5 papers · 1 filter
A VLM Answer Is Not an Anomaly Score: Rank Compression Across Image and Video Anomaly Detection
Inpyo Song, Jangwon Lee
Anomaly detection aims to identify observations that deviate from normal patterns. Recent work has increasingly used pretrained vision--language models (VLMs) for training-free ima…
Look Inside Each Video: Rethinking How Video Anomaly Detection Is Evaluated
Inpyo Song, Jangwon Lee
Video anomaly detection (VAD) aims to localize anomalous events by identifying when they occur. A common evaluation pools frame-level anomaly scores across all test videos and meas…
Rethinking Open-World Video Anomaly Detection: Diagnosing Definition Blindness
Inpyo Song, Jangwon Lee
Open-world video anomaly detection (OWVAD) aims to localize anomalous events in videos according to a user-specified definition. An OWVAD detector should therefore use the supplied…
Bounding-Box Trajectories Matter for Video Anomaly Detection
Inpyo Song, Jangwon Lee
Video anomaly detection is critical for public safety and security, yet remains highly challenging despite extensive research due to large variations in appearance, viewpoint, and…
Instance-Aligned Captions for Explainable Video Anomaly Detection
Inpyo Song, Minjun Joo, Joonhyung Kwon +2
Explainable video anomaly detection (VAD) is crucial for safety-critical applications, yet even with recent progress, much of the research still lacks spatial grounding, making the…