Enhancing Weakly Supervised Anomaly Detection in Surveillance Videos: The CLIP-Augmented Bimodal Memory Enhanced Network

Yinglong Wu, Zhaoyong Mao, Chenyang Yu, Guanglin Liu, Junge Shen

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

Aiming at the challenges of surveillance video anomaly detection(SVAD),especially the diversity and openness of its event types, we propose CLIP-Augmented Bimodal Memory Enhanced Network for weakly-supervised surveillance video anomaly detection. Specifically, we design a video feature extraction module based on CLIP feature, which significantly improves the ability to capture the semantic content of surveillance videos. Given the problem of semantic diversity of abnormal events, we further design a Bimodal Memory Unit(BMMU), which is used to enhance the model for all types of abnormal events by means of two kinds of memory module, storing the visual features and the textual descriptive features, in order to enhance the model's ability to remember and distinguish various types of anomalous features. Extensive experiments demonstrate that our approach achieves state-of-the-art performance on the UCF-Crime and XD-Violence benchmark datasets.

源语言英语
主期刊名2024 18th International Conference on Control, Automation, Robotics and Vision, ICARCV 2024
出版商Institute of Electrical and Electronics Engineers Inc.
756-762
页数7
ISBN(电子版)9798331518493
DOI
出版状态已出版 - 2024
活动18th International Conference on Control, Automation, Robotics and Vision, ICARCV 2024 - Dubai, 阿拉伯联合酋长国
期限: 12 12月 202415 12月 2024

出版系列

姓名2024 18th International Conference on Control, Automation, Robotics and Vision, ICARCV 2024

会议

会议18th International Conference on Control, Automation, Robotics and Vision, ICARCV 2024
国家/地区阿拉伯联合酋长国
Dubai
时期12/12/2415/12/24

指纹

探究 'Enhancing Weakly Supervised Anomaly Detection in Surveillance Videos: The CLIP-Augmented Bimodal Memory Enhanced Network' 的科研主题。它们共同构成独一无二的指纹。

引用此