Instance-Aligned Captions for Explainable Video Anomaly Detection
This addresses the need for trustworthy and interpretable anomaly detection in safety-critical applications, though it is incremental in improving spatial grounding.
The paper tackled the problem of unverifiable explanations in video anomaly detection by introducing instance-aligned captions that link textual claims to specific object instances, and it created VIEW360+, a comprehensive dataset with 868 additional videos and new anomaly types, revealing limitations in current methods.
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 explanations unverifiable. This limitation is especially pronounced in multi-entity interactions, where existing explainable VAD methods often produce incomplete or visually misaligned descriptions, reducing their trustworthiness. To address these challenges, we introduce instance-aligned captions that link each textual claim to specific object instances with appearance and motion attributes. Our framework captures who caused the anomaly, what each entity was doing, whom it affected, and where the explanationis grounded, enabling verifiable and actionable reasoning. We annotate eight widely used VAD benchmarks and extend the 360-degree egocentric dataset, VIEW360, with 868 additional videos, eight locations, and four new anomaly types, creating VIEW360+, a comprehensive testbed for explainable VAD. Experiments show that our instance-level spatially grounded captions reveal significant limitations in current LLM- and VLM-based methods while providing a robust benchmark for future research in trustworthy and interpretable anomaly detection.