{"url":"/task/anomaly-detection-in-surveillance-videos","name":"Anomaly Detection In Surveillance Videos","slug":"anomaly-detection-in-surveillance-videos","description_markdown":"\"The goal of a practical anomaly detection system is to timely signal an activity that deviates normal patterns and identify the time window of the occurring anomaly. [It] can be considered as coarse level video understanding, which filters out anomalies from normal patterns.\" A critical task in video surveillance is detecting anomalous events such as  traffic accidents, crimes or illegal activities. Anomalous events rarely occur as compared to normal activities. Hence the application of this task is to \"alleviate the waste of labor and time, developing intelligent computer vision algorithms for automatic video anomaly detection\".\r\n\r\n(Credit: Real-world Anomaly Detection in Surveillance Videos)","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Graphs","url":"/area/graphs"},{"name":"Methodology","url":"/area/methodology"},{"name":"Miscellaneous","url":"/area/miscellaneous"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":66,"papers_with_code":44,"benchmarks":7,"benchmark_tables_in_archive":7,"benchmark_tables_shown":7,"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":8,"subtasks":0,"parent_tasks":2},"benchmarks":[{"leaderboard":"/sota/anomaly-detection-in-surveillance-videos-on","slug":"anomaly-detection-in-surveillance-videos-on","dataset":"UCF-Crime","dataset_url":"/dataset/ucf-crime","rows_in_archive":21,"metrics":["ROC AUC","Decidability","EER","AUC"],"first_row_in_archive_order":{"model":"STEAD-Base","paper_title":"STEAD: Spatio-Temporal Efficient Anomaly Detection for Time and Compute Sensitive Applications","paper_url":"/paper/stead-spatio-temporal-efficient-anomaly-1","paper_date":"2025-03-11","arxiv_id":"2503.07942","code_links":[{"title":"agao8/STEAD","url":"https://github.com/agao8/STEAD"}],"syntology":null}},{"leaderboard":"/sota/anomaly-detection-in-surveillance-videos-on-2","slug":"anomaly-detection-in-surveillance-videos-on-2","dataset":"XD-Violence","dataset_url":"/dataset/xd-violence","rows_in_archive":17,"metrics":["AP"],"first_row_in_archive_order":{"model":"CFA-HLGAtt","paper_title":"Cross-Modal Fusion and Attention Mechanism for Weakly Supervised Video Anomaly Detection","paper_url":"/paper/cross-modal-fusion-and-attention-mechanism-1","paper_date":"2024-12-29","arxiv_id":"2412.20455","code_links":[],"syntology":null}},{"leaderboard":"/sota/anomaly-detection-in-surveillance-videos-on-1","slug":"anomaly-detection-in-surveillance-videos-on-1","dataset":"ShanghaiTech Weakly Supervised","dataset_url":"/dataset/shanghaitech-campus","rows_in_archive":12,"metrics":["AUC-ROC"],"first_row_in_archive_order":{"model":"PEL","paper_title":"Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detection","paper_url":"/paper/learning-prompt-enhanced-context-features-for","paper_date":"2023-06-26","arxiv_id":"2306.14451","code_links":[{"title":"yujiangpu20/pel4vad","url":"https://github.com/yujiangpu20/pel4vad"}],"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}}},{"leaderboard":"/sota/anomaly-detection-in-surveillance-videos-on-3","slug":"anomaly-detection-in-surveillance-videos-on-3","dataset":"UCSD Peds2","dataset_url":null,"rows_in_archive":6,"metrics":["AUC"],"first_row_in_archive_order":{"model":"Background-Agnostic Framework","paper_title":"A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Video","paper_url":"/paper/a-scene-agnostic-framework-with-adversarial","paper_date":"2020-08-27","arxiv_id":"2008.12328","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"}],"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}}},{"leaderboard":"/sota/anomaly-detection-in-surveillance-videos-on-5","slug":"anomaly-detection-in-surveillance-videos-on-5","dataset":"VFP290K","dataset_url":"/dataset/vfp290k","rows_in_archive":4,"metrics":["mAP @0.5:0.95","ROC AUC"],"first_row_in_archive_order":{"model":"Faster R-CNN (R101)","paper_title":"VFP290K: A