{"task":"Anomaly Detection","dataset":"ShanghaiTech","metric_names":["AUC","RBDC","TBDC"],"rows":[{"id":590445,"task":"Anomaly Detection","parent_task":null,"dataset":"ShanghaiTech","model_name":"PA-VAD","metrics":{"AUC":"98.2"},"paper_url":"https://paperswithcode.com/paper/pa-vad-diffusion-based-pseudo-only-video-anomaly-detection-via-domain-aligned-memory-updates","paper_title":"PA-VAD: Diffusion-Based Pseudo-Only Video Anomaly Detection via Domain-Aligned Memory Updates","paper_date":"2025-12-07","code_links":[],"metrics_order":null,"area":null,"uses_additional_data":null,"source":"auto","tags":[]},{"id":19701,"task":"Anomaly Detection","parent_task":null,"dataset":"ShanghaiTech","model_name":"DAC(STG-NF + Jigsaw)","metrics":{"AUC":"87.72%"},"paper_url":"https://arxiv.org/abs/2309.14622v2","paper_title":"Divide and Conquer in Video Anomaly Detection: A Comprehensive Review and New Approach","paper_date":"2023-09-26","code_links":[{"title":"XiaoJian923/Divide-and-Conquer","url":"https://github.com/XiaoJian923/Divide-and-Conquer"}],"metrics_order":"[\"AUC\", \"RBDC\", \"TBDC\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":19702,"task":"Anomaly Detection","parent_task":null,"dataset":"ShanghaiTech","model_name":"MULDE-object-centric-micro","metrics":{"AUC":"86.7%"},"paper_url":"https://arxiv.org/abs/2403.14497v1","paper_title":"MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detection","paper_date":"2024-03-21","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"}],"metrics_order":"[\"AUC\", \"RBDC\", \"TBDC\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":19703,"task":"Anomaly Detection","parent_task":null,"dataset":"ShanghaiTech","model_name":"AI-VAD","metrics":{"AUC":"85.94%"},"paper_url":"https://arxiv.org/abs/2212.00789v2","paper_title":"An Attribute-based Method for Video Anomaly Detection","paper_date":"2022-12-01","code_links":[{"title":"openvinotoolkit/anomalib","url":"https://github.com/openvinotoolkit/anomalib/tree/main/src/anomalib/models/ai_vad"},{"title":"talreiss/Mean-Shifted-Anomaly-Detection","url":"https://github.com/talreiss/Mean-Shifted-Anomaly-Detection"},{"title":"talreiss/accurate-interpretable-vad","url":"https://github.com/talreiss/accurate-interpretable-vad"},{"title":"talreiss/PANDA","url":"https://github.com/talreiss/PANDA"}],"metrics_order":"[\"AUC\", \"RBDC\", \"TBDC\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":19704,"task":"Anomaly Detection","parent_task":null,"dataset":"ShanghaiTech","model_name":"STG-NF","metrics":{"AUC":"85.9%"},"paper_url":"https://arxiv.org/abs/2211.10946v2","paper_title":"Normalizing Flows for Human Pose Anomaly Detection","paper_date":"2022-11-20","code_links":[{"title":"orhir/stg-nf","url":"https://github.com/orhir/stg-nf"}],"metrics_order":"[\"AUC\", \"RBDC\", \"TBDC\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":19705,"task":"Anomaly Detection","parent_task":null,"dataset":"ShanghaiTech","model_name":"AnomalyRuler","metrics":{"AUC":"85.2%"},"paper_url":"https://arxiv.org/abs/2407.10299v2","paper_title":"Follow the Rules: Reasoning for Video Anomaly Detection with Large Language Models","paper_date":"2024-07-14","code_links":[{"title":"Yuchen413/AnomalyRuler","url":"https://github.com/Yuchen413/AnomalyRuler"}],"metrics_order":"[\"AUC\", \"RBDC\", \"TBDC\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":19706,"task":"Anomaly