VAU-R1: Advancing Video Anomaly Understanding via Reinforcement Fine-Tuning
This addresses the problem of interpretability and reasoning in anomaly detection for applications like smart cities and security surveillance, though it appears incremental as it builds on existing MLLMs.
The paper tackles the challenge of Video Anomaly Understanding (VAU) by introducing VAU-R1, a framework using Reinforcement Fine-Tuning with Multimodal Large Language Models, and VAU-Bench, a new benchmark for evaluating reasoning; results show significant improvements in question answering accuracy, temporal grounding, and reasoning coherence.
Video Anomaly Understanding (VAU) is essential for applications such as smart cities, security surveillance, and disaster alert systems, yet remains challenging due to its demand for fine-grained spatio-temporal perception and robust reasoning under ambiguity. Despite advances in anomaly detection, existing methods often lack interpretability and struggle to capture the causal and contextual aspects of abnormal events. This limitation is further compounded by the absence of comprehensive benchmarks for evaluating reasoning ability in anomaly scenarios. To address both challenges, we introduce VAU-R1, a data-efficient framework built upon Multimodal Large Language Models (MLLMs), which enhances anomaly reasoning through Reinforcement Fine-Tuning (RFT). Besides, we propose VAU-Bench, the first Chain-of-Thought benchmark tailored for video anomaly reasoning, featuring multiple-choice QA, detailed rationales, temporal annotations, and descriptive captions. Empirical results show that VAU-R1 significantly improves question answering accuracy, temporal grounding, and reasoning coherence across diverse contexts. Together, our method and benchmark establish a strong foundation for interpretable and reasoning-aware video anomaly understanding. Our code is available at https://github.com/GVCLab/VAU-R1.