计算机科学
判别式
人工智能
光学(聚焦)
运动(物理)
异常检测
噪音(视频)
模式识别(心理学)
利用
计算机视觉
混乱
正态性
异常(物理)
语义学(计算机科学)
机器学习
分割
深度学习
鉴定(生物学)
背景噪声
边距(机器学习)
语义分析(机器学习)
分类
降噪
作者
Qiao Wang,Menghao Zhang,Lei Zhang,Qi Qi,Haifeng Sun,Pengfei Ren,Bo He,Jing Wang,Jingyu Wang
出处
期刊:
[Institute of Electrical and Electronics Engineers]
日期:2025-06-30
卷期号:: 1-6
被引量:1
标识
DOI:10.1109/icme59968.2025.11209544
摘要
Recent progress in video anomaly detection assumes that anomalies cannot be effectively reconstructed because they remain unseen during training. However, we observe that most existing methods excessively rely on appearance features, resulting in the accurate reconstruction of anomalies with subtle short-term appearance variations, which we refer to as appearance confusion. Meanwhile, many approaches fail to exploit sufficient semantic distinction, resulting in motion confusion for anomalies with motion patterns similar to normal ones. In this paper, we propose a masked self-supervised learning-based framework, which effectively addresses the two confusions by exploring context-aware motion patterns and discriminative semantic normality representations. First, we introduce reconstructing multi-pattern masked spatiotemporal information to motivate the model to capture motion patterns that focus on long-term context. Then, we design a semantic noise separation network to address motion confusion, facilitating the construction of semantic normality boundaries through semantic-aware separation. Extensive experiments on the Avenue and ShanghaiTech datasets validate the effectiveness of our proposed method.
科研通智能强力驱动
Strongly Powered by AbleSci AI