{"total":193,"rows":[{"id":"2101.10030","title":"Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning","created":"2021-01-25","cited_by_count":230,"area":null},{"id":"2104.01633","title":"MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection","created":"2021-04-04","cited_by_count":138,"area":null},{"id":"2203.03962","title":"Generative Cooperative Learning for Unsupervised Video Anomaly Detection","created":"2022-03-08","cited_by_count":102,"area":null},{"id":"2302.05160","title":"Dual Memory Units with Uncertainty Regulation for Weakly Supervised Video Anomaly Detection","created":"2023-02-10","cited_by_count":90,"area":null},{"id":"2211.15098","title":"MGFN: Magnitude-Contrastive Glance-and-Focus Network for Weakly-Supervised Video Anomaly Detection","created":"2022-11-28","cited_by_count":89,"area":null},{"id":"2404.01014","title":"Harnessing Large Language Models for Training-free Video Anomaly Detection","created":"2024-04-01","cited_by_count":87,"area":null},{"id":"2212.05136","title":"CLIP-TSA: CLIP-Assisted Temporal Self-Attention for Weakly-Supervised Video Anomaly Detection","created":"2022-12-09","cited_by_count":67,"area":null},{"id":"2303.12369","title":"Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detection","created":"2023-03-22","cited_by_count":64,"area":null},{"id":"2302.05087","title":"Generalized Video Anomaly Event Detection: Systematic Taxonomy and Comparison of Deep Models","created":"2023-02-10","cited_by_count":59,"area":null},{"id":"2311.07042","title":"Open-Vocabulary Video Anomaly Detection","created":"2023-11-13","cited_by_count":57,"area":null},{"id":"2401.06091","title":"A Closer Look at AUROC and AUPRC under Class Imbalance","created":"2024-01-11","cited_by_count":57,"area":null},{"id":"2304.05112","title":"Video Event Restoration Based on Keyframes for Video Anomaly Detection","created":"2023-04-11","cited_by_count":54,"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":"2405.16886","title":"Hawk: Learning to Understand Open-World Video Anomalies","created":"2024-05-27","cited_by_count":49,"area":null},{"id":"2212.04090","title":"Exploiting Completeness and Uncertainty of Pseudo Labels for Weakly Supervised Video Anomaly Detection","created":"2022-12-08","cited_by_count":47,"area":null},{"id":"2401.05702","title":"Video Anomaly Detection and Explanation via Large Language Models","created":"2024-01-11","cited_by_count":47,"area":null},{"id":"2306.14451","title":"Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detection","created":"2023-06-26","cited_by_count":43,"area":null},{"id":"2305.13611","title":"A New Comprehensive Benchmark for Semi-supervised Video Anomaly Detection and Anticipation","created":"2023-05-23","cited_by_count":42,"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":"2107.12059","title":"HANet: Hierarchical Alignment Networks for Video-Text Retrieval","created":"2021-07-26","cited_by_count":31,"area":null},{"id":"2207.10948","title":"Dynamic Local Aggregation Network with Adaptive Clusterer for Anomaly Detection","created":"2022-07-22","cited_by_count":27,"area":null},{"id":"2310.02835","title":"Delving into CLIP latent space for Video Anomaly Recognition","created":"2023-10-04","cited_by_count":27,"area":null},{"id":"2409.01980","title":"Large Language Models for Anomaly and Out-of-Distribution Detection: A Survey","created":"2024-09-03","cited_by_count":27,"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":"2208.11113","title":"Towards Open Set Video Anomaly Detection","created":"2022-08-23","cited_by_count":26,"area":null},{"id":"2211.00882","title":"DyAnNet: A Scene Dynamicity Guided Self-Trained Video Anomaly Detection Network","created":"2022-11-02","cited_by_count":26,"area":null},{"id":"2307.12545","title":"Towards Video Anomaly Retrieval from Video Anomaly Detection: New Benchmarks and Model","created":"2023-07-24","cited_by_count":25,"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":"2308.11072","title":"TeD-SPAD: Temporal Distinctiveness for Self-supervised Privacy-preservation for video Anomaly