{"url":"/task/video-anomaly-detection","name":"Video Anomaly Detection","slug":"video-anomaly-detection","description_markdown":null,"categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":262,"papers_with_code":111,"benchmarks":14,"benchmark_tables_in_archive":15,"benchmark_tables_shown":15,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":17,"subtasks":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/video-anomaly-detection-on-hr-shanghaitech","slug":"video-anomaly-detection-on-hr-shanghaitech","dataset":"HR-ShanghaiTech","dataset_url":"/dataset/hr-shanghaitech","rows_in_archive":14,"metrics":["AUC"],"first_row_in_archive_order":{"model":"PoseWatch-H","paper_title":"PoseWatch: A Transformer-based Architecture for Human-centric Video Anomaly Detection Using Spatio-temporal Pose Tokenization","paper_url":"/paper/posewatch-a-transformer-based-architecture","paper_date":"2024-08-27","arxiv_id":"2408.15185","code_links":[{"title":"TeCSAR-UNCC/SPARTA","url":"https://github.com/TeCSAR-UNCC/SPARTA"}],"syntology":null}},{"leaderboard":"/sota/video-anomaly-detection-on-hr-avenue","slug":"video-anomaly-detection-on-hr-avenue","dataset":"HR-Avenue","dataset_url":"/dataset/hr-avenue","rows_in_archive":11,"metrics":["AUC"],"first_row_in_archive_order":{"model":"TrajREC","paper_title":"Holistic Representation Learning for Multitask Trajectory Anomaly Detection","paper_url":"/paper/holistic-representation-learning-for","paper_date":"2023-11-03","arxiv_id":"2311.01851","code_links":[{"title":"alexandrosstergiou/TrajREC","url":"https://github.com/alexandrosstergiou/TrajREC"}],"syntology":null}},{"leaderboard":"/sota/video-anomaly-detection-on-hr-ubnormal","slug":"video-anomaly-detection-on-hr-ubnormal","dataset":"HR-UBnormal","dataset_url":"/dataset/hr-ubnormal","rows_in_archive":8,"metrics":["AUC"],"first_row_in_archive_order":{"model":"MoCoDAD","paper_title":"Multimodal Motion Conditioned Diffusion Model for Skeleton-based Video Anomaly Detection","paper_url":"/paper/multimodal-motion-conditioned-diffusion-model","paper_date":"2023-07-14","arxiv_id":"2307.07205","code_links":[{"title":"aleflabo/MoCoDAD","url":"https://github.com/aleflabo/MoCoDAD"}],"syntology":{"n":8,"n_ran":6,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/video-anomaly-detection-on-cuhk-avenue","slug":"video-anomaly-detection-on-cuhk-avenue","dataset":"CUHK Avenue","dataset_url":"/dataset/chuk-avenue","rows_in_archive":7,"metrics":["AUC","RBDC","TBDC"],"first_row_in_archive_order":{"model":"VideoPatchCore","paper_title":"VideoPatchCore: An Effective Method to Memorize Normality for Video Anomaly Detection","paper_url":"/paper/videopatchcore-an-effective-method-to","paper_date":"2024-09-24","arxiv_id":"2409.16225","code_links":[{"title":"SkiddieAhn/Paper-VideoPatchCore","url":"https://github.com/SkiddieAhn/Paper-VideoPatchCore"}],"syntology":null}},{"leaderboard":"/sota/video-anomaly-detection-on-shanghaitech-4","slug":"video-anomaly-detection-on-shanghaitech-4","dataset":"ShanghaiTech","dataset_url":"/dataset/shanghaitech","rows_in_archive":7,"metrics":["AUC","RBDC","TBDC"],"first_row_in_archive_order":{"model":"MULDE-object-centric-micro","paper_title":"MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detection","paper_url":"/paper/mulde-multiscale-log-density-estimation-via","paper_date":"2024-03-21","arxiv_id":"2403.14497","code_links":[{"title":"jakubmicorek/MULDE-Multiscale-Log-Density-Estimation-via-Denoising-Score-Matching-for-Video-Anomaly-Detection","url":"https://github.com/jakubmicorek/MULDE-Multiscale-Log-Density-Estimation-via-Denoising-Score-Matching-for-Video-Anomaly-Detection"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}}},{"leaderboard":"/sota/video-anomaly-detection-on-shanghaitech","slug":"video-anomaly-detection-on-shanghaitech","dataset":"ShanghaiTech