{"total":123,"rows":[{"id":"2403.06495","title":"Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Prompts","created":"2024-03-11","cited_by_count":89,"area":null},{"id":"2412.06171","title":"Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity","created":"2024-12-09","cited_by_count":70,"area":"mllm"},{"id":"2406.12235","title":"Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLM","created":"2024-06-18","cited_by_count":64,"area":"mllm"},{"id":"2311.07042","title":"Open-Vocabulary Video Anomaly Detection","created":"2023-11-13","cited_by_count":57,"area":null},{"id":"2402.04857","title":"Advancing Video Anomaly Detection: A Concise Review and a New Dataset","created":"2024-02-07","cited_by_count":49,"area":null},{"id":"2404.08531","title":"Text Prompt with Normality Guidance for Weakly Supervised Video Anomaly Detection","created":"2024-04-12","cited_by_count":49,"area":null},{"id":"2404.03248","title":"Learning Transferable Negative Prompts for Out-of-Distribution Detection","created":"2024-04-04","cited_by_count":43,"area":null},{"id":"2408.05905","title":"Weakly Supervised Video Anomaly Detection and Localization with Spatio-Temporal Prompts","created":"2024-08-12","cited_by_count":40,"area":null},{"id":"2409.09957","title":"Deep Graph Anomaly Detection: A Survey and New Perspectives","created":"2024-09-16","cited_by_count":40,"area":null},{"id":"2409.05383","title":"Deep Learning for Video Anomaly Detection: A Review","created":"2024-09-09","cited_by_count":27,"area":null},{"id":"2310.12790","title":"Anomaly Heterogeneity Learning for Open-set Supervised Anomaly Detection","created":"2023-10-19","cited_by_count":25,"area":null},{"id":"2412.01095","title":"VERA: Explainable Video Anomaly Detection via Verbalized Learning of Vision-Language Models","created":"2024-12-02","cited_by_count":24,"area":"mllm"},{"id":"2505.23504","title":"VAU-R1: Advancing Video Anomaly Understanding via Reinforcement Fine-Tuning","created":"2025-05-29","cited_by_count":24,"area":null},{"id":"2410.01506","title":"Learnable Expansion of Graph Operators for Multi-Modal Feature Fusion","created":"2024-10-02","cited_by_count":23,"area":null},{"id":"2410.10289","title":"Fine-grained Abnormality Prompt Learning for Zero-shot Anomaly Detection","created":"2024-10-14","cited_by_count":22,"area":null},{"id":"2509.26386","title":"PANDA: Towards Generalist Video Anomaly Detection via Agentic AI Engineer","created":"2025-09-30","cited_by_count":19,"area":"agents"},{"id":"2405.19387","title":"Video Anomaly Detection in 10 Years: A Survey and Outlook","created":"2024-05-29","cited_by_count":18,"area":null},{"id":"2402.05355","title":"A Survey on Safe Multi-Modal Learning System","created":"2024-02-08","cited_by_count":15,"area":null},{"id":"2503.18094","title":"Anomize: Better Open Vocabulary Video Anomaly Detection","created":"2025-03-23","cited_by_count":13,"area":null},{"id":"2505.15205","title":"Flashback: Memory-Driven Zero-shot, Real-time Video Anomaly Detection","created":"2025-05-21","cited_by_count":12,"area":null},{"id":"2511.00962","title":"A Unified Reasoning Framework for Holistic Zero-Shot Video Anomaly Analysis","created":"2025-11-02","cited_by_count":12,"area":null},{"id":"2411.14565","title":"Privacy-Preserving Video Anomaly Detection: A Survey","created":"2024-11-21","cited_by_count":11,"area":null},{"id":"2502.18863","title":"Sherlock: Towards Multi-scene Video Abnormal Event Extraction and Localization via a Global-local Spatial-sensitive LLM","created":"2025-02-26","cited_by_count":11,"area":null},{"id":"2503.03562","title":"Towards Visual Discrimination and Reasoning of Real-World Physical Dynamics: Physics-Grounded Anomaly Detection","created":"2025-03-05","cited_by_count":10,"area":null},{"id":"2401.03522","title":"Text-Driven Traffic Anomaly Detection with Temporal High-Frequency Modeling in Driving Videos","created":"2024-01-07","cited_by_count":9,"area":null},{"id":"2501.10067","title":"FiLo++: Zero-/Few-Shot Anomaly Detection by Fused Fine-Grained Descriptions and Deformable Localization","created":"2025-01-17","cited_by_count":8,"area":null},{"id":"2503.13160","title":"Language-guided