Large-Scale Benchmark Dataset for Vision-based Fallen Person Detection","paper_url":"/paper/vfp290k-a-large-scale-benchmark-dataset-for","paper_date":"2022-01-14","arxiv_id":null,"code_links":[{"title":"DASH-Lab/VFP290K","url":"https://github.com/DASH-Lab/VFP290K"}],"syntology":null}},{"leaderboard":"/sota/anomaly-detection-in-surveillance-videos-on-10","slug":"anomaly-detection-in-surveillance-videos-on-10","dataset":"VADD","dataset_url":"/dataset/vadd","rows_in_archive":1,"metrics":["ROC AUC"],"first_row_in_archive_order":{"model":"MTFL (VST, finetuned on VADD)","paper_title":"MTFL: Multi-Timescale Feature Learning for Weakly-Supervised Anomaly Detection in Surveillance Videos","paper_url":"/paper/mtfl-multi-timescale-feature-learning-for","paper_date":"2024-10-08","arxiv_id":"2410.05900","code_links":[{"title":"erktkdg/MTFL","url":"https://github.com/erktkdg/MTFL"}],"syntology":null}},{"leaderboard":"/sota/anomaly-detection-in-surveillance-videos-on-8","slug":"anomaly-detection-in-surveillance-videos-on-8","dataset":"ShanghaiTech","dataset_url":"/dataset/shanghaitech","rows_in_archive":1,"metrics":["AUC"],"first_row_in_archive_order":{"model":"LMM_VAD","paper_title":"10 Security and Privacy Problems in Large Foundation Models","paper_url":"/paper/10-security-and-privacy-problems-in-self","paper_date":"2021-10-28","arxiv_id":"2110.15444","code_links":[],"syntology":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/xd-violence","name":"XD-Violence","full_name":"","num_papers_in_archive":58},{"url":"/dataset/ubi-fights","name":"UBI-Fights","full_name":"Abnormal Event Detection Dataset","num_papers_in_archive":7},{"url":"/dataset/vfp290k","name":"VFP290K","full_name":"","num_papers_in_archive":2},{"url":"/dataset/vadd","name":"VADD","full_name":"Video Anomaly Detection Dataset (VADD)","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":[],"parent_tasks":[{"url":"/task/anomaly-detection","name":"Anomaly Detection"},{"url":"/task/video-understanding","name":"Video Understanding"}],"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":44,"tagged_in_all":66,"items":[{"url":"/paper/real-world-anomaly-detection-in-surveillance","title":"Real-world Anomaly Detection in Surveillance Videos","date":"2018-01-12","arxiv_id":"1801.04264","repositories_listed":9,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":4}},{"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/adnet-temporal-anomaly-detection-in","title":"ADNet: Temporal Anomaly Detection in Surveillance Videos","date":"2021-04-14","arxiv_id":"2104.06653","repositories_listed":2,"syntology":null},{"url":"/paper/a-scene-agnostic-framework-with-adversarial","title":"A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Video","date":"2020-08-27","arxiv_id":"2008.12328","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/learning-memory-guided-normality-for-anomaly","title":"Learning Memory-guided Normality for Anomaly Detection","date":"2020-03-30","arxiv_id":"2003.13228","repositories_listed":2,"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/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/stead-spatio-temporal-efficient-anomaly-1","title":"STEAD: Spatio-Temporal Efficient Anomaly Detection for Time and Compute Sensitive Applications","date":"2025-03-11","arxiv_id":"2503.07942","repositories_listed":1,"syntology":null},{"url":"/paper/aligning-first-then-fusing-a-novel-weakly","title":"Aligning First, Then Fusing: A Novel Weakly Supervised Multimodal Violence Detection Method","date":"2025-01-13","arxiv_id":"2501.07496","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/multi-scale-bottleneck-transformer-for-weakly","title":"Multi-scale Bottleneck Transformer for Weakly Supervised Multimodal Violence Detection","date":"2024-05-08","arxiv_id":"2405.05130","repositories_listed":1,"syntology":null},{"url":"/paper/mulde-multiscale-log-density-estimation-via","title":"MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detection","date":"2024-03-21","arxiv_id":"2403.14497","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/batchnorm-based-weakly-supervised-video","title":"BatchNorm-based