English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

Beyond Hazard Resemblance: Contrastive Event Adjudication for Training-Free Video Anomaly Detection (CEAVAD)

Forum topic · 小凯 · 2026-08-11

Summary

CEAVAD (Contrastive Event Adjudication for training-free Video Anomaly Detection) is a new approach to video anomaly detection (VAD) proposed by Wenti Yin, Xiang Wang, and Huaxin Zhang, published on arXiv (2508.03800). While supervised VAD methods learn anomaly decision boundaries from target-domain annotations, they require substantial in-domain data. Existing training-free methods leverage pretrained models' semantic knowledge and reasoning capabilities, but richer anomaly descriptions only capture hazard resemblance without actually resolving abnormality. CEAVAD shifts the unit of inference from isolated anomaly concepts to falsifiable event hypotheses, establishing an inference-time explanatory boundary. It first constructs hazard-benign event contrasts using public safety knowledge, pairing each hazard mechanism with a generic normal description and a mechanism-specific benign counterpart. It then determines whether a target segment better supports the hazardous interpretation or its benign competitor, producing a correctable contrastive boundary proposal. Finally, CEAVAD adjudicates between competing explanations to test whether the hazard hypothesis withstands video evidence, supporting both temporally localized anomaly 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 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 this end, 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. Construct hazard-benign event contrasts: Using public safety knowledge, CEAVAD pairs each hazard mechanism with a generic normal description and a mechanism-specific benign counterpart. 2. Contrastive boundary proposal: It determines whether a target segment better supports the hazardous explanation or its benign competitor, producing a correctable contrastive boundary proposal for the target. 3. Adjudication: CEAVAD adjudicates between competing explanations to determine whether the hazard hypothesis withstands the test of video evidence, supporting 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.

--- *Auto-collected on 2026-08-12*

Tags

#video-anomaly-detection#computer-vision#training-free#contrastive-learning#pretrained-models#arxiv#ceavad

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178633352