AI 中文总结
本研究针对无训练视频异常检测问题，提出CEAVAD方法，通过构建危害-正常事件对比并裁决竞争解释，在三个基准上实现了无训练范式下的最优性能。
AI 中文摘要
视频异常检测（VAD）旨在识别视频中的异常事件并对其进行时间定位。监督方法从目标域标注中学习异常决策边界，但需要大量目标域数据。现有无训练方法利用预训练模型丰富的语义知识和推理能力来解释视觉内容，但这些能力并未直接定义异常决策准则：更丰富的异常描述能更好地捕捉危害相似性，却无法解决异常性问题。为此，我们提出用于无训练视频异常检测的对比事件裁决（CEAVAD），该方法将推理单元从孤立的异常概念转向可证伪的事件假设，并通过竞争解释与视频证据的交互建立推理时的解释性边界。具体而言，CEAVAD首先利用公共安全知识构建危害-正常事件对比，将每种危害机制与通用正常解释及该机制特有的良性对应解释配对；接着判断目标区间更支持危害解释还是其良性竞争解释，为目标生成可修正的对比边界提议；最后，CEAVAD在竞争解释间进行裁决，确定危害假设是否通过视频证据验证，同时支持时间定位的异常检测和基于证据的解释。在三个广泛使用的VAD基准上的实验表明，CEAVAD在无训练范式下达到了最先进的性能。
英文摘要
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.
CommentsCode is available at https://github.com/lessiYin/CEAVAD