Open-world Video Anomaly Detection under Weak Supervision","created":"2025-03-17","cited_by_count":8,"area":null},{"id":"2506.05175","title":"Track Any Anomalous Object: A Granular Video Anomaly Detection Pipeline","created":"2025-06-05","cited_by_count":8,"area":null},{"id":"2506.09368","title":"Anomaly Detection and Generation with Diffusion Models: A Survey","created":"2025-06-11","cited_by_count":8,"area":"diffusion"},{"id":"2507.15905","title":"Foundation Models and Transformers for Anomaly Detection: A Survey","created":"2025-07-21","cited_by_count":8,"area":null},{"id":"2507.21507","title":"VAGU & GtS: LLM-Based Benchmark and Framework for Joint Video Anomaly Grounding and Understanding","created":"2025-07-29","cited_by_count":8,"area":null},{"id":"2508.06350","title":"Aligning Effective Tokens with Video Anomaly in Large Language Models","created":"2025-08-08","cited_by_count":8,"area":null},{"id":"2510.02155","title":"Unlocking Vision-Language Models for Video Anomaly Detection via Fine-Grained Prompting","created":"2025-10-02","cited_by_count":8,"area":"mllm"},{"id":"2602.19248","title":"No Need For Real Anomaly: MLLM Empowered Zero-Shot Video Anomaly Detection","created":"2026-02-22","cited_by_count":8,"area":null},{"id":"2403.06154","title":"GlanceVAD: Exploring Glance Supervision for Label-efficient Video Anomaly Detection","created":"2024-03-10","cited_by_count":7,"area":null},{"id":"2411.10945","title":"Anomaly Detection for People with Visual Impairments Using an Egocentric 360-Degree Camera","created":"2024-11-17","cited_by_count":7,"area":null},{"id":"2504.04495","title":"AVadCLIP: Audio-Visual Collaboration for Robust Video Anomaly Detection","created":"2025-04-06","cited_by_count":7,"area":null},{"id":"2508.06318","title":"Mixture of Experts Guided by Gaussian Splatters Matters: A new Approach to Weakly-Supervised Video Anomaly Detection","created":"2025-08-08","cited_by_count":6,"area":"moe"},{"id":"2507.12755","title":"Domain-Enhanced Dual-Branch Model for Efficient and Interpretable Accident Anticipation","created":"2025-07-17","cited_by_count":5,"area":null},{"id":"2511.19474","title":"Pistachio: Towards Synthetic, Balanced, and Long-Form Video Anomaly Benchmarks","created":"2025-11-22","cited_by_count":5,"area":null},{"id":"2507.07939","title":"SAGE: A Visual Language Model for Anomaly Detection via Fact Enhancement and Entropy-aware Alignment","created":"2025-07-10","cited_by_count":4,"area":"mllm"},{"id":"2507.21649","title":"The Evolution of Video Anomaly Detection: A Unified Framework from DNN to MLLM","created":"2025-07-29","cited_by_count":4,"area":null},{"id":"2508.14203","title":"A Survey on Video Anomaly Detection via Deep Learning: Human, Vehicle, and Environment","created":"2025-08-19","cited_by_count":4,"area":null},{"id":"2510.14896","title":"Leveraging Multimodal LLM Descriptions of Activity for Explainable Semi-Supervised Video Anomaly Detection","created":"2025-10-16","cited_by_count":4,"area":"mllm"},{"id":"2601.08155","title":"Instance-Aligned Captions for Explainable Video Anomaly Detection","created":"2026-01-13","cited_by_count":4,"area":null},{"id":"2602.24021","title":"Steering and Rectifying Latent Representation Manifolds in Frozen Multi-modal LLMs for Video Anomaly Detection","created":"2026-02-27","cited_by_count":4,"area":"mllm"},{"id":"2607.00622","title":"Learning to Watch: Active Video Anomaly Understanding via Interleaved Policy Optimization","created":"2026-07-01","cited_by_count":4,"area":null},{"id":"2505.13123","title":"Just Dance with $\\pi$! A Poly-modal Inductor for Weakly-supervised Video Anomaly Detection","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2505.19022","title":"Rethinking Metrics and Benchmarks of Video Anomaly Detection","created":"2025-05-25","cited_by_count":3,"area":null},{"id":"2506.13095","title":"Learning Event Completeness for Weakly Supervised Video Anomaly Detection","created":"2025-06-16","cited_by_count":3,"area":null},{"id":"2603.00550","title":"Weakly Supervised Video Anomaly Detection with Anomaly-Connected Components and Intention Reasoning","created":"2026-02-28","cited_by_count":3,"area":null},{"id":"2403.01169","title":"Learn