Detection","parent_task":null,"dataset":"ShanghaiTech","model_name":"VideoPatchCore","metrics":{"AUC":"85.1%"},"paper_url":"https://arxiv.org/abs/2409.16225v5","paper_title":"VideoPatchCore: An Effective Method to Memorize Normality for Video Anomaly Detection","paper_date":"2024-09-24","code_links":[{"title":"SkiddieAhn/Paper-VideoPatchCore","url":"https://github.com/SkiddieAhn/Paper-VideoPatchCore"}],"metrics_order":"[\"AUC\", \"RBDC\", \"TBDC\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":19707,"task":"Anomaly Detection","parent_task":null,"dataset":"ShanghaiTech","model_name":"Jigsaw-VAD","metrics":{"AUC":"84.3%"},"paper_url":"https://arxiv.org/abs/2207.10172v2","paper_title":"Video Anomaly Detection by Solving Decoupled Spatio-Temporal Jigsaw Puzzles","paper_date":"2022-07-20","code_links":[{"title":"gdwang08/jigsaw-vad","url":"https://github.com/gdwang08/jigsaw-vad"}],"metrics_order":"[\"AUC\", \"RBDC\", \"TBDC\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":19708,"task":"Anomaly Detection","parent_task":null,"dataset":"ShanghaiTech","model_name":"SSMTL++v2","metrics":{"AUC":"83.8%","RBDC":"47.10","TBDC":"85.60"},"paper_url":"https://arxiv.org/abs/2207.08003v4","paper_title":"SSMTL++: Revisiting Self-Supervised Multi-Task Learning for Video Anomaly Detection","paper_date":"2022-07-16","code_links":[],"metrics_order":"[\"AUC\", \"RBDC\", \"TBDC\"]","area":"Methodology","uses_additional_data":1,"source":"archive","tags":[]},{"id":19709,"task":"Anomaly Detection","parent_task":null,"dataset":"ShanghaiTech","model_name":"SSMTL+UBnormal","metrics":{"AUC":"83.7%","RBDC":"47.15","TBDC":"86.15"},"paper_url":"https://arxiv.org/abs/2111.08644v3","paper_title":"UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detection","paper_date":"2021-11-16","code_links":[{"title":"lilygeorgescu/ubnormal","url":"https://github.com/lilygeorgescu/ubnormal"}],"metrics_order":"[\"AUC\", \"RBDC\", \"TBDC\"]","area":"Methodology","uses_additional_data":1,"source":"archive","tags":[]},{"id":19710,"task":"Anomaly Detection","parent_task":null,"dataset":"ShanghaiTech","model_name":"two-stream","metrics":{"AUC":"83.7%"},"paper_url":"https://arxiv.org/abs/2209.02899v1","paper_title":"Context Recovery and Knowledge Retrieval: A Novel Two-Stream Framework for Video Anomaly Detection","paper_date":"2022-09-07","code_links":[{"title":"zugexiaodui/twostreamuvad","url":"https://github.com/zugexiaodui/twostreamuvad"}],"metrics_order":"[\"AUC\", \"RBDC\", \"TBDC\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":19711,"task":"Anomaly Detection","parent_task":null,"dataset":"ShanghaiTech","model_name":"SSMTL+++SSMCTB","metrics":{"AUC":"83.6%","RBDC":"47.73","TBDC":"85.65"},"paper_url":"https://arxiv.org/abs/2209.12148v2","paper_title":"Self-Supervised Masked Convolutional Transformer Block for Anomaly Detection","paper_date":"2022-09-25","code_links":[{"title":"ristea/ssmctb","url":"https://github.com/ristea/ssmctb"}],"metrics_order":"[\"AUC\", \"RBDC\", \"TBDC\"]","area":"Methodology","uses_additional_data":1,"source":"archive","tags":[]},{"id":19712,"task":"Anomaly Detection","parent_task":null,"dataset":"ShanghaiTech","model_name":"Background- Agnostic