{"url":"/sota/anomaly-detection-on-chuk-avenue","task":{"name":"Anomaly Detection","url":"/task/anomaly-detection","note":null},"dataset":{"name":"CUHK Avenue","url":"/dataset/chuk-avenue"},"category":"Computer Vision","categories":["Computer Vision","Graphs","Methodology","Miscellaneous"],"category_note":null,"description":"**Anomaly Detection** is a binary classification identifying unusual or unexpected patterns in a dataset, which deviate significantly from the majority of the data. The goal of anomaly detection is to identify such anomalies, which could represent errors, fraud, or other types of unusual events, and flag them for further investigation.\r\n\r\n[Image source]: [GAN-based Anomaly Detection in Imbalance Problems](https://paperswithcode.com/paper/gan-based-anomaly-detection-in-imbalance)","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["AUC","RBDC","TBDC","FPS"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"AUC":"higher","RBDC":null,"TBDC":null,"FPS":null}},"counts":{"rows":35,"rows_with_code":25,"rows_with_paper_page":34,"rows_dated":34,"rows_using_additional_data":2},"rows":[{"rank_in_archive_order":1,"model":"MULDE-object-centric-micro","metrics":{"AUC":"94.3%"},"uses_additional_data":false,"paper_date":"2024-03-21","paper":"/paper/mulde-multiscale-log-density-estimation-via","paper_url":"https://arxiv.org/abs/2403.14497v1","paper_title":"MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detection","code":"https://github.com/jakubmicorek/MULDE-Multiscale-Log-Density-Estimation-via-Denoising-Score-Matching-for-Video-Anomaly-Detection","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":2,"model":"AMSRC","metrics":{"AUC":"93.8%"},"uses_additional_data":false,"paper_date":"2022-04-08","paper":"/paper/a-video-anomaly-detection-framework-based-on","paper_url":"https://arxiv.org/abs/2204.04151v1","paper_title":"A Video Anomaly Detection Framework based on Appearance-Motion Semantics Representation Consistency","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"SSMTL++v1","metrics":{"AUC":"93.7%","FPS":"20","RBDC":"40.9","TBDC":"82.1"},"uses_additional_data":false,"paper_date":"2022-07-16","paper":"/paper/ssmtl-revisiting-self-supervised-multi-task","paper_url":"https://arxiv.org/abs/2207.08003v4","paper_title":"SSMTL++: Revisiting Self-Supervised Multi-Task Learning for Video Anomaly Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"AI-VAD","metrics":{"AUC":"93.7%"},"uses_additional_data":false,"paper_date":"2022-12-01","paper":"/paper/attribute-based-representations-for-accurate","paper_url":"https://arxiv.org/abs/2212.00789v2","paper_title":"An Attribute-based Method for Video Anomaly Detection","code":"https://github.com/openvinotoolkit/anomalib/tree/main/src/anomalib/models/ai_vad","n_code_links":4,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":5,"model":"Background-Agnostic Framework+SSMCTB","metrics":{"AUC":"93.2%","FPS":"24","RBDC":"66.04","TBDC":"65.12"},"uses_additional_data":false,"paper_date":"2022-09-25","paper":"/paper/self-supervised-masked-convolutional","paper_url":"https://arxiv.org/abs/2209.12148v2","paper_title":"Self-Supervised Masked Convolutional Transformer Block for Anomaly Detection","code":"https://github.com/ristea/ssmctb","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"SSMTL+UBnormal","metrics":{"AUC":"93.0%","RBDC":"61.10","TBDC":"61.38"},"uses_additional_data":true,"paper_date":"2021-11-16","paper":"/paper/ubnormal-new-benchmark-for-supervised-open","paper_url":"https://arxiv.org/abs/2111.08644v3","paper_title":"UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detection","code":"https://github.com/lilygeorgescu/ubnormal","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":7,"model":"Background- Agnostic