Text-guided Fine-Grained Video Anomaly Understanding

ArXi:2511.00524v3 Announce Type: replace Subtle abnormal events in videos often manifest as weak spatio-temporal cues that are easily overlooked by conventional anomaly detection systems. Existing video anomaly detection approaches typically provide coarse binary anomaly decisions without interpretable evidence, while large vision-language models (LVLMs) can produce textual judgments but lack precise localization of subtle visual signals.