Detection","created":"2023-08-21","cited_by_count":23,"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":"2311.15367","title":"BatchNorm-based Weakly Supervised Video Anomaly Detection","created":"2023-11-26","cited_by_count":22,"area":null},{"id":"2405.10347","title":"Networking Systems for Video Anomaly Detection: A Tutorial and Survey","created":"2024-05-16","cited_by_count":21,"area":null},{"id":"2203.12121","title":"Contrastive Transformer-based Multiple Instance Learning for Weakly Supervised Polyp Frame Detection","created":"2022-03-23","cited_by_count":20,"area":null},{"id":"2308.12558","title":"Hyperbolic Audio-visual Zero-shot Learning","created":"2023-08-24","cited_by_count":19,"area":null},{"id":"2503.12905","title":"UCF-Crime-DVS: A Novel Event-Based Dataset for Video Anomaly Detection with Spiking Neural Networks","created":"2025-03-17","cited_by_count":19,"area":null},{"id":"2212.09258","title":"CHAD: Charlotte Anomaly Dataset","created":"2022-12-19","cited_by_count":18,"area":null},{"id":"2302.00058","title":"Graph Anomaly Detection in Time Series: A Survey","created":"2023-01-31","cited_by_count":18,"area":null},{"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":"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":"2404.00847","title":"Collaborative Learning of Anomalies with Privacy (CLAP) for Unsupervised Video Anomaly Detection: A New Baseline","created":"2024-04-01","cited_by_count":17,"area":null},{"id":"2309.16309","title":"Weakly-Supervised Video Anomaly Detection with Snippet Anomalous Attention","created":"2023-09-28","cited_by_count":15,"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":"2303.13505","title":"A Large-scale Study of Spatiotemporal Representation Learning with a New Benchmark on Action Recognition","created":"2023-03-23","cited_by_count":14,"area":null},{"id":"2406.18815","title":"MissionGNN: Hierarchical Multimodal GNN-based Weakly Supervised Video Anomaly Recognition with Mission-Specific Knowledge Graph Generation","created":"2024-06-27","cited_by_count":14,"area":null},{"id":"2412.13845","title":"Do Language Models Understand Time?","created":"2024-12-18","cited_by_count":14,"area":null},{"id":"2310.17650","title":"A Coarse-to-Fine Pseudo-Labeling (C2FPL) Framework for Unsupervised Video Anomaly Detection","created":"2023-10-26","cited_by_count":13,"area":null},{"id":"2503.18094","title":"Anomize: Better Open Vocabulary Video Anomaly Detection","created":"2025-03-23","cited_by_count":13,"area":null},{"id":"2506.05372","title":"DVD: A Comprehensive Dataset for Advancing Violence Detection in Real-World Scenarios","created":"2025-05-29","cited_by_count":13,"area":null},{"id":"2102.10590","title":"Efficient Two-Stream Network for Violence Detection Using Separable Convolutional LSTM","created":"2021-02-21","cited_by_count":12,"area":null},{"id":"2207.10664","title":"Exploring Fine-Grained Audiovisual Categorization with the SSW60 Dataset","created":"2022-07-21","cited_by_count":12,"area":null},{"id":"2305.18797","title":"Learning Weakly Supervised Audio-Visual Violence Detection in Hyperbolic Space","created":"2023-05-30","cited_by_count":12,"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":"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":"2208.05251","title":"Consistency-based Self-supervised Learning for Temporal Anomaly Localization","created":"2022-08-10","cited_by_count":10,"area":null},{"id":"2308.07050","title":"Survey on video anomaly detection in dynamic scenes with moving cameras","created":"2023-08-14","cited_by_count":10,"area":null},{"id":"2311.16514","title":"Video Anomaly Detection via Spatio-Temporal Pseudo-Anomaly Generation : A Unified Approach","created":"2023-11-27","cited_by_count":10,"area":null},{"id":"2407.08130","title":"Spiking Tucker Fusion Transformer for Audio-Visual Zero-Shot Learning","created":"2024-07-11","cited_by_count":10,"area":null},{"id":"2412.20455","title":"Cross-Modal Fusion and Attention Mechanism for Weakly Supervised Video Anomaly Detection","created":"2024-12-29","cited_by_count":10,"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":"2208.05636","title":"Locality-aware Attention Network with Discriminative Dynamics Learning