{"total":57,"rows":[{"id":"2502.07601","title":"Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Models","created":"2025-02-11","cited_by_count":54,"area":"lr"},{"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":"2503.04504","title":"AnyAnomaly: Zero-Shot Customizable Video Anomaly Detection with LVLM","created":"2025-03-06","cited_by_count":15,"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":"2409.00304","title":"StimuVAR: Spatiotemporal Stimuli-aware Video Affective Reasoning with Multimodal Large Language Models","created":"2024-08-31","cited_by_count":8,"area":"lr"},{"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":"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":"2508.06203","title":"AnomalyMoE: Towards a Language-free Generalist Model for Unified Visual Anomaly Detection","created":"2025-08-08","cited_by_count":8,"area":"moe"},{"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":"2603.11106","title":"RC-NF: Robot-Conditioned Normalizing Flow for Real-Time Anomaly Detection in Robotic Manipulation","created":"2026-03-11","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":"2408.14329","title":"Towards Adaptive Human-centric Video Anomaly Detection: A Comprehensive Framework and A New Benchmark","created":"2024-08-26","cited_by_count":6,"area":null},{"id":"2410.20621","title":"Egocentric and Exocentric Methods: A Short Survey","created":"2024-10-27","cited_by_count":6,"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":"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":"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":"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":"2409.03236","title":"Unveiling Context-Related Anomalies: Knowledge Graph Empowered Decoupling of Scene and Action for Human-Related Video Anomaly Detection","created":"2024-09-05","cited_by_count":3,"area":null},{"id":"2409.17608","title":"Appearance Blur-driven AutoEncoder and Motion-guided Memory Module for Video Anomaly Detection","created":"2024-09-26","cited_by_count":3,"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":"2603.04723","title":"From Offline to Periodic Adaptation for Pose-Based Shoplifting Detection in Real-world Retail Security","created":"2026-03-05","cited_by_count":3,"area":null},{"id":"2603.19098","title":"TAU-R1: Visual Language Model for Traffic Anomaly Understanding","created":"2026-03-19","cited_by_count":3,"area":"mllm"},{"id":"2503.10653","title":"Video Anomaly Detection with Structured Keywords","created":"2025-03-07","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":"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":"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":"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":"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":"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":"2504.05254","title":"Explaining Low Perception Model Competency with High-Competency Counterfactuals","created":"2025-04-07","cited_by_count":0,"area":null},{"id":"2509.05315","title":"Evaluation of Large Language Models for Anomaly Detection in Autonomous Vehicles","created":"2025-08-29","cited_by_count":0,"area":"driving"},{"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":"2605.15054","title":"LATERN: Test-Time Context-Aware Explainable Video Anomaly Detection","created":"2026-05-14","cited_by_count":0,"area":"lr"},{"id":"2606.20312","title":"Reliability-Aware Prototype Calibration for Frozen Pose-Flow Video Anomaly Detection","created":"2026-06-18","cited_by_count":0,"area":null},{"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":"2608.08219","title":"VTO: Visual Tool Orchestration for Video Anomaly Detection","created":"2026-08-08","cited_by_count":0,"area":"lr"},{"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":"2609.07455","title":"Parser-Free VLM Verification for Federated Weakly Supervised Video Anomaly Detection","created":"2026-09-07","cited_by_count":0,"area":"mllm"},{"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}