e44c98bb2b41ca5346b1bbbc2bceaf4e0525d2cb79b7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16480. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present RISE (Roadside Infrastructure Sequence Understanding and Evaluation), a framework spanning metric 3D tracking and structured vision-language reasoning in roadside sequences. For metric tracking, our image-only method combines SAM3 video identities with calibration-guided mask agreement for multi-view identity association, recovering persistent 3D tracks without LiDAR or task-specific 3D training. Its calibration-conditioned geometry allows the procedure to be instantiated at different calibrated multi-camera intersections without layout-specific retraining. On 20 human-reviewed clips from six intersections, the generated tracks achieve 66.9 MOTA within the defined multi-view evaluation scope. For structured vision-language reasoning, a human-reviewed MLLM pipeline mines high-value clips and uses a constrained full-context Oracle to construct bbox-grounded predictive QA without exposing future evidence to evaluated models. The resulting RISE-VQA dataset contains 33,910 QA pairs from 557 clips across 16 intersections and 61 roadside views. Its intersection-held-out RISE-Bench evaluates semantic choices, coordinates, future boxes, and interaction sets with deterministic task-specific metrics. Experiments show consistent benefits from domain adaptation and generally from temporal context, while revealing persistent challenges in spatial grounding, future localization, and interaction reasoning.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.16480 — 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 2026-10-18T16:29:14.122Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).