Suspected Anomalies from Event Prompts for Video Anomaly Detection","created":"2024-03-02","cited_by_count":2,"area":null},{"id":"2410.21991","title":"A Lightweight Dual-Branch System for Weakly-Supervised Video Anomaly Detection on Consumer Edge Devices","created":"2024-10-29","cited_by_count":2,"area":null},{"id":"2503.18407","title":"VTD-CLIP: Video-to-Text Discretization via Prompting CLIP","created":"2025-03-24","cited_by_count":2,"area":"mllm"},{"id":"2505.06557","title":"Weakly Supervised Temporal Sentence Grounding via Positive Sample Mining","created":"2025-05-10","cited_by_count":2,"area":null},{"id":"2510.21532","title":"FrameShield: Adversarially Robust Video Anomaly Detection","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2511.00524","title":"Text-guided Fine-Grained Video Anomaly Understanding","created":"2025-11-01","cited_by_count":2,"area":null},{"id":"2603.04727","title":"Are Multimodal LLMs Ready for Surveillance? A Reality Check on Zero-Shot Anomaly Detection in the Wild","created":"2026-03-05","cited_by_count":2,"area":"mllm"},{"id":"2603.15237","title":"Multi-turn Physics-informed Vision-language Model for Physics-grounded Anomaly Detection","created":"2026-03-16","cited_by_count":2,"area":"lr"},{"id":"2605.08003","title":"SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2605.23116","title":"CoReVAD: A Contextual Reasoning Framework for Training-Free Video Anomaly Detection","created":"2026-05-22","cited_by_count":2,"area":"lr"},{"id":"2606.07669","title":"MemoVAD: Resource-Efficient Video Anomaly Detection via Dynamic Semantic Memory in Edge Computing Scenarios","created":"2026-06-04","cited_by_count":2,"area":null},{"id":"2607.20780","title":"Rethinking Open-World Video Anomaly Detection: Diagnosing Definition Blindness","created":"2026-07-22","cited_by_count":2,"area":null},{"id":"2608.11820","title":"TD-VAD: Breaking Visual Dependence in Video Anomaly Detection with Text-Driven Learning","created":"2026-08-12","cited_by_count":2,"area":null},{"id":"2310.05330","title":"A Lightweight Video Anomaly Detection Model with Weak Supervision and Adaptive Instance Selection","created":"2023-10-09","cited_by_count":1,"area":null},{"id":"2502.20861","title":"MESC-3D:Mining Effective Semantic Cues for 3D Reconstruction from a Single Image","created":"2025-02-28","cited_by_count":1,"area":null},{"id":"2504.21375","title":"Synergy-CLIP: Extending CLIP with Multi-modal Integration for Robust Representation Learning","created":"2025-04-30","cited_by_count":1,"area":null},{"id":"2505.02179","title":"ProDisc-VAD: An Efficient System for Weakly-Supervised Anomaly Detection in Video Surveillance Applications","created":"2025-05-04","cited_by_count":1,"area":null},{"id":"2505.02393","title":"Uncertainty-Weighted Fusion of Image and Synthetic Event for Video Anomaly Detection","created":"2025-05-05","cited_by_count":1,"area":null},{"id":"2508.00312","title":"GV-VAD : Exploring Video Generation for Weakly-Supervised Video Anomaly Detection","created":"2025-08-01","cited_by_count":1,"area":null},{"id":"2509.08232","title":"GTA-Crime: A Synthetic Dataset and Generation Framework for Fatal Violence Detection with Adversarial Snippet-Level Domain Adaptation","created":"2025-09-10","cited_by_count":1,"area":null},{"id":"2510.13630","title":"AVAR-Net: A Lightweight Audio-Visual Anomaly Recognition Framework with a Benchmark Dataset","created":"2025-10-15","cited_by_count":1,"area":null},{"id":"2510.21798","title":"An Evaluation of Hybrid Annotation Workflows on High-Ambiguity Spatiotemporal Video Footage","created":"2025-10-20","cited_by_count":1,"area":null},{"id":"2601.02927","title":"PrismVAU: Prompt-Refined Inference System for Multimodal Video Anomaly Understanding","created":"2026-01-06","cited_by_count":1,"area":null},{"id":"2602.07798","title":"CausalTAD: Injecting Causal Knowledge into Large Language Models for Tabular Anomaly Detection","created":"2026-02-08","cited_by_count":1,"area":null},{"id":"2602.10549","title":"Enhancing Weakly Supervised Multimodal Video Anomaly Detection through Text Guidance","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2602.18019","title":"DeepSVU: