EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MACD: Online Video Anomaly Detection via Multi‐Agent Counterfactual Dialectics

Xiaoye Ouyang, Shijie Liu, Liu Yuan, Yuan Wang, Xiaoling Zhu, Jipeng Qiang

IET Software · 2026-01 · 2026 (1)

DOI: 10.1049/sfw2/6947479 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IET Software, online erschienen am 17.04.2026. Verfasst von Xiaoye Ouyang und 5 weiteren Autor:innen. Die Arbeit nennt 19 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Online video anomaly detection (VAD) necessitates real‐time inference without access to future temporal context. Existing training‐free methods, while promising, often suffer from correlation bias, misclassifying infrequent but benign actions (e.g., running for exercise) as anomalies due to a lack of causal reasoning. In this paper, we introduce multi‐agent counterfactual dialectics (MACD), a novel framework that reframes VAD from statistical outlier detection to causal falsification. MACD operationalizes this via a structured adversarial debate among three specialized agents: a Prosecutor for high‐recall risk screening, a Skeptic that performs instruction‐conditioned causal interventions to generate benign counterfactual explanations, and an Arbitrator that adjudicates the final verdict based on the “evidence gap.” To ground this reasoning in visual reality, we construct a visual‐semantic world model using dynamic scene graphs (DSG) and set‐of‐mark (SoM) prompting, reinforced by a visual re‐verification loop (VRL) and a contextual memory bank to mitigate hallucinations. Our “screen‐debate‐decide” protocol ensures computational efficiency by reserving expensive dialectics only for ambiguous frames. Extensive experiments on UCF‐Crime and XD‐Violence demonstrate that MACD achieves state‐of‐the‐art zero‐shot performance.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Ouyang, X., Liu, S., Yuan, L., Wang, Y., Zhu, X., & Qiang, J. (2026). MACD: Online Video Anomaly Detection via Multi‐Agent Counterfactual Dialectics. IET Software, 2026(1). https://doi.org/10.1049/sfw2/6947479

Vancouver

Ouyang X, Liu S, Yuan L, Wang Y, Zhu X, Qiang J. MACD: Online Video Anomaly Detection via Multi‐Agent Counterfactual Dialectics. IET Software. 2026;2026(1). doi:10.1049/sfw2/6947479

BibTeX
@article{Ouyang2026,
  author = {Ouyang, Xiaoye and Liu, Shijie and Yuan, Liu and Wang, Yuan and Zhu, Xiaoling and Qiang, Jipeng},
  title = {MACD: Online Video Anomaly Detection via Multi‐Agent Counterfactual Dialectics},
  journal = {IET Software},
  year = {2026},
  volume = {2026},
  number = {1},
  doi = {10.1049/sfw2/6947479}
}
Kostenlos starten →