The paper introduces a lightweight two‑stage system for real‑time video anomaly detection. First, YOLO v11n‑pose detects people and extracts seventeen skeletal keypoints in a single forward pass. Second, each cropped person region is encoded with CLIP ViT‑B/32 and compared via cosine similarity to predefined textual descriptions of anomalous behaviors, removing the need for optical flow, separate pose estimators, or density‑based scoring. Experiments on CUHK Avenue, ShanghaiTech Campus, and a custom indoor dataset achieve about 51 FPS on an NVIDIA Titan XP, a 3.36× speedup over a multi‑feature baseline, while preserving high frame‑level AUROC scores (89.26%, 70.26%, and 84.13%).
By Vanodhya G. Warnasooriya, Amir Hajian, Watchara Ruangsang, Supavadee Aramvith
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.
arXiv:2608. 05069v1 Announce Type: cross 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.
By Narges Rashvand, Ghazal Alinezhad Noghre, Shanle Yao, Gabriel Maldonado, Hamed Tabkhi
arXiv:2608. 19987v1 Announce Type: new Abstract: Skeleton-based Video Anomaly Detection (VAD) offers a robust, privacy-preserving solution for identifying abnormal behaviors.
By Jakub Micorek, Mateusz Kozi\'nski, Horst Possegger
arXiv:2607. 18142v1 Announce Type: cross Abstract: Industrial Video Anomaly Detection (IVAD) aims to identify anomalous objects and events in an industrial process, which is crucial for modern manufacturing and quality control systems.
By Mei Yuan, Qi Long, Qifeng Wu, Zhenyang Li, Yizhou Zhao, Lei Wang, Yang Liu, Min Xu
RoboVAD is a large-scale benchmark for video anomaly detection in robotic arm manipulation, featuring cross-domain evaluation where both tasks and anomaly types are unseen during training. The dataset challenges existing VAD methods, with state-of-the-art approaches, including a new method tailored for robotic arms, still achieving less than 70% micro-averaged frame-level AUC in the hardest setting. The authors provide the dataset and code publicly for further research.
By Alexandru-Bogdan Dura, Sebastian Balmus, Radu Tudor Ionescu
arXiv:2505.02393v3 Announce Type: replace
Abstract: Most existing video anomaly detectors rely on RGB frames alone, which limit their ability to capture abrupt or transient motion cues that are criti...
By Sungheon Jeong, Jihong Park, Mohsen Imani
arXiv:2412.03044v3 Announce Type: replace
Abstract: Video anomaly detection (VAD) is a vital yet complex open-set task in computer vision, commonly tackled through reconstruction-based methods. Howev...
By Xiaofeng Tan, Hongsong Wang, Xin Geng, Liang Wang
arXiv:2606. 14724v1 Announce Type: cross Abstract: Video anomaly detection in surveillance settings must balance detection accuracy against real-time throughput, a tension that existing methods address either through stronger feature extractors or more efficient architectures, but rarely both.
By Xinze Zhang
arXiv:2609.01551v1 Announce Type: new
Abstract: Self-supervised video foundation models learn rich spatiotemporal representations, yet it remains unclear what visual concepts these representations en...
By Sharon S. Musa, Fereshteh Forghani, Harrish Thasarathan, Sonia Joseph, Matthew Kowal, Konstantinos G. Derpanis
The paper introduces TITAnD, a Trajectory Image Transformer that converts dense and sparse GPS trajectories into a Hyperspectral Trajectory Image (HTI) and applies vision-based classification and segmentation for anomaly detection. It employs a Cyclic Factorized Transformer (CFT) that splits attention along within-day and across-day axes, drastically reducing computational cost and enabling multi-month analysis. Empirical results show TITAnD outperforms existing sparse and dense benchmarks, achieving higher AUC-PR and faster inference than comparable Transformers.
By Md Awsafur Rahman, Chandrakanth Gudavalli, Hardik Prajapati, B. S. Manjunath
Weakly supervised video anomaly detection (WSVAD) has predominantly focused on temporal localization, identifying when anomalies occur while largely neglecting their spatial extent within frames. Yet, spatial localization is essential for interpretability and practical deployment in real-world settings.