Metraipolis › archive › dc_bc95fcb81dad

Glance, Scrutinize, and Think: Advancing Video Anomaly Detection from Training-Free to Agentic Reasoning — arXiv:2608.11260

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.11260
License (as archived): CC0-1.0
Archived: 2026-10-19T05:15:18.194Z
SHA-256 of the archived text: 88b7d875305d02e4d24eef3dc3feee2fe2ce34fe702731abcdae1bd0412d9f77
Stable URL of this page: https://metraipolis.com/documento/dc_bc95fcb81dad

How to cite

Glance, Scrutinize, and Think: Advancing Video Anomaly Detection from Training-Free to Agentic Reasoning — arXiv:2608.11260 — arXiv (en), https://arxiv.org/abs/2608.11260 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bc95fcb81dad (Metraipolis archive dc_bc95fcb81dad, sha256 88b7d875305d02e4d24eef3dc3feee2fe2ce34fe702731abcdae1bd0412d9f77)

BibTeX

@misc{dcbc95fcb81dad,
  title = {Glance, Scrutinize, and Think: Advancing Video Anomaly Detection from Training-Free to Agentic Reasoning — arXiv:2608.11260},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.11260},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bc95fcb81dad; sha256 88b7d875305d02e4d24eef3dc3feee2fe2ce34fe702731abcdae1bd0412d9f77},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11260. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Video Anomaly Detection (VAD) aims to identify anomalous events and localize their temporal intervals. Existing approaches exhibit a "when-what" dissociation: traditional DNN-based methods localize when anomalies occur but lack semantic understanding, whereas LLM-based methods explain what happens but neglect precise temporal grounding. We attribute this to the absence of a unified reasoning paradigm. Inspired by how humans inspect surveillance videos - glancing globally to form temporal hypotheses, scrutinizing suspicious segments, and thinking iteratively to correct errors - we study this global-to-local paradigm from two perspectives. We first propose Glance then Scrutinize (GtS), a training-free framework using static and dynamic textual guidance for coarse-to-fine anomaly grounding and understanding, balancing accuracy and speed. To break the ceiling imposed by frozen external modules, we further propose a tool-augmented agentic VAD method, where a multimodal large language model learns to invoke a video cropping tool, inspect densely resampled frames, and self-correct mislocalized hypotheses, via cold-start supervised fine-tuning followed by reinforcement learning with a joint answer-grounding reward. For training and evaluation, we extend our prior VAGU benchmark into VAGU-T (Video Anomaly Grounding, Understanding, and Thinking), comprising 7,567 real-world videos over 21 anomaly categories with human-validated grounding, explanations, QA pairs, and chain-of-thought tool-calling traces. We further introduce JeAUG, a metric jointly evaluating semantic interpretability and temporal precision. Experiments show that GtS substantially surpasses training-free baselines, while the agentic model delivers both higher accuracy and faster inference.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-13 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.11260 — 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 2026-10-19T05:08:46.617Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).