{"total":577,"rows":[{"id":"2104.04015","title":"CutPaste: Self-Supervised Learning for Anomaly Detection and Localization","created":"2021-04-08","cited_by_count":531,"area":null},{"id":"2406.04264","title":"MLVU: Benchmarking Multi-task Long Video Understanding","created":"2024-06-06","cited_by_count":292,"area":null},{"id":"2203.14712","title":"Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities","created":"2022-03-28","cited_by_count":287,"area":null},{"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":"2310.10647","title":"A Survey on Video Diffusion Models","created":"2023-10-16","cited_by_count":206,"area":"diffusion"},{"id":"2112.09045","title":"The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localization","created":"2021-12-16","cited_by_count":178,"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":"2108.06852","title":"A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Prediction","created":"2021-08-16","cited_by_count":129,"area":null},{"id":"2308.11681","title":"VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detection","created":"2023-08-22","cited_by_count":123,"area":"mllm"},{"id":"2111.09099","title":"Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection","created":"2021-11-17","cited_by_count":119,"area":null},{"id":"2406.09418","title":"VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding","created":"2024-06-13","cited_by_count":115,"area":"mllm"},{"id":"2311.16103","title":"Video-Bench: A Comprehensive Benchmark and Toolkit for Evaluating Video-based Large Language Models","created":"2023-11-27","cited_by_count":107,"area":null},{"id":"2203.14506","title":"Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detection","created":"2022-03-28","cited_by_count":104,"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":"2107.03055","title":"Blind Image Super-Resolution: A Survey and Beyond","created":"2021-07-07","cited_by_count":93,"area":null},{"id":"2111.08644","title":"UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detection","created":"2021-11-16","cited_by_count":93,"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":"2111.12264","title":"Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenes","created":"2021-11-24","cited_by_count":83,"area":null},{"id":"2203.00259","title":"Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detection","created":"2022-03-01","cited_by_count":80,"area":null},{"id":"2104.06689","title":"Learning Normal Dynamics in Videos with Meta Prototype Network","created":"2021-04-14","cited_by_count":71,"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":"2108.00462","title":"Explainable Deep Few-shot Anomaly Detection with Deviation Networks","created":"2021-08-01","cited_by_count":69,"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":"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":"2109.02973","title":"Unpaired Deep Image Deraining Using Dual Contrastive Learning","created":"2021-09-07","cited_by_count":60,"area":null},{"id":"2211.10946","title":"Normalizing Flows for Human Pose Anomaly Detection","created":"2022-11-20","cited_by_count":60,"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":"2105.13353","title":"Unsupervised Action Segmentation by Joint Representation Learning and Online Clustering","created":"2021-05-27","cited_by_count":49,"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":"2103.17260","title":"Learning by Aligning Videos in Time","created":"2021-03-31","cited_by_count":48,"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":"2207.08003","title":"SSMTL++: Revisiting Self-Supervised Multi-Task Learning for Video Anomaly Detection","created":"2022-07-16","cited_by_count":45,"area":"distill"},{"id":"2104.07268","title":"Weakly Supervised Video Anomaly Detection via Center-guided Discriminative Learning","created":"2021-04-15","cited_by_count":44,"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":"2307.07205","title":"Multimodal Motion Conditioned Diffusion Model for Skeleton-based Video Anomaly Detection","created":"2023-07-14","cited_by_count":42,"area":"diffusion"},{"id":"2309.13925","title":"Towards Surveillance Video-and-Language Understanding: New Dataset, Baselines, and Challenges","created":"2023-09-25","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":"2303.13051","title":"Hierarchical Semantic Contrast for Scene-aware Video Anomaly Detection","created":"2023-03-23","cited_by_count":39,"area":null},{"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":"2306.12041","title":"Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectors","created":"2023-06-21","cited_by_count":37,"area":null},{"id":"2404.09654","title":"Do LLMs Understand Visual Anomalies? Uncovering LLM's Capabilities in Zero-shot Anomaly Detection","created":"2024-04-15","cited_by_count":36,"area":"mllm"},{"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":"2107.12589","title":"Cross-modal Consensus Network for Weakly Supervised Temporal Action Localization","created":"2021-07-27","cited_by_count":34,"area":null},{"id":"2209.12148","title":"Self-Supervised Masked Convolutional Transformer Block for Anomaly Detection","created":"2022-09-25","cited_by_count":34,"area":null},{"id":"2310.03535","title":"Towards Unified Deep Image Deraining: A Survey and A New Benchmark","created":"2023-10-05","cited_by_count":34,"area":null},{"id":"2108.03825","title":"Weakly-Supervised Spatio-Temporal Anomaly Detection in Surveillance Video","created":"2021-08-09","cited_by_count":32,"area":null},{"id":"2110.00111","title":"Deep Learning-based Action Detection in Untrimmed Videos: A Survey","created":"2021-09-30","cited_by_count":32,"area":null},{"id":"2110.04538","title":"Focus Your Distribution: Coarse-to-Fine Non-Contrastive Learning for Anomaly Detection