{"total":87,"rows":[{"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":"2412.06878","title":"SafeWatch: An Efficient Safety-Policy Following Video Guardrail Model with Transparent Explanations","created":"2024-12-09","cited_by_count":38,"area":"safety"},{"id":"2407.21794","title":"Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Survey","created":"2024-07-31","cited_by_count":36,"area":"mllm"},{"id":"2501.02765","title":"Visual Large Language Models for Generalized and Specialized Applications","created":"2025-01-06","cited_by_count":36,"area":"mllm"},{"id":"2409.05383","title":"Deep Learning for Video Anomaly Detection: A Review","created":"2024-09-09","cited_by_count":27,"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":"2509.26386","title":"PANDA: Towards Generalist Video Anomaly Detection via Agentic AI Engineer","created":"2025-09-30","cited_by_count":19,"area":"agents"},{"id":"2510.22693","title":"VADTree: Explainable Training-Free Video Anomaly Detection via Hierarchical Granularity-Aware Tree","created":"2025-10-26","cited_by_count":18,"area":null},{"id":"2504.11199","title":"Video Summarization with Large Language Models","created":"2025-04-15","cited_by_count":16,"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":"2510.21449","title":"MoniTor: Exploiting Large Language Models with Instruction for Online Video Anomaly Detection","created":"2025-10-24","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":"2412.07183","title":"Exploring What Why and How: A Multifaceted Benchmark for Causation Understanding of Video Anomaly","created":"2024-12-10","cited_by_count":9,"area":null},{"id":"2507.17394","title":"HiProbe-VAD: Video Anomaly Detection via Hidden States Probing in Tuning-Free Multimodal LLMs","created":"2025-07-23","cited_by_count":9,"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":"2507.15905","title":"Foundation Models and Transformers for Anomaly Detection: A Survey","created":"2025-07-21","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":"2504.04495","title":"AVadCLIP: Audio-Visual Collaboration for Robust Video Anomaly Detection","created":"2025-04-06","cited_by_count":7,"area":null},{"id":"2507.20163","title":"Player-Centric Multimodal Prompt Generation for Large Language Model Based Identity-Aware Basketball Video Captioning","created":"2025-07-27","cited_by_count":7,"area":null},{"id":"2505.21962","title":"A2Seek: Towards Reasoning-Centric Benchmark for Aerial Anomaly Understanding","created":"2025-05-28","cited_by_count":5,"area":"lr"},{"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":"2506.12992","title":"SmartHome-Bench: A Comprehensive Benchmark for Video Anomaly Detection in Smart Homes Using Multi-Modal Large Language Models","created":"2025-06-15","cited_by_count":4,"area":null},{"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":"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":"2511.07299","title":"VADER: Towards Causal Video Anomaly Understanding with Relation-Aware Large Language Models","created":"2025-11-10","cited_by_count":4,"area":null},{"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":"2502.06911","title":"Foundation Models for Anomaly Detection: Vision and Challenges","created":"2025-02-10","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":"2510.23190","title":"Evaluation of Vision-LLMs in Surveillance Video","created":"2025-10-27","cited_by_count":3,"area":null},{"id":"2511.08173","title":"VLMDiff: Leveraging Vision-Language Models for Multi-Class Anomaly Detection with Diffusion","created":"2025-11-11","cited_by_count":3,"area":"mllm"},{"id":"2603.19098","title":"TAU-R1: Visual Language Model for Traffic Anomaly Understanding","created":"2026-03-19","cited_by_count":3,"area":"mllm"},{"id":"2405.02068","title":"Advancing Pre-trained Teacher: Towards Robust Feature Discrepancy for Anomaly Detection","created":"2024-05-03","cited_by_count":2,"area":"distill"},{"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":"2603.15237","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":"2606.21579","title":"The Unreasonable Effectiveness of VLMs for Zero-shot Procedural Mistake Detection","created":"2026-06-19","cited_by_count":2,"area":"lr"},{"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":"2503.18507","title":"Can Text-to-Video Generation help Video-Language Alignment?","created":"2025-03-24","cited_by_count":1,"area":null},{"id":"2509.11058","title":"Action Hints: Semantic Typicality and Context Uniqueness for Generalizable Skeleton-based Video Anomaly Detection","created":"2025-09-14","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":"2511.00580","title":"TRACES: Temporal Recall with Contextual Embeddings for Real-Time Video Anomaly Detection","created":"2025-11-01","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":"2603.13306","title":"Benchmarking