Campus","dataset_url":"/dataset/shanghaitech-campus","rows_in_archive":4,"metrics":["AUC"],"first_row_in_archive_order":{"model":"PoseWatch-H","paper_title":"PoseWatch: A Transformer-based Architecture for Human-centric Video Anomaly Detection Using Spatio-temporal Pose Tokenization","paper_url":"/paper/posewatch-a-transformer-based-architecture","paper_date":"2024-08-27","arxiv_id":"2408.15185","code_links":[{"title":"TeCSAR-UNCC/SPARTA","url":"https://github.com/TeCSAR-UNCC/SPARTA"}],"syntology":null}},{"leaderboard":"/sota/video-anomaly-detection-on-ubnormal","slug":"video-anomaly-detection-on-ubnormal","dataset":"UBnormal","dataset_url":"/dataset/ubnormal","rows_in_archive":4,"metrics":["AUC"],"first_row_in_archive_order":{"model":"AnyAnomaly","paper_title":"AnyAnomaly: Zero-Shot Customizable Video Anomaly Detection with LVLM","paper_url":"/paper/anyanomaly-zero-shot-customizable-video-1","paper_date":"2025-03-06","arxiv_id":"2503.04504","code_links":[{"title":"SkiddieAhn/Paper-AnyAnomaly","url":"https://github.com/SkiddieAhn/Paper-AnyAnomaly"}],"syntology":null}},{"leaderboard":"/sota/video-anomaly-detection-on-ucsd-ped2-1","slug":"video-anomaly-detection-on-ucsd-ped2-1","dataset":"UCSD Ped2","dataset_url":"/dataset/ucsd","rows_in_archive":3,"metrics":["AUC"],"first_row_in_archive_order":{"model":"MULDE-object-centric-micro","paper_title":"MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detection","paper_url":"/paper/mulde-multiscale-log-density-estimation-via","paper_date":"2024-03-21","arxiv_id":"2403.14497","code_links":[{"title":"jakubmicorek/MULDE-Multiscale-Log-Density-Estimation-via-Denoising-Score-Matching-for-Video-Anomaly-Detection","url":"https://github.com/jakubmicorek/MULDE-Multiscale-Log-Density-Estimation-via-Denoising-Score-Matching-for-Video-Anomaly-Detection"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}}},{"leaderboard":"/sota/video-anomaly-detection-on-chad","slug":"video-anomaly-detection-on-chad","dataset":"CHAD","dataset_url":"/dataset/chad","rows_in_archive":1,"metrics":["AUC"],"first_row_in_archive_order":{"model":"PoseWatch-H","paper_title":"PoseWatch: A Transformer-based Architecture for Human-centric Video Anomaly Detection Using Spatio-temporal Pose Tokenization","paper_url":"/paper/posewatch-a-transformer-based-architecture","paper_date":"2024-08-27","arxiv_id":"2408.15185","code_links":[{"title":"TeCSAR-UNCC/SPARTA","url":"https://github.com/TeCSAR-UNCC/SPARTA"}],"syntology":null}},{"leaderboard":"/sota/video-anomaly-detection-on-chuk-avenue","slug":"video-anomaly-detection-on-chuk-avenue","dataset":"CHUK Avenue","dataset_url":null,"rows_in_archive":1,"metrics":["AUC"],"first_row_in_archive_order":{"model":"MULDE-object-centric-micro","paper_title":"MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detection","paper_url":"/paper/mulde-multiscale-log-density-estimation-via","paper_date":"2024-03-21","arxiv_id":"2403.14497","code_links":[{"title":"jakubmicorek/MULDE-Multiscale-Log-Density-Estimation-via-Denoising-Score-Matching-for-Video-Anomaly-Detection","url":"https://github.com/jakubmicorek/MULDE-Multiscale-Log-Density-Estimation-via-Denoising-Score-Matching-for-Video-Anomaly-Detection"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}}},{"leaderboard":"/sota/video-anomaly-detection-on-iitb-corridor-1","slug":"video-anomaly-detection-on-iitb-corridor-1","dataset":"IITB Corridor","dataset_url":"/dataset/iitb-corridor","rows_in_archive":1,"metrics":["AUC"],"first_row_in_archive_order":{"model":"VideoPatchCore","paper_title":"VideoPatchCore: An Effective Method to Memorize Normality for Video Anomaly