Advancing Adaptive Multi-Stage Video Anomaly Reasoning: A Benchmark Dataset and Method

TL;DR

This paper introduces a new benchmark dataset and method for Video Anomaly Reasoning (VAR), enabling multi-stage, structured reasoning in video anomaly detection and understanding, with improved performance over existing approaches.

Contribution

It defines the novel task of VAR, creates a large annotated dataset with structured reasoning chains, and proposes an MLLM-based model supporting adaptive hierarchical reasoning and decision making.

Findings

The dataset contains over 8,600 videos with 50,000+ annotated reasoning samples.

The proposed Vad-R1-Plus model outperforms existing baselines on VAR tasks.

Systematic evaluation shows improved reasoning and decision-making capabilities.

Abstract

Recent progress in reasoning capabilities of Multimodal Large Language Models(MLLMs) has highlighted their potential for performing complex video understanding tasks. However, in the domain of Video Anomaly Detection and Understanding (VAD&U), existing MLLM-based methods are largely limited to anomaly localization or post-hoc description, lacking explicit reasoning processes, risk awareness, and decision-oriented interpretation. To address this gap, we define a new task termed Video Anomaly Reasoning (VAR), which elevates video anomaly analysis from descriptive understanding to structured, multi-stage reasoning. VAR explicitly requires models to perform progressive reasoning over anomalous events before answering anomaly-related questions, encompassing visual perception, causal interpretation, and risk-aware decision making. To support this task, we present a new dataset with 8,641 videos, where each video is annotated with diverse question types corresponding to different reasoning depths, totaling more than 50,000 samples, making it one of the largest datasets for video anomaly. The annotations are based on a structured Perception-Cognition-Action Chain-of-Thought (PerCoAct-CoT), which formalizes domain-specific reasoning priors for video anomaly understanding. This design enables systematic evaluation of multi-stage and adaptive anomaly reasoning. In addition, we propose Anomaly-Aware Group Relative Policy Optimization to further enhance reasoning reliability under weak supervision. Building upon the proposed task and dataset, we develop an end-to-end MLLM-based VAR model termed Vad-R1-Plus, which supports adaptive hierarchical reasoning and risk-aware decision making. Extensive experiments demonstrate that the proposed benchmark and method effectively advance the reasoning capabilities of MLLMs on VAR tasks, outperforming both open-source and proprietary baselines.