CEAVAD: Contrastive Event Adjudication for Training-Free Video Anomaly Detection

Forum topic · 小凯 · 2026-08-11

Summary

CEAVAD (Contrastive Event Adjudication for Video Anomaly Detection) is a training-free approach to video anomaly detection (VAD) proposed by Wenti Yin, Xiang Wang, and Huaxin Zhang (arXiv:2508.03800). The method shifts inference from isolated anomaly concepts to falsifiable event hypotheses. It first constructs hazard-benign event contrasts using common-sense safety knowledge, pairing each hazardous mechanism with a generic normal description and a mechanism-specific benign counterpart. It then determines whether a target interval better supports the hazardous explanation or its benign competitor, producing a correctable contrastive boundary proposal. Finally, CEAVAD adjudicates between competing explanations to test whether the hazard hypothesis withstands the video evidence, supporting both temporally localized detection and evidence-based explanation. Experiments on three widely used VAD benchmarks show state-of-the-art performance in the training-free paradigm.

Paper Overview

Research Area: Computer Vision (CV) Authors: Wenti Yin, Xiang Wang, Huaxin Zhang Published: 2026-08-11 arXiv: 2508.03800

Abstract

Video anomaly detection (VAD) aims to identify and temporally localize abnormal events in videos. Supervised methods learn anomaly decision boundaries from target-domain annotations but require substantial in-domain data. Existing training-free methods leverage the rich semantic knowledge and reasoning capabilities of pretrained models to interpret visual content, yet these capabilities do not directly define an anomaly decision criterion: richer anomaly descriptions better capture hazard resemblance without resolving abnormality.

To address this, the authors propose Contrastive Event Adjudication for training-free Video Anomaly Detection (CEAVAD), which shifts the unit of inference from isolated anomaly concepts to falsifiable event hypotheses and establishes an inference-time explanatory boundary through interaction between competing explanations and video evidence.

Method

1. Hazard-benign event contrasts: Using common-sense safety knowledge, CEAVAD pairs each hazardous mechanism with a generic normal description and a mechanism-specific benign counterpart. 2. Contrastive boundary proposal: It determines whether a target interval better supports the hazardous explanation or its benign competitor, yielding a correctable contrastive boundary proposal. 3. Adjudication: CEAVAD adjudicates between competing explanations to decide whether the hazard hypothesis withstands the video evidence, enabling both temporally localized anomaly detection and evidence-based explanation.

Results

Experiments on three widely used VAD benchmarks demonstrate that CEAVAD achieves state-of-the-art performance under the training-free paradigm.

---

*Automatically collected on 2026-08-12.*