Retrieval-Guided Contextual Inference for Training-Free Video Anomaly Detection in Low-Light Scenarios

作者：Mengjingcheng Mo, Jiankang Zheng, Jiaxu Leng, Xinbo Gao · 年份：2026 · DOI：10.1145/3805622.3810823 · 被引用次数：1 · 研究领域：Anomaly Detection Techniques and Applications、Human Pose and Action Recognition、Adversarial Robustness in Machine Learning

Real-world surveillance often operates in low-light environments, where degraded visual evidence can make training-free anomaly reasoning unreliable. However, current training-free methods typically assume sufficiently clean inputs, which can lead to hallucinated semantics and unstable anomaly scores under visual degradation. To address this issue, we propose Retrieval-augmented Contextual Inference (ReCI), a training-free framework that leverages retrieval-augmented context for robust low-light video anomaly detection. ReCI constructs Semantic Context (SC) through hierarchical captioning by aggregating clip-level local captions into a video-level global description. It then performs contextualized anomaly inference using Reference Context (RC) retrieved from a reference pool built during inference. The VLM outputs anomaly scores and associated confidence values, which we use as a heuristic reliability signal for temporal refinement. Experiments on XD-Violence and UCF-Crime show that ReCI consistently improves over prior training-free baselines, with particularly clear gains on the low-light subset.