QVAD: A Question-Centric Agentic Framework for Efficient and Training-Free Video Anomaly Detection

• URL: http://arxiv.org/abs/2604.03040v1
• Date: Fri, 03 Apr 2026 13:48:34 GMT
• Title: QVAD: A Question-Centric Agentic Framework for Efficient and Training-Free Video Anomaly Detection
• Abstract summary: Video Anomaly Detection (VAD) is a fundamental challenge in computer vision.<n>We propose QVAD, a question-centric agentic framework that treats VLM-LLM interaction as a dynamic dialogue.<n>QVAD achieves high inference speeds with minimal memory footprints, making advanced VAD capabilities deployable on resource-constrained edge devices.
• Score: 11.652235163237117
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• MemoVAD: Resource-Efficient Video Anomaly Detection via Dynamic Semantic Memory in Edge Computing Scenarios [11.065570477454225]
  Video Anomaly Detection (VAD) in real-world surveillance faces a fundamental tension between the demand for high-level semantics to ensure effectiveness and the limited computational resources of edge devices.<n>To address the challenge, we propose MemoVAD, an edge-cloud collaborative framework that selectively incorporates VLM semantics into streaming VAD.
  arXiv  Detail & Related papers  (2026-06-04T06:57:28Z)
• AVERY: Adaptive VLM Split Computing through Embodied Self-Awareness for Efficient Disaster Response Systems [6.294240680169978]
  Unmanned Aerial Vehicles (UAVs) in disaster response require complex, queryable intelligence that on-board CNNs cannot provide.<n>We present AVERY, a framework that enables VLM deployment through adaptive split computing.
  arXiv  Detail & Related papers  (2025-11-22T18:42:04Z)
• Sparse Reasoning is Enough: Biological-Inspired Framework for Video Anomaly Detection with Large Pre-trained Models [36.38859440184592]
  Video anomaly detection (VAD) plays a vital role in real-world applications such as security surveillance, autonomous driving, and industrial monitoring.<n>Recent advances in large pre-trained models have opened new opportunities for training-free VAD by leveraging rich prior knowledge and general reasoning capabilities.<n>This raises a fundamental question: Is dense reasoning truly necessary when using powerful pre-trained models in VAD systems?<n>We propose ReCoVAD, a novel framework inspired by the dual reflex and conscious pathways of the human nervous system, enabling selective frame processing to reduce redundant computation.
  arXiv  Detail & Related papers  (2025-11-21T09:50:21Z)
• Efficient Onboard Vision-Language Inference in UAV-Enabled Low-Altitude Economy Networks via LLM-Enhanced Optimization [61.55616421408666]
  Low-Altitude Economy Networks (LAENets) have enabled a variety of applications, including aerial surveillance, environmental sensing, and semantic data collection.<n> onboard vision (VLMs) offer inference for real-time inference but limited onboard dynamic network conditions.<n>We propose a UAV-enabled LAENet system that improves communication efficiency under dynamic LAENet conditions.
  arXiv  Detail & Related papers  (2025-10-11T05:11:21Z)
• Training-free Uncertainty Guidance for Complex Visual Tasks with MLLMs [61.64185573373394]
  We propose a training-free framework that uses an MLLM's intrinsic uncertainty as a proactive guidance signal.<n>We introduce a unified mechanism that scores candidate visual inputs by response uncertainty, enabling the model to autonomously focus on the most salient data.<n>Our work validates that harnessing intrinsic uncertainty is a powerful, general strategy for enhancing fine-grained multimodal performance.
  arXiv  Detail & Related papers  (2025-10-01T09:20:51Z)
• ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding [71.654781631463]
  ReAgent-V is a novel agentic video understanding framework.<n>It integrates efficient frame selection with real-time reward generation during inference.<n>Extensive experiments on 12 datasets demonstrate significant gains in generalization and reasoning.
  arXiv  Detail & Related papers  (2025-06-02T04:23:21Z)
• AssistPDA: An Online Video Surveillance Assistant for Video Anomaly Prediction, Detection, and Analysis [52.261173507177396]
  We introduce AssistPDA, the first online video anomaly surveillance assistant (VAPDA) that unifies anomaly prediction, detection, and analysis (VAPDA) within a single framework.<n> AssistPDA enables real-time inference on streaming videos while supporting interactive user engagement.<n>We also introduce a novel event-level anomaly prediction task, enabling proactive anomaly forecasting before anomalies fully unfold.
  arXiv  Detail & Related papers  (2025-03-27T18:30:47Z)
• Integrating Frequency-Domain Representations with Low-Rank Adaptation in Vision-Language Models [0.6715525121432597]
  This research presents a novel vision language model (VLM) framework to enhance feature extraction, scalability, and efficiency.<n>We evaluate the proposed model on caption generation and Visual Question Answering (VQA) tasks using benchmark datasets with varying levels of Gaussian noise.<n>Our model provides more detailed and contextually relevant responses, particularly for real-world images captured by a RealSense camera mounted on an Unmanned Ground Vehicle (UGV)
  arXiv  Detail & Related papers  (2025-03-08T01:22:10Z)
• AnyAnomaly: Zero-Shot Customizable Video Anomaly Detection with LVLM [2.5988879420706095]
  Video anomaly detection (VAD) is crucial for video analysis and surveillance in computer vision.<n>Existing VAD models rely on learned normal patterns, which makes them difficult to apply to diverse environments.<n>This study proposes customizable video anomaly detection (C-VAD) technique and the AnyAnomaly model.
  arXiv  Detail & Related papers  (2025-03-06T14:52:34Z)
• Multi-Modal Prompt Learning on Blind Image Quality Assessment [65.0676908930946]
  Image Quality Assessment (IQA) models benefit significantly from semantic information, which allows them to treat different types of objects distinctly. Traditional methods, hindered by a lack of sufficiently annotated data, have employed the CLIP image-text pretraining model as their backbone to gain semantic awareness. Recent approaches have attempted to address this mismatch using prompt technology, but these solutions have shortcomings. This paper introduces an innovative multi-modal prompt-based methodology for IQA.
  arXiv  Detail & Related papers  (2024-04-23T11:45:32Z)
• Correlation Information Bottleneck: Towards Adapting Pretrained Multimodal Models for Robust Visual Question Answering [63.87200781247364]
  Correlation Information Bottleneck (CIB) seeks a tradeoff between compression and redundancy in representations. We derive a tight theoretical upper bound for the mutual information between multimodal inputs and representations.
  arXiv  Detail & Related papers  (2022-09-14T22:04:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.