| Cross-Modal Fusion and Attention Mechanism for Weakly Supervised Video Anomaly Detection | | 86.34 | CFA-HLGAtt | 2024-12-29 |
| Aligning First, Then Fusing: A Novel Weakly Supervised Multimodal Violence Detection Method | ✓ Link | 86.07 | MAVD | 2025-01-13 |
| Learning Weakly Supervised Audio-Visual Violence Detection in Hyperbolic Space | ✓ Link | 85.67 | HyperVD | 2023-05-30 |
| Distilling Aggregated Knowledge for Weakly-Supervised Video Anomaly Detection | | 85.61 | DAKD | 2024-06-05 |
| Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detection | ✓ Link | 85.59 | PEL | 2023-06-26 |
| BatchNorm-based Weakly Supervised Video Anomaly Detection | ✓ Link | 84.93 | BN-WVAD | 2023-11-26 |
| MTFL: Multi-Timescale Feature Learning for Weakly-Supervised Anomaly Detection in Surveillance Videos | ✓ Link | 84.57 | MTFL (VST) | 2024-10-08 |
| Multi-scale Bottleneck Transformer for Weakly Supervised Multimodal Violence Detection | ✓ Link | 84.32 | MSBT | 2024-05-08 |
| Audio-Guided Attention Network for Weakly Supervised Violence Detection | ✓ Link | 83.54 | CMA_LA | 2022-02-21 |
| Modality-Aware Contrastive Instance Learning with Self-Distillation for Weakly-Supervised Audio-Visual Violence Detection | ✓ Link | 83.4 | MACIL_SD | 2022-07-12 |
| Self-supervised Sparse Representation for Video Anomaly Detection | ✓ Link | 80.26 | S3R (without audio imformation) | 2022-10-23 |
| MGFN: Magnitude-Contrastive Glance-and-Focus Network for Weakly-Supervised Video Anomaly Detection | ✓ Link | 80.11 | MGFN | 2022-11-28 |
| MTFL: Multi-Timescale Feature Learning for Weakly-Supervised Anomaly Detection in Surveillance Videos | ✓ Link | 79.40 | MTFL (VST, finetuned on VADD) | 2024-10-08 |
| Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision | ✓ Link | 78.64 | A Neural Network Containing Three Parallel Branches (holistic, localized, and score branch) | 2020-07-09 |
| Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning | ✓ Link | 77.81 | RTFM | 2021-01-25 |
| | 76.9 | Contrastive Attention for Video Anomaly Detection | |
| Consistency-based Self-supervised Learning for Temporal Anomaly Localization | ✓ Link | 71.68 | CSL_TAL | 2022-08-10 |