and Localization","created":"2021-10-09","cited_by_count":32,"area":null},{"id":"2107.13720","title":"Convolutional Transformer based Dual Discriminator Generative Adversarial Networks for Video Anomaly Detection","created":"2021-07-29","cited_by_count":31,"area":null},{"id":"2110.09742","title":"Learning Not to Reconstruct Anomalies","created":"2021-10-19","cited_by_count":31,"area":null},{"id":"2308.15985","title":"Vision-Based Traffic Accident Detection and Anticipation: A Survey","created":"2023-08-30","cited_by_count":31,"area":null},{"id":"2401.03717","title":"Universal Time-Series Representation Learning: A Survey","created":"2024-01-08","cited_by_count":30,"area":null},{"id":"2203.10808","title":"AnoViT: Unsupervised Anomaly Detection and Localization with Vision Transformer-based Encoder-Decoder","created":"2022-03-21","cited_by_count":29,"area":null},{"id":"2403.13349","title":"Hierarchical Gaussian Mixture Normalizing Flow Modeling for Unified Anomaly Detection","created":"2024-03-20","cited_by_count":28,"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":"2507.09313","title":"ProactiveVideoQA: A Comprehensive Benchmark Evaluating Proactive Interactions in Video Large Language Models","created":"2025-07-12","cited_by_count":27,"area":null},{"id":"2108.06524","title":"Foreground-Action Consistency Network for Weakly Supervised Temporal Action Localization","created":"2021-08-14","cited_by_count":26,"area":null},{"id":"2110.09768","title":"Synthetic Temporal Anomaly Guided End-to-End Video Anomaly Detection","created":"2021-10-19","cited_by_count":26,"area":null},{"id":"2207.05500","title":"Modality-Aware Contrastive Instance Learning with Self-Distillation for Weakly-Supervised Audio-Visual Violence Detection","created":"2022-07-12","cited_by_count":26,"area":"distill"},{"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":"2103.16024","title":"Augmented Transformer with Adaptive Graph for Temporal Action Proposal Generation","created":"2021-03-30","cited_by_count":25,"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":"2308.15300","title":"MSFlow: Multi-Scale Flow-based Framework for Unsupervised Anomaly Detection","created":"2023-08-29","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":"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":"2203.12840","title":"Bayesian Nonparametric Submodular Video Partition for Robust Anomaly Detection","created":"2022-03-24","cited_by_count":23,"area":null},{"id":"2207.10785","title":"Inductive and Transductive Few-Shot Video Classification via Appearance and Temporal Alignments","created":"2022-07-21","cited_by_count":23,"area":null},{"id":"2304.05841","title":"Exploring Diffusion Models for Unsupervised Video Anomaly Detection","created":"2023-04-12","cited_by_count":23,"area":"diffusion"},{"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":"2112.03649","title":"Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detection","created":"2021-12-07","cited_by_count":22,"area":null},{"id":"2302.04549","title":"Weakly Supervised Anomaly Detection: A Survey","created":"2023-02-09","cited_by_count":22,"area":null},{"id":"2311.15367","title":"BatchNorm-based Weakly Supervised Video Anomaly Detection","created":"2023-11-26","cited_by_count":22,"area":null},{"id":"2403.14497","title":"MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detection","created":"2024-03-21","cited_by_count":22,"area":null},{"id":"2108.01975","title":"Deep Anomaly Discovery From Unlabeled Videos via Normality Advantage and Self-Paced Refinement","created":"2021-08-04","cited_by_count":21,"area":null},{"id":"2303.15167","title":"Prompt-Guided Zero-Shot Anomaly Action Recognition using Pretrained Deep Skeleton Features","created":"2023-03-27","cited_by_count":21,"area":null},{"id":"2307.04956","title":"PKU-GoodsAD: A Supermarket Goods Dataset for Unsupervised Anomaly Detection and Segmentation","created":"2023-07-11","cited_by_count":21,"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":"2112.04771","title":"Progressive Attention on Multi-Level Dense Difference Maps for Generic Event Boundary Detection","created":"2021-12-09","cited_by_count":20,"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":"2206.04149","title":"A Survey of Graph-based Deep Learning for Anomaly Detection in Distributed Systems","created":"2022-06-08","cited_by_count":20,"area":null},{"id":"2209.12386","title":"TAD: A Large-Scale Benchmark for Traffic Accidents Detection from Video Surveillance","created":"2022-09-26","cited_by_count":20,"area":null},{"id":"2212.07010","title":"Cross-Domain Video Anomaly Detection without Target Domain Adaptation","created":"2022-12-14","cited_by_count":20,"area":null},{"id":"2403.11083","title":"Customizing Visual-Language Foundation Models for Multi-modal Anomaly Detection and Reasoning","created":"2024-03-17","cited_by_count":20,"area":null},{"id":"2406.10326","title":"VANE-Bench: Video Anomaly Evaluation Benchmark for Conversational LMMs","created":"2024-06-14","cited_by_count":20,"area":null},{"id":"2104.02967","title":"ACM-Net: Action Context Modeling Network for Weakly-Supervised Temporal Action Localization","created":"2021-04-07","cited_by_count":19,"area":null},{"id":"2203.09338","title":"Object Localization under Single Coarse Point Supervision","created":"2022-03-17","cited_by_count":19,"area":null},{"id":"2307.01533","title":"Unsupervised Video Anomaly Detection with Diffusion Models Conditioned on Compact Motion Representations","created":"2023-07-04","cited_by_count":19,"area":"diffusion"},{"id":"2406.15395","title":"An Exploratory Study on Human-Centric Video Anomaly Detection through Variational Autoencoders and Trajectory Prediction","created":"2024-04-29","cited_by_count":19,"area":null}],"next_cursor":"100"}