Training-Free Video Anomaly Detection

Also known as VAD

Follow this topic Ask about this topic

Latest papers

12 papers3 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Anomaly-Guided Observation and Two-Level Semantic Feedback for Training-Free Video Anomaly Analysis
Oct 12, 2026Hangil Park, Seungheon Kim, Tae-Kyun KimTraining-Free Video Anomaly Detection Video Anomaly Detection
Korea Advanced Institute of Science and Technology (KAIST)
Cog-VADU: A Training-Free Cognitive Reasoning Framework for Video Anomaly Detection and Understanding
Oct 1, 2026Mohd Ubaid Wani, Sara Atito, Josef Kittler +1CoT Reasoning Interpretable Anomaly Detection
Centre for Vision, Speech and Signal Processing (CVSSP) University of Surrey, UK · Surrey Institute for People-Centred AI (PAI) University of Surrey, UK
PARSEE-VAD: Efficient Training-Free Online Video Anomaly Detection via Proposition-Aware Reasoning and Streaming Evidence Escalation
Sep 27, 2026Ji Wang, Shuangqing Zhang, Guo-Sen Xie +1Efficient Multimodal Inference Streaming Video Understanding
Global Institute of Future Technology Shanghai Jiao Tong University Shanghai, 200240, China · School of Intelligence Science and Technology Nanjing University Suzhou, 215163, China · School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing, 210094, China
Probe-VAD: Ordinal Likelihood Probing for Training-Free Video Anomaly Detection
Sep 15, 2026Jiawei Gu, Qilin Zhao, Tengkuo Guo +6Video Anomaly Detection Training-Free Video Anomaly Detection
School of Intelligence Science and Technology, Nanjing University, Suzhou 215163, China · Faculty of Life Science and Medicine, School of Medicine and Health, Harbin Institute of Technology, Harbin 150001, China · School of Instrumentation Science and Engineering, Harbin Institute of Technology, Harbin 150001, China +2
NOVA: Normal-Side Modeling for Training-Free Zero-Shot Video Anomaly Detection
Sep 6, 2026Wei-Chih Yin, Yun-Ching Kao, Cheng-Kuan Lin +1Training-Free Video Anomaly Detection Video Anomaly Detection
Department of Computer Science, National Yang Ming Chiao Tung University, Hsinchu, Taiwan
Beyond Hazard Resemblance: Contrastive Event Adjudication for Training-Free Video Anomaly Detection
Aug 10, 2026Wenti Yin, Xiang Wang, Huaxin Zhang +4Interpretable Anomaly Detection Anomaly Localization
Key Laboratory of Image Processing and Intelligent Control, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology · Alibaba Group · The Hong Kong University of Science and Technology (Guangzhou)
Context-structured Video Anomaly Detection with Large Vision-Language Models
Jul 21, 2026Dongjun Kim, Changjae Oh, Andrea Cavallaro +1Reference-Based Video Anomaly Detection Video Anomaly Detection
Yonsei University, Seoul, Republic of Korea · Queen Mary University of London, London, United Kingdom · EPFL, Lausanne, Switzerland
CoReVAD: A Contextual Reasoning Framework for Training-Free Video Anomaly Detection
May 22, 2026Hyeongmuk Lim, Youngbum HurInterpretable Anomaly Detection VLM Reasoning
Department of Industrial Engineering, Inha University, Incheon, Republic of Korea
SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere
May 8, 2026Chao Huang, Pengfei Wei, Wei Wang +5Video Anomaly Detection Training-Free Video Anomaly Detection
Shenzhen Campus of Sun Yat-sen University · Harbin Institute of Technology, Shenzhen
ESOM: Efficiently Understanding Streaming Video Anomalies with Open-world Dynamic Definitions
Apr 9, 2026Zihao Liu, Xiaoyu Wu, Wenna Li +2Video Anomaly Detection Anomaly Localization
State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China
GridVAD: Open-Set Video Anomaly Detection via Spatial Reasoning over Stratified Frame Grids
Mar 26, 2026Mohamed Eltahir, Ahmed O. Ibrahim, Obada Siralkhatim +2Video Anomaly Detection Training-Free Video Anomaly Detection
King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia · African Institute for Mathematical Sciences (AIMS), Cape Town, South Africa · Independent Researcher +1
Geometry-Aware Semantic Reasoning for Training Free Video Anomaly Detection
Mar 10, 2026Ali Zia, Usman Ali, Muhammad Umer Ramzan +3Training-Free Video Anomaly Detection Video Anomaly Detection
School of Computing, Engineering & Mathematical Sciences, La Trobe University, Melbourne, Australia · School of Engineering and Applied Sciences, GIFT University, Gujranwala 52250, Pakistan

Oct 12, 2026J/K move · Enter open · S save

Anomaly-Guided Observation and Two-Level Semantic Feedback for Training-Free Video Anomaly Analysis

Hangil Park, Seungheon Kim, Tae-Kyun Kim

Korea Advanced Institute of Science and Technology (KAIST)

Training-Free Video Anomaly Detection Video Anomaly Detection

Open paper AskPDF arXiv

Training-free language-based video anomaly detection (VAD) uses frozen vision--language models (VLMs) and large language models (LLMs) to localize abnormal events without task-specific model-weight optimization. Existing approaches increasingly exploit broader temporal and semantic context, yet generic context does not necessarily foreground abnormal events or specify how video-level semantics should modify local anomaly scores. We introduce a training-free semantic feedback framework that uses VAD-guided active observation for video anomaly understanding (VAU) and returns the resulting anomaly-focused description to refine temporal detection. Starting from an upstream anomaly-score curve, we adapt reasoning-based iterative frame selection: high-score regions seed the observations, and anomaly scores together with VLM relevance assessments guide subsequent temporal exploration. A frozen video-language model generates a single open-ended anomaly description from the selected frames. The description is returned through two complementary feedback levels: video-level feedback determines whether the score distribution should be suppressed, preserved, or sharpened, with selective visual rechecking, while local feedback retrieves event-related windows and promotes scores only after target-local visual verification. All model weights remain frozen, and feedback is applied once without regenerating the description. On the HIVAU video-summary evaluations of UCF-Crime and XD-Violence, VAD-guided observation improves GPT-rated reasonability, detail, and consistency over the matched CLIP-guided variant. For VAD, semantic feedback improves the re-evaluated upstream detector from 84.36% to 86.25% AUC on UCF-Crime and from 68.07% to 72.58% AP on XD-Violence, where the final AUC is 91.74%.