Detection","paper_url":"/paper/videopatchcore-an-effective-method-to","paper_date":"2024-09-24","arxiv_id":"2409.16225","code_links":[{"title":"SkiddieAhn/Paper-VideoPatchCore","url":"https://github.com/SkiddieAhn/Paper-VideoPatchCore"}],"syntology":null}},{"leaderboard":"/sota/video-anomaly-detection-on-ped2","slug":"video-anomaly-detection-on-ped2","dataset":"Ped2","dataset_url":null,"rows_in_archive":1,"metrics":["AUC"],"first_row_in_archive_order":{"model":"HF2-VAD","paper_title":"A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Prediction","paper_url":"/paper/a-hybrid-video-anomaly-detection-framework","paper_date":"2021-08-16","arxiv_id":"2108.06852","code_links":[{"title":"LiUzHiAn/hf2vad","url":"https://github.com/LiUzHiAn/hf2vad"}],"syntology":{"n":11,"n_ran":0,"n_unverified":11,"n_pointer_only":0}}},{"leaderboard":"/sota/video-anomaly-detection-on-street-scene","slug":"video-anomaly-detection-on-street-scene","dataset":"Street Scene","dataset_url":"/dataset/street-scene","rows_in_archive":1,"metrics":["AUC","RBDC","TBDC"],"first_row_in_archive_order":{"model":"PGM","paper_title":"Bounding Boxes and Probabilistic Graphical Models: Video Anomaly Detection Simplified","paper_url":"/paper/bounding-boxes-and-probabilistic-graphical","paper_date":"2024-07-08","arxiv_id":"2407.06000","code_links":[{"title":"milestonesys-research/vad-with-pgms","url":"https://github.com/milestonesys-research/vad-with-pgms"}],"syntology":null}},{"leaderboard":"/sota/video-anomaly-detection-on-ucf-crime-2","slug":"video-anomaly-detection-on-ucf-crime-2","dataset":"UCF-Crime","dataset_url":"/dataset/ucf-crime","rows_in_archive":1,"metrics":["AUC"],"first_row_in_archive_order":{"model":"MULDE-frame-centric-micro-one-class-classification","paper_title":"MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detection","paper_url":"/paper/mulde-multiscale-log-density-estimation-via","paper_date":"2024-03-21","arxiv_id":"2403.14497","code_links":[{"title":"jakubmicorek/MULDE-Multiscale-Log-Density-Estimation-via-Denoising-Score-Matching-for-Video-Anomaly-Detection","url":"https://github.com/jakubmicorek/MULDE-Multiscale-Log-Density-Estimation-via-Denoising-Score-Matching-for-Video-Anomaly-Detection"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}}},{"leaderboard":null,"slug":"video-anomaly-detection-on-xd-violence-1","dataset":"XD-Violence","dataset_url":"/dataset/xd-violence","rows_in_archive":0,"metrics":["Average Precision (%)"],"first_row_in_archive_order":null}],"datasets":[{"url":"/dataset/shanghaitech","name":"ShanghaiTech","full_name":"","num_papers_in_archive":277},{"url":"/dataset/shanghaitech-campus","name":"ShanghaiTech Campus","full_name":"","num_papers_in_archive":207},{"url":"/dataset/ucf-crime","name":"UCF-Crime","full_name":"","num_papers_in_archive":142},{"url":"/dataset/ucsd","name":"UCSD Ped2","full_name":"UCSD Anomaly Detection Dataset","num_papers_in_archive":92},{"url":"/dataset/xd-violence","name":"XD-Violence","full_name":"","num_papers_in_archive":58},{"url":"/dataset/chuk-avenue","name":"CUHK Avenue","full_name":"","num_papers_in_archive":48},{"url":"/dataset/ubnormal","name":"UBnormal","full_name":"University of Bucharest Abnormal Videos","num_papers_in_archive":47},{"url":"/dataset/street-scene","name":"Street Scene","full_name":"","num_papers_in_archive":26},{"url":"/dataset/goodsad","name":"GoodsAD","full_name":"","num_papers_in_archive":15},{"url":"/dataset/hr-shanghaitech","name":"HR-ShanghaiTech","full_name":"","num_papers_in_archive":14},{"url":"/dataset/aebad","name":"AeBAD","full_name":"Aero-engine Blade Anomaly Detection Dataset","num_papers_in_archive":11},{"url":"/dataset/hr-avenue","name":"HR-Avenue","full_name":"","num_papers_in_archive":11},{"url":"/dataset/chad","name":"CHAD","full_name":"Charlotte Anomaly Dataset","num_papers_in_archive":7},{"url":"/dataset/hr-ubnormal","name":"HR-UBnormal","full_name":"","num_papers_in_archive":7},{"url":"/dataset/iitb-corridor","name":"IITB Corridor","full_name":"","num_papers_in_archive":5},{"url":"/dataset/hawk-annotation-dataset","name":"Hawk Annotation Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/camnuvem-dataset","name":"CamNuvem