for Weakly Supervised Anomaly Detection","created":"2022-08-11","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":"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":"2202.06503","title":"Adaptive Graph Convolutional Networks for Weakly Supervised Anomaly Detection in Videos","created":"2022-02-14","cited_by_count":7,"area":null},{"id":"2209.12074","title":"Self-supervised Learning for Unintentional Action Prediction","created":"2022-09-24","cited_by_count":7,"area":null},{"id":"2302.06670","title":"Unveiling the Unseen: A Comprehensive Survey on Explainable Anomaly Detection in Images and Videos","created":"2023-02-13","cited_by_count":7,"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":"2210.06688","title":"Overlooked Video Classification in Weakly Supervised Video Anomaly Detection","created":"2022-10-13","cited_by_count":6,"area":null},{"id":"2408.05191","title":"Cross-Domain Learning for Video Anomaly Detection with Limited Supervision","created":"2024-08-09","cited_by_count":6,"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":"2112.09172","title":"An Audio-Visual Dataset and Deep Learning Frameworks for Crowded Scene Classification","created":"2021-12-16","cited_by_count":5,"area":null},{"id":"2311.08151","title":"Rethink Cross-Modal Fusion in Weakly-Supervised Audio-Visual Video Parsing","created":"2023-11-14","cited_by_count":5,"area":null},{"id":"2401.13551","title":"Interleaving One-Class and Weakly-Supervised Models with Adaptive Thresholding for Unsupervised Video Anomaly Detection","created":"2024-01-24","cited_by_count":5,"area":null},{"id":"2409.00942","title":"VQ-Flow: Taming Normalizing Flows for Multi-Class Anomaly Detection via Hierarchical Vector Quantization","created":"2024-09-02","cited_by_count":5,"area":null},{"id":"2501.07496","title":"Aligning First, Then Fusing: A Novel Weakly Supervised Multimodal Violence Detection Method","created":"2025-01-13","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":"2106.05003","title":"Dual-Modality Vehicle Anomaly Detection via Bilateral Trajectory Tracing","created":"2021-06-09","cited_by_count":4,"area":null},{"id":"2207.13430","title":"Concept Drift Challenge in Multimedia Anomaly Detection: A Case Study with Facial Datasets","created":"2022-07-27","cited_by_count":4,"area":null},{"id":"2301.07923","title":"Human-Scene Network: A Novel Baseline with Self-rectifying Loss for Weakly supervised Video Anomaly Detection","created":"2023-01-19","cited_by_count":4,"area":null},{"id":"2309.09972","title":"Artificial Intelligence for Web 3.0: A Comprehensive Survey","created":"2023-08-17","cited_by_count":4,"area":null},{"id":"2404.01282","title":"LoSA: Long-Short-range Adapter for Scaling End-to-End Temporal Action Localization","created":"2024-04-01","cited_by_count":4,"area":null},{"id":"2410.22623","title":"PV-VTT: A Privacy-Centric Dataset for Mission-Specific Anomaly Detection and Natural Language Interpretation","created":"2024-10-30","cited_by_count":4,"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":"2509.20851","title":"Poisoning Prompt-Guided Sampling in Video Large Language Models","created":"2025-09-25","cited_by_count":4,"area":null},{"id":"2511.00613","title":"CueBench: Advancing Unified Understanding of Context-Aware Video Anomalies in Real-World","created":"2025-11-01","cited_by_count":4,"area":null},{"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":"2511.13204","title":"RefineVAD: Semantic-Guided Feature Recalibration for Weakly Supervised Video Anomaly Detection","created":"2025-11-17","cited_by_count":4,"area":null},{"id":"2512.17601","title":"HeadHunt-VAD: Hunting Robust Anomaly-Sensitive Heads in MLLM for Tuning-Free Video Anomaly Detection","created":"2025-12-19","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":"2310.02894","title":"Human-centric Behavior Description in Videos: New Benchmark and Model","created":"2023-10-04","cited_by_count":3,"area":null},{"id":"2405.05130","title":"Multi-scale Bottleneck Transformer for Weakly Supervised Multimodal Violence Detection","created":"2024-05-08","cited_by_count":3,"area":null}],"next_cursor":"100"}