Framework+SSPCAB","metrics":{"AUC":"83.6%"},"paper_url":"https://arxiv.org/abs/2111.09099v6","paper_title":"Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection","paper_date":"2021-11-17","code_links":[{"title":"openvinotoolkit/anomalib","url":"https://github.com/openvinotoolkit/anomalib/tree/main/anomalib/models/draem"},{"title":"ristea/sspcab","url":"https://github.com/ristea/sspcab"},{"title":"wasve/DRAEM-SSPCAB","url":"https://github.com/wasve/DRAEM-SSPCAB"},{"title":"2023-MindSpore-1/ms-code-26","url":"https://github.com/2023-MindSpore-1/ms-code-26"}],"metrics_order":"[\"AUC\", \"RBDC\", \"TBDC\"]","area":"Methodology","uses_additional_data":1,"source":"archive","tags":[]},{"id":19713,"task":"Anomaly Detection","parent_task":null,"dataset":"ShanghaiTech","model_name":"MoPRL","metrics":{"AUC":"83.35"},"paper_url":"https://arxiv.org/abs/2112.03649v2","paper_title":"Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detection","paper_date":"2021-12-07","code_links":[{"title":"Yui010206/MoPRL","url":"https://github.com/Yui010206/MoPRL"}],"metrics_order":"[\"AUC\", \"RBDC\", \"TBDC\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":19714,"task":"Anomaly Detection","parent_task":null,"dataset":"ShanghaiTech","model_name":"SSMTL++v1","metrics":{"AUC":"82.9%","RBDC":"43.2","TBDC":"84.1"},"paper_url":"https://arxiv.org/abs/2207.08003v4","paper_title":"SSMTL++: Revisiting Self-Supervised Multi-Task Learning for Video Anomaly Detection","paper_date":"2022-07-16","code_links":[],"metrics_order":"[\"AUC\", \"RBDC\", \"TBDC\"]","area":"Methodology","uses_additional_data":1,"source":"archive","tags":[]},{"id":19715,"task":"Anomaly Detection","parent_task":null,"dataset":"ShanghaiTech","model_name":"Background-Agnostic Framework","metrics":{"AUC":"82.7%"},"paper_url":"https://arxiv.org/abs/2008.12328v5","paper_title":"A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Video","paper_date":"2020-08-27","code_links":[{"title":"m-3lab/awesome-visual-sensory-anomaly-detection","url":"https://github.com/m-3lab/awesome-visual-sensory-anomaly-detection"},{"title":"lilygeorgescu/AED","url":"https://github.com/lilygeorgescu/AED"}],"metrics_order":"[\"AUC\", \"RBDC\", \"TBDC\"]","area":"Methodology","uses_additional_data":1,"source":"archive","tags":[]},{"id":19716,"task":"Anomaly Detection","parent_task":null,"dataset":"ShanghaiTech","model_name":"SSMTL","metrics":{"AUC":"82.4%"},"paper_url":"https://arxiv.org/abs/2011.07491v3","paper_title":"Anomaly Detection in Video via Self-Supervised and Multi-Task Learning","paper_date":"2020-11-15","code_links":[{"title":"lilygeorgescu/AED-SSMTL","url":"https://github.com/lilygeorgescu/AED-SSMTL"}],"metrics_order":"[\"AUC\", \"RBDC\", \"TBDC\"]","area":"Methodology","uses_additional_data":1,"source":"archive","tags":[]},{"id":19717,"task":"Anomaly Detection","parent_task":null,"dataset":"ShanghaiTech","model_name":"MULDE-frame-centric-micro","metrics":{"AUC":"81.3%"},"paper_url":"https://arxiv.org/abs/2403.14497v1","paper_title":"MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detection","paper_date":"2024-03-21","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"}],"metrics_order":"[\"AUC\", \"RBDC\", \"TBDC\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":19718,"task":"Anomaly Detection","parent_task":null,"dataset":"ShanghaiTech","model_name":"TSGAD","metrics":{"AUC":"80.6%"},"paper_url":"https://arxiv.org/abs/2406.15395v1","paper_title":"An Exploratory