Compact VLMs for Clip-Level Surveillance Anomaly Detection Under Weak Supervision","created":"2026-03-03","cited_by_count":1,"area":null},{"id":"2603.22872","title":"ForeSea: AI Forensic Search with Multi-modal Queries for Video Surveillance","created":"2026-03-24","cited_by_count":1,"area":null},{"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":"2604.03819","title":"ActivityForensics: A Comprehensive Benchmark for Localizing Manipulated Activity in Videos","created":"2026-04-04","cited_by_count":1,"area":null},{"id":"2605.12725","title":"Is Video Anomaly Detection Misframed? Evidence from LLM-Based and Multi-Scene Models","created":"2026-05-12","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":"2608.21244","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":"2609.34180","title":"Decision Readouts for Text-Mediated Video Anomaly Detection: An Exploratory Evaluation of Jev and Qwen","created":"2026-09-28","cited_by_count":1,"area":null},{"id":"2504.05254","title":"Explaining Low Perception Model Competency with High-Competency Counterfactuals","created":"2025-04-07","cited_by_count":0,"area":null},{"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":"2602.01004","title":"SRVAU-R1: Enhancing Video Anomaly Understanding via Reflection-Aware Learning","created":"2026-02-01","cited_by_count":0,"area":"lr"},{"id":"2602.09637","title":"Towards Training-free Multimodal Hate Localisation with Large Language Models","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2603.13374","title":"Geometry-Aware Semantic Reasoning for Training Free Video Anomaly Detection","created":"2026-03-10","cited_by_count":0,"area":"lr"},{"id":"2603.25467","title":"GridVAD: Open-Set Video Anomaly Detection via Spatial Reasoning over Stratified Frame Grids","created":"2026-03-26","cited_by_count":0,"area":"lr"},{"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},{"id":"2605.15054","title":"LATERN: Test-Time Context-Aware Explainable Video Anomaly Detection","created":"2026-05-14","cited_by_count":0,"area":"lr"},{"id":"2605.25806","title":"An Analysis Focused on Womens Safety: Can VAD Models Be Enhanced by a Multi-modal Dataset?","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2605.31196","title":"Probing Collision Grounding in Vision-Language Models for Safe Human-Robot Collaboration","created":"2026-05-29","cited_by_count":0,"area":"mllm"},{"id":"2606.31875","title":"SENSE-VAD: Sentient and Semantic Video Anomaly Detection for Autonomous Driving","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.10598","title":"Anomalous Frame Detection by Grouping Frame Similarities between Two Videos Computed by Vision-Language Model to Extract Expert Workers' Unique Actions","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2607.13239","title":"Cost-Optimal Foundation Model Deployment Portfolio for Transportation Management","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2608.08867","title":"Zero-Shot Traffic Accident Detection via a Coarse-to-Fine VLM-Tracking Pipeline","created":"2026-08-09","cited_by_count":0,"area":null},{"id":"2608.21854","title":"Look Inside Each Video: Rethinking How Video Anomaly Detection Is Evaluated","created":"2026-08-22","cited_by_count":0,"area":null},{"id":"2608.25935","title":"TAU-Agent: An Agentic Retrieval-Augmented Framework for Traffic Anomaly Understanding","created":"2026-08-26","cited_by_count":0,"area":"rag"},{"id":"2609.06360","title":"NOVA: Normal-Side Modeling for Training-Free Zero-Shot Video Anomaly Detection","created":"2026-09-06","cited_by_count":0,"area":"mllm"},{"id":"2609.07455","title":"Parser-Free VLM Verification for Federated Weakly Supervised Video Anomaly Detection","created":"2026-09-07","cited_by_count":0,"area":"mllm"},{"id":"2609.07941","title":"ReactVAU: A Slow-Fast Decoupled Framework for Streaming Video Anomaly Understanding","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.17843","title":"RoboVAD: A Large Cross-Domain Evaluation Benchmark for Anomaly Detection in Robotic Arm Manipulation Videos","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.18836","title":"Copy What Is Seen, Generate What Is Not: Training-Free Anomaly-Aware Video Restoration","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2610.01754","title":"Cog-VADU: A Training-Free Cognitive Reasoning Framework for Video Anomaly Detection and Understanding","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.16299","title":"Learning Temporal Evidence Selection for Video Anomaly Understanding","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.16324","title":"Anomaly-Guided Observation and Two-Level Semantic Feedback for Training-Free Video Anomaly Analysis","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}