Framework+SSPCAB","metrics":{"AUC":"92.9%","FPS":"24","RBDC":"65.99"},"uses_additional_data":false,"paper_date":"2021-11-17","paper":"/paper/self-supervised-predictive-convolutional","paper_url":"https://arxiv.org/abs/2111.09099v6","paper_title":"Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection","code":"https://github.com/openvinotoolkit/anomalib/tree/main/anomalib/models/draem","n_code_links":4,"syntology":null},{"rank_in_archive_order":8,"model":"DMAD","metrics":{"AUC":"92.8%"},"uses_additional_data":false,"paper_date":"2023-03-09","paper":"/paper/diversity-measurable-anomaly-detection","paper_url":"https://arxiv.org/abs/2303.05047v1","paper_title":"Diversity-Measurable Anomaly Detection","code":"https://github.com/FlappyPeggy/DMAD","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":5,"n_samples":11,"n_pointer_only_licence":11}},{"rank_in_archive_order":9,"model":"VideoPatchCore","metrics":{"AUC":"92.8%"},"uses_additional_data":false,"paper_date":"2024-09-24","paper":"/paper/videopatchcore-an-effective-method-to","paper_url":"https://arxiv.org/abs/2409.16225v5","paper_title":"VideoPatchCore: An Effective Method to Memorize Normality for Video Anomaly Detection","code":"https://github.com/SkiddieAhn/Paper-VideoPatchCore","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"PGM","metrics":{"AUC":"92.72%","RBDC":"60.18","TBDC":"72.09"},"uses_additional_data":false,"paper_date":"2024-07-08","paper":"/paper/bounding-boxes-and-probabilistic-graphical","paper_url":"https://arxiv.org/abs/2407.06000v2","paper_title":"Bounding Boxes and Probabilistic Graphical Models: Video Anomaly Detection Simplified","code":"https://github.com/milestonesys-research/vad-with-pgms","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"Background-Agnostic Framework","metrics":{"AUC":"92.3%","FPS":"25","RBDC":"65.05","TBDC":"66.85"},"uses_additional_data":true,"paper_date":"2020-08-27","paper":"/paper/a-scene-agnostic-framework-with-adversarial","paper_url":"https://arxiv.org/abs/2008.12328v5","paper_title":"A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Video","code":"https://github.com/m-3lab/awesome-visual-sensory-anomaly-detection","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":12,"model":"SSMTL++v2","metrics":{"AUC":"91.6%","FPS":"19","RBDC":"47.8","TBDC":"85.2"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":13,"model":"SSMTL","metrics":{"AUC":"91.5%","FPS":"51","RBDC":"57.00","TBDC":"58.30"},"uses_additional_data":false,"paper_date":"2020-11-15","paper":"/paper/anomaly-detection-in-video-via-self","paper_url":"https://arxiv.org/abs/2011.07491v3","paper_title":"Anomaly Detection in Video via Self-Supervised and Multi-Task Learning","code":"https://github.com/lilygeorgescu/AED-SSMTL","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"SD-MAE","metrics":{"AUC":"91.3%","FPS":"1670","RBDC":"46.77","TBDC":"66.58"},"uses_additional_data":false,"paper_date":"2023-06-21","paper":"/paper/self-distilled-masked-auto-encoders-are","paper_url":"https://arxiv.org/abs/2306.12041v2","paper_title":"Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectors","code":"https://github.com/ristea/aed-mae","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"MAMA","metrics":{"AUC":"91.2%"},"uses_additional_data":false,"paper_date":"2024-02-26","paper":"/paper/making-anomalies-more-anomalous-video-anomaly","paper_url":"https://ieeexplore.ieee.org/document/10462109","paper_title":"Making Anomalies More Anomalous: Video Anomaly Detection Using a Novel Generator and Destroyer","code":"https://github.com/SkiddieAhn/Paper-Making-Anomalies-More-Anomalous","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"VALD-GAN","metrics":{"AUC":"91.03"},"uses_additional_data":false,"paper_date":"2023-10-18","paper":"/paper/vald-gan-video-anomaly-detection-using-latent","paper_url":"https://doi.org/10.1007/s11760-023-02750-5","paper_title":"VALD-GAN: video anomaly detection using latent discriminator augmented GAN","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":17,"model":"Two-stream","metrics":{"AUC":"90.8%"},"uses_additional_data":false,"paper_date":"2022-09-07","paper":"/paper/context-recovery-and-knowledge-retrieval-a","paper_url":"https://arxiv.org/abs/2209.02899v1","paper_title":"Context Recovery and Knowledge Retrieval: A Novel Two-Stream Framework for Video Anomaly