发表机构
Institute of Visual Computing, Graz University of Technology; Institute for Medical Informatics, Statistics and Documentation, Medical University of Graz（格拉茨工业大学视觉计算研究所; 格拉茨医科大学医学信息学、统计学与文档研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出STEP框架，通过PCA投影姿态序列并引入序列级加权机制，在UBnormal数据集上比现有最优方法提升12.2%，实现高效的人体姿态视频异常检测。
AI 中文摘要
基于骨骼的视频异常检测（VAD）为识别异常行为提供了一种鲁棒、隐私保护的解决方案。为了建模正常静态和动态姿态的分布，现有方法通过去噪分数匹配（DSM）训练基于能量的模型（EBM）。然而，训练所需的直接向原始关节坐标注入噪声会产生物理上不可能的姿态，且这种结构崩溃会随时间窗口扩大而严重加剧。为解决该问题，本文提出STEP这一简单框架，利用主成分分析（PCA）将姿态序列投影到紧凑的白化主成分空间。在该行为良好的主成分空间中学习数据密度，可确保注入的噪声转化为物理上合理的变化，使模型能处理更长的视频序列，而不会出现原始坐标基线的性能崩溃。此外，为缓解遮挡或运动模糊导致的固有姿态估计误差，本文整合了基于估计器置信度分数的序列级加权机制。该框架运算效率达实时水平，在极具挑战性的UBnormal数据集上，比此前基于骨骼的最优方法提升12.2%（AUROC达90.1%），并在ShanghaiTech基准上取得极具竞争力的结果。
英文摘要
Skeleton-based Video Anomaly Detection (VAD) offers a robust, privacy-preserving solution for identifying abnormal behaviors. To model the distribution of normal static and moving poses, recent methods train Energy-Based Models (EBMs) via Denoising Score Matching (DSM). However, directly injecting noise, required for training, into raw joint coordinates creates physically impossible poses, and this structural collapse severely worsens as the temporal window expands. To address this, we introduce STEP, a simple framework that utilizes Principal Component Analysis (PCA) to project pose sequences into a compact, whitened PC-space. Learning the data density within this well-behaved PC-space ensures that the injected noise translates into physically plausible variations, which allows the model to process longer video sequences without the performance collapse of raw coordinate baselines. Additionally, to mitigate inherent pose estimation inaccuracies arising from occlusions or motion blur, we integrate a sequence-level weighting mechanism based on the estimator's confidence scores. Operating at real-time computational efficiency, our simple and lightweight framework outperforms the previous skeleton-based state-of-the-art by 12.2% (90.1% AUROC) on the challenging UBnormal dataset and achieves highly competitive results by improving on the ShanghaiTech benchmark.
CommentsAccepted to ECCV 2026. Project page: https://jakubmicorek.github.io/STEP-demo | Code: https://github.com/jakubmicorek/STEP