Dataset","full_name":"CamNuvem: A Robbery Dataset for Video Anomaly Detection","num_papers_in_archive":0}],"subtasks":[{"url":"/task/weakly-supervised-video-anomaly-detection","name":"Weakly-supervised Video Anomaly Detection"}],"parent_tasks":[{"url":"/task/3d-anomaly-detection","name":"3D Anomaly Detection"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":111,"tagged_in_all":262,"items":[{"url":"/paper/adversarially-learned-one-class-classifier","title":"Adversarially Learned One-Class Classifier for Novelty Detection","date":"2018-02-25","arxiv_id":"1802.09088","repositories_listed":5,"syntology":null},{"url":"/paper/attribute-based-representations-for-accurate","title":"An Attribute-based Method for Video Anomaly Detection","date":"2022-12-01","arxiv_id":"2212.00789","repositories_listed":4,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":3}},{"url":"/paper/weakly-supervised-video-anomaly-detection","title":"Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning","date":"2021-01-25","arxiv_id":"2101.10030","repositories_listed":3,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":5}},{"url":"/paper/when-where-and-what-a-new-dataset-for-anomaly","title":"When, Where, and What? A New Dataset for Anomaly Detection in Driving Videos","date":"2020-04-06","arxiv_id":"2004.03044","repositories_listed":3,"syntology":null},{"url":"/paper/quo-vadis-anomaly-detection-llms-and-vlms-in","title":"Quo Vadis, Anomaly Detection? LLMs and VLMs in the Spotlight","date":"2024-12-24","arxiv_id":"2412.18298","repositories_listed":2,"syntology":null},{"url":"/paper/weakly-supervised-video-anomaly-detection-2","title":"Weakly-Supervised Video Anomaly Detection with Snippet Anomalous Attention","date":"2023-09-28","arxiv_id":"2309.16309","repositories_listed":2,"syntology":null},{"url":"/paper/clip-tsa-clip-assisted-temporal-self","title":"CLIP-TSA: CLIP-Assisted Temporal Self-Attention for Weakly-Supervised Video Anomaly Detection","date":"2022-12-09","arxiv_id":"2212.05136","repositories_listed":2,"syntology":null},{"url":"/paper/unsupervised-traffic-accident-detection-in","title":"Unsupervised Traffic Accident Detection in First-Person Videos","date":"2019-03-02","arxiv_id":"1903.00618","repositories_listed":2,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/learning-temporal-regularity-in-video","title":"Learning Temporal Regularity in Video Sequences","date":"2016-04-15","arxiv_id":"1604.04574","repositories_listed":2,"syntology":null},{"url":"/paper/sequential-keypoint-density-estimator-an","title":"Sequential keypoint density estimator: an overlooked baseline of skeleton-based video anomaly detection","date":"2025-06-23","arxiv_id":"2506.18368","repositories_listed":1,"syntology":null},{"url":"/paper/smarthome-bench-a-comprehensive-benchmark-for","title":"SmartHome-Bench: A Comprehensive Benchmark for Video Anomaly Detection in Smart Homes Using Multi-Modal Large Language Models","date":"2025-06-15","arxiv_id":"2506.12992","repositories_listed":1,"syntology":null},{"url":"/paper/dual-detector-re-optimization-for-federated","title":"Dual‑detector Re‑optimization for Federated Weakly Supervised Video Anomaly Detection Via Adaptive Dynamic Recursive Mapping","date":"2025-06-13","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-learning-of-echocardiographic","title":"Self-supervised Learning of Echocardiographic Video Representations via Online Cluster Distillation","date":"2025-06-13","arxiv_id":"2506.11777","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_unverified":2,"n_pointer_only":10}},{"url":"/paper/vad-r1-towards-video-anomaly-reasoning-via","title":"Vad-R1: Towards Video Anomaly Reasoning via Perception-to-Cognition Chain-of-Thought","date":"2025-05-26","arxiv_id":"2505.19877","repositories_listed":1,"syntology":null},{"url":"/paper/uncertainty-weighted-image-event-multimodal","title":"Uncertainty-Weighted