使用弱监督双编码器模型识别监控视频中的异常事件 / Recognition of Abnormal Events in Surveillance Videos using Weakly Supervised Dual-Encoder Models
1️⃣ 一句话总结
这篇论文提出了一种仅需视频级别标注的弱监督方法，通过结合卷积和Transformer两种网络的优势，有效检测监控视频中罕见且多样的异常行为，在标准数据集上取得了优异的性能。
🤖 系统
Abstract - Recognition of Abnormal Events in Surveillance Videos using Weakly Supervised Dual-Encoder Models
We address the challenge of detecting rare and diverse anomalies in surveillance videos using only video-level supervision. Our dual-backbone framework combines convolutional and transformer representations through top-k pooling, achieving 90.7% area under the curve (AUC) on the UCF-Crime dataset.