{"url":"/dataset/xd-violence","name":"XD-Violence","full_name":null,"description_markdown":"XD-Violence is a large-scale audio-visual dataset for violence detection in videos.","description_withheld":null,"homepage":"https://roc-ng.github.io/XD-Violence/","introduced_date":"2020-07-09","introduced_date_note":null,"introduced_by":{"paper":"/paper/not-only-look-but-also-listen-learning","title":"Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision","first_author":"Peng Wu","url":null},"license":null,"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Video Anomaly Detection","url":"/task/video-anomaly-detection","datasets_with_task":"/datasets/task/video-anomaly-detection"},{"name":"Anomaly Detection In Surveillance Videos","url":"/task/anomaly-detection-in-surveillance-videos","datasets_with_task":"/datasets/task/anomaly-detection-in-surveillance-videos"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"French","url":"/datasets/language/french"}],"variants":["XD-Violence"],"data_loaders":[],"num_papers_in_archive":58,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/anomaly-detection-in-surveillance-videos-on-2","task":"Anomaly Detection In Surveillance Videos","dataset_variant":"XD-Violence","rows":17,"metrics":["AP"],"first_row_in_archive_order":{"model":"CFA-HLGAtt","paper":"/paper/cross-modal-fusion-and-attention-mechanism-1","metrics":{"AP":"86.34"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-anomaly-detection-on-xd-violence-1","task":"Video Anomaly Detection","dataset_variant":"XD-Violence","rows":0,"metrics":["Average Precision (%)"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/cross-modal-fusion-and-attention-mechanism-1","title":"Cross-Modal Fusion and Attention Mechanism for Weakly Supervised Video Anomaly Detection","date":"2024-12-29","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/distilling-aggregated-knowledge-for-weakly","title":"Distilling Aggregated Knowledge for Weakly-Supervised Video Anomaly Detection","date":"2024-06-05","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/multi-scale-bottleneck-transformer-for-weakly","title":"Multi-scale Bottleneck Transformer for Weakly Supervised Multimodal Violence Detection","date":"2024-05-08","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/batchnorm-based-weakly-supervised-video","title":"BatchNorm-based Weakly Supervised Video Anomaly Detection","date":"2023-11-26","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":3,"samples_unverified":2,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-prompt-enhanced-context-features-for","title":"Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detection","date":"2023-06-26","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":0,"samples_unverified":9,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-weakly-supervised-audio-visual","title":"Learning Weakly Supervised Audio-Visual Violence Detection in Hyperbolic Space","date":"2023-05-30","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/self-supervised-sparse-representation-for","title":"Self-supervised Sparse Representation for Video Anomaly Detection","date":"2022-10-23","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/consistency-based-self-supervised-learning","title":"Consistency-based Self-supervised Learning for Temporal Anomaly Localization","date":"2022-08-10","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":2,"samples_unverified":8,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/audio-guided-attention-network-for-weakly","title":"Audio-Guided Attention Network for Weakly Supervised Violence Detection","date":"2022-02-21","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/weakly-supervised-video-anomaly-detection","title":"Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning","date":"2021-01-25","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":4,"samples_unverified":1,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/not-only-look-but-also-listen-learning","title":"Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision","date":"2020-07-09","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":4,"samples_harvested":29,"samples_ran":9,"samples_unverified":20,"pointer_only_for_licence":10,"papers_with_no_sample_that_ran":1,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}