Image-Event Multimodal Fusion for Video Anomaly Detection","date":"2025-05-05","arxiv_id":"2505.02393","repositories_listed":1,"syntology":null},{"url":"/paper/prodisc-vad-an-efficient-system-for-weakly","title":"ProDisc-VAD: An Efficient System for Weakly-Supervised Anomaly Detection in Video Surveillance Applications","date":"2025-05-04","arxiv_id":"2505.02179","repositories_listed":1,"syntology":null},{"url":"/paper/vadmamba-exploring-state-space-models-for","title":"VADMamba: Exploring State Space Models for Fast Video Anomaly Detection","date":"2025-03-27","arxiv_id":"2503.21169","repositories_listed":1,"syntology":null},{"url":"/paper/ucf-crime-dvs-a-novel-event-based-dataset-for","title":"UCF-Crime-DVS: A Novel Event-Based Dataset for Video Anomaly Detection with Spiking Neural Networks","date":"2025-03-17","arxiv_id":"2503.12905","repositories_listed":1,"syntology":null},{"url":"/paper/video-anomaly-detection-with-structured","title":"Video Anomaly Detection with Structured Keywords","date":"2025-03-07","arxiv_id":"2503.10653","repositories_listed":1,"syntology":null},{"url":"/paper/anyanomaly-zero-shot-customizable-video-1","title":"AnyAnomaly: Zero-Shot Customizable Video Anomaly Detection with LVLM","date":"2025-03-06","arxiv_id":"2503.04504","repositories_listed":1,"syntology":null},{"url":"/paper/hstforu-anomaly-detection-in-aerial-and","title":"HSTforU: anomaly detection in aerial and ground-based videos with hierarchical spatio-temporal transformer for U-net","date":"2025-01-03","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/dual-conditioned-motion-diffusion-for-pose","title":"Dual Conditioned Motion Diffusion for Pose-Based Video Anomaly Detection","date":"2024-12-23","arxiv_id":"2412.17210","repositories_listed":1,"syntology":null},{"url":"/paper/video-anomaly-detection-with-motion-and","title":"Video Anomaly Detection with Motion and Appearance Guided Patch Diffusion Model","date":"2024-12-12","arxiv_id":"2412.09026","repositories_listed":1,"syntology":null},{"url":"/paper/frequency-guided-diffusion-model-with","title":"Frequency-Guided Diffusion Model with Perturbation Training for Skeleton-Based Video Anomaly Detection","date":"2024-12-04","arxiv_id":"2412.03044","repositories_listed":1,"syntology":null},{"url":"/paper/low-latency-video-anonymization-for-crowd","title":"Low-Latency Video Anonymization for Crowd Anomaly Detection: Privacy vs. Performance","date":"2024-10-24","arxiv_id":"2410.18717","repositories_listed":1,"syntology":null},{"url":"/paper/mtfl-multi-timescale-feature-learning-for","title":"MTFL: Multi-Timescale Feature Learning for Weakly-Supervised Anomaly Detection in Surveillance Videos","date":"2024-10-08","arxiv_id":"2410.05900","repositories_listed":1,"syntology":null},{"url":"/paper/videopatchcore-an-effective-method-to","title":"VideoPatchCore: An Effective Method to Memorize Normality for Video Anomaly Detection","date":"2024-09-24","arxiv_id":"2409.16225","repositories_listed":1,"syntology":null},{"url":"/paper/posewatch-a-transformer-based-architecture","title":"PoseWatch: A Transformer-based Architecture for Human-centric Video Anomaly Detection Using Spatio-temporal Pose Tokenization","date":"2024-08-27","arxiv_id":"2408.15185","repositories_listed":1,"syntology":null},{"url":"/paper/pheva-a-privacy-preserving-human-centric","title":"PHEVA: A Privacy-preserving Human-centric Video Anomaly Detection Dataset","date":"2024-08-26","arxiv_id":"2408.14329","repositories_listed":1,"syntology":null},{"url":"/paper/what-matters-in-autonomous-driving-anomaly","title":"What Matters in Autonomous Driving Anomaly Detection: A Weakly Supervised Horizon","date":"2024-08-10","arxiv_id":"2408.05562","repositories_listed":1,"syntology":null}],"syntology_records":4,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}