Study on Human-Centric Video Anomaly Detection through Variational Autoencoders and Trajectory Prediction","paper_date":"2024-04-29","code_links":[{"title":"tecsar-uncc/tsgad","url":"https://github.com/tecsar-uncc/tsgad"}],"metrics_order":"[\"AUC\", \"RBDC\", \"TBDC\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":19719,"task":"Anomaly Detection","parent_task":null,"dataset":"ShanghaiTech","model_name":"DMAD","metrics":{"AUC":"78.8%"},"paper_url":"https://arxiv.org/abs/2303.05047v1","paper_title":"Diversity-Measurable Anomaly Detection","paper_date":"2023-03-09","code_links":[{"title":"FlappyPeggy/DMAD","url":"https://github.com/FlappyPeggy/DMAD"}],"metrics_order":"[\"AUC\", \"RBDC\", \"TBDC\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":19720,"task":"Anomaly Detection","parent_task":null,"dataset":"ShanghaiTech","model_name":"Object-centric AE","metrics":{"AUC":"78.7%"},"paper_url":"http://arxiv.org/abs/1812.04960v2","paper_title":"Object-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in Video","paper_date":"2018-12-11","code_links":[{"title":"fjchange/object_centric_VAD","url":"https://github.com/fjchange/object_centric_VAD"}],"metrics_order":"[\"AUC\", \"RBDC\", \"TBDC\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":19721,"task":"Anomaly Detection","parent_task":null,"dataset":"ShanghaiTech","model_name":"STPT","metrics":{"AUC":"77.1%","RBDC":"51.6","TBDC":"84.6"},"paper_url":"https://arxiv.org/abs/2210.15741v2","paper_title":"Spatio-temporal predictive tasks for abnormal event detection in videos","paper_date":"2022-10-27","code_links":[],"metrics_order":"[\"AUC\", \"RBDC\", \"TBDC\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":19722,"task":"Anomaly Detection","parent_task":null,"dataset":"ShanghaiTech","model_name":"EVAL","metrics":{"AUC":"76.63%","RBDC":"59.21","TBDC":"89.44"},"paper_url":"https://arxiv.org/abs/2212.07900v1","paper_title":"EVAL: Explainable Video Anomaly Localization","paper_date":"2022-12-15","code_links":[],"metrics_order":"[\"AUC\", \"RBDC\", \"TBDC\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":19723,"task":"Anomaly Detection","parent_task":null,"dataset":"ShanghaiTech","model_name":"MAMA","metrics":{"AUC":"76.5%"},"paper_url":"https://ieeexplore.ieee.org/document/10462109","paper_title":"Making Anomalies More Anomalous: Video Anomaly Detection Using a Novel Generator and Destroyer","paper_date":"2024-02-26","code_links":[{"title":"SkiddieAhn/Paper-Making-Anomalies-More-Anomalous","url":"https://github.com/SkiddieAhn/Paper-Making-Anomalies-More-Anomalous"}],"metrics_order":"[\"AUC\", \"RBDC\", \"TBDC\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":19724,"task":"Anomaly Detection","parent_task":null,"dataset":"ShanghaiTech","model_name":"STAN","metrics":{"AUC":"76.2%"},"paper_url":"http://arxiv.org/abs/1804.08381v1","paper_title":"STAN: Spatio-Temporal Adversarial Networks for Abnormal Event Detection","paper_date":"2018-04-23","code_links":[],"metrics_order":"[\"AUC\", \"RBDC\", \"TBDC\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":19725,"task":"Anomaly Detection","parent_task":null,"dataset":"ShanghaiTech","model_name":"Multi-timescale Prediction","metrics":{"AUC":"76.03%"},"paper_url":"https://arxiv.org/abs/1908.04321v1","paper_title":"Multi-timescale Trajectory Prediction for Abnormal Human Activity