Detection","code":"https://github.com/zugexiaodui/twostreamuvad","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"AnomalyRuler","metrics":{"AUC":"89.7%"},"uses_additional_data":false,"paper_date":"2024-07-14","paper":"/paper/follow-the-rules-reasoning-for-video-anomaly","paper_url":"https://arxiv.org/abs/2407.10299v2","paper_title":"Follow the Rules: Reasoning for Video Anomaly Detection with Large Language Models","code":"https://github.com/Yuchen413/AnomalyRuler","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":19,"model":"Cloze Test","metrics":{"AUC":"89.6%","FPS":"5"},"uses_additional_data":false,"paper_date":"2020-08-27","paper":"/paper/cloze-test-helps-effective-video-anomaly","paper_url":"https://arxiv.org/abs/2008.11988v1","paper_title":"Cloze Test Helps: Effective Video Anomaly Detection via Learning to Complete Video Events","code":"https://github.com/yuguangnudt/VEC_VAD","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"Narrowed Normality Clusters","metrics":{"AUC":"88.9%"},"uses_additional_data":false,"paper_date":"2018-01-12","paper":"/paper/detecting-abnormal-events-in-video-using","paper_url":"http://arxiv.org/abs/1801.05030v4","paper_title":"Detecting abnormal events in video using Narrowed Normality Clusters","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":21,"model":"AKD-VAD","metrics":{"AUC":"88.3%","FPS":"1480"},"uses_additional_data":false,"paper_date":"2022-11-28","paper":"/paper/lightning-fast-video-anomaly-detection-via","paper_url":"https://arxiv.org/abs/2211.15597v4","paper_title":"Lightning Fast Video Anomaly Detection via Adversarial Knowledge Distillation","code":"https://github.com/ristea/fast-aed","n_code_links":1,"syntology":null},{"rank_in_archive_order":22,"model":"Object-centric AE","metrics":{"AUC":"87.4%","RBDC":"15.77","TBDC":"27.01"},"uses_additional_data":false,"paper_date":"2018-12-11","paper":"/paper/object-centric-auto-encoders-and-dummy","paper_url":"http://arxiv.org/abs/1812.04960v2","paper_title":"Object-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in Video","code":"https://github.com/fjchange/object_centric_VAD","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":21,"n_samples":21,"n_pointer_only_licence":0}},{"rank_in_archive_order":23,"model":"Siamese Net","metrics":{"AUC":"87.2%","RBDC":"41.20","TBDC":"78.60"},"uses_additional_data":false,"paper_date":"2020-01-24","paper":"/paper/learning-a-distance-function-with-a-siamese","paper_url":"https://arxiv.org/abs/2001.09189v1","paper_title":"Learning a distance function with a Siamese network to localize anomalies in videos","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":24,"model":"Learning not to reconstruct","metrics":{"AUC":"87.1%"},"uses_additional_data":false,"paper_date":"2021-10-19","paper":"/paper/learning-not-to-reconstruct-anomalies","paper_url":"https://arxiv.org/abs/2110.09742v2","paper_title":"Learning Not to Reconstruct Anomalies","code":"https://github.com/aseuteurideu/LearningNotToReconstructAnomalies","n_code_links":1,"syntology":null},{"rank_in_archive_order":25,"model":"Appearance-Motion Correspondence","metrics":{"AUC":"86.9%"},"uses_additional_data":false,"paper_date":"2019-08-17","paper":"/paper/anomaly-detection-in-video-sequence-with","paper_url":"https://arxiv.org/abs/1908.06351v1","paper_title":"Anomaly Detection in Video Sequence with Appearance-Motion Correspondence","code":"https://github.com/nguyetn89/Anomaly_detection_ICCV2019","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":26,"model":"ASTNet","metrics":{"AUC":"86.7%"},"uses_additional_data":false,"paper_date":"2022-05-25","paper":"/paper/attention-based-residual-autoencoder-for","paper_url":"https://link.springer.com/article/10.1007/s10489-022-03613-1","paper_title":"Attention-based residual autoencoder for video anomaly detection","code":"https://github.com/vt-le/astnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":27,"model":"Any-Shot Sequential","metrics":{"AUC":"86.4%"},"uses_additional_data":false,"paper_date":"2020-04-05","paper":"/paper/any-shot-sequential-anomaly-detection-in","paper_url":"https://arxiv.org/abs/2004.02072v1","paper_title":"Any-Shot