Beyond Hazard Resemblance: Contrastive Event Adjudication for Training-Free Video Anomaly Detection
2026-08-10 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors propose a new method called CEAVAD for detecting unusual events in videos without needing any training data. Instead of looking for specific anomalies, their approach compares possible dangerous events with similar normal ones to decide what’s happening. By weighing different explanations against the video, CEAVAD can spot problems and explain why it thinks they are abnormal. Tests show their method works well compared to other training-free approaches.
Video Anomaly DetectionTraining-Free MethodsContrastive LearningEvent HypothesesHazard DetectionTemporal LocalizationPretrained ModelsExplanation-Based Reasoning
Authors
Wenti Yin, Xiang Wang, Huaxin Zhang, Hanqing Wang, Hongbo Shao, Changxin Gao, Nong Sang
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, we 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 the interaction between competing explanations and video evidence. Specifically, CEAVAD first uses public-safety knowledge to construct hazard-benign event contrasts, pairing each hazard mechanism with a generic normal account and a mechanism-specific benign counterpart. It then determines whether the target interval better supports a hazard explanation or its benign competitor, yielding a revisable contrastive boundary proposal for the target. Finally, CEAVAD adjudicates between the competing explanations to determine whether the hazard hypothesis survives the video evidence, supporting both temporally localized anomaly detection and evidence-grounded explanations. Experiments on three widely used VAD benchmarks demonstrate that CEAVAD achieves state-of-the-art performance under the training-free paradigm.