QVAD: A Question-Centric Agentic Framework for Efficient and Training-Free Video Anomaly Detection
This addresses the problem of efficient and training-free anomaly detection for computer vision applications, offering a novel approach that is incremental in improving existing VLM methods.
The paper tackles video anomaly detection by proposing QVAD, a question-centric agentic framework that uses dynamic dialogue between LLMs and VLMs to refine queries, achieving state-of-the-art performance on datasets like UCF-Crime with fewer parameters and enabling deployment on edge devices.
Video Anomaly Detection (VAD) is a fundamental challenge in computer vision, particularly due to the open-set nature of anomalies. While recent training-free approaches utilizing Vision-Language Models (VLMs) have shown promise, they typically rely on massive, resource-intensive foundation models to compensate for the ambiguity of static prompts. We argue that the bottleneck in VAD is not necessarily model capacity, but rather the static nature of inquiry. We propose QVAD, a question-centric agentic framework that treats VLM-LLM interaction as a dynamic dialogue. By iteratively refining queries based on visual context, our LLM agent guides smaller VLMs to produce high-fidelity captions and precise semantic reasoning without parameter updates. This ``prompt-updating" mechanism effectively unlocks the latent capabilities of lightweight models, enabling state-of-the-art performance on UCF-Crime, XD-Violence, and UBNormal using a fraction of the parameters required by competing methods. We further demonstrate exceptional generalizability on the single-scene ComplexVAD dataset. Crucially, QVAD achieves high inference speeds with minimal memory footprints, making advanced VAD capabilities deployable on resource-constrained edge devices.