Smart City Gnosys
Smart city article details
| Title | Adversarial Erasure Network Based On Multi-Instance Learning For Weakly Supervised Video Anomaly Detection |
|---|---|
| ID_Doc | 6735 |
| Authors | Song X.; Liu P.; Li S.; Xu S.; Wang K. |
| Year | 2025 |
| Published | Neurocomputing, 636 |
| DOI | http://dx.doi.org/10.1016/j.neucom.2025.130030 |
| Abstract | Weakly supervised video anomaly detection (WSVAD) aims to precisely locate temporal windows of abnormal events in untrimmed videos using only video-level labels. By accurately locating anomalies, WSVAD has great application potential in the security domain and contributes to the progress of smart city development. However, the lack of frame-level annotations during training makes it highly challenging to infer the status of each frame. Multiple-Instance Learning (MIL) is the dominant method in WSVAD. Due to the limitation of video-level annotations, most MIL-based methods detect obvious abnormal segments to represent the overall anomaly level of the video while overlooking weak abnormal segments. To focus on the discrimination of weak anomalies, we propose a novel WSVAD framework named Adversarial Erasure Network (AE-Net). AE-Net consists of two key components: (1) a dual-branch architecture that highlights weak anomalies by erasing the most obvious abnormal features and combining the erased features with the original ones. (2) a novel triplet loss function that improves weak anomaly representation by separating abnormal and normal features in the erased feature space. Through the above design, AE-Net can reduce false negatives in real-world anomaly detection. Extensive experiments on three WSVAD benchmarks demonstrate that our method outperforms most existing state-of-the-art methods. Specifically, AE-Net achieves an AUC of 88.40% on the UCF-Crime dataset and 98.27% on the ShanghaiTech dataset, which demonstrates that AE-Net can effectively distinguish between normal and abnormal events. Moreover, AE-Net achieves an AP of 85.13% on the XD-Violence dataset, which highlights that AE-Net can accurately detect abnormal events. © 2025 Elsevier B.V. |
| Author Keywords | Adversarial erasure learning; Multiple-instance learning; Video anomaly detection; Weakly supervised |
Similar Articles
| Id | Similarity | Authors | Title | Published |
|---|---|---|---|---|
17976  | 0.898 | Priya S.; Nayak R.; Pati U.C. | Deep Learning-Based Weakly Supervised Video Anomaly Detection Methods For Smart City Applications | 2024 3rd International Conference on Artificial Intelligence for Internet of Things, AIIoT 2024 (2024) |
| 3576 | 0.869 | Huang H.; Zhao B.; Gao F.; Chen P.; Wang J.; Hussain A. | A Novel Unsupervised Video Anomaly Detection Framework Based On Optical Flow Reconstruction And Erased Frame Prediction | Sensors, 23, 10 (2023) |
| 48481 | 0.861 | Ullah W.; Min Ullah F.U.; Ahmad Khan Z.; Wook Baik S. | Sequential Attention Mechanism For Weakly Supervised Video Anomaly Detection | Expert Systems with Applications, 230 (2023) |
| 61219 | 0.853 | Ullah W.; Hussain T.; Baik S.W. | Vision Transformer Attention With Multi-Reservoir Echo State Network For Anomaly Recognition | Information Processing and Management, 60, 3 (2023) |