Sequential Anomaly Detection in Surveillance Videos","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":28,"model":"EVAL","metrics":{"AUC":"86.02%","RBDC":"68.2","TBDC":"87.56"},"uses_additional_data":false,"paper_date":"2022-12-15","paper":"/paper/eval-explainable-video-anomaly-localization","paper_url":"https://arxiv.org/abs/2212.07900v1","paper_title":"EVAL: Explainable Video Anomaly Localization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":29,"model":"STemGAN","metrics":{"AUC":"86.0"},"uses_additional_data":false,"paper_date":"2023-09-22","paper":"/paper/stemgan-spatio-temporal-generative","paper_url":"https://doi.org/10.1007/s10489-023-04940-7","paper_title":"STemGAN: spatio-temporal generative adversarial network for video anomaly detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":30,"model":"FastAno","metrics":{"AUC":"85.3%","FPS":"195"},"uses_additional_data":false,"paper_date":"2021-06-16","paper":"/paper/fastano-fast-anomaly-detection-via-spatio","paper_url":"https://arxiv.org/abs/2106.08613v4","paper_title":"FastAno: Fast Anomaly Detection via Spatio-temporal Patch Transformation","code":"https://github.com/codnjsqkr/FastAno_official","n_code_links":1,"syntology":null},{"rank_in_archive_order":31,"model":"Future Frame Prediction","metrics":{"AUC":"85.1%","FPS":"25","RBDC":"19.59","TBDC":"56.01"},"uses_additional_data":false,"paper_date":"2017-12-28","paper":"/paper/future-frame-prediction-for-anomaly-detection","paper_url":"http://arxiv.org/abs/1712.09867v3","paper_title":"Future Frame Prediction for Anomaly Detection -- A New Baseline","code":"https://github.com/stevenliuwen/ano_pred_cvpr2018","n_code_links":1,"syntology":null},{"rank_in_archive_order":32,"model":"ConvVQ","metrics":{"AUC":"84.3%"},"uses_additional_data":false,"paper_date":"2023-03-09","paper":"/paper/diversity-measurable-anomaly-detection","paper_url":"https://arxiv.org/abs/2303.05047v1","paper_title":"Diversity-Measurable Anomaly Detection","code":"https://github.com/FlappyPeggy/DMAD","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":5,"n_samples":11,"n_pointer_only_licence":11}},{"rank_in_archive_order":33,"model":"Sparse Coding Stacked RNN","metrics":{"AUC":"81.7%"},"uses_additional_data":false,"paper_date":"2017-10-01","paper":"/paper/a-revisit-of-sparse-coding-based-anomaly","paper_url":"http://openaccess.thecvf.com/content_iccv_2017/html/Luo_A_Revisit_of_ICCV_2017_paper.html","paper_title":"A Revisit of Sparse Coding Based Anomaly Detection in Stacked RNN Framework","code":"https://github.com/StevenLiuWen/sRNN_TSC_Anomaly_Detection","n_code_links":1,"syntology":null},{"rank_in_archive_order":34,"model":"Unmasking","metrics":{"AUC":"80.6%"},"uses_additional_data":false,"paper_date":"2017-05-23","paper":"/paper/unmasking-the-abnormal-events-in-video","paper_url":"http://arxiv.org/abs/1705.08182v3","paper_title":"Unmasking the abnormal events in video","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":35,"model":"HF2VAD+SSPCAB","metrics":{"TBDC":"89.28"},"uses_additional_data":false,"paper_date":"2021-11-17","paper":"/paper/self-supervised-predictive-convolutional","paper_url":"https://arxiv.org/abs/2111.09099v6","paper_title":"Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection","code":"https://github.com/openvinotoolkit/anomalib/tree/main/anomalib/models/draem","n_code_links":4,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 7,081 of the 9,623 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9623,"papers_checked":7081,"papers_extracted_not_yet_verified":217,"boards_without_verdict":27,"papers_not_yet_extracted":2325},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":9,"rows_with_any_sample_ran":7,"distinct_papers_with_graph_line":8,"distinct_papers_with_any_sample_ran":6,"samples_over_distinct_papers":{"n_ran":15,"n_unverified":28,"n_samples":43,"n_pointer_only_licence":19,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":21,"n_unverified":33,"n_samples":54,"n_pointer_only_licence":30,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}