Detection","paper_date":"2019-08-12","code_links":[],"metrics_order":"[\"AUC\", \"RBDC\", \"TBDC\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":19726,"task":"Anomaly Detection","parent_task":null,"dataset":"ShanghaiTech","model_name":"ASTNet","metrics":{"AUC":"73.6"},"paper_url":"https://link.springer.com/article/10.1007/s10489-022-03613-1","paper_title":"Attention-based residual autoencoder for video anomaly detection","paper_date":"2022-05-25","code_links":[{"title":"vt-le/astnet","url":"https://github.com/vt-le/astnet"}],"metrics_order":"[\"AUC\", \"RBDC\", \"TBDC\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":19727,"task":"Anomaly Detection","parent_task":null,"dataset":"ShanghaiTech","model_name":"MPED-RNN","metrics":{"AUC":"73.40%"},"paper_url":"http://arxiv.org/abs/1903.03295v2","paper_title":"Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videos","paper_date":"2019-03-08","code_links":[{"title":"RomeroBarata/skeleton_based_anomaly_detection","url":"https://github.com/RomeroBarata/skeleton_based_anomaly_detection"}],"metrics_order":"[\"AUC\", \"RBDC\", \"TBDC\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":19728,"task":"Anomaly Detection","parent_task":null,"dataset":"ShanghaiTech","model_name":"Any-Shot Sequential","metrics":{"AUC":"71.6%"},"paper_url":"https://arxiv.org/abs/2004.02072v1","paper_title":"Any-Shot Sequential Anomaly Detection in Surveillance Videos","paper_date":"2020-04-05","code_links":[],"metrics_order":"[\"AUC\", \"RBDC\", \"TBDC\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":19729,"task":"Anomaly Detection","parent_task":null,"dataset":"ShanghaiTech","model_name":"Sparse Coding Stacked RNN","metrics":{"AUC":"68.0%"},"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","paper_date":"2017-10-01","code_links":[{"title":"StevenLiuWen/sRNN_TSC_Anomaly_Detection","url":"https://github.com/StevenLiuWen/sRNN_TSC_Anomaly_Detection"}],"metrics_order":"[\"AUC\", \"RBDC\", \"TBDC\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":19730,"task":"Anomaly Detection","parent_task":null,"dataset":"ShanghaiTech","model_name":"PGM","metrics":{"AUC":"61.28%","RBDC":"45.40","TBDC":"81.87"},"paper_url":"https://arxiv.org/abs/2407.06000v2","paper_title":"Bounding Boxes and Probabilistic Graphical Models: Video Anomaly Detection Simplified","paper_date":"2024-07-08","code_links":[{"title":"milestonesys-research/vad-with-pgms","url":"https://github.com/milestonesys-research/vad-with-pgms"}],"metrics_order":"[\"AUC\", \"RBDC\", \"TBDC\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":19731,"task":"Anomaly Detection","parent_task":null,"dataset":"ShanghaiTech","model_name":"HF2VAD+SSPCAB","metrics":{"RBDC":"45.45","TBDC":"84.50"},"paper_url":"https://arxiv.org/abs/2111.09099v6","paper_title":"Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection","paper_date":"2021-11-17","code_links":[{"title":"openvinotoolkit/anomalib","url":"https://github.com/openvinotoolkit/anomalib/tree/main/anomalib/models/draem"},{"title":"ristea/sspcab","url":"https://github.com/ristea/sspcab"},{"title":"wasve/DRAEM-SSPCAB","url":"https://github.com/wasve/DRAEM-SSPCAB"},{"title":"2023-MindSpore-1/ms-code-26","url":"https://github.com/2023-MindSpore-1/ms-code-26"}],"metrics_order":"[\"AUC\", \"RBDC\", \"TBDC\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]}]}