VQ-VAD: Vector-quantized Motion Representation Learning for Human-centric Video Anomaly Detection

• URL: http://arxiv.org/abs/2608.05069v1
• Date: Wed, 05 Aug 2026 17:12:39 GMT
• Title: VQ-VAD: Vector-quantized Motion Representation Learning for Human-centric Video Anomaly Detection
• Abstract summary: Video Anomaly Detection (VAD) is inherently challenging due to the scarcity of anomalies and the large visual variability in surveillance footage.<n>We propose Vector-Quantized Video Anomaly Detection (VQ-VAD), a novel human-centric anomaly detection framework that learns discrete motion representations.
• Score: 9.506999074910238
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Video Anomaly Detection (VAD) is inherently challenging due to the scarcity of anomalies and the large visual variability in surveillance footage, including changes in lighting, viewpoint, and human appearance. To mitigate visual noise and address privacy concerns, recent work has shifted to pose-based VAD, which focuses on motion dynamics rather than raw video data. However, existing pose-based approaches model human behavior in continuous latent spaces, limiting their ability to learn compact motion patterns necessary for robust behavior analysis. We address this by proposing Vector-Quantized Video Anomaly Detection (VQ-VAD), a novel human-centric anomaly detection framework that learns discrete motion representations. VQ-VAD adapts Vector-Quantized GAN (VQ-GAN), originally developed for image generation, to operate on keypoint sequences and construct a motion codebook of normal behavior. Trained exclusively on normal motion sequences, VQ-VAD detects anomalies by identifying high reconstruction errors when an observed motion sequence cannot be mapped to the learned codebook. We conduct extensive experiments across three complementary evaluation settings, including in-domain, cross-domain, and cross-dataset generalization, on four anomaly detection benchmarks. VQ-VAD achieves strong in-domain accuracy (81.83% on HR-SHT [15]), effective cross-domain transfer from CMU Panoptic [14] (76.69% on HR-SHT [15] without retraining), and competitive cross-dataset robustness. The code base for this work is available at https://github.com/TeCSAR-UNCC/VQ-VAD.

Related papers

• Physics-Driven Spatiotemporal Modeling for AI-Generated Video Detection [73.51855469884195]
  We propose an AI-driven video detection paradigm based on probability flow conservation principles.<n>We develop an NSG-based video detection method (NSG-VD) that computes the Mean Discrepancy (MMD) between NSG features of the test and real videos as a detection metric.
  arXiv  Detail & Related papers  (2025-10-09T11:00:35Z)
• Autoregressive Denoising Score Matching is a Good Video Anomaly Detector [36.96911195723131]
  Video anomaly detection (VAD) is an important computer vision problem.<n>We introduce a noise-conditioned score transformer for denoising score matching.<n>Then, we introduce a scene-dependent and motion-aware score function.<n>We integrate unaffected visual information via a novel autoregressive denoising score matching mechanism.
  arXiv  Detail & Related papers  (2025-06-29T15:14:32Z)
• Track Any Anomalous Object: A Granular Video Anomaly Detection Pipeline [63.96226274616927]
  A new framework called Track Any Anomalous Object (TAO) introduces a granular video anomaly detection pipeline.<n>Unlike methods that assign anomaly scores to every pixel, our approach transforms the problem into pixel-level tracking of anomalous objects.<n>Experiments demonstrate that TAO sets new benchmarks in accuracy and robustness.
  arXiv  Detail & Related papers  (2025-06-05T15:49:39Z)
• Dual Conditioned Motion Diffusion for Pose-Based Video Anomaly Detection [12.100563798908777]
  Video Anomaly Detection (VAD) is essential for computer vision research.<n>Existing VAD methods utilize either reconstruction-based or prediction-based frameworks.<n>We address pose-based video anomaly detection and introduce a novel framework called Dual Conditioned Motion Diffusion.
  arXiv  Detail & Related papers  (2024-12-23T01:31:39Z)
• Appearance Blur-driven AutoEncoder and Motion-guided Memory Module for Video Anomaly Detection [14.315287192621662]
  Video anomaly detection (VAD) often learns the distribution of normal samples and detects the anomaly through measuring significant deviations. Most VADs cannot cope with cross-dataset validation for new target domains. We propose a novel VAD method with a motion-guided memory module to achieve cross-dataset validation with zero-shot.
  arXiv  Detail & Related papers  (2024-09-26T07:48:20Z)
• Weakly Supervised Video Anomaly Detection and Localization with Spatio-Temporal Prompts [57.01985221057047]
  This paper introduces a novel method that learnstemporal prompt embeddings for weakly supervised video anomaly detection and localization (WSVADL) based on pre-trained vision-language models (VLMs) Our method achieves state-of-theart performance on three public benchmarks for the WSVADL task.
  arXiv  Detail & Related papers  (2024-08-12T03:31:29Z)
• Occlusion-Aware 3D Motion Interpretation for Abnormal Behavior Detection [10.782354892545651]
  We present OAD2D, which discriminates against motion abnormalities based on reconstructing 3D coordinates of mesh vertices and human joints from monocular videos. We reformulate the abnormal posture estimation by coupling it with Motion to Text (M2T) model in which, the VQVAE is employed to quantize motion features. Our approach demonstrates the robustness of abnormal behavior detection against severe and self-occlusions, as it reconstructs human motion trajectories in global coordinates.
  arXiv  Detail & Related papers  (2024-07-23T18:41:16Z)
• Dynamic Erasing Network Based on Multi-Scale Temporal Features for Weakly Supervised Video Anomaly Detection [103.92970668001277]
  We propose a Dynamic Erasing Network (DE-Net) for weakly supervised video anomaly detection. We first propose a multi-scale temporal modeling module, capable of extracting features from segments of varying lengths. Then, we design a dynamic erasing strategy, which dynamically assesses the completeness of the detected anomalies.
  arXiv  Detail & Related papers  (2023-12-04T09:40:11Z)
• Self-Supervised Masked Convolutional Transformer Block for Anomaly Detection [122.4894940892536]
  We present a novel self-supervised masked convolutional transformer block (SSMCTB) that comprises the reconstruction-based functionality at a core architectural level. In this work, we extend our previous self-supervised predictive convolutional attentive block (SSPCAB) with a 3D masked convolutional layer, a transformer for channel-wise attention, as well as a novel self-supervised objective based on Huber loss.
  arXiv  Detail & Related papers  (2022-09-25T04:56:10Z)
• Differentiable Frequency-based Disentanglement for Aerial Video Action Recognition [56.91538445510214]
  We present a learning algorithm for human activity recognition in videos. Our approach is designed for UAV videos, which are mainly acquired from obliquely placed dynamic cameras. We conduct extensive experiments on the UAV Human dataset and the NEC Drone dataset.
  arXiv  Detail & Related papers  (2022-09-15T22:16:52Z)

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.