Towards In-depth Security-oriented Video Understanding via Unified Physical-world Regularized MoE","created":"2026-02-20","cited_by_count":1,"area":"moe"},{"id":"2603.17374","title":"Shot-Aware Frame Sampling for Video Understanding","created":"2026-03-18","cited_by_count":1,"area":"mllm"},{"id":"2603.24991","title":"Towards Video Anomaly Detection from Event Streams: A Baseline and Benchmark Datasets","created":"2026-03-26","cited_by_count":1,"area":null},{"id":"2604.03040","title":"QVAD: A Question-Centric Agentic Framework for Efficient and Training-Free Video Anomaly Detection","created":"2026-04-03","cited_by_count":1,"area":"agents"},{"id":"2604.07772","title":"ESOM: Efficiently Understanding Streaming Video Anomalies with Open-world Dynamic Definitions","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2605.15325","title":"COPRA: Conditional Parameter Adaptation with Reinforcement Learning for Video Anomaly Detection","created":"2026-05-14","cited_by_count":1,"area":"lr"},{"id":"2608.11985","title":"Auditing Frame-Level AUC in Weakly Supervised Video Anomaly Detection: Granularity, Resolution, and Scene Bias","created":"2026-08-12","cited_by_count":1,"area":null},{"id":"2608.21244","title":"A VLM Answer Is Not an Anomaly Score: Rank Compression Across Image and Video Anomaly Detection","created":"2026-08-21","cited_by_count":1,"area":null},{"id":"2608.31074","title":"Real-Time Video Anomaly Detection Using YOLO Pose Estimation and CLIP-Based Semantic Scoring","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2609.17211","title":"Probe-VAD: Ordinal Likelihood Probing for Training-Free Video Anomaly Detection","created":"2026-09-15","cited_by_count":1,"area":null},{"id":"2412.20201","title":"Injecting Explainability and Lightweight Design into Weakly Supervised Video Anomaly Detection Systems","created":"2024-12-28","cited_by_count":0,"area":null},{"id":"2501.06224","title":"Detection, Retrieval, and Explanation Unified: A Violence Detection System Based on Knowledge Graphs and GAT","created":"2025-01-07","cited_by_count":0,"area":null},{"id":"2504.18866","title":"PiercingEye: Dual-Space Video Violence Detection with Hyperbolic Vision-Language Guidance","created":"2025-04-26","cited_by_count":0,"area":null},{"id":"2507.20629","title":"DAMS:Dual-Branch Adaptive Multiscale Spatiotemporal Framework for Video Anomaly Detection","created":"2025-07-28","cited_by_count":0,"area":null},{"id":"2509.18571","title":"Live-E2T: Real-time Threat Monitoring in Video via Deduplicated Event Reasoning and Chain-of-Thought","created":"2025-09-23","cited_by_count":0,"area":"lr"},{"id":"2509.22544","title":"HyCoVAD: A Hybrid SSL-LLM Model for Complex Video Anomaly Detection","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2510.20268","title":"GMFVAD: Using Grained Multi-modal Feature to Improve Video Anomaly Detection","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2511.10958","title":"Text-guided Weakly Supervised Framework for Dynamic Facial Expression Recognition","created":"2025-11-14","cited_by_count":0,"area":null},{"id":"2511.20088","title":"Explainable Visual Anomaly Detection via Concept Bottleneck Models","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2512.06845","title":"PA-VAD: Diffusion-Based Pseudo-Only Video Anomaly Detection via Domain-Aligned Memory Updates","created":"2025-12-07","cited_by_count":0,"area":null},{"id":"2601.06204","title":"Cascading multi-agent anomaly detection in surveillance systems via vision-language models and embedding-based classification","created":"2026-01-08","cited_by_count":0,"area":"mllm"},{"id":"2602.17077","title":"Cross Pseudo Labeling For Weakly Supervised Video Anomaly Detection","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2604.04632","title":"InCTRLv2: Generalist Residual Models for Few-Shot Anomaly Detection and Segmentation","created":"2026-04-06","cited_by_count":0,"area":null},{"id":"2605.01512","title":"Two-Pass Zero-Shot Temporal-Spatial Grounding of Rare Traffic Events in Surveillance Video","created":"2026-05-02","cited_by_count":0,"area":null}],"next_cursor":"100"}