{"ID":6536433,"CreatedAt":"2026-07-14T01:21:01.169441415Z","UpdatedAt":"2026-07-14T12:57:06.499178768Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.10298","arxiv_id":"2607.10298","title":"Structured Evidence Selection for Weakly Supervised Video Anomaly Detection","abstract":"Weakly supervised video anomaly detection relies solely on video-level labels for training, making it difficult to accurately localize anomalous events in complex scenes. In real-world videos, anomalous behaviors exhibit large variations in appearance and temporal duration, while scene appearance and action dynamics are often tightly entangled. Consequently, existing models tend to rely on scene-related statistical cues rather than true behavioral deviations, resulting in unstable detection performance. To address this challenge, we propose a Structured Evidence Selection framework (SESAD) that reformulates anomaly detection as a structured reasoning process over clip-level visual evidence. Instead of directly mapping aggregated features to anomaly scores, SESAD reorganizes clip representations into semantically structured candidate evidence and performs context-conditioned selection under scene and action constraints. This mechanism adaptively emphasizes anomaly-relevant semantics while suppressing scene interference, thereby alleviating semantic entanglement under weak supervision. Furthermore, we introduce a lightweight geometric discrimination module that constructs a dual-prototype structure in the embedding space, enabling anomaly decisions through relative geometric relations. Extensive experiments on UBnormal, ShanghaiTech, and UCF-Crime show that SESAD achieves 67.92, 97.99, and 88.46 AUC, respectively, while maintaining high computational efficiency and overall consistently stable anomaly discrimination.","short_abstract":"Weakly supervised video anomaly detection relies solely on video-level labels for training, making it difficult to accurately localize anomalous events in complex scenes. In real-world videos, anomalous behaviors exhibit large variations in appearance and temporal duration, while scene appearance and action dynamics ar...","url_abs":"https://arxiv.org/abs/2607.10298","url_pdf":"https://arxiv.org/pdf/2607.10298v1","authors":"[\"Chenglizhao Chen\",\"Tianxiang Nan\",\"Wen Li\",\"Xinyu Liu\",\"Guisheng Zhang\",\"Mengke Song\",\"Xiaomin Yu\"]","published":"2026-07-11T13:01:01Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Generative Adversarial Network\"]","has_code":false}