Weakly Supervised Video Anomaly Detection","date":"2023-11-26","arxiv_id":"2311.15367","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_unverified":2,"n_pointer_only":5}},{"url":"/paper/a-mil-approach-for-anomaly-detection-in","title":"A MIL Approach for Anomaly Detection in Surveillance Videos from Multiple Camera Views","date":"2023-07-02","arxiv_id":"2307.00562","repositories_listed":1,"syntology":null},{"url":"/paper/learning-prompt-enhanced-context-features-for","title":"Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detection","date":"2023-06-26","arxiv_id":"2306.14451","repositories_listed":1,"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/learning-weakly-supervised-audio-visual","title":"Learning Weakly Supervised Audio-Visual Violence Detection in Hyperbolic Space","date":"2023-05-30","arxiv_id":"2305.18797","repositories_listed":1,"syntology":null},{"url":"/paper/diversity-measurable-anomaly-detection","title":"Diversity-Measurable Anomaly Detection","date":"2023-03-09","arxiv_id":"2303.05047","repositories_listed":1,"syntology":{"n":11,"n_ran":6,"n_unverified":5,"n_pointer_only":11}},{"url":"/paper/mgfn-magnitude-contrastive-glance-and-focus","title":"MGFN: Magnitude-Contrastive Glance-and-Focus Network for Weakly-Supervised Video Anomaly Detection","date":"2022-11-28","arxiv_id":"2211.15098","repositories_listed":1,"syntology":null},{"url":"/paper/normalizing-flows-for-human-pose-anomaly","title":"Normalizing Flows for Human Pose Anomaly Detection","date":"2022-11-20","arxiv_id":"2211.10946","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-sparse-representation-for","title":"Self-supervised Sparse Representation for Video Anomaly Detection","date":"2022-10-23","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/consistency-based-self-supervised-learning","title":"Consistency-based Self-supervised Learning for Temporal Anomaly Localization","date":"2022-08-10","arxiv_id":"2208.05251","repositories_listed":1,"syntology":null},{"url":"/paper/modality-aware-contrastive-instance-learning","title":"Modality-Aware Contrastive Instance Learning with Self-Distillation for Weakly-Supervised Audio-Visual Violence Detection","date":"2022-07-12","arxiv_id":"2207.05500","repositories_listed":1,"syntology":{"n":10,"n_ran":2,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/anomaly-detection-in-surveillance-videos","title":"Anomaly detection in surveillance videos using transformer based attention model","date":"2022-06-03","arxiv_id":"2206.01524","repositories_listed":1,"syntology":null},{"url":"/paper/attention-based-residual-autoencoder-for","title":"Attention-based residual autoencoder for video anomaly detection","date":"2022-05-25","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/audio-guided-attention-network-for-weakly","title":"Audio-Guided Attention Network for Weakly Supervised Violence Detection","date":"2022-02-21","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/vfp290k-a-large-scale-benchmark-dataset-for","title":"VFP290K: A Large-Scale Benchmark Dataset for Vision-based Fallen Person Detection","date":"2022-01-14","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/regularity-learning-via-explicit-distribution","title":"Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detection","date":"2021-12-07","arxiv_id":"2112.03649","repositories_listed":1,"syntology":null},{"url":"/paper/fastano-fast-anomaly-detection-via-spatio","title":"FastAno: Fast Anomaly Detection via Spatio-temporal Patch Transformation","date":"2021-06-16","arxiv_id":"2106.08613","repositories_listed":1,"syntology":null},{"url":"/paper/real-time-anomaly-detection-and-feature","title":"Real-Time Anomaly Detection and Feature Analysis Based on Time Series for Surveillance Video","date":"2021-05-11","arxiv_id":null,"repositories_listed":1,"syntology":null}],"syntology_records":8,"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"}}