Metraipolis › archive › dc_65a7fd580d71

From Detection to Understanding: TAR and TAR-Bench for Multi-Task Traffic Anomaly Reasoning — arXiv:2608.10317

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.10317
License (as archived)
CC0-1.0
Archived
2026-10-19T06:30:11.662Z
SHA-256 of the archived text
3e3789c0a51c148a6adaf09ffa3eb8409e61960e858772a13ffec5ff12787a6b
Stable URL of this page
https://metraipolis.com/documento/dc_65a7fd580d71

How to cite

From Detection to Understanding: TAR and TAR-Bench for Multi-Task Traffic Anomaly Reasoning — arXiv:2608.10317 — arXiv (en), https://arxiv.org/abs/2608.10317 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_65a7fd580d71 (Metraipolis archive dc_65a7fd580d71, sha256 3e3789c0a51c148a6adaf09ffa3eb8409e61960e858772a13ffec5ff12787a6b)
BibTeX
@misc{dc65a7fd580d71,
  title = {From Detection to Understanding: TAR and TAR-Bench for Multi-Task Traffic Anomaly Reasoning — arXiv:2608.10317},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.10317},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_65a7fd580d71; sha256 3e3789c0a51c148a6adaf09ffa3eb8409e61960e858772a13ffec5ff12787a6b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10317. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Detecting a traffic anomaly does not establish whether a video-language model can explain what happened, localize it in time, or identify its causes. We introduce TAR (Traffic Anomaly Reasoning) and TAR-Bench, paired resources for training and evaluating these complementary capabilities across 10 tasks spanning question answering, temporal reasoning, and scene understanding. TAR contains 44,040 automatically generated annotations with chain-of-thought traces for 3,670 CCTV videos from eight public datasets. TAR-Bench provides 960 human-curated annotations for 80 held-out clips from 17 public YouTube videos. Evaluation of eleven vision-language models reveals a gap between question-answering performance and temporal or scene reasoning. Progressively adding task groups during supervised fine-tuning improves aggregate performance on both Cosmos-Reason2-8B and Qwen3-VL-8B-Instruct. Training on all 10 tasks raises their mean benchmark scores from 34.3 to 55.7 and from 30.9 to 53.9, respectively. These results support joint training across complementary tasks as a promising approach to traffic anomaly understanding, while highlighting persistent limitations in temporal precision and causal attribution. TAR and TAR-Bench serve as the official training and in-domain evaluation resources for AI City Challenge 2026 Track this http URL dataset is available at this https URL

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-12 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.10317 — 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 2026-10-19T06:25:27.240Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).